JP2026014281A - system - Google Patents

Abstract

A system is provided.
A method for collecting review comments;
a means for performing data preprocessing of review comments;
A means for determining product relevance by comparing the review comments with a feature word list;
A means for analyzing patterns of review comments and determining unnatural reviews;
A method for comparing review comments and determining whether comments with the same content are copy-paste reviews,
A means of providing feedback on the relevance, unnaturalness, and copy-paste judgment results of reviews,
A system including:
[Selected Figure] Figure 1

Description

The technology disclosed herein relates to a system.

Patent document 1 discloses a persona chatbot control method executed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Japanese Patent Application Laid-Open No. 2022-180282

On online shopping platforms, product reviews are an important source of information for buyers. However, some reviews have problems such as fake reviews, unnatural reviews, and copied and pasted reviews, which reduces the reliability of the reviews. These fraudulent reviews can distort the actual evaluation of a product and be misleading to consumers. For this reason, there is a need for a system that provides accurate and reliable review information.

The present invention includes a means for collecting review comments, performing data preprocessing, and then comparing each review comment with a list of characteristic words to determine product relevance. It also includes a means for analyzing the patterns of the review comments to determine unnatural reviews, and a means for comparing review comments to determine whether comments with identical content are copy-and-paste reviews. Furthermore, by providing feedback on the review relevance, unnaturalness, and copy-and-paste determination results, a system is provided that provides accurate and reliable review information. The system of the present invention enables consumers to make purchasing decisions based on more accurate information, contributing to improving the quality of the entire online shopping platform.

"Review comments" are text information in which users write their ratings and opinions about products they have purchased.

"Data preprocessing" is the process of removing unnecessary information from collected text data and preparing it in an analyzable form.

A "feature word list" is a list of pre-defined words based on specific product attributes or characteristics, and is used to determine product relevance.

"Product relevance determination" is the process of determining whether a review comment is relevant to a particular product.

"Pattern analysis" is a method of analyzing the content and patterns of multiple review comments to detect similarities and anomalies.

"Unnatural reviews" are review comments that have similar content and are posted consecutively within a short period of time, which may appear unnatural.

A "copy-and-paste review" is a review comment that is posted by copying and pasting the exact same text as an existing review comment.

"Feedback means" refers to the system part that includes a function to notify the reviewer and administrator of the results of the assessment of relevance, unnaturalness, and copy-and-paste.

1 is a conceptual diagram illustrating an example of the configuration of a data processing system according to a first embodiment. 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. 10 is a conceptual diagram illustrating an example of the configuration of a data processing system according to a second embodiment. FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. FIG. 10 is a conceptual diagram illustrating an example of the configuration of a data processing system according to a third embodiment. FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. 1 shows an emotion map onto which multiple emotions are mapped. 1 shows an emotion map onto which multiple emotions are mapped. FIG. 2 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in application example 1. FIG. 10 is a sequence diagram showing the flow of processing of the data processing system in the second embodiment when an emotion engine is combined. FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined.

Below, an example of an embodiment of a system relating to the technology disclosed herein will be described with reference to the accompanying drawings.

First, let me explain the terminology used in the following explanation.

In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, a processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose Computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

In the following embodiments, coded random access memory (RAM) is memory in which information is temporarily stored and is used as work memory by the processor.

In the following embodiments, the coded storage refers to one or more non-volatile storage devices that store various programs, parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

In the following embodiments, a communication I/F (Interface) with a symbol is an interface that includes a communication processor, an antenna, etc. The communication I/F controls communication between multiple computers. Examples of communication standards that can be applied to the communication I/F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

In the following embodiments, "A and/or B" is synonymous with "at least one of A and B." In other words, "A and/or B" means that it may be just A, just B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and/or B" also applies when three or more things are expressed connected by "and/or."

[First embodiment]

Figure 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

The data processing device 12 includes a computer 22, a database 24, and a communication I/F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and communication I/F 26 are also connected to the bus 34. The communication I/F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and/or a LAN (Local Area Network).

The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I/F 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

The reception device 38 is equipped with a touch panel 38A, a microphone 38B, etc., and receives user input. The touch panel 38A detects contact with an indicator (e.g., a pen or finger) to receive user input via the indicator. The microphone 38B detects the user's voice to receive user input via voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

The output device 40 is equipped with a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible by the user 20 (e.g., audio and/or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

The communication I/F 44 is connected to the network 54. The communication I/Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54.

Figure 2 shows an example of the main functions of the data processing device 12 and smart device 14.

As shown in FIG. 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

Storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

Next, we will explain the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart device 14 will be referred to as the "terminal."

The system of the present invention evaluates the reliability of review comments on shopping platforms and provides appropriate feedback, allowing users to obtain more accurate review information. The program processing of this system is explained below in natural language.

Process Overview

1. Collecting review comments

The server periodically retrieves all review comments from the shopping platform via API, allowing new review comments to be added to the system.

2. Data Preprocessing

The server preprocesses the collected review comment data. Preprocessing includes removing unnecessary spaces and special characters, splitting review comments, and standardizing language.

3. Product Relevance Assessment

The server compares the review comment with a feature word list based on product attributes. For example, if the review is about a smartphone, a word list such as "image quality," "battery," and "operability" will be set.

The server scores the frequency with which words included in the word list appear in the review comments, and if the score is above a certain level, the review comment is determined to be a "review with high product relevance."

Example:

Product: Smartphone

Review comment: "The image quality of this smartphone is amazing."

Score: "Image quality" is included in the word list, so the score is high.

4. Identifying unnatural reviews

The server analyzes patterns in review comments posted within a certain period of time, checking to see if similar reviews have been posted consecutively within a short period of time.

The server will flag reviews if any unusual patterns are detected.

Example:

Review 1: "Great product!"

Review 2: "Great product!"

Review 3: "Great product!"

Verdict: Unnatural review and flagging.

5. Judging Copy-Paste Reviews

Every time a new review comment is posted, the server compares it with all existing review comments to see if any have the exact same content.

If the server finds an exact match, it will flag the review as a "copy-and-paste review."

Example:

Review 1: "This product is amazing!"

Review 2: "This product is amazing!"

Verdict: Copy and paste review and flagging.

6. Feedback

When a review is submitted, the server will only allow it to be submitted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted.

The server filters out inappropriate reviews and displays an error message to the user. It also notifies the administrator of the review content and the judgment result.

This system allows users to select products based on reliable review information, improving the quality of reviews across the entire online shopping platform.

The processing flow is explained below.

Step 1:

Collecting review comments

The server uses an API from the shopping platform to periodically retrieve all review comments. This collection includes review comments for all products.

Step 2:

Data preprocessing

The server stores the collected review comments as text data. Next, it performs a cleaning process to remove unnecessary spaces, special characters, and HTML tags from the review comments. It then tokenizes the review comments into words and sentences, converting them into an analyzable form.

Step 3:

Product relevance determination

The server pre-sets a word list based on the characteristics and attributes of each product. When a review comment is posted, the server compares the words in the comment with the word list. For example, for a review about a smartphone, a word list such as "image quality," "battery," and "operability" is used. The server scores how often words from the word list appear in the comment, and if the score is above a certain level, it determines that the review is "highly relevant to the product."

Step 4:

Determining unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It determines whether reviews with similar content or writing style have been posted in succession within a short period of time. If the server detects an unnatural pattern, it flags the review comment.

Step 5:

Copy-and-paste review verdict

Each time a new review comment is submitted, the server compares it with all existing review comments. It uses sophisticated text comparison algorithms to determine whether a review comment with the exact same content already exists. If the server finds a match, it flags the review comment as a "copy-and-paste review."

Step 6:

Feedback and filtering

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not flagged as being inappropriate, unnatural, or copied and pasted. If a flag is raised, the server will display an error message to the user explaining the reason for the posting. The server will also notify administrators of the fraudulent review and help them review the review.

Based on these concrete steps, we will be able to provide users with reliable review information and improve the quality of the entire shopping platform.

(Example 1)

Next, we will explain Example 1. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

On online shopping platforms, the reliability of review comments, which users use as a reference when selecting products, is important. However, fake reviews, copy-and-paste reviews, and reviews with unnatural patterns are rampant, making it difficult for users to obtain accurate information. For this reason, there is a need for a system that can evaluate the reliability of review comments and provide users with accurate review information.

The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

In this invention, the server includes means for collecting review comments, means for pre-processing data on the review comments, means for comparing the review comments with a feature word list to determine product relevance, means for analyzing patterns of the review comments to determine unnatural reviews, means for comparing review comments to determine comments with identical content as copy-and-paste reviews, and means for providing feedback on the review relevance, unnaturalness, and copy-and-paste determination results. This enables users to select products based on highly reliable review information.

"Review comments" are opinions and ratings posted by users about products on online shopping platforms.

"Data preprocessing" refers to the process of removing unnecessary spaces and special characters from the text data of collected review comments, and performing tokenization and language standardization.

A "characteristic word list" is a list of keywords based on product attributes that are set up to evaluate the reliability of review comments about a product.

"Product relevance" is an indicator that shows the degree to which review comments mention a specific product and the degree of match with the feature word list.

"Pattern analysis" is the process of analyzing the posting patterns of review comments and determining whether the same or similar content has been posted consecutively within a certain period of time.

An "unnatural review" is a review that is deemed to deviate from normal user behavior, such as when similar comments are posted in succession within a short period of time.

A "copy-and-paste review" is a comment that is posted by simply copying an existing review comment, and refers to a review with exactly the same content.

"Feedback" is a process that notifies users and administrators of the relevance, unnaturalness, and copy-and-paste judgment results of review comments, allowing only appropriate reviews.

The present invention is a system that evaluates the reliability of review comments on online shopping platforms, allowing users to obtain more accurate review information. Specific embodiments are described in detail below.

Collecting review comments

The server periodically retrieves all review comments using the shopping platform's API. This periodically saves the comments, including the most recent ones, to the database. The specific software used is the Python requests library.

Data preprocessing

The server preprocesses the collected review comment data. This includes removing unnecessary whitespace and special characters, tokenizing the text data, and unifying the language. This process uses the Python nltk library and re module.

Product relevance determination

The server compares the review comments with a feature word list based on product attributes. For example, for a review about a smartphone, a feature word list such as "image quality," "battery," and "operability" is set. The server scores the frequency with which words included in the word list appear in the review comments, and if the score is above a certain level, the review comment is deemed to be "highly relevant to the product." The specific software used is the Python scikit-learn library.

Specific examples

Product: Smartphone

Review comment: "The image quality of this smartphone is amazing."

Since "image quality" is included in the word list, it is judged to have a high score.

Identifying unnatural reviews

The server analyzes patterns in review comments posted within a certain period of time, checking to see if similar reviews have been posted consecutively within a short period of time. If the server detects an unnatural pattern, it flags those reviews. This process uses Python's Pandas library and time series analysis.

Specific examples

Review 1: "Great product!"

Review 2: "Great product!"

Review 3: "Great product!"

The server will identify these as unnatural reviews and flag them.

Copy-and-paste review verdict

Every time a new review comment is posted, the server compares it with all existing review comments to see if there are any identical comments. If the server finds a matching comment, it flags the review as a "copy-and-paste review." The software uses the Python difflib library.

Specific examples

Review 1: "This product is amazing!"

Review 2: "This product is amazing!"

The server determines that Review 2 is a copy-and-paste review and flags it.

Feedback

When a review is posted, the server will only allow it to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. Inappropriate reviews are filtered out and an error message is displayed to the user. The server also notifies the administrator of the review content and the result of the judgment. This process uses the Python Flask or Django framework and an email server (SMTP) for notifications.

Example prompt

Please rate the user-submitted review comment, "This phone has excellent battery life." and provide feedback based on the following criteria:

Conditions:

1. To determine whether a review is highly relevant to the product, it is scored based on a list of characteristic words such as "battery," "lifespan," and "excellent."

2. Check to see if similar reviews have been posted consecutively within a certain period of time.

3. Compare with existing review comments to check if the review is a copy-and-paste one.

This system will enable users to select products based on reliable review information, and is expected to improve the quality of reviews across online shopping platforms.

The flow of the identification process in Example 1 will be explained using Figure 11.

Step 1:

Collects review comments. The server periodically retrieves all review comments through the shopping platform's API. The input is the API request, and the output is the retrieved review comment data in JSON format. The server sends the API request and stores the received data in a database.

Step 2:

Performs data preprocessing. The server performs preprocessing on the collected review comment data. The input is JSON-formatted review comment data, and the output is preprocessed text data. The server removes unnecessary whitespace and special characters, tokenizes the text data, and standardizes the language.

Step 3:

Determines product relevance. The server compares preprocessed review comments with a feature word list based on product attributes. The input is preprocessed text data and a feature word list, and the output is scored review comment data. The server scores how often words included in the word list appear in the review comments, and if the score is above a certain level, it determines the review to be "highly relevant to the product."

Step 4:

Identifies unnatural reviews. The server analyzes patterns in review comments posted within a certain period of time. The input is review comment data from a specific period of time, and the output is the judgment result and flagged data. The server checks whether reviews with similar content have been posted in succession within a short period of time, and if an unnatural pattern is detected, it flags those reviews.

Step 5:

Determines copy-and-paste reviews. Every time a new review comment is posted, the server compares it with all existing review comments. The input is the new review comment and existing review comment data, and the output is the determination result and flagged data. If the server finds a matching comment, it flags the review as a "copy-and-paste review."

Step 6:

Provides feedback. The server will only allow a review to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. The input is the review comment and various judgment results, and the output is notifications to the user and administrator. The server filters out inappropriate reviews, displays an error message to the user, and notifies the administrator of the review content and judgment results.

(Application Example 1)

Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart device 14 will be referred to as the "terminal."

On conventional shopping platforms, many unreliable review comments were posted, causing users to make incorrect purchasing decisions. There was also the problem of similar reviews and copy-paste reviews being posted within a short period of time, reducing the reliability of the reviews. Therefore, there was a need to develop a system that could provide users with reliable review information and help them make more accurate purchasing decisions.

The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

In this invention, the server includes means for collecting review comments, means for pre-processing data on the review comments, means for comparing the review comments with a list of characteristic words to determine product relevance, means for analyzing patterns of the review comments to determine unnatural reviews, means for comparing review comments to determine comments with identical content as copy-and-paste reviews, means for providing feedback on the relevance, unnaturalness, and copy-and-paste determination results of the reviews, means for evaluating and providing feedback on the reliability of the review comments in real time, and means for displaying reviews in order of reliability. This allows users to receive reliable reviews in real time and make more accurate purchasing decisions based on them.

A "review comment" is a written comment written by a user expressing their evaluation or opinion of a product or service.

"Means of collection" refers to the method by which data is obtained from online platforms and entered into the system.

"Data preprocessing" is the process of removing unnecessary information and formatting acquired data to make it easier to analyze.

A "characteristic word list" is a list of important keywords related to a specific product or service.

"Product relevance" is the degree to which a review comment relates to a particular product or service.

"Pattern analysis methods" are methods for detecting certain templates or similarities in review comments.

"Unnatural reviews" are comments that deviate from normal user behavior, such as those posted in large numbers in a short period of time or those that contain repeated, repeated comments.

A "copy-and-paste review" is a review comment in which the exact same content as another comment is copied and pasted.

"Means of providing feedback" refers to methods for notifying users and administrators of evaluation results and encouraging them to take appropriate action.

"Means for assessing trustworthiness in real time" refers to a method that automatically determines the accuracy and credibility of a review the moment it is posted.

"Displaying in order of reliability" is a method of displaying highly rated review comments at the top, making them easier for users to refer to.

The system of the present invention evaluates the reliability of review comments on shopping platforms, allowing users to obtain more accurate review information. This system is implemented through the following process:

Hardware to use

Smartphone: Used by users as a device to post review comments.

Server: A central computer that collects review comments, preprocesses data, analyzes, evaluates, and provides feedback.

API server: Used as an interface to retrieve review comments from the shopping platform.

Software used

Python: Used for server-side data processing and analysis.

Flask: A Python web framework used to build API servers.

MySQL: Used as a database management system to store collected review comments.

Natural language processing library: Used for preprocessing and parsing review comments.

Data processing and calculation flow

1. Collecting review comments

The server periodically retrieves review comments from the shopping platform via API. This API server is built using Flask, and the retrieved data is stored in a MySQL database.

2. Data Preprocessing

The server preprocesses the retrieved review comment data. This preprocessing includes removing unnecessary whitespace and special characters, splitting review comments, and standardizing language using a Python natural language processing library.

3. Product Relevance Assessment

The server compares the review comment with a list of characteristic words based on product attributes. For example, a review about a smartphone would use keywords such as "image quality," "battery," and "operability." The server then scores the review comment, and if it scores above a certain level, it determines that the review comment is "highly relevant to the product."

4. Identifying unnatural reviews

The server analyzes review comments posted within a certain period of time to see if similar reviews have been posted in succession within a short period of time. If an unnatural pattern is detected, those reviews are flagged.

5. Judging Copy-Paste Reviews

The server compares the newly posted review comment with all existing review comments. It checks to see if there are any identical comments, and if there is an exact match, it flags it as a "copy-and-paste review."

6. Feedback

When a review is posted, the server will only allow it to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted, and will provide real-time feedback to the user. It also has a function to display reviews in order of reliability.

Specific examples and prompt sentence examples

As a concrete example, consider the following review comment:

Product: Smartphone

Review: "This phone's battery lasts a long time."

An example of a prompt is as follows:

"Please tell us if this review is relevant to the product: 'This phone's battery lasts a long time.'"

"Please tell us if this review fits any unnatural pattern: 'This phone's battery lasts a long time.'"

"Please tell us if this review exactly matches an existing review: 'This phone's battery lasts a long time.'"

This will allow users to choose products based on reliable reviews, improving the quality of ratings across online shopping platforms.

The flow of the specific processing in Application Example 1 will be explained using Figure 12.

Step 1:

Collecting review comments:

The server periodically collects review comments using an API provided by the shopping platform. The server receives the review comments obtained via the API in JSON format and stores them in a MySQL database. The input is the JSON data obtained from the API, and the output is the review comments stored in the database.

Step 2:

Data preprocessing:

The server preprocesses the collected review comment data. It uses Python's regular expression library to remove unnecessary whitespace and special characters and split the review comments into sentences. It also converts data in different formats into a unified format. The input is the raw review comments, and the output is the preprocessed, clean data.

Step 3:

Product relevance determination:

The server compares the preprocessed review comments with a pre-set feature word list. The server calculates the frequency of occurrence of words included in the feature word list, and determines that a product is highly relevant if the frequency is above a certain score. The input is the preprocessed review comments and the feature word list, and the output is data flagged as highly relevant reviews.

Step 4:

Determining unnatural reviews:

The server compares the preprocessed review comments with other review comments posted within a certain period of time and analyzes patterns. If a large number of similar review comments are posted in a short period of time, the server determines that they are unnatural reviews and flags them. The input is the preprocessed review comments and past review comments, and the output is data flagged as unnatural reviews.

Step 5:

Copy and paste review verdict:

The server compares the newly posted review comment with all existing review comments based on content similarity. If the server finds a review comment with exactly the same content, it flags it as a copy-and-paste review. The input is the new review comment and the existing review comment, and the output is the data determined to be a copy-and-paste review.

Step 6:

Feedback:

The server provides real-time feedback to reviewers based on the review's relevance, unnaturalness, and copy-and-paste assessment results. Reviews are displayed on the user's device in order of reliability. Reviews with low reliability are rejected, and the user is notified of the reason. The input is the review assessment results, and the output is a feedback message.

This allows users to make more accurate purchasing decisions based on reliable review comments.

Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

The system of the present invention evaluates the reliability of review comments on shopping platforms and further optimizes review information by recognizing user sentiment. The program processing of this system is explained below in natural language.

Process Overview

1. Collecting review comments

The server periodically retrieves all review comments from the shopping platform via API. The collected review comments are stored in a database.

2. Data Preprocessing

The server cleans the collected review comments, removing unnecessary whitespace, special characters, and HTML tags. It also tokenizes the review comments into words and sentences, making them easier to analyze.

3. Product Relevance Assessment

The server compares review comments with a word list based on the features and attributes of each product. For example, for a review about a smartphone, a word list would be prepared, including "image quality," "battery," and "operability."

The server scores the number of times the words in the word list appear in the review comments, and if the score is above a certain level, it determines the review to be "highly relevant to the product."

Example:

Product: Smartphone

Review comment: "The image quality of this smartphone is outstanding."

Score: "Image quality" is included in the word list, so the score is high.

4. Identifying unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It checks to see if reviews with similar content or writing style have been posted consecutively within a short period of time.

If the server detects any unusual patterns, it will flag the review comment.

Example:

Review 1: "This is a great product!"

Review 2: "This is a great product!"

Review 3: "This is a great product!"

Verdict: Unnatural review and flagging.

5. Judging Copy-Paste Reviews

Every time a new review comment is submitted, the server compares it with all existing review comments, using an advanced text comparison algorithm to check whether a review comment with the exact same content already exists.

If the server finds a match, it flags the review comment as a "copy-and-paste review."

Example:

Review 1: "This product is amazing!"

Review 2: "This product is amazing!"

Verdict: Copy and paste review and flagging.

6. Emotion Recognition Using an Emotion Engine

The server analyzes the review comments using an emotion engine and classifies them into positive, negative, or neutral sentiment.

The server calculates the emotional score of the review comments based on the scoring by the emotion engine and reflects this in the overall rating of the product.

Example:

Review comment: "This phone's battery dies so quickly it's useless."

Sentiment analysis result: Negative

Score: Reflected as a low rating.

7. Feedback and Filtering

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. If a flag is raised, the server will display an error message to the user explaining the reason for the post.

The server notifies the user and administrator of the feedback along with the emotion score generated by the emotion engine. Administrators are also notified to further review and respond to the review.

As a result, the system of the present invention ensures the reliability of review comments and provides a platform that users can use with peace of mind. The introduction of an emotion engine further improves the quality and reliability of reviews, and more accurately reflects product evaluation information.

The processing flow is explained below.

Step 1:

Collecting review comments

The server periodically retrieves all review comments from the shopping platform via API. The collected review comments are stored in a database.

Step 2:

Data preprocessing

The server cleans the collected review comments. Specifically, it removes unnecessary spaces, special characters, and HTML tags. It also tokenizes the review comments into words and sentences, preparing them in an analyzable form.

Step 3:

Product relevance determination

The server compares review comments using a word list based on the features and attributes of each product. It compares the words in the review comments with the word list and generates a score. For example, a word list related to smartphones might include "image quality," "battery," and "operability."

The server scores the frequency with which words included in the word list appear, and if the score is above a certain level, it determines that the review is "highly relevant to the product."

Step 4:

Determining unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It determines whether reviews with similar content or writing style have been posted in succession within a short period of time. In particular, it compares sentence length, the words used, sentence structure, etc.

If the server detects any unusual patterns, it will flag the review comment.

Step 5:

Copy-and-paste review verdict

Every time a new review comment is submitted, the server compares it with all existing review comments, using an advanced text comparison algorithm to check whether a review comment with the exact same content already exists.

If the server finds a match, it flags the review comment as a "copy-and-paste review."

Step 6:

Emotion recognition using an emotion engine

The server uses an emotion engine to analyze review comments and classify them into positive, negative, or neutral sentiment. Specifically, it uses a natural language processing algorithm to extract and score emotional expressions contained in the sentences.

The server calculates the emotional score of the review comments based on the scoring by the emotion engine and reflects this in the overall rating of the product.

Step 7:

Feedback and filtering

The server will only allow a review comment to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. If any flags are raised, the server will display an error message to the user explaining why the post was rejected.

The server filters out inappropriate reviews and notifies users and administrators, including the sentiment score generated by the sentiment engine. Administrators are sent detailed information such as the review content, the reason it was flagged, and the sentiment score, and are offered help in re-checking the review if necessary.

Based on these specific steps, the system of the present invention ensures the reliability of review comments and provides a platform that users can use with confidence. The integration of an emotion engine further improves the quality and reliability of reviews, and more accurately reflects product evaluation information.

(Example 2)

Next, we will explain Example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

Traditional shopping platforms lacked an appropriate mechanism for determining the authenticity of review comments, leaving users at risk of making purchasing decisions based on inaccurate information. This has created a need to improve the reliability of review comments and provide an environment where users can use them with peace of mind. It is also necessary to accurately understand the sentiment behind review comments in order to more accurately reflect product evaluation information.

The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting review comments, means for performing data preprocessing of the review comments, means for determining product relevance by comparing the review comments with a characteristic word list, means for analyzing the patterns of the review comments to determine unnatural reviews, means for comparing the review comments to determine comments with identical content as copy-and-paste reviews, means for analyzing the sentiment of the review comments, means for providing feedback on the review relevance, unnaturalness, copy-and-paste determination results, and sentiment analysis results, and means for rejecting the posting of review comments that are unnatural or copy-and-paste. This improves the reliability of review comments, provides an environment where users can refer to reviews with confidence, and makes it possible to more accurately reflect product evaluation information.

"Review comments" are textual opinions and evaluations written by users on shopping platforms about products and services.

"Data preprocessing" is the process of removing unnecessary elements from collected review comments and converting them into a format suitable for analysis.

A "characteristic word list" is a list of keywords related to a specific product or service that is used to compare with review comments.

"Product relevance determination" is the process of determining whether a review comment is relevant to a specific product or service.

"Pattern analysis" is the process of analyzing the content and format of review comments to detect specific patterns or anomalies.

"Unnatural reviews" are review comments that show an unusual pattern, such as content or writing style being posted repeatedly within a short period of time.

A "copy-and-paste review" refers to a review comment that has exactly the same content as an existing review comment.

"Sentiment analysis" is the process of analyzing the content of review comments and classifying their sentiments as positive, negative, or neutral.

"Feedback" refers to the provision of information to notify users or administrators of analysis and judgment results, and to encourage them to take necessary action.

"Posting refusal" refers to the action of not allowing users to post in order to prevent unnatural reviews or copy-and-paste reviews from being posted.

A "server" is a computer system that manages and executes a series of processes, including the collection, preprocessing, analysis, judgment, feedback, and rejection of review comments.

The system of the present invention evaluates the reliability of review comments on a shopping platform, recognizes user emotions, and optimizes review information. The specific operations and processes for this purpose are described below.

1. Collecting review comments

The system retrieves review comments through the shopping platform's API. The server periodically sends requests to the API endpoint and stores the retrieved review comments in a database. Specifically, MySQL or PostgreSQL can be used as the database.

For example, the server accesses the API endpoint "https://example.com/api/reviews" and stores the retrieved review comments in the "reviews" table.

2. Data Preprocessing

The server cleans the retrieved review comments. Specifically, it removes unnecessary whitespace, special characters, and HTML tags. It also tokenizes the review comments into words and sentences. This preprocessing can be performed using NLPK, a Python NLP library.

For example, a comment such as "This product is <p>great</p>!" is text cleaned to "This product is great!" and then tokenized.

3. Product Relevance Assessment

The server generates a word list based on the features and attributes of each product and compares it with the review comments. For example, for smartphone reviews, a word list containing keywords such as "image quality," "battery," and "operability" is used.

Specifically, the frequency of keywords appearing in review comments is scored, and if the score is above a certain level, it is determined to be a "review with high product relevance." For example, the server analyzes a comment such as "The image quality of this smartphone is outstanding," and assigns a high score because "image quality" is included in the word list.

4. Identifying unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. Specifically, it checks to see if review comments with similar content or format have been posted consecutively within a short period of time.

If an unnatural pattern is detected, the review comment is flagged. For example, if the server sees multiple reviews with the same content, such as "Great product!", posted within a short period of time, it will flag them as unnatural.

5. Judging Copy-Paste Reviews

Each time a new review comment is submitted, the server compares it with all existing review comments, using sophisticated text comparison algorithms (e.g., Python's difflib library) to determine whether there is a match.

If a match is found, the server will flag the review comment as a "copy-and-paste review." For example, if a comment already exists that says "This product is amazing!", the server will add a flag.

6. Emotion Recognition Using an Emotion Engine

The server inputs the review comments into a sentiment analysis engine and classifies them into positive, negative, or neutral sentiment. Specifically, sentiment analysis libraries such as TextBlob and VADER can be used.

This allows us to calculate an emotional score, which is then reflected in the overall rating of the product. For example, we can use TextBlob to analyze a comment such as "This phone's battery runs out quickly, so it's useless" and assign it a negative score.

7. Feedback and Filtering

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not related to the product, unnatural, or copied and pasted. If so, an error message will be displayed to the user explaining the reason for the post.

The emotion engine also notifies users and administrators of the emotion score, helping to improve the reliability of reviews. For example, the server may notify users that "this review has been flagged as unnatural" and encourage them to resubmit. It may also notify administrators that "a new unnatural review has been detected. Please check it."

Example prompt for a generative AI model

"Please classify whether this review comment relates to a specific product and its sentiment. Example: 'The image quality of this phone is outstanding.'"

"Please determine whether the review comments on this listing are unnatural. Example: 'Great product!', 'Great product!'"

"Check if this review comment matches an existing comment or is a copypasta review. Example: 'This product is amazing!'"

The above is a form for implementing the system of the present invention.

The flow of the identification process in Example 2 will be explained using Figure 13.

Step 1:

Collecting review comments:

Input: Shopping platform API endpoint URL

Specific behavior: The server periodically sends requests to an API endpoint to retrieve review comments. For example, it accesses the API endpoint "https://example.com/api/reviews".

Data processing: Metadata (user ID, product ID, posting date and time, etc.) is added to the acquired review comments.

Output: Dataset containing review comments and metadata

Specific operation: The server stores the acquired dataset in a database (e.g., MySQL or PostgreSQL).

Step 2:

Data preprocessing:

Input: Review comments stored in the database

What it does: The server cleans the review comments. Specifically, it uses a Python NLP library (e.g., NLPK) to remove unnecessary whitespace, special characters, and HTML tags.

Data processing: Tokenize review comments into words and sentences.

Output: Clean, tokenized review comments

Specific operation: For example, a comment such as "This product is <p>great</p>!" is cleaned to "This product is great!" and separated into individual words.

Step 3:

Product relevance determination:

Input: Clean, tokenized review comments, product feature word list

Specific operation: The server compares the review comments with the feature word list. The word list includes keywords based on product attributes such as "image quality," "battery," and "operability."

Data calculation: Score the frequency of keywords appearing in review comments.

Output: Product relevance score

Specific behavior: For example, a comment such as "The image quality of this smartphone is outstanding" will be given a high score if the word list includes "image quality."

Step 4:

Determining unnatural reviews:

Input: All review comments posted within a certain period

Specific operation: The server analyzes the content patterns of review comments. It checks whether reviews with the same content or writing style have been posted consecutively.

Data calculations: Analysis to detect unnatural patterns

Output: Review comments flagged as unnatural

Specific behavior: For example, if the same review saying "This is a great product!" is posted multiple times within a short period of time, it will be flagged as unnatural.

Step 5:

Copy and paste review verdict:

Input: New review comment, Existing review comment

What it does: The server uses advanced text comparison algorithms (e.g., Python's difflib library) to compare the new comment with existing review comments.

Data calculation: The process of checking whether the content of comments matches.

Output: Review comments flagged as copy-paste reviews

Specific behavior: For example, if a comment saying "This product is amazing!" already exists, add a flag.

Step 6:

Emotion recognition using the emotion engine:

Enter: Review comment

Specific operation: The server inputs the review comments into a sentiment analysis engine (e.g., TextBlob or VADER) and classifies the sentiment.

Data calculation: Calculating emotion scores

Output: Review comments with sentiment scores

Specific behavior: For example, a comment such as "This smartphone's battery runs out quickly, making it useless" is scored as negative.

Step 7:

Feedback and filtering:

Input: Review comments (with flags for relevance, unnaturalness, and copy-paste), sentiment score

Specific behavior: When an attempt is made to post a review comment, the server will only allow it to be posted if it is not related to the product, unnatural, or copied and pasted. If so, an error message will be displayed to the user.

Data calculation: feedback and submission evaluation

Output: Notification to users and administrators

Specific behavior: For example, the server notifies the user that "this review has been flagged as unnatural" and encourages them to resubmit, while simultaneously notifying the administrator that "a new unnatural review has been detected."

The above are the specific processing steps of this system's program.

(Application Example 2)

Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart device 14 will be referred to as the "terminal."

Traditional review comment rating systems often lack the functionality to fully guarantee the reliability of reviews. For example, they often contain a mixture of reviews that are unrelated to the product, unnatural reviews, and copy-and-paste reviews, making it difficult for users to obtain accurate information. There is also a demand for more accurate product ratings through sentiment analysis of review comments. However, current systems lack sentiment analysis functionality, making it impossible to improve the quality and reliability of reviews.

The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

In this invention, the server includes means for collecting review comments, means for pre-processing data on the review comments, means for comparing the review comments with a list of characteristic words to determine product relevance, means for analyzing patterns of the review comments to determine unnatural reviews, means for comparing review comments to determine comments with identical content as copy-and-paste reviews, means for performing sentiment analysis on the review comments, and means for providing feedback on the review relevance, unnaturalness, copy-and-paste determination results, and sentiment analysis results. This allows users to obtain highly reliable review information and more accurately evaluate products.

"Review comments" refer to impressions and evaluations written by users about products and services.

"Means of collection" refers to the process or function of obtaining specific information from the Internet or a database.

"Data preprocessing" refers to the process of analyzing collected data or performing pre-analysis processing to remove unnecessary parts and format the data.

A "characteristic word list" refers to a list of important keywords related to a specific product or category.

"Means for determining product relevance" refers to the methods or algorithms used to evaluate how relevant a review comment is to a particular product.

"Methods of analyzing patterns to identify unnatural reviews" refers to methods of analyzing the content and posting patterns of review comments to detect unnatural content and typical actions.

A "copy-and-paste review" refers to a review comment that contains the same content as another review comment, copied and pasted exactly as is.

"Sentiment analysis" refers to the technology of analyzing user emotions and intentions from text data and classifying them as positive, negative, or neutral.

"Feedback" refers to the process of returning analysis and evaluation results to the user or system.

Form for implementing the invention

This invention is a system that improves the reliability of review comments on shopping platforms and provides users with optimal information. This system collects review comments, performs data preprocessing, and analyzes product relevance, unnaturalness, whether or not they have been copied and pasted, and sentiment before providing feedback.

System Overview

The server includes the following means:

1. How to collect review comments:

The server periodically retrieves all review comments from the shopping platform via API. These collected review comments are stored in a database.

2. Methods for preprocessing review comment data:

The server cleans the collected review comments. Specifically, it removes unnecessary whitespace, special characters, and HTML tags, tokenizes the review comments into words and sentences, and prepares them in an analyzable form.

3. How to determine product relevance by comparing review comments with a list of characteristic words:

The server compares review comments with a word list based on the characteristics and attributes of each product. For example, for a review about a smartphone, a word list such as "image quality," "battery," and "operability" would be prepared. The server scores the number of times words from the word list appear in the review comments, and if the score is above a certain level, it is determined to be a "review highly relevant to the product."

4. How to analyze review comment patterns and identify unnatural reviews:

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It checks to see if reviews with similar content or writing style have been posted consecutively within a short period of time, and if an unnatural pattern is detected, it flags the review comment.

5. How to compare review comments and identify comments with identical content as copy-and-paste reviews:

Every time a new review comment is submitted, the server compares it with all existing review comments. Using sophisticated text comparison algorithms, it checks whether an identical review comment already exists, and if a match is found, it flags the review comment as a "copy-and-paste review."

6. How to perform sentiment analysis on review comments:

The server analyzes the review comments using an emotion engine and classifies them into positive, negative, and neutral emotions. Based on the scoring by the emotion engine, the emotion score of the review comments is calculated and reflected in the overall rating of the product.

7. Means of providing feedback on review relevance, unnaturalness, copy-paste determination results, and sentiment analysis results:

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not flagged as being inappropriate, unnatural, or copied and pasted. If a flag is raised, an error message will be displayed to the user, explaining the reason for the post. Feedback will be provided to the user and administrator, along with the sentiment score calculated by the sentiment engine, and administrators will be notified, urging them to further review and take action.

Hardware and software used

Hardware: Servers, cloud storage devices

Software: Python, requests, BeautifulSoup, re, nltk, textblob, scikit-learn, emotion engine (TextBlob, etc.)

Specific examples

As a concrete example, we will show the steps for processing the review comment "The image quality of this smartphone is outstanding." This comment is determined to be highly relevant to the product because it contains the keyword "image quality," and is approved because it does not match unnatural reviews or copy-paste reviews.

Example prompt

Example of a prompt to input to a generative AI model:

Analyze the new review comment, "The image quality of this phone is outstanding." We'll rate it based on the following criteria:

1. Product Relevance

2. Unnatural patterns

3. Copy and paste

4. Sentiment analysis

The flow of the specific processing in Application Example 2 will be explained using Figure 14.

Step 1:

Collecting review comments

The server periodically calls the shopping platform's API to retrieve review comments for each product. As input, it uses the API endpoint URL and authentication information. As output, it generates JSON data containing the retrieved review comments. This data is stored in the server's database.

Step 2:

Data preprocessing

The server cleans the collected review comments. As input, it uses the text data of the review comments stored in the database. Specifically, it removes unnecessary whitespace, special characters, and HTML tags, and tokenizes the review comments into words and sentences. As output, clean text data is generated and passed to the next step.

Step 3:

Product relevance determination

The server evaluates the relevance of review comments using a word list based on the features and attributes of each product. As input, it uses the clean review comments and the feature word list. Specifically, it scores how often words included in the feature word list appear in the review comments. As output, it generates a relevance score for each review comment.

Step 4:

Determining unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns. As input, it uses text data from review comments over a certain period of time in the past and the current review comment. Specifically, it applies a text pattern matching algorithm to evaluate the similarity. As output, it generates a flag indicating whether the review is unnatural.

Step 5:

Copy-and-paste review verdict

Each time a new review comment is posted, the server compares it with all existing review comments. It uses the data of the new review comment and the existing review comments as input. Specifically, it uses an advanced text comparison algorithm (e.g., cosine similarity) to check whether a review comment with the exact same content exists. As output, it generates a flag indicating whether the review is a copy-and-paste review.

Step 6:

sentiment analysis

The server parses the review comments into the sentiment engine. It uses the clean review comments as input. Specifically, it sends the text to the sentiment engine (e.g., TextBlob) and obtains a sentiment score: positive, negative, or neutral. The output is a sentiment score for each review comment.

Step 7:

Feedback and filtering

When an attempt is made to post a review comment, the server provides feedback based on the judgment results obtained in the previous steps. All judgment results (relevance, unnaturalness, copy-paste judgment results, and sentiment score) are used as input. Specific behavior is to allow posting only if no flags are raised, and to display an error message to the user if a flag is raised. More detailed feedback is then provided to the administrator. As output, an error message or approval message is displayed to the user, and the review comment is saved in the database.

The specific processing unit 290 transmits the results of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the results of the specific processing. The microphone 38B acquires audio indicating the user input regarding the results of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

Data generation model 58 is what is known as generative AI (artificial intelligence). Examples of data generation model 58 include generative AI such as ChatGPT (Internet search <URL: https://openai.com/blog/chatgpt>) and Gemini (Internet search <URL: https://gemini.google.com/?hl=ja>). Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing an instruction is input to data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input. Data generation model 58 performs inference on the input inference data in accordance with the instructions indicated by the prompt, and outputs the inference results in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization.

In the above embodiment, an example was given in which the specific processing was performed by the data processing device 12, but the technology disclosed herein is not limited to this, and the specific processing may also be performed by the smart device 14.

[Second embodiment]

Figure 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

As shown in FIG. 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

The data processing device 12 includes a computer 22, a database 24, and a communication I/F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and communication I/F 26 are also connected to the bus 34. The communication I/F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and/or a LAN (Local Area Network).

The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I/F 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user 20's surroundings (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

The communication I/F 44 is connected to the network 54. The communication I/Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I/Fs 44 and 26 is carried out in a secure manner.

Figure 4 shows an example of the main functions of the data processing device 12 and smart glasses 214. As shown in Figure 4, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32.

The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as the specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

Storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

Next, we will explain the identification process performed by the identification processing unit 290 of the data processing device 12. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

The system of the present invention evaluates the reliability of review comments on shopping platforms and provides appropriate feedback, allowing users to obtain more accurate review information. The program processing of this system is explained below in natural language.

Process Overview

1. Collecting review comments

The server periodically retrieves all review comments from the shopping platform via API, allowing new review comments to be added to the system.

2. Data Preprocessing

The server preprocesses the collected review comment data. Preprocessing includes removing unnecessary spaces and special characters, splitting review comments, and standardizing language.

3. Product Relevance Assessment

The server compares the review comment with a feature word list based on product attributes. For example, if the review is about a smartphone, a word list such as "image quality," "battery," and "operability" will be set.

The server scores the frequency with which words included in the word list appear in the review comments, and if the score is above a certain level, the review comment is determined to be a "review with high product relevance."

Example:

Product: Smartphone

Review comment: "The image quality of this smartphone is amazing."

Score: "Image quality" is included in the word list, so the score is high.

4. Identifying unnatural reviews

The server analyzes patterns in review comments posted within a certain period of time, checking to see if similar reviews have been posted consecutively within a short period of time.

The server will flag reviews if any unusual patterns are detected.

Example:

Review 1: "Great product!"

Review 2: "Great product!"

Review 3: "Great product!"

Verdict: Unnatural review and flagging.

5. Judging Copy-Paste Reviews

Every time a new review comment is posted, the server compares it with all existing review comments to see if any have the exact same content.

If the server finds an exact match, it will flag the review as a "copy-and-paste review."

Example:

Review 1: "This product is amazing!"

Review 2: "This product is amazing!"

Verdict: Copy and paste review and flagging.

6. Feedback

When a review is submitted, the server will only allow it to be submitted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted.

The server filters out inappropriate reviews and displays an error message to the user. It also notifies the administrator of the review content and the judgment result.

This system allows users to select products based on reliable review information, improving the quality of reviews across the entire online shopping platform.

The processing flow is explained below.

Step 1:

Collecting review comments

The server uses an API from the shopping platform to periodically retrieve all review comments. This collection includes review comments for all products.

Step 2:

Data preprocessing

The server stores the collected review comments as text data. Next, it performs a cleaning process to remove unnecessary spaces, special characters, and HTML tags from the review comments. It then tokenizes the review comments into words and sentences, converting them into an analyzable form.

Step 3:

Product relevance determination

The server pre-sets a word list based on the characteristics and attributes of each product. When a review comment is posted, the server compares the words in the comment with the word list. For example, for a review about a smartphone, a word list such as "image quality," "battery," and "operability" is used. The server scores how often words from the word list appear in the comment, and if the score is above a certain level, it determines that the review is "highly relevant to the product."

Step 4:

Determining unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It determines whether reviews with similar content or writing style have been posted in succession within a short period of time. If the server detects an unnatural pattern, it flags the review comment.

Step 5:

Copy-and-paste review verdict

Each time a new review comment is submitted, the server compares it with all existing review comments. It uses sophisticated text comparison algorithms to determine whether a review comment with the exact same content already exists. If the server finds a match, it flags the review comment as a "copy-and-paste review."

Step 6:

Feedback and filtering

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not flagged as being inappropriate, unnatural, or copied and pasted. If a flag is raised, the server will display an error message to the user explaining the reason for the posting. The server will also notify administrators of the fraudulent review and help them review the review.

Based on these concrete steps, we will be able to provide users with reliable review information and improve the quality of the entire shopping platform.

(Example 1)

Next, we will explain Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

On online shopping platforms, the reliability of review comments, which users use as a reference when selecting products, is important. However, fake reviews, copy-and-paste reviews, and reviews with unnatural patterns are rampant, making it difficult for users to obtain accurate information. For this reason, there is a need for a system that can evaluate the reliability of review comments and provide users with accurate review information.

The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

In this invention, the server includes means for collecting review comments, means for pre-processing data on the review comments, means for comparing the review comments with a feature word list to determine product relevance, means for analyzing patterns of the review comments to determine unnatural reviews, means for comparing review comments to determine comments with identical content as copy-and-paste reviews, and means for providing feedback on the review relevance, unnaturalness, and copy-and-paste determination results. This enables users to select products based on highly reliable review information.

"Review comments" are opinions and ratings posted by users about products on online shopping platforms.

"Data preprocessing" refers to the process of removing unnecessary spaces and special characters from the text data of collected review comments, and performing tokenization and language standardization.

A "characteristic word list" is a list of keywords based on product attributes that are set up to evaluate the reliability of review comments about a product.

"Product relevance" is an indicator that shows the degree to which review comments mention a specific product and the degree of match with the feature word list.

"Pattern analysis" is the process of analyzing the posting patterns of review comments and determining whether the same or similar content has been posted consecutively within a certain period of time.

An "unnatural review" is a review that is deemed to deviate from normal user behavior, such as when similar comments are posted in succession within a short period of time.

A "copy-and-paste review" is a comment that is posted by simply copying an existing review comment, and refers to a review with exactly the same content.

"Feedback" is a process that notifies users and administrators of the relevance, unnaturalness, and copy-and-paste judgment results of review comments, allowing only appropriate reviews.

The present invention is a system that evaluates the reliability of review comments on online shopping platforms, allowing users to obtain more accurate review information. Specific embodiments are described in detail below.

Collecting review comments

The server periodically retrieves all review comments using the shopping platform's API. This periodically saves the comments, including the most recent ones, to the database. The specific software used is the Python requests library.

Data preprocessing

The server preprocesses the collected review comment data. This includes removing unnecessary whitespace and special characters, tokenizing the text data, and unifying the language. This process uses the Python nltk library and re module.

Product relevance determination

The server compares the review comments with a feature word list based on product attributes. For example, for a review about a smartphone, a feature word list such as "image quality," "battery," and "operability" is set. The server scores the frequency with which words included in the word list appear in the review comments, and if the score is above a certain level, the review comment is deemed to be "highly relevant to the product." The specific software used is the Python scikit-learn library.

Specific examples

Product: Smartphone

Review comment: "The image quality of this smartphone is amazing."

Since "image quality" is included in the word list, it is judged to have a high score.

Identifying unnatural reviews

The server analyzes patterns in review comments posted within a certain period of time, checking to see if similar reviews have been posted consecutively within a short period of time. If the server detects an unnatural pattern, it flags those reviews. This process uses Python's Pandas library and time series analysis.

Specific examples

Review 1: "Great product!"

Review 2: "Great product!"

Review 3: "Great product!"

The server will flag these as unnatural reviews.

Copy-and-paste review verdict

Every time a new review comment is posted, the server compares it with all existing review comments to see if there are any identical comments. If the server finds a matching comment, it flags the review as a "copy-and-paste review." The software uses the Python difflib library.

Specific examples

Review 1: "This product is amazing!"

Review 2: "This product is amazing!"

The server determines that Review 2 is a copy-and-paste review and flags it.

Feedback

When a review is posted, the server will only allow it to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. Inappropriate reviews are filtered out and an error message is displayed to the user. The server also notifies the administrator of the review content and the result of the judgment. This process uses the Python Flask or Django framework and an email server (SMTP) for notifications.

Example prompt

Please rate the user-submitted review comment, "This phone has excellent battery life." and provide feedback based on the following criteria:

Conditions:

1. To determine whether a review is highly relevant to the product, it is scored based on a list of characteristic words such as "battery," "lifespan," and "excellent."

2. Check to see if similar reviews have been posted consecutively within a certain period of time.

3. Compare with existing review comments to check if the review is a copy-and-paste one.

This system will enable users to select products based on reliable review information, and is expected to improve the quality of reviews across online shopping platforms.

The flow of the identification process in Example 1 will be explained using Figure 11.

Step 1:

Collects review comments. The server periodically retrieves all review comments through the shopping platform's API. The input is the API request, and the output is the retrieved review comment data in JSON format. The server sends the API request and stores the received data in a database.

Step 2:

Performs data preprocessing. The server performs preprocessing on the collected review comment data. The input is JSON-formatted review comment data, and the output is preprocessed text data. The server removes unnecessary whitespace and special characters, tokenizes the text data, and standardizes the language.

Step 3:

Determines product relevance. The server compares preprocessed review comments with a feature word list based on product attributes. The input is preprocessed text data and a feature word list, and the output is scored review comment data. The server scores how often words included in the word list appear in the review comments, and if the score is above a certain level, it determines the review to be "highly relevant to the product."

Step 4:

Identifies unnatural reviews. The server analyzes patterns in review comments posted within a certain period of time. The input is review comment data from a specific period of time, and the output is the judgment result and flagged data. The server checks whether reviews with similar content have been posted in succession within a short period of time, and if an unnatural pattern is detected, it flags those reviews.

Step 5:

Determines copy-and-paste reviews. Every time a new review comment is posted, the server compares it with all existing review comments. The input is the new review comment and existing review comment data, and the output is the determination result and flagged data. If the server finds a matching comment, it flags the review as a "copy-and-paste review."

Step 6:

Provides feedback. The server will only allow a review to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. The input is the review comment and various judgment results, and the output is notifications to the user and administrator. The server filters out inappropriate reviews, displays an error message to the user, and notifies the administrator of the review content and judgment results.

(Application Example 1)

Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

On conventional shopping platforms, many unreliable review comments were posted, causing users to make incorrect purchasing decisions. There was also the problem of similar reviews and copy-paste reviews being posted within a short period of time, reducing the reliability of the reviews. Therefore, there was a need to develop a system that could provide users with reliable review information and help them make more accurate purchasing decisions.

The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

In this invention, the server includes means for collecting review comments, means for pre-processing data on the review comments, means for comparing the review comments with a list of characteristic words to determine product relevance, means for analyzing patterns of the review comments to determine unnatural reviews, means for comparing review comments to determine comments with identical content as copy-and-paste reviews, means for providing feedback on the relevance, unnaturalness, and copy-and-paste determination results of the reviews, means for evaluating and providing feedback on the reliability of the review comments in real time, and means for displaying reviews in order of reliability. This allows users to receive reliable reviews in real time and make more accurate purchasing decisions based on them.

A "review comment" is a written comment written by a user expressing their evaluation or opinion of a product or service.

"Means of collection" refers to the method by which data is obtained from online platforms and entered into the system.

"Data preprocessing" is the process of removing unnecessary information and formatting acquired data to make it easier to analyze.

A "characteristic word list" is a list of important keywords related to a specific product or service.

"Product relevance" is the degree to which a review comment relates to a particular product or service.

"Pattern analysis methods" are methods for detecting certain templates or similarities in review comments.

"Unnatural reviews" are comments that deviate from normal user behavior, such as those posted in large numbers in a short period of time or those that contain repeated, repeated comments.

A "copy-and-paste review" is a review comment in which the exact same content as another comment is copied and pasted.

"Means of providing feedback" refers to methods for notifying users and administrators of evaluation results and encouraging them to take appropriate action.

"Means for assessing trustworthiness in real time" refers to a method that automatically determines the accuracy and credibility of a review the moment it is posted.

"Displaying in order of reliability" is a method of displaying highly rated review comments at the top, making them easier for users to refer to.

The system of the present invention evaluates the reliability of review comments on shopping platforms, allowing users to obtain more accurate review information. This system is implemented through the following process:

Hardware to use

Smartphone: Used by users as a device to post review comments.

Server: A central computer that collects review comments, preprocesses data, analyzes, evaluates, and provides feedback.

API server: Used as an interface to retrieve review comments from the shopping platform.

Software used

Python: Used for server-side data processing and analysis.

Flask: A Python web framework used to build API servers.

MySQL: Used as a database management system to store collected review comments.

Natural language processing library: Used for preprocessing and parsing review comments.

Data processing and calculation flow

1. Collecting review comments

The server periodically retrieves review comments from the shopping platform via API. This API server is built using Flask, and the retrieved data is stored in a MySQL database.

2. Data Preprocessing

The server preprocesses the retrieved review comment data. This preprocessing includes removing unnecessary whitespace and special characters, splitting review comments, and standardizing language using a Python natural language processing library.

3. Product Relevance Assessment

The server compares the review comment with a list of characteristic words based on product attributes. For example, a review about a smartphone would use keywords such as "image quality," "battery," and "operability." The server then scores the review comment, and if it scores above a certain level, it determines that the review comment is "highly relevant to the product."

4. Identifying unnatural reviews

The server analyzes review comments posted within a certain period of time to see if similar reviews have been posted in succession within a short period of time. If an unnatural pattern is detected, those reviews are flagged.

5. Judging Copy-Paste Reviews

The server compares the newly posted review comment with all existing review comments. It checks to see if there are any identical comments, and if there is an exact match, it flags it as a "copy-and-paste review."

6. Feedback

When a review is posted, the server will only allow it to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted, and will provide real-time feedback to the user. It also has a function to display reviews in order of reliability.

Specific examples and prompt sentence examples

As a concrete example, consider the following review comment:

Product: Smartphone

Review: "This phone's battery lasts a long time."

An example of a prompt is as follows:

"Please tell us if this review is relevant to the product: 'This phone's battery lasts a long time.'"

"Please tell us if this review fits any unnatural pattern: 'This phone's battery lasts a long time.'"

"Please tell us if this review exactly matches an existing review: 'This phone's battery lasts a long time.'"

This will allow users to choose products based on reliable reviews, improving the quality of ratings across online shopping platforms.

The flow of the specific processing in Application Example 1 will be explained using Figure 12.

Step 1:

Collecting review comments:

The server periodically collects review comments using an API provided by the shopping platform. The server receives the review comments obtained via the API in JSON format and stores them in a MySQL database. The input is the JSON data obtained from the API, and the output is the review comments stored in the database.

Step 2:

Data preprocessing:

The server preprocesses the collected review comment data. It uses Python's regular expression library to remove unnecessary whitespace and special characters and split the review comments into sentences. It also converts data in different formats into a unified format. The input is the raw review comments, and the output is the preprocessed, clean data.

Step 3:

Product relevance determination:

The server compares the preprocessed review comments with a pre-set feature word list. The server calculates the frequency of occurrence of words included in the feature word list, and determines that a product is highly relevant if the frequency is above a certain score. The input is the preprocessed review comments and the feature word list, and the output is data flagged as highly relevant reviews.

Step 4:

Determining unnatural reviews:

The server compares the preprocessed review comments with other review comments posted within a certain period of time and analyzes patterns. If a large number of similar review comments are posted in a short period of time, the server determines that they are unnatural reviews and flags them. The input is the preprocessed review comments and past review comments, and the output is data flagged as unnatural reviews.

Step 5:

Copy and paste review verdict:

The server compares the newly posted review comment with all existing review comments based on content similarity. If the server finds a review comment with exactly the same content, it flags it as a copy-and-paste review. The input is the new review comment and the existing review comment, and the output is the data determined to be a copy-and-paste review.

Step 6:

Feedback:

The server provides real-time feedback to reviewers based on the review's relevance, unnaturalness, and copy-and-paste assessment results. Reviews are displayed on the user's device in order of reliability. Reviews with low reliability are rejected, and the user is notified of the reason. The input is the review assessment results, and the output is a feedback message.

This allows users to make more accurate purchasing decisions based on reliable review comments.

It is also possible to further combine an emotion engine that estimates the user's emotion. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

The system of the present invention evaluates the reliability of review comments on shopping platforms and further optimizes review information by recognizing user sentiment. The program processing of this system is explained below in natural language.

Process Overview

1. Collecting review comments

The server periodically retrieves all review comments from the shopping platform via API. The collected review comments are stored in a database.

2. Data Preprocessing

The server cleans the collected review comments, removing unnecessary whitespace, special characters, and HTML tags. It also tokenizes the review comments into words and sentences, making them easier to analyze.

3. Product Relevance Assessment

The server compares review comments with a word list based on the features and attributes of each product. For example, for a review about a smartphone, a word list would be prepared, including "image quality," "battery," and "operability."

The server scores how often words from the word list appear in the review comments, and if the score is above a certain level, it determines the review to be "highly relevant to the product."

Example:

Product: Smartphone

Review comment: "The image quality of this smartphone is outstanding."

Score: "Image quality" is included in the word list, so the score is high.

4. Identifying unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It checks to see if reviews with similar content or writing style have been posted consecutively within a short period of time.

If the server detects any unusual patterns, it will flag the review comment.

Example:

Review 1: "This is a great product!"

Review 2: "This is a great product!"

Review 3: "This is a great product!"

Verdict: Unnatural review and flagging.

5. Judging Copy-Paste Reviews

Every time a new review comment is submitted, the server compares it with all existing review comments, using an advanced text comparison algorithm to check whether a review comment with the exact same content already exists.

If the server finds a match, it flags the review comment as a "copy-and-paste review."

Example:

Review 1: "This product is amazing!"

Review 2: "This product is amazing!"

Verdict: Copy and paste review and flagging.

6. Emotion Recognition Using an Emotion Engine

The server analyzes the review comments using an emotion engine and classifies them into positive, negative, or neutral sentiment.

The server calculates the emotional score of the review comments based on the scoring by the emotion engine and reflects this in the overall rating of the product.

Example:

Review comment: "This phone's battery dies so quickly it's useless."

Sentiment analysis result: Negative

Score: Reflected as a low rating.

7. Feedback and Filtering

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. If a flag is raised, the server will display an error message to the user explaining the reason for the post.

The server notifies the user and administrator of the feedback along with the emotion score generated by the emotion engine. Administrators are also notified to further review and respond to the review.

As a result, the system of the present invention ensures the reliability of review comments and provides a platform that users can use with peace of mind. The introduction of an emotion engine further improves the quality and reliability of reviews, and more accurately reflects product evaluation information.

The processing flow is explained below.

Step 1:

Collecting review comments

The server periodically retrieves all review comments from the shopping platform via API. The collected review comments are stored in a database.

Step 2:

Data preprocessing

The server cleans the collected review comments. Specifically, it removes unnecessary spaces, special characters, and HTML tags. It also tokenizes the review comments into words and sentences, preparing them in an analyzable form.

Step 3:

Product relevance determination

The server compares review comments using a word list based on the features and attributes of each product. It compares the words in the review comments with the word list and generates a score. For example, a word list related to smartphones might include "image quality," "battery," and "operability."

The server scores the frequency with which words included in the word list appear, and if the score is above a certain level, it determines that the review is "highly relevant to the product."

Step 4:

Determining unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It determines whether reviews with similar content or writing style have been posted in succession within a short period of time. In particular, it compares sentence length, the words used, sentence structure, etc.

If the server detects any unusual patterns, it will flag the review comment.

Step 5:

Copy-and-paste review verdict

Every time a new review comment is submitted, the server compares it with all existing review comments, using an advanced text comparison algorithm to check whether a review comment with the exact same content already exists.

If the server finds a match, it flags the review comment as a "copy-and-paste review."

Step 6:

Emotion recognition using an emotion engine

The server uses an emotion engine to analyze review comments and classify them into positive, negative, or neutral sentiment. Specifically, it uses a natural language processing algorithm to extract and score emotional expressions contained in the sentences.

The server calculates the emotional score of the review comments based on the scoring by the emotion engine and reflects this in the overall rating of the product.

Step 7:

Feedback and filtering

The server will only allow a review comment to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. If any flags are raised, the server will display an error message to the user explaining why the post was rejected.

The server filters out inappropriate reviews and notifies users and administrators, including the sentiment score generated by the sentiment engine. Administrators are sent detailed information such as the review content, the reason it was flagged, and the sentiment score, and are offered help in re-checking the review if necessary.

Based on these specific steps, the system of the present invention ensures the reliability of review comments and provides a platform that users can use with confidence. The integration of an emotion engine further improves the quality and reliability of reviews, and more accurately reflects product evaluation information.

(Example 2)

Next, we will explain Example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

Traditional shopping platforms lacked an appropriate mechanism for determining the authenticity of review comments, leaving users at risk of making purchasing decisions based on inaccurate information. This has created a need to improve the reliability of review comments and provide an environment where users can use them with peace of mind. It is also necessary to accurately understand the sentiment behind review comments in order to more accurately reflect product evaluation information.

The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting review comments, means for performing data preprocessing of the review comments, means for determining product relevance by comparing the review comments with a characteristic word list, means for analyzing the patterns of the review comments to determine unnatural reviews, means for comparing the review comments to determine comments with identical content as copy-and-paste reviews, means for analyzing the sentiment of the review comments, means for providing feedback on the review relevance, unnaturalness, copy-and-paste determination results, and sentiment analysis results, and means for rejecting the posting of review comments that are unnatural or copy-and-paste. This improves the reliability of review comments, provides an environment where users can refer to reviews with confidence, and makes it possible to more accurately reflect product evaluation information.

"Review comments" are textual opinions and evaluations written by users on shopping platforms about products and services.

"Data preprocessing" is the process of removing unnecessary elements from collected review comments and converting them into a format suitable for analysis.

A "characteristic word list" is a list of keywords related to a specific product or service that is used to compare with review comments.

"Product relevance determination" is the process of determining whether a review comment is relevant to a specific product or service.

"Pattern analysis" is the process of analyzing the content and format of review comments to detect specific patterns or anomalies.

"Unnatural reviews" are review comments that show an unusual pattern, such as content or writing style being posted repeatedly within a short period of time.

A "copy-and-paste review" refers to a review comment that has exactly the same content as an existing review comment.

"Sentiment analysis" is the process of analyzing the content of review comments and classifying their sentiments as positive, negative, or neutral.

"Feedback" refers to the provision of information to notify users or administrators of analysis and judgment results, and to encourage them to take necessary action.

"Posting refusal" refers to the action of not allowing users to post in order to prevent unnatural reviews or copy-and-paste reviews from being posted.

A "server" is a computer system that manages and executes a series of processes, including the collection, preprocessing, analysis, judgment, feedback, and rejection of review comments.

The system of the present invention evaluates the reliability of review comments on a shopping platform, recognizes user emotions, and optimizes review information. The specific operations and processes for this purpose are described below.

1. Collecting review comments

The system retrieves review comments through the shopping platform's API. The server periodically sends requests to the API endpoint and stores the retrieved review comments in a database. Specifically, MySQL or PostgreSQL can be used as the database.

For example, the server accesses the API endpoint "https://example.com/api/reviews" and stores the retrieved review comments in the "reviews" table.

2. Data Preprocessing

The server cleans the retrieved review comments. Specifically, it removes unnecessary whitespace, special characters, and HTML tags. It also tokenizes the review comments into words and sentences. This preprocessing can be performed using NLPK, a Python NLP library.

For example, a comment such as "This product is <p>great</p>!" is text cleaned to "This product is great!" and then tokenized.

3. Product Relevance Assessment

The server generates a word list based on the features and attributes of each product and compares it with the review comments. For example, for smartphone reviews, a word list containing keywords such as "image quality," "battery," and "operability" is used.

Specifically, the frequency of keywords appearing in review comments is scored, and if the score is above a certain level, it is determined to be a "review with high product relevance." For example, the server analyzes a comment such as "The image quality of this smartphone is outstanding," and assigns a high score because "image quality" is included in the word list.

4. Identifying unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. Specifically, it checks to see if review comments with similar content or format have been posted consecutively within a short period of time.

If an unnatural pattern is detected, the review comment is flagged. For example, if the server sees multiple reviews with the same content, such as "Great product!", posted within a short period of time, it will flag them as unnatural.

5. Judging Copy-Paste Reviews

Each time a new review comment is submitted, the server compares it with all existing review comments, using sophisticated text comparison algorithms (e.g., Python's difflib library) to determine whether there is a match.

If a match is found, the server will flag the review comment as a "copy-and-paste review." For example, if a comment already exists that says "This product is amazing!", the server will add a flag.

6. Emotion Recognition Using an Emotion Engine

The server inputs the review comments into a sentiment analysis engine and classifies them into positive, negative, or neutral sentiment. Specifically, sentiment analysis libraries such as TextBlob and VADER can be used.

This allows us to calculate an emotional score, which is then reflected in the overall rating of the product. For example, we can use TextBlob to analyze a comment such as "This phone's battery runs out quickly, so it's useless" and assign it a negative score.

7. Feedback and Filtering

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not related to the product, unnatural, or copied and pasted. If so, an error message will be displayed to the user explaining the reason for the post.

The emotion engine also notifies users and administrators of the emotion score, helping to improve the reliability of reviews. For example, the server may notify users that "this review has been flagged as unnatural" and encourage them to resubmit. It may also notify administrators that "a new unnatural review has been detected. Please check it."

Example prompt for a generative AI model

"Did this review comment relate to a specific product? Please categorize its sentiment. Example: 'The image quality of this phone is outstanding.'"

"Please determine whether the review comments on this listing are unnatural. Example: 'Great product!', 'Great product!'"

"Check if this review comment matches an existing comment or is a copypasta review. Example: 'This product is amazing!'"

The above is a form for implementing the system of the present invention.

The flow of the identification process in Example 2 will be explained using Figure 13.

Step 1:

Collecting review comments:

Input: Shopping platform API endpoint URL

Specific behavior: The server periodically sends requests to an API endpoint to retrieve review comments. For example, it accesses the API endpoint "https://example.com/api/reviews".

Data processing: Metadata (user ID, product ID, posting date and time, etc.) is added to the acquired review comments.

Output: Dataset containing review comments and metadata

Specific operation: The server stores the acquired dataset in a database (e.g., MySQL or PostgreSQL).

Step 2:

Data preprocessing:

Input: Review comments stored in the database

What it does: The server cleans the review comments. Specifically, it uses a Python NLP library (e.g., NLPK) to remove unnecessary whitespace, special characters, and HTML tags.

Data processing: Tokenize review comments into words and sentences.

Output: Clean, tokenized review comments

Specific operation: For example, a comment such as "This product is <p>great</p>!" is cleaned to "This product is great!" and separated into individual words.

Step 3:

Product relevance determination:

Input: Clean, tokenized review comments, product feature word list

Specific operation: The server compares the review comments with the feature word list. The word list includes keywords based on product attributes such as "image quality," "battery," and "operability."

Data calculation: Score the frequency of keywords appearing in review comments.

Output: Product relevance score

Specific behavior: For example, a comment such as "The image quality of this smartphone is outstanding" will be given a high score if the word list includes "image quality."

Step 4:

Determining unnatural reviews:

Input: All review comments posted within a certain period

Specific operation: The server analyzes the content patterns of review comments. It checks whether reviews with the same content or writing style have been posted consecutively.

Data calculations: Analysis to detect unnatural patterns

Output: Review comments flagged as unnatural

Specific behavior: For example, if the same review saying "This is a great product!" is posted multiple times within a short period of time, it will be flagged as unnatural.

Step 5:

Copy and paste review verdict:

Input: New review comment, Existing review comment

What it does: The server uses advanced text comparison algorithms (e.g., Python's difflib library) to compare the new comment with existing review comments.

Data calculation: The process of checking whether the content of comments matches.

Output: Review comments flagged as copy-paste reviews

Specific behavior: For example, if a comment saying "This product is amazing!" already exists, add a flag.

Step 6:

Emotion recognition using the emotion engine:

Enter: Review comment

Specific operation: The server inputs the review comments into a sentiment analysis engine (e.g., TextBlob or VADER) and classifies the sentiment.

Data calculation: Calculating emotion scores

Output: Review comments with sentiment scores

Specific behavior: For example, a comment such as "This smartphone's battery runs out quickly, making it useless" is scored as negative.

Step 7:

Feedback and filtering:

Input: Review comments (with flags for relevance, unnaturalness, and copy-paste), sentiment score

Specific behavior: When an attempt is made to post a review comment, the server will only allow it to be posted if it is not related to the product, unnatural, or copied and pasted. If so, an error message will be displayed to the user.

Data calculation: feedback and submission evaluation

Output: Notification to users and administrators

Specific behavior: For example, the server notifies the user that "this review has been flagged as unnatural" and encourages them to resubmit, while simultaneously notifying the administrator that "a new unnatural review has been detected."

The above are the specific processing steps of this system's program.

(Application Example 2)

Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

Traditional review comment rating systems often lack the functionality to fully guarantee the reliability of reviews. For example, they often contain a mixture of reviews that are unrelated to the product, unnatural reviews, and copy-and-paste reviews, making it difficult for users to obtain accurate information. There is also a demand for more accurate product ratings through sentiment analysis of review comments. However, current systems lack sentiment analysis functionality, making it impossible to improve the quality and reliability of reviews.

The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

In this invention, the server includes means for collecting review comments, means for pre-processing data on the review comments, means for comparing the review comments with a list of characteristic words to determine product relevance, means for analyzing patterns of the review comments to determine unnatural reviews, means for comparing review comments to determine comments with identical content as copy-and-paste reviews, means for performing sentiment analysis on the review comments, and means for providing feedback on the review relevance, unnaturalness, copy-and-paste determination results, and sentiment analysis results. This allows users to obtain highly reliable review information and more accurately evaluate products.

"Review comments" refer to impressions and evaluations written by users about products and services.

"Means of collection" refers to the process or function of obtaining specific information from the Internet or a database.

"Data preprocessing" refers to the process of analyzing collected data or performing pre-analysis processing to remove unnecessary parts and format the data.

A "characteristic word list" refers to a list of important keywords related to a specific product or category.

"Means for determining product relevance" refers to the methods or algorithms used to evaluate how relevant a review comment is to a particular product.

"Methods of analyzing patterns to identify unnatural reviews" refers to methods of analyzing the content and posting patterns of review comments to detect unnatural content and typical actions.

A "copy-and-paste review" refers to a review comment that contains the same content as another review comment, copied and pasted exactly as is.

"Sentiment analysis" refers to the technology of analyzing user emotions and intentions from text data and classifying them as positive, negative, or neutral.

"Feedback" refers to the process of returning analysis and evaluation results to the user or system.

Form for implementing the invention

This invention is a system that improves the reliability of review comments on shopping platforms and provides users with optimal information. This system collects review comments, performs data preprocessing, and analyzes product relevance, unnaturalness, whether or not they have been copied and pasted, and sentiment before providing feedback.

System Overview

The server includes the following means:

1. How to collect review comments:

The server periodically retrieves all review comments from the shopping platform via API. These collected review comments are stored in a database.

2. Methods for preprocessing review comment data:

The server cleans the collected review comments. Specifically, it removes unnecessary whitespace, special characters, and HTML tags, tokenizes the review comments into words and sentences, and prepares them in an analyzable form.

3. How to determine product relevance by comparing review comments with a list of characteristic words:

The server compares review comments with a word list based on the characteristics and attributes of each product. For example, for a review about a smartphone, a word list such as "image quality," "battery," and "operability" would be prepared. The server scores the number of times words from the word list appear in the review comments, and if the score is above a certain level, it is determined to be a "review highly relevant to the product."

4. How to analyze review comment patterns and identify unnatural reviews:

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It checks to see if reviews with similar content or writing style have been posted consecutively within a short period of time, and if an unnatural pattern is detected, it flags the review comment.

5. How to compare review comments and identify comments with identical content as copy-and-paste reviews:

Every time a new review comment is submitted, the server compares it with all existing review comments. Using sophisticated text comparison algorithms, it checks whether an identical review comment already exists, and if a match is found, it flags the review comment as a "copy-and-paste review."

6. How to perform sentiment analysis on review comments:

The server analyzes the review comments using an emotion engine and classifies them into positive, negative, and neutral emotions. Based on the scoring by the emotion engine, the emotion score of the review comments is calculated and reflected in the overall rating of the product.

7. Means of providing feedback on review relevance, unnaturalness, copy-paste determination results, and sentiment analysis results:

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not flagged as being inappropriate, unnatural, or copied and pasted. If a flag is raised, an error message will be displayed to the user, explaining the reason for the post. Feedback will be provided to the user and administrator, along with the sentiment score calculated by the sentiment engine, and administrators will be notified, urging them to further review and take action.

Hardware and software used

Hardware: Servers, cloud storage devices

Software: Python, requests, BeautifulSoup, re, nltk, textblob, scikit-learn, emotion engine (TextBlob, etc.)

Specific examples

As a concrete example, we will show the steps for processing the review comment "The image quality of this smartphone is outstanding." This comment is determined to be highly relevant to the product because it contains the keyword "image quality," and is approved because it does not match unnatural reviews or copy-paste reviews.

Example prompt

Example of a prompt to input to a generative AI model:

Analyze the new review comment, "The image quality of this phone is outstanding." We'll rate it based on the following criteria:

1. Product Relevance

2. Unnatural patterns

3. Copy and paste

4. Sentiment analysis

The flow of the specific processing in Application Example 2 will be explained using Figure 14.

Step 1:

Collecting review comments

The server periodically calls the shopping platform's API to retrieve review comments for each product. As input, it uses the API endpoint URL and authentication information. As output, it generates JSON data containing the retrieved review comments. This data is stored in the server's database.

Step 2:

Data preprocessing

The server cleans the collected review comments. As input, it uses the text data of the review comments stored in the database. Specifically, it removes unnecessary whitespace, special characters, and HTML tags, and tokenizes the review comments into words and sentences. As output, clean text data is generated and passed to the next step.

Step 3:

Product relevance determination

The server evaluates the relevance of review comments using a word list based on the features and attributes of each product. As input, it uses the clean review comments and the feature word list. Specifically, it scores how often words included in the feature word list appear in the review comments. As output, it generates a relevance score for each review comment.

Step 4:

Determining unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns. As input, it uses text data from review comments over a certain period of time in the past and the current review comment. Specifically, it applies a text pattern matching algorithm to evaluate the similarity. As output, it generates a flag indicating whether the review is unnatural.

Step 5:

Copy-and-paste review verdict

Each time a new review comment is posted, the server compares it with all existing review comments. It uses the data of the new review comment and the existing review comments as input. Specifically, it uses an advanced text comparison algorithm (e.g., cosine similarity) to check whether a review comment with the exact same content exists. As output, it generates a flag indicating whether the review is a copy-and-paste review.

Step 6:

sentiment analysis

The server parses the review comments into the sentiment engine. It uses the clean review comments as input. Specifically, it sends the text to the sentiment engine (e.g., TextBlob) and obtains a sentiment score: positive, negative, or neutral. The output is a sentiment score for each review comment.

Step 7:

Feedback and filtering

When an attempt is made to post a review comment, the server provides feedback based on the judgment results obtained in the previous steps. All judgment results (relevance, unnaturalness, copy-paste judgment results, and sentiment score) are used as input. Specific behavior is to allow posting only if no flags are raised, and to display an error message to the user if a flag is raised. More detailed feedback is then provided to the administrator. As output, an error message or approval message is displayed to the user, and the review comment is saved in the database.

The specific processing unit 290 transmits the results of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the results of the specific processing. The microphone 238 acquires audio indicating the user input regarding the results of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

Data generation model 58 is what is known as generative AI (artificial intelligence). Examples of data generation model 58 include generative AI such as ChatGPT (Internet search <URL: https://openai.com/blog/chatgpt>) and Gemini (Internet search <URL: https://gemini.google.com/?hl=ja>). Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing an instruction is input to data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input. Data generation model 58 performs inference on the input inference data in accordance with the instructions indicated by the prompt, and outputs the inference results in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization.

In the above embodiment, an example was given in which the specific processing was performed by the data processing device 12, but the technology disclosed herein is not limited to this, and the specific processing may also be performed by the smart glasses 214.

[Third embodiment]

Figure 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

As shown in FIG. 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

The data processing device 12 includes a computer 22, a database 24, and a communication I/F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and communication I/F 26 are also connected to the bus 34. The communication I/F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and/or a LAN (Local Area Network).

The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I/F 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user 20's surroundings (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

The communication I/F 44 is connected to the network 54. The communication I/Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I/Fs 44 and 26 is carried out in a secure manner.

Figure 6 shows an example of the main functions of the data processing device 12 and headset terminal 314. As shown in Figure 6, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32.

The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as the specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

Storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

In the headset terminal 314, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

Next, we will explain the identification process performed by the identification processing unit 290 of the data processing device 12. In the following explanation, the data processing device 12 will be referred to as the "server" and the headset-type terminal 314 will be referred to as the "terminal."

The system of the present invention evaluates the reliability of review comments on shopping platforms and provides appropriate feedback, allowing users to obtain more accurate review information. The program processing of this system is explained below in natural language.

Process Overview

1. Collecting review comments

The server periodically retrieves all review comments from the shopping platform via API, allowing new review comments to be added to the system.

2. Data Preprocessing

The server preprocesses the collected review comment data. Preprocessing includes removing unnecessary spaces and special characters, splitting review comments, and standardizing language.

3. Product Relevance Assessment

The server compares the review comment with a feature word list based on product attributes. For example, if the review is about a smartphone, a word list such as "image quality," "battery," and "operability" will be set.

The server scores the frequency with which words included in the word list appear in the review comments, and if the score is above a certain level, the review comment is determined to be a "review with high product relevance."

Example:

Product: Smartphone

Review comment: "The image quality of this smartphone is amazing."

Score: "Image quality" is included in the word list, so the score is high.

4. Identifying unnatural reviews

The server analyzes patterns in review comments posted within a certain period of time, checking to see if similar reviews have been posted consecutively within a short period of time.

The server will flag reviews if any unusual patterns are detected.

Example:

Review 1: "Great product!"

Review 2: "Great product!"

Review 3: "Great product!"

Verdict: Unnatural review and flagging.

5. Judging Copy-Paste Reviews

Every time a new review comment is posted, the server compares it with all existing review comments to see if any have the exact same content.

If the server finds an exact match, it will flag the review as a "copy-and-paste review."

Example:

Review 1: "This product is amazing!"

Review 2: "This product is amazing!"

Verdict: Copy and paste review and flagging.

6. Feedback

When a review is submitted, the server will only allow it to be submitted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted.

The server filters out inappropriate reviews and displays an error message to the user. It also notifies the administrator of the review content and the judgment result.

This system allows users to select products based on reliable review information, improving the quality of reviews across the entire online shopping platform.

The processing flow is explained below.

Step 1:

Collecting review comments

The server uses an API from the shopping platform to periodically retrieve all review comments. This collection includes review comments for all products.

Step 2:

Data preprocessing

The server stores the collected review comments as text data. Next, it performs a cleaning process to remove unnecessary spaces, special characters, and HTML tags from the review comments. It then tokenizes the review comments into words and sentences, converting them into an analyzable form.

Step 3:

Product relevance determination

The server pre-sets a word list based on the characteristics and attributes of each product. When a review comment is posted, the server compares the words in the comment with the word list. For example, for a review about a smartphone, a word list such as "image quality," "battery," and "operability" is used. The server scores how often words from the word list appear in the comment, and if the score is above a certain level, it determines that the review is "highly relevant to the product."

Step 4:

Determining unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It determines whether reviews with similar content or writing style have been posted in succession within a short period of time. If the server detects an unnatural pattern, it flags the review comment.

Step 5:

Copy-and-paste review verdict

Each time a new review comment is submitted, the server compares it with all existing review comments. It uses sophisticated text comparison algorithms to determine whether a review comment with the exact same content already exists. If the server finds a match, it flags the review comment as a "copy-and-paste review."

Step 6:

Feedback and filtering

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not flagged as being inappropriate, unnatural, or copied and pasted. If a flag is raised, the server will display an error message to the user explaining the reason for the posting. The server will also notify administrators of the fraudulent review and help them review the review.

Based on these concrete steps, we will be able to provide users with reliable review information and improve the quality of the entire shopping platform.

(Example 1)

Next, Example 1 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset-type terminal 314 will be referred to as the "terminal."

On online shopping platforms, the reliability of review comments, which users use as a reference when selecting products, is important. However, fake reviews, copy-and-paste reviews, and reviews with unnatural patterns are rampant, making it difficult for users to obtain accurate information. For this reason, there is a need for a system that can evaluate the reliability of review comments and provide users with accurate review information.

The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

In this invention, the server includes means for collecting review comments, means for pre-processing data on the review comments, means for comparing the review comments with a feature word list to determine product relevance, means for analyzing patterns of the review comments to determine unnatural reviews, means for comparing review comments to determine comments with identical content as copy-and-paste reviews, and means for providing feedback on the review relevance, unnaturalness, and copy-and-paste determination results. This enables users to select products based on highly reliable review information.

"Review comments" are opinions and ratings posted by users about products on online shopping platforms.

"Data preprocessing" refers to the process of removing unnecessary spaces and special characters from the text data of collected review comments, and performing tokenization and language standardization.

A "characteristic word list" is a list of keywords based on product attributes that are set up to evaluate the reliability of review comments about a product.

"Product relevance" is an indicator that shows the degree to which review comments mention a specific product and the degree of match with the feature word list.

"Pattern analysis" is the process of analyzing the posting patterns of review comments and determining whether the same or similar content has been posted consecutively within a certain period of time.

An "unnatural review" is a review that is deemed to deviate from normal user behavior, such as when similar comments are posted in succession within a short period of time.

A "copy-and-paste review" is a comment that is posted by simply copying an existing review comment, and refers to a review with exactly the same content.

"Feedback" is a process that notifies users and administrators of the relevance, unnaturalness, and copy-and-paste judgment results of review comments, allowing only appropriate reviews.

The present invention is a system that evaluates the reliability of review comments on online shopping platforms, allowing users to obtain more accurate review information. Specific embodiments are described in detail below.

Collecting review comments

The server periodically retrieves all review comments using the shopping platform's API. This periodically saves the comments, including the most recent ones, to the database. The specific software used is the Python requests library.

Data preprocessing

The server preprocesses the collected review comment data. This includes removing unnecessary whitespace and special characters, tokenizing the text data, and unifying the language. This process uses the Python nltk library and re module.

Product relevance determination

The server compares the review comments with a feature word list based on product attributes. For example, for a review about a smartphone, a feature word list such as "image quality," "battery," and "operability" is set. The server scores the frequency with which words included in the word list appear in the review comments, and if the score is above a certain level, the review comment is deemed to be "highly relevant to the product." The specific software used is the Python scikit-learn library.

Specific examples

Product: Smartphone

Review comment: "The image quality of this smartphone is amazing."

Since "image quality" is included in the word list, it is judged to have a high score.

Identifying unnatural reviews

The server analyzes patterns in review comments posted within a certain period of time, checking to see if similar reviews have been posted consecutively within a short period of time. If the server detects an unnatural pattern, it flags those reviews. This process uses Python's Pandas library and time series analysis.

Specific examples

Review 1: "Great product!"

Review 2: "Great product!"

Review 3: "Great product!"

The server will identify these as unnatural reviews and flag them.

Copy-and-paste review verdict

Every time a new review comment is posted, the server compares it with all existing review comments to see if there are any identical comments. If the server finds a matching comment, it flags the review as a "copy-and-paste review." The software uses the Python difflib library.

Specific examples

Review 1: "This product is amazing!"

Review 2: "This product is amazing!"

The server determines that Review 2 is a copy-and-paste review and flags it.

Feedback

When a review is posted, the server will only allow it to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. Inappropriate reviews are filtered out and an error message is displayed to the user. The server also notifies the administrator of the review content and the result of the judgment. This process uses the Python Flask or Django framework and an email server (SMTP) for notifications.

Example prompt

Please rate the user-submitted review comment, "This phone has excellent battery life." and provide feedback based on the following criteria:

Conditions:

1. To determine whether a review is highly relevant to the product, it is scored based on a list of characteristic words such as "battery," "lifespan," and "excellent."

2. Check to see if similar reviews have been posted consecutively within a certain period of time.

3. Compare with existing review comments to check if the review is a copy-and-paste one.

This system will enable users to select products based on reliable review information, and is expected to improve the quality of reviews across online shopping platforms.

The flow of the identification process in Example 1 will be explained using Figure 11.

Step 1:

Collects review comments. The server periodically retrieves all review comments through the shopping platform's API. The input is the API request, and the output is the retrieved review comment data in JSON format. The server sends the API request and stores the received data in a database.

Step 2:

Performs data preprocessing. The server performs preprocessing on the collected review comment data. The input is JSON-formatted review comment data, and the output is preprocessed text data. The server removes unnecessary whitespace and special characters, tokenizes the text data, and standardizes the language.

Step 3:

Determines product relevance. The server compares preprocessed review comments with a feature word list based on product attributes. The input is preprocessed text data and a feature word list, and the output is scored review comment data. The server scores how often words included in the word list appear in the review comments, and if the score is above a certain level, it determines the review to be "highly relevant to the product."

Step 4:

Identifies unnatural reviews. The server analyzes patterns in review comments posted within a certain period of time. The input is review comment data from a specific period of time, and the output is the judgment result and flagged data. The server checks whether reviews with similar content have been posted in succession within a short period of time, and if an unnatural pattern is detected, it flags those reviews.

Step 5:

Determines copy-and-paste reviews. Every time a new review comment is posted, the server compares it with all existing review comments. The input is the new review comment and existing review comment data, and the output is the determination result and flagged data. If the server finds a matching comment, it flags the review as a "copy-and-paste review."

Step 6:

Provides feedback. The server will only allow a review to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. The input is the review comment and various judgment results, and the output is notifications to the user and administrator. The server filters out inappropriate reviews, displays an error message to the user, and notifies the administrator of the review content and judgment results.

(Application Example 1)

Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the headset-type terminal 314 will be referred to as the "terminal."

On conventional shopping platforms, many unreliable review comments were posted, causing users to make incorrect purchasing decisions. There was also the problem of similar reviews and copy-paste reviews being posted within a short period of time, reducing the reliability of the reviews. Therefore, there was a need to develop a system that could provide users with reliable review information and help them make more accurate purchasing decisions.

The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

In this invention, the server includes means for collecting review comments, means for pre-processing data on the review comments, means for comparing the review comments with a list of characteristic words to determine product relevance, means for analyzing patterns of the review comments to determine unnatural reviews, means for comparing review comments to determine comments with identical content as copy-and-paste reviews, means for providing feedback on the relevance, unnaturalness, and copy-and-paste determination results of the reviews, means for evaluating and providing feedback on the reliability of the review comments in real time, and means for displaying reviews in order of reliability. This allows users to receive reliable reviews in real time and make more accurate purchasing decisions based on them.

A "review comment" is a written comment written by a user expressing their evaluation or opinion of a product or service.

"Means of collection" refers to the method by which data is obtained from online platforms and entered into the system.

"Data preprocessing" is the process of removing unnecessary information and formatting acquired data to make it easier to analyze.

A "characteristic word list" is a list of important keywords related to a specific product or service.

"Product relevance" is the degree to which a review comment relates to a particular product or service.

"Pattern analysis methods" are methods for detecting certain templates or similarities in review comments.

"Unnatural reviews" are comments that deviate from normal user behavior, such as those posted in large numbers in a short period of time or those that contain repeated, repeated comments.

A "copy-and-paste review" is a review comment in which the exact same content as another comment is copied and pasted.

"Means of providing feedback" refers to methods for notifying users and administrators of evaluation results and encouraging them to take appropriate action.

"Means for assessing trustworthiness in real time" refers to a method that automatically determines the accuracy and credibility of a review the moment it is posted.

"Displaying in order of reliability" is a method of displaying highly rated review comments at the top, making them easier for users to refer to.

The system of the present invention evaluates the reliability of review comments on shopping platforms, allowing users to obtain more accurate review information. This system is implemented through the following process:

Hardware to use

Smartphone: Used by users as a device to post review comments.

Server: A central computer that collects review comments, preprocesses data, analyzes, evaluates, and provides feedback.

API server: Used as an interface to retrieve review comments from the shopping platform.

Software used

Python: Used for server-side data processing and analysis.

Flask: A Python web framework used to build API servers.

MySQL: Used as a database management system to store collected review comments.

Natural language processing library: Used for preprocessing and parsing review comments.

Data processing and calculation flow

1. Collecting review comments

The server periodically retrieves review comments from the shopping platform via API. This API server is built using Flask, and the retrieved data is stored in a MySQL database.

2. Data Preprocessing

The server preprocesses the retrieved review comment data. This preprocessing includes removing unnecessary whitespace and special characters, splitting review comments, and standardizing language using a Python natural language processing library.

3. Product Relevance Assessment

The server compares the review comment with a list of characteristic words based on product attributes. For example, a review about a smartphone would use keywords such as "image quality," "battery," and "operability." The server then scores the review comment, and if it scores above a certain level, it determines that the review comment is "highly relevant to the product."

4. Identifying unnatural reviews

The server analyzes review comments posted within a certain period of time to see if similar reviews have been posted in succession within a short period of time. If an unnatural pattern is detected, those reviews are flagged.

5. Judging Copy-Paste Reviews

The server compares the newly posted review comment with all existing review comments. It checks to see if there are any identical comments, and if there is an exact match, it flags it as a "copy-and-paste review."

6. Feedback

When a review is posted, the server will only allow it to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted, and will provide real-time feedback to the user. It also has a function to display reviews in order of reliability.

Specific examples and prompt sentence examples

As a concrete example, consider the following review comment:

Product: Smartphone

Review: "This phone's battery lasts a long time."

An example of a prompt is as follows:

"Please tell us if this review is relevant to the product: 'This phone's battery lasts a long time.'"

"Please tell us if this review fits any unnatural pattern: 'This phone's battery lasts a long time.'"

"Please tell us if this review exactly matches an existing review: 'This phone's battery lasts a long time.'"

This will allow users to choose products based on reliable reviews, improving the quality of ratings across online shopping platforms.

The flow of the specific processing in Application Example 1 will be explained using Figure 12.

Step 1:

Collecting review comments:

The server periodically collects review comments using an API provided by the shopping platform. The server receives the review comments obtained via the API in JSON format and stores them in a MySQL database. The input is the JSON data obtained from the API, and the output is the review comments stored in the database.

Step 2:

Data preprocessing:

The server preprocesses the collected review comment data. It uses Python's regular expression library to remove unnecessary whitespace and special characters and split the review comments into sentences. It also converts data in different formats into a unified format. The input is the raw review comments, and the output is the preprocessed, clean data.

Step 3:

Product relevance determination:

The server compares the preprocessed review comments with a pre-set feature word list. The server calculates the frequency of occurrence of words included in the feature word list, and determines that a product is highly relevant if the frequency is above a certain score. The input is the preprocessed review comments and the feature word list, and the output is data flagged as highly relevant reviews.

Step 4:

Determining unnatural reviews:

The server compares the preprocessed review comments with other review comments posted within a certain period of time and analyzes patterns. If a large number of similar review comments are posted in a short period of time, the server determines that they are unnatural reviews and flags them. The input is the preprocessed review comments and past review comments, and the output is data flagged as unnatural reviews.

Step 5:

Copy and paste review verdict:

The server compares the newly posted review comment with all existing review comments based on content similarity. If the server finds a review comment with exactly the same content, it flags it as a copy-and-paste review. The input is the new review comment and the existing review comment, and the output is the data determined to be a copy-and-paste review.

Step 6:

Feedback:

The server provides real-time feedback to reviewers based on the review's relevance, unnaturalness, and copy-and-paste assessment results. Reviews are displayed on the user's device in order of reliability. Reviews with low reliability are rejected, and the user is notified of the reason. The input is the review assessment results, and the output is a feedback message.

This allows users to make more accurate purchasing decisions based on reliable review comments.

It is also possible to further combine an emotion engine that estimates the user's emotion. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

The system of the present invention evaluates the reliability of review comments on shopping platforms and further optimizes review information by recognizing user sentiment. The program processing of this system is explained below in natural language.

Process Overview

1. Collecting review comments

The server periodically retrieves all review comments from the shopping platform via API. The collected review comments are stored in a database.

2. Data Preprocessing

The server cleans the collected review comments, removing unnecessary whitespace, special characters, and HTML tags. It also tokenizes the review comments into words and sentences, making them easier to analyze.

3. Product Relevance Assessment

The server compares review comments with a word list based on the features and attributes of each product. For example, for a review about a smartphone, a word list would be prepared, including "image quality," "battery," and "operability."

The server scores how often words from the word list appear in the review comments, and if the score is above a certain level, it determines the review to be "highly relevant to the product."

Example:

Product: Smartphone

Review comment: "The image quality of this smartphone is outstanding."

Score: "Image quality" is included in the word list, so the score is high.

4. Identifying unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It checks to see if reviews with similar content or writing style have been posted consecutively within a short period of time.

If the server detects any unusual patterns, it will flag the review comment.

Example:

Review 1: "This is a great product!"

Review 2: "This is a great product!"

Review 3: "This is a great product!"

Verdict: Unnatural review and flagging.

5. Judging Copy-Paste Reviews

Every time a new review comment is submitted, the server compares it with all existing review comments, using an advanced text comparison algorithm to check whether a review comment with the exact same content already exists.

If the server finds a match, it flags the review comment as a "copy-and-paste review."

Example:

Review 1: "This product is amazing!"

Review 2: "This product is amazing!"

Verdict: Copy and paste review and flagging.

6. Emotion Recognition Using an Emotion Engine

The server analyzes the review comments using an emotion engine and classifies them into positive, negative, or neutral sentiment.

The server calculates the emotional score of the review comments based on the scoring by the emotion engine and reflects this in the overall rating of the product.

Example:

Review comment: "This phone's battery dies so quickly it's useless."

Sentiment analysis result: Negative

Score: Reflected as a low rating.

7. Feedback and Filtering

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. If a flag is raised, the server will display an error message to the user explaining the reason for the post.

The server notifies the user and administrator of the feedback along with the emotion score generated by the emotion engine. Administrators are also notified to further review and respond to the review.

As a result, the system of the present invention ensures the reliability of review comments and provides a platform that users can use with peace of mind. The introduction of an emotion engine further improves the quality and reliability of reviews, and more accurately reflects product evaluation information.

The processing flow is explained below.

Step 1:

Collecting review comments

The server periodically retrieves all review comments from the shopping platform via API. The collected review comments are stored in a database.

Step 2:

Data preprocessing

The server cleans the collected review comments. Specifically, it removes unnecessary spaces, special characters, and HTML tags. It also tokenizes the review comments into words and sentences, preparing them in an analyzable form.

Step 3:

Product relevance determination

The server compares review comments using a word list based on the features and attributes of each product. It compares the words in the review comments with the word list and generates a score. For example, a word list related to smartphones might include "image quality," "battery," and "operability."

The server scores the frequency with which words included in the word list appear, and if the score is above a certain level, it determines that the review is "highly relevant to the product."

Step 4:

Determining unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It determines whether reviews with similar content or writing style have been posted in succession within a short period of time. In particular, it compares sentence length, the words used, sentence structure, etc.

If the server detects any unusual patterns, it will flag the review comment.

Step 5:

Copy-and-paste review verdict

Every time a new review comment is submitted, the server compares it with all existing review comments, using an advanced text comparison algorithm to check whether a review comment with the exact same content already exists.

If the server finds a match, it flags the review comment as a "copy-and-paste review."

Step 6:

Emotion recognition using an emotion engine

The server uses an emotion engine to analyze review comments and classify them into positive, negative, or neutral sentiment. Specifically, it uses a natural language processing algorithm to extract and score emotional expressions contained in the sentences.

The server calculates the emotional score of the review comments based on the scoring by the emotion engine and reflects this in the overall rating of the product.

Step 7:

Feedback and filtering

The server will only allow a review comment to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. If any flags are raised, the server will display an error message to the user explaining why the post was rejected.

The server filters out inappropriate reviews and notifies users and administrators, including the sentiment score generated by the sentiment engine. Administrators are sent detailed information such as the review content, the reason it was flagged, and the sentiment score, and are offered help in re-checking the review if necessary.

Based on these specific steps, the system of the present invention ensures the reliability of review comments and provides a platform that users can use with confidence. The integration of an emotion engine further improves the quality and reliability of reviews, and more accurately reflects product evaluation information.

(Example 2)

Next, Example 2 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset-type terminal 314 will be referred to as the "terminal."

Traditional shopping platforms lacked an appropriate mechanism for determining the authenticity of review comments, leaving users at risk of making purchasing decisions based on inaccurate information. This has created a need to improve the reliability of review comments and provide an environment where users can use them with peace of mind. It is also necessary to accurately understand the sentiment behind review comments in order to more accurately reflect product evaluation information.

The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting review comments, means for performing data preprocessing of the review comments, means for determining product relevance by comparing the review comments with a characteristic word list, means for analyzing the patterns of the review comments to determine unnatural reviews, means for comparing the review comments to determine comments with identical content as copy-and-paste reviews, means for analyzing the sentiment of the review comments, means for providing feedback on the review relevance, unnaturalness, copy-and-paste determination results, and sentiment analysis results, and means for rejecting the posting of review comments that are unnatural or copy-and-paste. This improves the reliability of review comments, provides an environment where users can refer to reviews with confidence, and makes it possible to more accurately reflect product evaluation information.

"Review comments" are textual opinions and evaluations written by users on shopping platforms about products and services.

"Data preprocessing" is the process of removing unnecessary elements from collected review comments and converting them into a format suitable for analysis.

A "characteristic word list" is a list of keywords related to a specific product or service that is used to compare with review comments.

"Product relevance determination" is the process of determining whether a review comment is relevant to a specific product or service.

"Pattern analysis" is the process of analyzing the content and format of review comments to detect specific patterns or anomalies.

"Unnatural reviews" are review comments that show an unusual pattern, such as content or writing style being posted repeatedly within a short period of time.

A "copy-and-paste review" refers to a review comment that has exactly the same content as an existing review comment.

"Sentiment analysis" is the process of analyzing the content of review comments and classifying their sentiments as positive, negative, or neutral.

"Feedback" refers to the provision of information to notify users or administrators of analysis and judgment results, and to encourage them to take necessary action.

"Posting refusal" refers to the action of not allowing users to post in order to prevent unnatural reviews or copy-and-paste reviews from being posted.

A "server" is a computer system that manages and executes a series of processes, including the collection, preprocessing, analysis, judgment, feedback, and rejection of review comments.

The system of the present invention evaluates the reliability of review comments on a shopping platform, recognizes user emotions, and optimizes review information. The specific operations and processes for this purpose are described below.

1. Collecting review comments

The system retrieves review comments through the shopping platform's API. The server periodically sends requests to the API endpoint and stores the retrieved review comments in a database. Specifically, MySQL or PostgreSQL can be used as the database.

For example, the server accesses the API endpoint "https://example.com/api/reviews" and stores the retrieved review comments in the "reviews" table.

2. Data Preprocessing

The server cleans the retrieved review comments. Specifically, it removes unnecessary whitespace, special characters, and HTML tags. It also tokenizes the review comments into words and sentences. This preprocessing can be performed using NLPK, a Python NLP library.

For example, a comment such as "This product is <p>great</p>!" is text cleaned to "This product is great!" and then tokenized.

3. Product Relevance Assessment

The server generates a word list based on the features and attributes of each product and compares it with the review comments. For example, for smartphone reviews, a word list containing keywords such as "image quality," "battery," and "operability" is used.

Specifically, the frequency of keywords appearing in review comments is scored, and if the score is above a certain level, it is determined to be a "review with high product relevance." For example, the server analyzes a comment such as "The image quality of this smartphone is outstanding," and assigns a high score because "image quality" is included in the word list.

4. Identifying unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. Specifically, it checks to see if review comments with similar content or format have been posted consecutively within a short period of time.

If an unnatural pattern is detected, the review comment is flagged. For example, if the server sees multiple reviews with the same content, such as "Great product!", posted within a short period of time, it will flag them as unnatural.

5. Judging Copy-Paste Reviews

Each time a new review comment is submitted, the server compares it with all existing review comments, using sophisticated text comparison algorithms (e.g., Python's difflib library) to determine whether there is a match.

If a match is found, the server will flag the review comment as a "copy-and-paste review." For example, if a comment already exists that says "This product is amazing!", the server will add a flag.

6. Emotion Recognition Using an Emotion Engine

The server inputs the review comments into a sentiment analysis engine and classifies them into positive, negative, or neutral sentiment. Specifically, sentiment analysis libraries such as TextBlob and VADER can be used.

This allows us to calculate an emotional score, which is then reflected in the overall rating of the product. For example, we can use TextBlob to analyze a comment such as "This phone's battery runs out quickly, so it's useless" and assign it a negative score.

7. Feedback and Filtering

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not related to the product, unnatural, or copied and pasted. If so, an error message will be displayed to the user explaining the reason for the post.

The emotion engine also notifies users and administrators of the emotion score, helping to improve the reliability of reviews. For example, the server may notify users that "this review has been flagged as unnatural" and encourage them to resubmit. It may also notify administrators that "a new unnatural review has been detected. Please check it."

Example prompt for a generative AI model

"Did this review comment relate to a specific product? Please categorize its sentiment. Example: 'The image quality of this phone is outstanding.'"

"Please determine whether the review comments on this listing are unnatural. Example: 'Great product!', 'Great product!'"

"Check if this review comment matches an existing comment or is a copypasta review. Example: 'This product is amazing!'"

The above is a form for implementing the system of the present invention.

The flow of the identification process in Example 2 will be explained using Figure 13.

Step 1:

Collecting review comments:

Input: Shopping platform API endpoint URL

Specific behavior: The server periodically sends requests to an API endpoint to retrieve review comments. For example, it accesses the API endpoint "https://example.com/api/reviews".

Data processing: Metadata (user ID, product ID, posting date and time, etc.) is added to the acquired review comments.

Output: Dataset containing review comments and metadata

Specific operation: The server stores the acquired dataset in a database (e.g., MySQL or PostgreSQL).

Step 2:

Data preprocessing:

Input: Review comments stored in the database

What it does: The server cleans the review comments. Specifically, it uses a Python NLP library (e.g., NLPK) to remove unnecessary whitespace, special characters, and HTML tags.

Data processing: Tokenize review comments into words and sentences.

Output: Clean, tokenized review comments

Specific operation: For example, a comment such as "This product is <p>great</p>!" is cleaned to "This product is great!" and separated into individual words.

Step 3:

Product relevance determination:

Input: Clean, tokenized review comments, product feature word list

Specific operation: The server compares the review comments with the feature word list. The word list includes keywords based on product attributes such as "image quality," "battery," and "operability."

Data calculation: Score the frequency of keywords appearing in review comments.

Output: Product relevance score

Specific operation: For example, a comment such as "The image quality of this smartphone is outstanding" will be given a high score if "image quality" is included in the word list.

Step 4:

Determining unnatural reviews:

Input: All review comments posted within a certain period

Specific operation: The server analyzes the content patterns of review comments. It checks whether reviews with the same content or writing style have been posted consecutively.

Data calculations: Analysis to detect unnatural patterns

Output: Review comments flagged as unnatural

Specific behavior: For example, if the same review saying "This is a great product!" is posted multiple times in a short period of time, it will be flagged as unnatural.

Step 5:

Copy and paste review verdict:

Input: New review comment, Existing review comment

What it does: The server uses advanced text comparison algorithms (e.g., Python's difflib library) to compare the new comment with existing review comments.

Data calculation: The process of checking whether the content of comments matches.

Output: Review comments flagged as copy-paste reviews

Specific behavior: For example, if a comment saying "This product is amazing!" already exists, add a flag.

Step 6:

Emotion recognition using the emotion engine:

Enter: Review comment

Specific operation: The server inputs the review comments into a sentiment analysis engine (e.g., TextBlob or VADER) and classifies the sentiment.

Data calculation: Calculating emotion scores

Output: Review comments with sentiment scores

Specific behavior: For example, a comment such as "This smartphone's battery runs out quickly, making it useless" is scored as negative.

Step 7:

Feedback and filtering:

Input: Review comments (with flags for relevance, unnaturalness, and copy-paste), sentiment score

Specific behavior: When an attempt is made to post a review comment, the server will only allow it to be posted if it is not related to the product, unnatural, or copied and pasted. If so, an error message will be displayed to the user.

Data calculation: feedback and submission evaluation

Output: Notification to users and administrators

Specific behavior: For example, the server notifies the user that "this review has been flagged as unnatural" and encourages them to resubmit, while simultaneously notifying the administrator that "a new unnatural review has been detected."

The above are the specific processing steps of this system's program.

(Application Example 2)

Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the headset-type terminal 314 will be referred to as the "terminal."

Traditional review comment rating systems often lack the functionality to fully guarantee the reliability of reviews. For example, they often contain a mixture of reviews that are unrelated to the product, unnatural reviews, and copy-and-paste reviews, making it difficult for users to obtain accurate information. There is also a demand for more accurate product ratings through sentiment analysis of review comments. However, current systems lack sentiment analysis functionality, making it impossible to improve the quality and reliability of reviews.

The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

In this invention, the server includes means for collecting review comments, means for pre-processing data on the review comments, means for comparing the review comments with a list of characteristic words to determine product relevance, means for analyzing patterns of the review comments to determine unnatural reviews, means for comparing review comments to determine comments with identical content as copy-and-paste reviews, means for performing sentiment analysis on the review comments, and means for providing feedback on the review relevance, unnaturalness, copy-and-paste determination results, and sentiment analysis results. This allows users to obtain highly reliable review information and more accurately evaluate products.

"Review comments" refer to impressions and evaluations written by users about products and services.

"Means of collection" refers to the process or function of obtaining specific information from the Internet or a database.

"Data preprocessing" refers to the process of analyzing collected data or performing pre-analysis processing to remove unnecessary parts and format the data.

A "characteristic word list" refers to a list of important keywords related to a specific product or category.

"Means for determining product relevance" refers to the methods or algorithms used to evaluate how relevant a review comment is to a particular product.

"Methods for analyzing patterns to identify unnatural reviews" refers to methods for analyzing the content and posting patterns of review comments to detect unnatural content and typical actions.

A "copy-and-paste review" refers to a review comment that contains the same content as another review comment, copied and pasted exactly as is.

"Sentiment analysis" refers to the technology of analyzing user emotions and intentions from text data and classifying them as positive, negative, or neutral.

"Feedback" refers to the process of returning analysis and evaluation results to the user or system.

Form for implementing the invention

This invention is a system that improves the reliability of review comments on shopping platforms and provides users with optimal information. This system collects review comments, performs data preprocessing, and analyzes product relevance, unnaturalness, whether or not they have been copied and pasted, and sentiment before providing feedback.

System Overview

The server includes the following means:

1. How to collect review comments:

The server periodically retrieves all review comments from the shopping platform via API. These collected review comments are stored in a database.

2. Methods for preprocessing review comment data:

The server cleans the collected review comments. Specifically, it removes unnecessary whitespace, special characters, and HTML tags, tokenizes the review comments into words and sentences, and prepares them in an analyzable form.

3. How to determine product relevance by comparing review comments with a list of characteristic words:

The server compares review comments with a word list based on the characteristics and attributes of each product. For example, for a review about a smartphone, a word list such as "image quality," "battery," and "operability" would be prepared. The server scores the number of times words from the word list appear in the review comments, and if the score is above a certain level, it is determined to be a "review highly relevant to the product."

4. How to analyze review comment patterns and identify unnatural reviews:

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It checks to see if reviews with similar content or writing style have been posted consecutively within a short period of time, and if an unnatural pattern is detected, it flags the review comment.

5. How to compare review comments and identify comments with identical content as copy-and-paste reviews:

Every time a new review comment is submitted, the server compares it with all existing review comments. Using sophisticated text comparison algorithms, it checks whether an identical review comment already exists, and if a match is found, it flags the review comment as a "copy-and-paste review."

6. How to perform sentiment analysis on review comments:

The server analyzes the review comments using an emotion engine and classifies them into positive, negative, and neutral emotions. Based on the scoring by the emotion engine, the emotion score of the review comments is calculated and reflected in the overall rating of the product.

7. Means of providing feedback on review relevance, unnaturalness, copy-paste determination results, and sentiment analysis results:

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not flagged as being inappropriate, unnatural, or copied and pasted. If a flag is raised, an error message will be displayed to the user, explaining the reason for the post. Feedback will be provided to the user and administrator, along with the sentiment score calculated by the sentiment engine, and administrators will be notified, urging them to further review and take action.

Hardware and software used

Hardware: Servers, cloud storage devices

Software: Python, requests, BeautifulSoup, re, nltk, textblob, scikit-learn, emotion engine (TextBlob, etc.)

Specific examples

As a concrete example, we will show the steps for processing the review comment "The image quality of this smartphone is outstanding." This comment is determined to be highly relevant to the product because it contains the keyword "image quality," and is approved because it does not match unnatural reviews or copy-paste reviews.

Example prompt

Example of a prompt to input to a generative AI model:

Analyze the new review comment, "The image quality of this phone is outstanding." We'll rate it based on the following criteria:

1. Product Relevance

2. Unnatural patterns

3. Copy and paste

4. Sentiment analysis

The flow of the specific processing in Application Example 2 will be explained using Figure 14.

Step 1:

Collecting review comments

The server periodically calls the shopping platform's API to retrieve review comments for each product. As input, it uses the API endpoint URL and authentication information. As output, it generates JSON data containing the retrieved review comments. This data is stored in the server's database.

Step 2:

Data preprocessing

The server cleans the collected review comments. As input, it uses the text data of the review comments stored in the database. Specifically, it removes unnecessary whitespace, special characters, and HTML tags, and tokenizes the review comments into words and sentences. As output, clean text data is generated and passed to the next step.

Step 3:

Product relevance determination

The server evaluates the relevance of review comments using a word list based on the features and attributes of each product. As input, it uses the clean review comments and the feature word list. Specifically, it scores how often words included in the feature word list appear in the review comments. As output, it generates a relevance score for each review comment.

Step 4:

Determining unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns. As input, it uses text data from review comments over a certain period of time in the past and the current review comment. Specifically, it applies a text pattern matching algorithm to evaluate the similarity. As output, it generates a flag indicating whether the review is unnatural.

Step 5:

Copy-and-paste review verdict

Each time a new review comment is posted, the server compares it with all existing review comments. It uses the data of the new review comment and the existing review comments as input. Specifically, it uses an advanced text comparison algorithm (e.g., cosine similarity) to check whether a review comment with the exact same content exists. As output, it generates a flag indicating whether the review is a copy-and-paste review.

Step 6:

sentiment analysis

The server parses the review comments into the sentiment engine. It uses the clean review comments as input. Specifically, it sends the text to the sentiment engine (e.g., TextBlob) and obtains a sentiment score: positive, negative, or neutral. The output is a sentiment score for each review comment.

Step 7:

Feedback and filtering

When an attempt is made to post a review comment, the server provides feedback based on the judgment results obtained in the previous steps. All judgment results (relevance, unnaturalness, copy-paste judgment results, and sentiment score) are used as input. Specific behavior is to allow posting only if no flags are raised, and to display an error message to the user if a flag is raised. More detailed feedback is then provided to the administrator. As output, an error message or approval message is displayed to the user, and the review comment is saved in the database.

The specific processing unit 290 transmits the results of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the results of the specific processing. The microphone 238 acquires audio indicating the user input regarding the results of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

Data generation model 58 is what is known as generative AI (artificial intelligence). Examples of data generation model 58 include generative AI such as ChatGPT (Internet search <URL: https://openai.com/blog/chatgpt>) and Gemini (Internet search <URL: https://gemini.google.com/?hl=ja>). Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing an instruction is input to data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input. Data generation model 58 performs inference on the input inference data in accordance with the instructions indicated by the prompt, and outputs the inference results in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization.

In the above embodiment, an example was given in which the specific processing was performed by the data processing device 12, but the technology disclosed herein is not limited to this, and the specific processing may also be performed by the headset-type terminal 314.

[Fourth embodiment]

Figure 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

As shown in FIG. 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

The data processing device 12 includes a computer 22, a database 24, and a communication I/F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and communication I/F 26 are also connected to the bus 34. The communication I/F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and/or a LAN (Local Area Network).

The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I/F 44, and a control target 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and control target 443 are also connected to the bus 52.

The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user 20's surroundings (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

The communication I/F 44 is connected to the network 54. The communication I/Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I/Fs 44 and 26 is carried out in a secure manner.

The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32.

The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as the specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

Storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

In the robot 414, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

Next, we will explain the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 will be referred to as the "terminal."

The system of the present invention evaluates the reliability of review comments on shopping platforms and provides appropriate feedback, allowing users to obtain more accurate review information. The program processing of this system is explained below in natural language.

Process Overview

1. Collecting review comments

The server periodically retrieves all review comments from the shopping platform via API, allowing new review comments to be added to the system.

2. Data Preprocessing

The server preprocesses the collected review comment data. Preprocessing includes removing unnecessary spaces and special characters, splitting review comments, and standardizing language.

3. Product Relevance Assessment

The server compares the review comment with a feature word list based on product attributes. For example, if the review is about a smartphone, a word list such as "image quality," "battery," and "operability" will be set.

The server scores the frequency with which words included in the word list appear in the review comments, and if the score is above a certain level, the review comment is determined to be a "review with high product relevance."

Example:

Product: Smartphone

Review comment: "The image quality of this smartphone is amazing."

Score: "Image quality" is included in the word list, so the score is high.

4. Identifying unnatural reviews

The server analyzes patterns in review comments posted within a certain period of time, checking to see if similar reviews have been posted consecutively within a short period of time.

The server will flag reviews if any unusual patterns are detected.

Example:

Review 1: "Great product!"

Review 2: "Great product!"

Review 3: "Great product!"

Verdict: Unnatural review and flagging.

5. Judging Copy-Paste Reviews

Every time a new review comment is posted, the server compares it with all existing review comments to see if any have the exact same content.

If the server finds an exact match, it will flag the review as a "copy-and-paste review."

Example:

Review 1: "This product is amazing!"

Review 2: "This product is amazing!"

Verdict: Copy and paste review and flagging.

6. Feedback

When a review is submitted, the server will only allow it to be submitted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted.

The server filters out inappropriate reviews and displays an error message to the user. It also notifies the administrator of the review content and the judgment result.

This system allows users to select products based on reliable review information, improving the quality of reviews across the entire online shopping platform.

The processing flow is explained below.

Step 1:

Collecting review comments

The server uses an API from the shopping platform to periodically retrieve all review comments. This collection includes review comments for all products.

Step 2:

Data preprocessing

The server stores the collected review comments as text data. Next, it performs a cleaning process to remove unnecessary spaces, special characters, and HTML tags from the review comments. It then tokenizes the review comments into words and sentences, converting them into an analyzable form.

Step 3:

Product relevance determination

The server pre-sets a word list based on the characteristics and attributes of each product. When a review comment is posted, the server compares the words in the comment with the word list. For example, for a review about a smartphone, a word list such as "image quality," "battery," and "operability" is used. The server scores how often words from the word list appear in the comment, and if the score is above a certain level, it determines that the review is "highly relevant to the product."

Step 4:

Determining unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It determines whether reviews with similar content or writing style have been posted in succession within a short period of time. If the server detects an unnatural pattern, it flags the review comment.

Step 5:

Copy-and-paste review verdict

Each time a new review comment is submitted, the server compares it with all existing review comments. It uses sophisticated text comparison algorithms to determine whether a review comment with the exact same content already exists. If the server finds a match, it flags the review comment as a "copy-and-paste review."

Step 6:

Feedback and filtering

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not flagged as being inappropriate, unnatural, or copied and pasted. If a flag is raised, the server will display an error message to the user explaining the reason for the posting. The server will also notify administrators of the fraudulent review and help them review the review.

Based on these concrete steps, we will be able to provide users with reliable review information and improve the quality of the entire shopping platform.

(Example 1)

Next, Example 1 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 will be referred to as the "terminal."

On online shopping platforms, the reliability of review comments, which users use as a reference when selecting products, is important. However, fake reviews, copy-and-paste reviews, and reviews with unnatural patterns are rampant, making it difficult for users to obtain accurate information. For this reason, there is a need for a system that can evaluate the reliability of review comments and provide users with accurate review information.

The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

In this invention, the server includes means for collecting review comments, means for pre-processing data on the review comments, means for comparing the review comments with a feature word list to determine product relevance, means for analyzing patterns of the review comments to determine unnatural reviews, means for comparing review comments to determine comments with identical content as copy-and-paste reviews, and means for providing feedback on the review relevance, unnaturalness, and copy-and-paste determination results. This enables users to select products based on highly reliable review information.

"Review comments" are opinions and ratings posted by users about products on online shopping platforms.

"Data preprocessing" refers to the process of removing unnecessary spaces and special characters from the text data of collected review comments, and performing tokenization and language standardization.

A "characteristic word list" is a list of keywords based on product attributes that are set up to evaluate the reliability of review comments about a product.

"Product relevance" is an indicator that shows the degree to which review comments mention a specific product and the degree of match with the feature word list.

"Pattern analysis" is the process of analyzing the posting patterns of review comments and determining whether the same or similar content has been posted consecutively within a certain period of time.

An "unnatural review" is a review that is deemed to deviate from normal user behavior, such as when similar comments are posted in succession within a short period of time.

A "copy-and-paste review" is a comment that is posted by simply copying an existing review comment, and refers to a review with exactly the same content.

"Feedback" is a process that notifies users and administrators of the relevance, unnaturalness, and copy-and-paste judgment results of review comments, allowing only appropriate reviews.

The present invention is a system that evaluates the reliability of review comments on online shopping platforms, allowing users to obtain more accurate review information. Specific embodiments are described in detail below.

Collecting review comments

The server periodically retrieves all review comments using the shopping platform's API. This periodically saves the comments, including the most recent ones, to the database. The specific software used is the Python requests library.

Data preprocessing

The server preprocesses the collected review comment data. This includes removing unnecessary whitespace and special characters, tokenizing the text data, and unifying the language. This process uses the Python nltk library and re module.

Product relevance determination

The server compares the review comments with a feature word list based on product attributes. For example, for a review about a smartphone, a feature word list such as "image quality," "battery," and "operability" is set. The server scores the frequency with which words included in the word list appear in the review comments, and if the score is above a certain level, the review comment is deemed to be "highly relevant to the product." The specific software used is the Python scikit-learn library.

Specific examples

Product: Smartphone

Review comment: "The image quality of this smartphone is amazing."

Since "image quality" is included in the word list, it is judged to have a high score.

Identifying unnatural reviews

The server analyzes patterns in review comments posted within a certain period of time, checking to see if similar reviews have been posted consecutively within a short period of time. If the server detects an unnatural pattern, it flags those reviews. This process uses Python's Pandas library and time series analysis.

Specific examples

Review 1: "Great product!"

Review 2: "Great product!"

Review 3: "Great product!"

The server will identify these as unnatural reviews and flag them.

Copy-and-paste review verdict

Every time a new review comment is posted, the server compares it with all existing review comments to see if there are any identical comments. If the server finds a matching comment, it flags the review as a "copy-and-paste review." The software uses the Python difflib library.

Specific examples

Review 1: "This product is amazing!"

Review 2: "This product is amazing!"

The server determines that Review 2 is a copy-and-paste review and flags it.

Feedback

When a review is posted, the server will only allow it to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. Inappropriate reviews are filtered out and an error message is displayed to the user. The server also notifies the administrator of the review content and the result of the judgment. This process uses the Python Flask or Django framework and an email server (SMTP) for notifications.

Example prompt

Please rate the user-submitted review comment, "This phone has excellent battery life." and provide feedback based on the following criteria:

Conditions:

1. To determine whether a review is highly relevant to the product, it is scored based on a list of characteristic words such as "battery," "lifespan," and "excellent."

2. Check to see if similar reviews have been posted consecutively within a certain period of time.

3. Compare with existing review comments to check if the review is a copy-and-paste one.

This system will enable users to select products based on reliable review information, and is expected to improve the quality of reviews across online shopping platforms.

The flow of the identification process in Example 1 will be explained using Figure 11.

Step 1:

Collects review comments. The server periodically retrieves all review comments through the shopping platform's API. The input is the API request, and the output is the retrieved review comment data in JSON format. The server sends the API request and stores the received data in a database.

Step 2:

Performs data preprocessing. The server performs preprocessing on the collected review comment data. The input is JSON-formatted review comment data, and the output is preprocessed text data. The server removes unnecessary whitespace and special characters, tokenizes the text data, and standardizes the language.

Step 3:

Determines product relevance. The server compares preprocessed review comments with a feature word list based on product attributes. The input is preprocessed text data and a feature word list, and the output is scored review comment data. The server scores how often words included in the word list appear in the review comments, and if the score is above a certain level, it determines the review to be "highly relevant to the product."

Step 4:

Identifies unnatural reviews. The server analyzes patterns in review comments posted within a certain period of time. The input is review comment data from a specific period of time, and the output is the judgment result and flagged data. The server checks whether reviews with similar content have been posted in succession within a short period of time, and if an unnatural pattern is detected, it flags those reviews.

Step 5:

Determines copy-and-paste reviews. Every time a new review comment is posted, the server compares it with all existing review comments. The input is the new review comment and existing review comment data, and the output is the determination result and flagged data. If the server finds a matching comment, it flags the review as a "copy-and-paste review."

Step 6:

Provides feedback. The server will only allow a review to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. The input is the review comment and various judgment results, and the output is notifications to the user and administrator. The server filters out inappropriate reviews, displays an error message to the user, and notifies the administrator of the review content and judgment results.

(Application Example 1)

Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 will be referred to as the "terminal."

On conventional shopping platforms, many unreliable review comments were posted, causing users to make incorrect purchasing decisions. There was also the problem of similar reviews and copy-paste reviews being posted within a short period of time, reducing the reliability of the reviews. Therefore, there was a need to develop a system that could provide users with reliable review information and help them make more accurate purchasing decisions.

The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

In this invention, the server includes means for collecting review comments, means for pre-processing data on the review comments, means for comparing the review comments with a list of characteristic words to determine product relevance, means for analyzing patterns of the review comments to determine unnatural reviews, means for comparing review comments to determine comments with identical content as copy-and-paste reviews, means for providing feedback on the relevance, unnaturalness, and copy-and-paste determination results of the reviews, means for evaluating and providing feedback on the reliability of the review comments in real time, and means for displaying reviews in order of reliability. This allows users to receive reliable reviews in real time and make more accurate purchasing decisions based on them.

A "review comment" is a written comment written by a user expressing their evaluation or opinion of a product or service.

"Means of collection" refers to the method by which data is obtained from online platforms and entered into the system.

"Data preprocessing" is the process of removing unnecessary information and formatting acquired data to make it easier to analyze.

A "characteristic word list" is a list of important keywords related to a specific product or service.

"Product relevance" is the degree to which a review comment relates to a particular product or service.

"Pattern analysis methods" are methods for detecting certain templates or similarities in review comments.

"Unnatural reviews" are comments that deviate from normal user behavior, such as those posted in large numbers in a short period of time or those that contain repeated, repeated comments.

A "copy-and-paste review" is a review comment in which the exact same content as another comment is copied and pasted.

"Means of providing feedback" refers to methods for notifying users and administrators of evaluation results and encouraging them to take appropriate action.

"Means for assessing trustworthiness in real time" refers to a method that automatically determines the accuracy and credibility of a review the moment it is posted.

"Displaying in order of reliability" is a method of displaying highly rated review comments at the top, making them easier for users to refer to.

The system of the present invention evaluates the reliability of review comments on shopping platforms, allowing users to obtain more accurate review information. This system is implemented through the following process:

Hardware to use

Smartphone: Used by users as a device to post review comments.

Server: A central computer that collects review comments, preprocesses data, analyzes, evaluates, and provides feedback.

API server: Used as an interface to retrieve review comments from the shopping platform.

Software used

Python: Used for server-side data processing and analysis.

Flask: A Python web framework used to build API servers.

MySQL: Used as a database management system to store collected review comments.

Natural language processing library: Used for preprocessing and parsing review comments.

Data processing and calculation flow

1. Collecting review comments

The server periodically retrieves review comments from the shopping platform via API. This API server is built using Flask, and the retrieved data is stored in a MySQL database.

2. Data Preprocessing

The server preprocesses the retrieved review comment data. This preprocessing includes removing unnecessary whitespace and special characters, splitting review comments, and standardizing language using a Python natural language processing library.

3. Product Relevance Assessment

The server compares the review comment with a list of characteristic words based on product attributes. For example, a review about a smartphone would use keywords such as "image quality," "battery," and "operability." The server then scores the review comment, and if it scores above a certain level, it determines that the review comment is "highly relevant to the product."

4. Identifying unnatural reviews

The server analyzes review comments posted within a certain period of time to see if similar reviews have been posted in succession within a short period of time. If an unnatural pattern is detected, those reviews are flagged.

5. Judging Copy-Paste Reviews

The server compares the newly posted review comment with all existing review comments. It checks to see if there are any identical comments, and if there is an exact match, it flags it as a "copy-and-paste review."

6. Feedback

When a review is posted, the server will only allow it to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted, and will provide real-time feedback to the user. It also has a function to display reviews in order of reliability.

Specific examples and prompt sentence examples

As a concrete example, consider the following review comment:

Product: Smartphone

Review: "This phone's battery lasts a long time."

An example of a prompt is as follows:

"Please tell us if this review is relevant to the product: 'This phone's battery lasts a long time.'"

"Please tell us if this review fits any unnatural pattern: 'This phone's battery lasts a long time.'"

"Please tell us if this review exactly matches an existing review: 'This phone's battery lasts a long time.'"

This will allow users to choose products based on reliable reviews, improving the quality of ratings across online shopping platforms.

The flow of the specific processing in Application Example 1 will be explained using Figure 12.

Step 1:

Collecting review comments:

The server periodically collects review comments using an API provided by the shopping platform. The server receives the review comments obtained via the API in JSON format and stores them in a MySQL database. The input is the JSON data obtained from the API, and the output is the review comments stored in the database.

Step 2:

Data preprocessing:

The server preprocesses the collected review comment data. It uses Python's regular expression library to remove unnecessary whitespace and special characters and split the review comments into sentences. It also converts data in different formats into a unified format. The input is the raw review comments, and the output is the preprocessed, clean data.

Step 3:

Product relevance determination:

The server compares the preprocessed review comments with a pre-set feature word list. The server calculates the frequency of occurrence of words included in the feature word list, and determines that a product is highly relevant if the frequency is above a certain score. The input is the preprocessed review comments and the feature word list, and the output is data flagged as highly relevant reviews.

Step 4:

Determining unnatural reviews:

The server compares the preprocessed review comments with other review comments posted within a certain period of time and analyzes patterns. If a large number of similar review comments are posted in a short period of time, the server determines that they are unnatural reviews and flags them. The input is the preprocessed review comments and past review comments, and the output is data flagged as unnatural reviews.

Step 5:

Copy and paste review verdict:

The server compares the newly posted review comment with all existing review comments based on content similarity. If the server finds a review comment with exactly the same content, it flags it as a copy-and-paste review. The input is the new review comment and the existing review comment, and the output is the data determined to be a copy-and-paste review.

Step 6:

Feedback:

The server provides real-time feedback to reviewers based on the review's relevance, unnaturalness, and copy-and-paste assessment results. Reviews are displayed on the user's device in order of reliability. Reviews with low reliability are rejected, and the user is notified of the reason. The input is the review assessment results, and the output is a feedback message.

This allows users to make more accurate purchasing decisions based on reliable review comments.

It is also possible to further combine an emotion engine that estimates the user's emotion. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

The system of the present invention evaluates the reliability of review comments on shopping platforms and further optimizes review information by recognizing user sentiment. The program processing of this system is explained below in natural language.

Process Overview

1. Collecting review comments

The server periodically retrieves all review comments from the shopping platform via API. The collected review comments are stored in a database.

2. Data Preprocessing

The server cleans the collected review comments, removing unnecessary whitespace, special characters, and HTML tags. It also tokenizes the review comments into words and sentences, making them easier to analyze.

3. Product Relevance Assessment

The server compares review comments with a word list based on the features and attributes of each product. For example, for a review about a smartphone, a word list would be prepared, including "image quality," "battery," and "operability."

The server scores how often words from the word list appear in the review comments, and if the score is above a certain level, it determines the review to be "highly relevant to the product."

Example:

Product: Smartphone

Review comment: "The image quality of this smartphone is outstanding."

Score: "Image quality" is included in the word list, so the score is high.

4. Identifying unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It checks to see if reviews with similar content or writing style have been posted consecutively within a short period of time.

If the server detects any unusual patterns, it will flag the review comment.

Example:

Review 1: "This is a great product!"

Review 2: "This is a great product!"

Review 3: "This is a great product!"

Verdict: Unnatural review and flagging.

5. Judging Copy-Paste Reviews

Every time a new review comment is submitted, the server compares it with all existing review comments, using an advanced text comparison algorithm to check whether a review comment with the exact same content already exists.

If the server finds a match, it flags the review comment as a "copy-and-paste review."

Example:

Review 1: "This product is amazing!"

Review 2: "This product is amazing!"

Verdict: Copy and paste review and flagging.

6. Emotion Recognition Using an Emotion Engine

The server analyzes the review comments using an emotion engine and classifies them into positive, negative, or neutral sentiment.

The server calculates the emotional score of the review comments based on the scoring by the emotion engine and reflects this in the overall rating of the product.

Example:

Review comment: "This phone's battery dies so quickly it's useless."

Sentiment analysis result: Negative

Score: Reflected as a low rating.

7. Feedback and Filtering

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. If a flag is raised, the server will display an error message to the user explaining the reason for the post.

The server notifies the user and administrator of the feedback along with the emotion score generated by the emotion engine. Administrators are also notified to further review and respond to the review.

As a result, the system of the present invention ensures the reliability of review comments and provides a platform that users can use with peace of mind. The introduction of an emotion engine further improves the quality and reliability of reviews, and more accurately reflects product evaluation information.

The processing flow is explained below.

Step 1:

Collecting review comments

The server periodically retrieves all review comments from the shopping platform via API. The collected review comments are stored in a database.

Step 2:

Data preprocessing

The server cleans the collected review comments. Specifically, it removes unnecessary spaces, special characters, and HTML tags. It also tokenizes the review comments into words and sentences, preparing them in an analyzable form.

Step 3:

Product relevance determination

The server compares review comments using a word list based on the features and attributes of each product. It compares the words in the review comments with the word list and generates a score. For example, a word list related to smartphones might include "image quality," "battery," and "operability."

The server scores the frequency with which words included in the word list appear, and if the score is above a certain level, it determines that the review is "highly relevant to the product."

Step 4:

Determining unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It determines whether reviews with similar content or writing style have been posted in succession within a short period of time. In particular, it compares sentence length, the words used, sentence structure, etc.

If the server detects any unusual patterns, it will flag the review comment.

Step 5:

Copy-and-paste review verdict

Every time a new review comment is submitted, the server compares it with all existing review comments, using an advanced text comparison algorithm to check whether a review comment with the exact same content already exists.

If the server finds a match, it flags the review comment as a "copy-and-paste review."

Step 6:

Emotion recognition using an emotion engine

The server uses an emotion engine to analyze review comments and classify them into positive, negative, or neutral sentiment. Specifically, it uses a natural language processing algorithm to extract and score emotional expressions contained in the sentences.

The server calculates the emotional score of the review comments based on the scoring by the emotion engine and reflects this in the overall rating of the product.

Step 7:

Feedback and filtering

The server will only allow a review comment to be posted if it is not flagged as being unrelated to the product, unnatural, or copied and pasted. If any flags are raised, the server will display an error message to the user explaining why the post was rejected.

The server filters out inappropriate reviews and notifies users and administrators, including the sentiment score generated by the sentiment engine. Administrators are sent detailed information such as the review content, the reason it was flagged, and the sentiment score, and are offered help in re-checking the review if necessary.

Based on these specific steps, the system of the present invention ensures the reliability of review comments and provides a platform that users can use with confidence. The integration of an emotion engine further improves the quality and reliability of reviews, and more accurately reflects product evaluation information.

(Example 2)

Next, Example 2 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

Traditional shopping platforms lacked an appropriate mechanism for determining the authenticity of review comments, leaving users at risk of making purchasing decisions based on inaccurate information. This has created a need to improve the reliability of review comments and provide an environment where users can use them with peace of mind. It is also necessary to accurately understand the sentiment behind review comments in order to more accurately reflect product evaluation information.

The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting review comments, means for performing data preprocessing of the review comments, means for determining product relevance by comparing the review comments with a characteristic word list, means for analyzing the patterns of the review comments to determine unnatural reviews, means for comparing the review comments to determine comments with identical content as copy-and-paste reviews, means for analyzing the sentiment of the review comments, means for providing feedback on the review relevance, unnaturalness, copy-and-paste determination results, and sentiment analysis results, and means for rejecting the posting of review comments that are unnatural or copy-and-paste. This improves the reliability of review comments, provides an environment where users can refer to reviews with confidence, and makes it possible to more accurately reflect product evaluation information.

"Review comments" are textual opinions and evaluations written by users on shopping platforms about products and services.

"Data preprocessing" is the process of removing unnecessary elements from collected review comments and converting them into a format suitable for analysis.

A "characteristic word list" is a list of keywords related to a specific product or service that is used to compare with review comments.

"Product relevance determination" is the process of determining whether a review comment is relevant to a specific product or service.

"Pattern analysis" is the process of analyzing the content and format of review comments to detect specific patterns or anomalies.

"Unnatural reviews" are review comments that show an unusual pattern, such as content or writing style being posted repeatedly within a short period of time.

A "copy-and-paste review" refers to a review comment that has exactly the same content as an existing review comment.

"Sentiment analysis" is the process of analyzing the content of review comments and classifying their sentiments as positive, negative, or neutral.

"Feedback" refers to the provision of information to notify users or administrators of analysis and judgment results, and to encourage them to take necessary action.

"Posting refusal" refers to the action of not allowing users to post in order to prevent unnatural reviews or copy-and-paste reviews from being posted.

A "server" is a computer system that manages and executes a series of processes, including the collection, preprocessing, analysis, judgment, feedback, and rejection of review comments.

The system of the present invention evaluates the reliability of review comments on a shopping platform, recognizes user emotions, and optimizes review information. The specific operations and processes for this purpose are described below.

1. Collecting review comments

The system retrieves review comments through the shopping platform's API. The server periodically sends requests to the API endpoint and stores the retrieved review comments in a database. Specifically, MySQL or PostgreSQL can be used as the database.

For example, the server accesses the API endpoint "https://example.com/api/reviews" and stores the retrieved review comments in the "reviews" table.

2. Data Preprocessing

The server cleans the retrieved review comments. Specifically, it removes unnecessary whitespace, special characters, and HTML tags. It also tokenizes the review comments into words and sentences. This preprocessing can be performed using NLPK, a Python NLP library.

For example, a comment such as "This product is <p>great</p>!" is text cleaned to "This product is great!" and then tokenized.

3. Product Relevance Assessment

The server generates a word list based on the features and attributes of each product and compares it with the review comments. For example, for smartphone reviews, a word list containing keywords such as "image quality," "battery," and "operability" is used.

Specifically, the frequency of keywords appearing in review comments is scored, and if the score is above a certain level, it is determined to be a "review with high product relevance." For example, the server analyzes a comment such as "The image quality of this smartphone is outstanding," and assigns a high score because "image quality" is included in the word list.

4. Identifying unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. Specifically, it checks to see if review comments with similar content or format have been posted consecutively within a short period of time.

If an unnatural pattern is detected, the review comment is flagged. For example, if the server sees multiple reviews with the same content, such as "Great product!", posted within a short period of time, it will flag them as unnatural.

5. Judging Copy-Paste Reviews

Each time a new review comment is submitted, the server compares it with all existing review comments, using sophisticated text comparison algorithms (e.g., Python's difflib library) to determine whether there is a match.

If a match is found, the server will flag the review comment as a "copy-and-paste review." For example, if a comment already exists that says "This product is amazing!", the server will add a flag.

6. Emotion Recognition Using an Emotion Engine

The server inputs the review comments into a sentiment analysis engine and classifies them into positive, negative, or neutral sentiment. Specifically, sentiment analysis libraries such as TextBlob and VADER can be used.

This allows us to calculate an emotional score, which is then reflected in the overall rating of the product. For example, we can use TextBlob to analyze a comment such as "This phone's battery runs out quickly, so it's useless" and assign it a negative score.

7. Feedback and Filtering

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not related to the product, unnatural, or copied and pasted. If so, an error message will be displayed to the user explaining the reason for the post.

The emotion engine also notifies users and administrators of the emotion score, helping to improve the reliability of reviews. For example, the server may notify users that "this review has been flagged as unnatural" and encourage them to resubmit. It may also notify administrators that "a new unnatural review has been detected. Please check it."

Example prompt for a generative AI model

"Did this review comment relate to a specific product? Please categorize its sentiment. Example: 'The image quality of this phone is outstanding.'"

"Please determine whether the review comments on this listing are unnatural. Example: 'Great product!', 'Great product!'"

"Check if this review comment matches an existing comment or is a copypasta review. Example: 'This product is amazing!'"

The above is a form for implementing the system of the present invention.

The flow of the identification process in Example 2 will be explained using Figure 13.

Step 1:

Collecting review comments:

Input: Shopping platform API endpoint URL

Specific behavior: The server periodically sends requests to an API endpoint to retrieve review comments. For example, it accesses the API endpoint "https://example.com/api/reviews".

Data processing: Metadata (user ID, product ID, posting date and time, etc.) is added to the acquired review comments.

Output: Dataset containing review comments and metadata

Specific operation: The server stores the acquired dataset in a database (e.g., MySQL or PostgreSQL).

Step 2:

Data preprocessing:

Input: Review comments stored in the database

What it does: The server cleans the review comments. Specifically, it uses a Python NLP library (e.g., NLPK) to remove unnecessary whitespace, special characters, and HTML tags.

Data processing: Tokenize review comments into words and sentences.

Output: Clean, tokenized review comments

Specific operation: For example, a comment such as "This product is <p>great</p>!" is cleaned to "This product is great!" and separated into individual words.

Step 3:

Product relevance determination:

Input: Clean, tokenized review comments, product feature word list

Specific operation: The server compares the review comments with the feature word list. The word list includes keywords based on product attributes such as "image quality," "battery," and "operability."

Data calculation: Score the frequency of keywords appearing in review comments.

Output: Product relevance score

Specific behavior: For example, a comment such as "The image quality of this smartphone is outstanding" will be given a high score if "image quality" is included in the word list.

Step 4:

Determining unnatural reviews:

Input: All review comments posted within a certain period

Specific operation: The server analyzes the content patterns of review comments. It checks whether reviews with the same content or writing style have been posted consecutively.

Data calculations: Analysis to detect unnatural patterns

Output: Review comments flagged as unnatural

Specific behavior: For example, if the same review saying "This is a great product!" is posted multiple times within a short period of time, it will be flagged as unnatural.

Step 5:

Copy and paste review verdict:

Input: New review comment, Existing review comment

What it does: The server uses advanced text comparison algorithms (e.g., Python's difflib library) to compare the new comment with existing review comments.

Data calculation: The process of checking whether the content of comments matches.

Output: Review comments flagged as copy-paste reviews

Specific behavior: For example, if a comment saying "This product is amazing!" already exists, add a flag.

Step 6:

Emotion recognition using the emotion engine:

Enter: Review comment

Specific operation: The server inputs the review comments into a sentiment analysis engine (e.g., TextBlob or VADER) and classifies the sentiment.

Data calculation: Calculating emotion scores

Output: Review comments with sentiment scores

Specific behavior: For example, a comment such as "This smartphone's battery runs out quickly, making it useless" is scored as negative.

Step 7:

Feedback and filtering:

Input: Review comments (with flags for relevance, unnaturalness, and copy-paste), sentiment score

Specific behavior: When an attempt is made to post a review comment, the server will only allow it to be posted if it is not related to the product, unnatural, or copied and pasted. If so, an error message will be displayed to the user.

Data calculation: feedback and submission evaluation

Output: Notification to users and administrators

Specific behavior: For example, the server notifies the user that "this review has been flagged as unnatural" and encourages them to resubmit, while simultaneously notifying the administrator that "a new unnatural review has been detected."

The above are the specific processing steps of this system's program.

(Application Example 2)

Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 will be referred to as the "terminal."

Traditional review comment rating systems often lack the functionality to fully guarantee the reliability of reviews. For example, they often contain a mixture of reviews that are unrelated to the product, unnatural reviews, and copy-and-paste reviews, making it difficult for users to obtain accurate information. There is also a demand for more accurate product ratings through sentiment analysis of review comments. However, current systems lack sentiment analysis functionality, making it impossible to improve the quality and reliability of reviews.

The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

In this invention, the server includes means for collecting review comments, means for pre-processing data on the review comments, means for comparing the review comments with a list of characteristic words to determine product relevance, means for analyzing patterns of the review comments to determine unnatural reviews, means for comparing review comments to determine comments with identical content as copy-and-paste reviews, means for performing sentiment analysis on the review comments, and means for providing feedback on the review relevance, unnaturalness, copy-and-paste determination results, and sentiment analysis results. This allows users to obtain highly reliable review information and more accurately evaluate products.

"Review comments" refer to impressions and evaluations written by users about products and services.

"Means of collection" refers to the process or function of obtaining specific information from the Internet or a database.

"Data preprocessing" refers to the process of analyzing collected data or performing pre-analysis processing to remove unnecessary parts and format the data.

A "characteristic word list" refers to a list of important keywords related to a specific product or category.

"Means for determining product relevance" refers to the methods or algorithms used to evaluate how relevant a review comment is to a particular product.

"Methods of analyzing patterns to identify unnatural reviews" refers to methods of analyzing the content and posting patterns of review comments to detect unnatural content and typical actions.

A "copy-and-paste review" refers to a review comment that contains the same content as another review comment, copied and pasted exactly as is.

"Sentiment analysis" refers to the technology of analyzing user emotions and intentions from text data and classifying them as positive, negative, or neutral.

"Feedback" refers to the process of returning analysis and evaluation results to the user or system.

Form for implementing the invention

This invention is a system that improves the reliability of review comments on shopping platforms and provides users with optimal information. This system collects review comments, performs data preprocessing, and analyzes product relevance, unnaturalness, whether or not they have been copied and pasted, and sentiment before providing feedback.

System Overview

The server includes the following means:

1. How to collect review comments:

The server periodically retrieves all review comments from the shopping platform via API. These collected review comments are stored in a database.

2. Methods for preprocessing review comment data:

The server cleans the collected review comments. Specifically, it removes unnecessary whitespace, special characters, and HTML tags, tokenizes the review comments into words and sentences, and prepares them in an analyzable form.

3. How to determine product relevance by comparing review comments with a list of characteristic words:

The server compares review comments with a word list based on the characteristics and attributes of each product. For example, for a review about a smartphone, a word list such as "image quality," "battery," and "operability" would be prepared. The server scores the number of times words from the word list appear in the review comments, and if the score is above a certain level, it is determined to be a "review highly relevant to the product."

4. How to analyze review comment patterns and identify unnatural reviews:

The server analyzes all review comments posted within a certain period of time and checks for patterns in content. It checks to see if reviews with similar content or writing style have been posted consecutively within a short period of time, and if an unnatural pattern is detected, it flags the review comment.

5. How to compare review comments and identify comments with identical content as copy-and-paste reviews:

Every time a new review comment is submitted, the server compares it with all existing review comments. Using sophisticated text comparison algorithms, it checks whether an identical review comment already exists, and if a match is found, it flags the review comment as a "copy-and-paste review."

6. How to perform sentiment analysis on review comments:

The server analyzes the review comments using an emotion engine and classifies them into positive, negative, and neutral emotions. Based on the scoring by the emotion engine, the emotion score of the review comments is calculated and reflected in the overall rating of the product.

7. Means of providing feedback on review relevance, unnaturalness, copy-paste determination results, and sentiment analysis results:

When an attempt is made to post a review comment, the server will only allow it to be posted if it is not flagged as being inappropriate, unnatural, or copied and pasted. If a flag is raised, an error message will be displayed to the user, explaining the reason for the post. Feedback will be provided to the user and administrator, along with the sentiment score calculated by the sentiment engine, and administrators will be notified, urging them to further review and take action.

Hardware and software used

Hardware: Servers, cloud storage devices

Software: Python, requests, BeautifulSoup, re, nltk, textblob, scikit-learn, emotion engine (TextBlob, etc.)

Specific examples

As a concrete example, we will show the steps for processing the review comment "The image quality of this smartphone is outstanding." This comment is determined to be highly relevant to the product because it contains the keyword "image quality," and is approved because it does not match unnatural reviews or copy-paste reviews.

Example prompt

Example of a prompt to input to a generative AI model:

Analyze the new review comment, "The image quality of this phone is outstanding." We'll rate it based on the following criteria:

1. Product Relevance

2. Unnatural patterns

3. Copy and paste

4. Sentiment analysis

The flow of the specific processing in Application Example 2 will be explained using Figure 14.

Step 1:

Collecting review comments

The server periodically calls the shopping platform's API to retrieve review comments for each product. As input, it uses the API endpoint URL and authentication information. As output, it generates JSON data containing the retrieved review comments. This data is stored in the server's database.

Step 2:

Data preprocessing

The server cleans the collected review comments. As input, it uses the text data of the review comments stored in the database. Specifically, it removes unnecessary whitespace, special characters, and HTML tags, and tokenizes the review comments into words and sentences. As output, clean text data is generated and passed to the next step.

Step 3:

Product relevance determination

The server evaluates the relevance of review comments using a word list based on the features and attributes of each product. As input, it uses the clean review comments and the feature word list. Specifically, it scores how often words included in the feature word list appear in the review comments. As output, it generates a relevance score for each review comment.

Step 4:

Determining unnatural reviews

The server analyzes all review comments posted within a certain period of time and checks for patterns. As input, it uses text data from review comments over a certain period of time in the past and the current review comment. Specifically, it applies a text pattern matching algorithm to evaluate the similarity. As output, it generates a flag indicating whether the review is unnatural.

Step 5:

Copy-and-paste review verdict

Each time a new review comment is posted, the server compares it with all existing review comments. It uses the data of the new review comment and the existing review comments as input. Specifically, it uses an advanced text comparison algorithm (e.g., cosine similarity) to check whether a review comment with the exact same content exists. As output, it generates a flag indicating whether the review is a copy-and-paste review.

Step 6:

sentiment analysis

The server parses the review comments into the sentiment engine. It uses the clean review comments as input. Specifically, it sends the text to the sentiment engine (e.g., TextBlob) and obtains a sentiment score: positive, negative, or neutral. The output is a sentiment score for each review comment.

Step 7:

Feedback and filtering

When an attempt is made to post a review comment, the server provides feedback based on the judgment results obtained in the previous steps. All judgment results (relevance, unnaturalness, copy-paste judgment results, and sentiment score) are used as input. Specific behavior is to allow posting only if no flags are raised, and to display an error message to the user if a flag is raised. More detailed feedback is then provided to the administrator. As output, an error message or approval message is displayed to the user, and the review comment is saved in the database.

The specific processing unit 290 transmits the results of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the results of the specific processing. The microphone 238 acquires audio indicating the user input regarding the results of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

Data generation model 58 is what is known as generative AI (artificial intelligence). Examples of data generation model 58 include generative AI such as ChatGPT (Internet search <URL: https://openai.com/blog/chatgpt>) and Gemini (Internet search <URL: https://gemini.google.com/?hl=ja>). Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing an instruction is input to data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input. Data generation model 58 performs inference on the input inference data in accordance with the instructions indicated by the prompt, and outputs the inference results in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization.

In the above embodiment, an example was given in which the specific processing was performed by the data processing device 12, but the technology disclosed herein is not limited to this, and the specific processing may also be performed by the robot 414.

The emotion identification model 59, which serves as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see Figure 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

Figure 9 shows an emotion map 400 on which multiple emotions are mapped. In emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both emotions and mental states. Emotions that are generally generated from reactions that occur in the brain are arranged on the left side of the concentric circles. Emotions that are generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged above and below the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the top side of the concentric circles, and the emotion of "discomfort" is arranged on the bottom side. In this way, emotion map 400 maps multiple emotions based on the structure by which emotions are generated, with emotions that tend to occur simultaneously being mapped close together.

These emotions are distributed in the 3 o'clock direction on emotion map 400, and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness takes precedence over internal sensations, resulting in a calm impression.

The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible (expressed in behavior) the emotion becomes.

Here, human emotions are based on various balances such as posture and blood sugar levels, and when these balances deviate from the ideal, it indicates discomfort, and when they approach the ideal, it indicates pleasure. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and remaining battery life, so that when these balances deviate from the ideal, it indicates discomfort, and when they approach the ideal, it indicates pleasure. Emotion maps may be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and emotional brain physiological signal analysis systems, Tokushima University, doctoral dissertation: https://ci.nii.ac.jp/naid/500000375379). The left half of the emotion map is lined with emotions belonging to an area called "reaction," where sensation is dominant. The right half of the emotion map is lined with emotions belonging to an area called "situation," where situational awareness is dominant.

The emotion map defines two emotions that encourage learning. One is the negative emotion around the middle of "repentance" or "reflection" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot experiences positive feelings such as "I want more" or "I want to know more."

The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are close to each other have similar values, as in the emotion map 900 shown in Figure 10. Figure 10 shows an example in which multiple emotions, such as "relieved," "calm," and "reassuring," have similar emotion values.

The system according to the present disclosure has been described above primarily in terms of the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may also be implemented as a general information processing system. The present disclosure may also be implemented, for example, as a software program that runs on a personal computer or an application that runs on a smartphone, etc. The method according to the present disclosure may also be provided to users in the form of SaaS (Software as a Service).

In the above embodiment, an example was given in which a specific process was performed by a single computer 22, but the technology of the present disclosure is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including the computer 22. For example, the data generation model 58 may be provided in a device external to the data processing device 12, and data may be generated in that external device in response to input data.

In the above embodiment, an example was described in which the specific processing program 56 is stored in the storage 32, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

It is not necessary to store the entire specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entire specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

The following types of processors can be used as hardware resources for executing specific processes. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource for executing specific processes by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which are processors with a circuit configuration designed specifically for executing specific processes. All processors have built-in or connected memory, and all use the memory to execute specific processes.

The hardware resource that executes the specific processing may be composed of one of these various processors, or may be composed of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). The hardware resource that executes the specific processing may also be a single processor.

As an example of a configuration using a single processor, first, there is a configuration in which one processor is configured using a combination of one or more CPUs and software, and this processor functions as a hardware resource that executes specific processing. Second, there is a configuration in which a processor is used to realize the functions of an entire system, including multiple hardware resources that execute specific processing, on a single IC chip, as typified by SoC (System-on-a-chip). In this way, specific processing is realized using one or more of the various processors listed above as hardware resources.

More specifically, the hardware structure of these various processors can be an electrical circuit that combines circuit elements such as semiconductor devices. Furthermore, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps can be added, or the processing order can be rearranged, all within the scope of the spirit of the invention.

The above-described written content and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above explanation of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or substitutions may be made to the above-described written content and illustrations, as long as they do not deviate from the spirit of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described written content and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

All publications, patent applications, and technical standards mentioned in this specification are incorporated by reference herein to the same extent as if each individual publication, patent application, and technical standard was specifically and individually indicated to be incorporated by reference.

The following is further disclosed regarding the above embodiments.

(Claim 1)

Methods for collecting review comments,

A means of preprocessing review comment data,

A means of determining product relevance by comparing review comments with a list of characteristic words,

A method for analyzing review comment patterns and identifying unnatural reviews,

A method for comparing review comments and determining whether comments with identical content are copy-paste reviews,

Methods for providing feedback on the relevance, unnaturalness, and copy-paste judgment results of reviews,

A system including

(Claim 2)

The system described in claim 1, characterized in that the characteristic word list for review comments is set based on product attributes.

(Claim 3)

The system described in claim 1, characterized in that the pattern analysis of review comments is performed based on the degree of content consistency of review comments within a certain period of time.

"Example 1"

(Claim 1)

Methods for collecting review comments,

A means of preprocessing review comment data,

A means of determining product relevance by comparing with a list of feature words from review comments,

A method for analyzing review comment patterns and identifying unnatural reviews,

A method for comparing review comments and determining whether comments with identical content are copy-paste reviews,

Methods for providing feedback on the relevance, unnaturalness, and copy-paste judgment results of reviews,

A system including

(Claim 2)

The system described in claim 1, characterized in that the list of characteristic words for review comments is set based on product attributes.

(Claim 3)

The system described in claim 1, characterized in that the pattern analysis of review comments is performed based on the degree of content consistency of review comments within a certain period of time.

"Application Example 1"

(Claim 1)

Methods for collecting review comments,

A means of preprocessing review comment data,

A means of determining product relevance by comparing review comments with a list of characteristic words,

A method for analyzing review comment patterns and identifying unnatural reviews,

A method for comparing review comments and determining whether comments with identical content are copy-paste reviews,

Methods for providing feedback on the relevance, unnaturalness, and copy-paste judgment results of reviews,

A means to evaluate and provide feedback on the reliability of review comments in real time,

A way to display reviews in order of reliability,

A system including

(Claim 2)

The system described in claim 1, characterized in that the characteristic word list for review comments is set based on product attributes.

(Claim 3)

The system described in claim 1, characterized in that the pattern analysis of review comments is performed based on the degree of content consistency of review comments within a certain period of time.

"Example 2: Combining Emotion Engines"

(Claim 1)

Methods for collecting review comments,

A means of preprocessing review comment data,

A means of determining product relevance by comparing review comments with a list of characteristic words,

A method for analyzing review comment patterns and identifying unnatural reviews,

A method for comparing review comments and determining whether comments with identical content are copy-paste reviews,

Methods for analyzing the sentiment of review comments,

Means of providing feedback on review relevance, unnaturalness, copy-paste determination results, and sentiment analysis results,

If a review comment is unnatural or copied and pasted, there are ways to reject the post,

A system including

(Claim 2)

The system described in claim 1, characterized in that the characteristic word list for review comments is set based on product attributes.

(Claim 3)

The system described in claim 1, characterized in that the pattern analysis of review comments is performed based on the degree of content consistency of review comments within a certain period of time.

"Application Example 2: Combining Emotion Engines"

(Claim 1)

Methods for collecting review comments,

A means of preprocessing review comment data,

A means of determining product relevance by comparing review comments with a list of characteristic words,

A method for analyzing review comment patterns and identifying unnatural reviews,

A method for comparing review comments and determining whether comments with identical content are copy-paste reviews,

Methods for sentiment analysis of review comments,

Means for providing feedback on review relevance, unnaturalness, copy-paste determination results, and sentiment analysis results,

A system including

(Claim 2)

The system described in claim 1, characterized in that the characteristic word list for review comments is set based on product attributes.

(Claim 3)

The system described in claim 1, characterized in that the pattern analysis of review comments is performed based on the degree of content consistency of review comments within a certain period of time.

10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset type terminal 414 Robot

Claims (3)

a means for collecting review comments;
a means for performing data preprocessing of review comments;
A means for determining product relevance by comparing the review comments with a feature word list;
A means for analyzing patterns of review comments and determining unnatural reviews;
A method for comparing review comments and determining whether comments with the same content are copy-paste reviews,
A means of providing feedback on the relevance, unnaturalness, and copy-paste judgment results of reviews,
A system including: The system described in claim 1, characterized in that the characteristic word list for review comments is set based on product attributes. The system described in claim 1, characterized in that the pattern analysis of review comments is performed based on the degree of content consistency of review comments within a certain period of time.