JP2026018514A - system - Google Patents

Abstract

A system according to an embodiment aims to provide reliable reviews from an online review platform.
[Solution] A system according to an embodiment includes a review collection unit, a review analysis unit, a malicious review exclusion unit, and a reliable review providing unit. The review collection unit collects reviews from an online review platform. The review analysis unit analyzes the reviews collected by the review collection unit. The malicious review exclusion unit excludes malicious reviews based on the results of the analysis by the review analysis unit. The reliable review providing unit provides the reliable reviews excluded by the malicious review exclusion unit.
[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

With conventional technology, online review platforms often contained malicious reviews, making it difficult to obtain reliable reviews.

The system according to the embodiment aims to provide reliable reviews from online review platforms.

The system according to the embodiment includes a review collection unit, a review analysis unit, a malicious review exclusion unit, and a reliable review providing unit. The review collection unit collects reviews from online review platforms. The review analysis unit analyzes the reviews collected by the review collection unit. The malicious review exclusion unit excludes malicious reviews based on the results of the analysis by the review analysis unit. The reliable review providing unit provides the reliable reviews excluded by the malicious review exclusion unit.

The system according to the embodiment can provide reliable reviews from online review platforms.

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.

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), or a TPU (Tensor Processing Unit).

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) is an interface that includes a communication processor, an antenna, and the like. 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 A alone, B alone, 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]
FIG. 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 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 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input via the pointer. 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 (see Figure 2) acquires the data indicating the user input.

The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form that the user can perceive (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. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores the specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart device 14 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain processing results (prediction results, etc.) using the data generation model 58. The data processing device 12 may also be a server device, or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

(Example 1)
A review extraction system according to an embodiment of the present invention is a system for extracting true user experiences from online review platforms and providing reliable reviews, thereby filtering out malicious reviews and providing reliable reviews.

The review extraction system according to the embodiment includes a review collection unit, a review analysis unit, a malicious review exclusion unit, and a reliable review providing unit. The review collection unit collects reviews from online review platforms. For example, the review collection unit automatically obtains reviews from platforms such as Google Maps and Tabelog via an API. The review collection unit can also centrally collect reviews related to specific restaurants or tourist attractions. The review analysis unit analyzes the collected reviews. For example, the review analysis unit uses natural language processing technology with generative AI to understand the content of each review. The review analysis unit can also perform sentiment analysis and keyword extraction to evaluate the credibility of reviews. The malicious review exclusion unit excludes malicious reviews based on the results of the analysis by the review analysis unit. For example, the malicious review exclusion unit detects and excludes systematically inflated high ratings and inappropriate posts by bots. The malicious review exclusion unit can also filter out unnatural rumors and fake reviews. The reliable review providing unit provides reliable reviews excluded by the malicious review exclusion unit. For example, the reliable review providing unit displays only reliable reviews to the user. The reliable review providing unit can also summarize the content of the review to allow the user to understand it in a short amount of time. This allows the review extraction system according to the embodiment to filter out malicious reviews and provide reliable reviews. For example, users can obtain accurate information based on reliable reviews. This also improves the reliability of the entire platform.

The review collection unit can prioritize collecting reviews limited to specific regions or time periods based on the user's location information. The review collection unit, for example, obtains the user's location information and prioritizes collecting reviews limited to specific regions. For example, it may concentrate on collecting reviews related to specific cities or tourist destinations. The review collection unit can also prioritize collecting reviews limited to specific time periods. For example, it may collect reviews during peak times or during specific events. In this way, by prioritizing the collection of reviews limited to specific regions or time periods, it is possible to provide more relevant reviews.

The review collection unit can refer to the user's past review history and prioritize collecting reviews from highly reliable users. The review collection unit, for example, analyzes the user's past review history and prioritizes collecting reviews from highly reliable users. For example, it prioritizes reviews from users who have posted many reviews that have received high ratings in the past. The review collection unit can also prioritize collecting reviews from users who have received high ratings from other users. For example, it prioritizes reviews from users who have received a large number of "likes" and comments from other users. In this way, by preferentially collecting reviews from highly reliable users, it is possible to provide more reliable reviews.

The review collection unit can simultaneously collect not only text but also image and video reviews, and analyze visual information as well. For example, when collecting reviews, the review collection unit can simultaneously collect images and videos posted by users and analyze visual information. For example, it can collect restaurant food photos and video reviews of tourist spots. The review collection unit can also analyze visual information using image recognition technology and video analysis technology. For example, it can analyze the content of images and reflect this in the review rating. In this way, by analyzing visual information as well, more multifaceted review analysis is possible.

The review aggregator can detect duplicate reviews across different review platforms and filter out the duplicate reviews. For example, the review aggregator can compare reviews collected from different review platforms and detect duplicate reviews. For example, it can identify reviews posted by the same user on multiple platforms. The review aggregator can also use an algorithm to filter out duplicate reviews. For example, it can calculate text similarity and filter out duplicate reviews. This can provide more reliable reviews by filtering out duplicate reviews.

The review analysis unit learns users' writing habits and writing style, and can detect malicious reviews based on individual user characteristics. The review analysis unit, for example, learns users' writing habits and writing style, and can detect malicious reviews based on individual user characteristics. For example, it analyzes reviews from users who frequently use specific phrases or expressions. The review analysis unit can also detect reviews from unreliable users based on past posting history. For example, it can exclude reviews from users who have posted inappropriate reviews in the past. This allows for more accurate review analysis by detecting malicious reviews based on individual user characteristics.

The review analysis unit can take into account the number of "likes" or comments from other users to evaluate the credibility of the review content. The review analysis unit, for example, takes into account the number of "likes" or comments from other users to evaluate the credibility of the review content. For example, it may determine that reviews with many "likes" are highly credible. The review analysis unit can also evaluate reviews with many comments as highly credible. For example, it may prioritize reviews with many positive comments. In this way, by taking feedback from other users into account, the credibility of a review can be evaluated more accurately.

The review analysis unit can automatically translate reviews in different languages and perform multilingual analysis. For example, when analyzing reviews, the review analysis unit can automatically translate reviews in different languages and perform multilingual analysis. For example, it can translate reviews in English, French, Chinese, etc. The review analysis unit can also use machine translation algorithms to improve translation accuracy. For example, it can translate reviews using Google Translate. This allows for multilingual analysis, making it possible to analyze a wider range of reviews.

The review analysis unit can detect abnormal patterns by taking into account the time and frequency of review posting. The review analysis unit can detect abnormal patterns by taking into account, for example, the time and frequency of review posting. For example, it can identify cases where a large number of reviews are posted in a short period of time. The review analysis unit can also detect reviews that are posted in large concentrations during specific time periods. For example, it can identify reviews that are posted in large concentrations late at night. By detecting abnormal patterns in this way, it is possible to provide more reliable reviews.

The malicious review exclusion unit can take into account reports and feedback from other users. The malicious review exclusion unit, for example, takes into account reports and feedback from other users. For example, it prioritizes excluding reviews reported by multiple users. The malicious review exclusion unit can also identify malicious reviews based on comments and ratings from users. For example, it excludes reviews with a lot of negative feedback. In this way, by taking into account reports and feedback from other users, it is possible to provide more reliable reviews.

The malicious review exclusion unit can consider not only the content of the review, but also the device and IP address from which the review was posted. The malicious review exclusion unit can, for example, consider not only the content of the review, but also the device and IP address from which the review was posted. For example, it can detect large numbers of posts from the same IP address. The malicious review exclusion unit can also identify and exclude posts from specific devices. For example, it can detect posts from specific smartphones or PCs. This makes it possible to provide more reliable reviews by considering the device and IP address from which the review was posted.

The malicious review excluding unit can detect abnormal patterns by taking into account the geographic location information of the review's posting source. The malicious review excluding unit can, for example, detect abnormal patterns by taking into account the geographic location information of the review's posting source. For example, it can detect large numbers of posts from specific regions. The malicious review excluding unit can also identify and exclude posts from specific countries or cities. For example, it can detect spam posts from specific countries. In this way, by taking into account the geographic location information of the posting source, it is possible to provide more reliable reviews.

The reliable review providing unit can provide the most suitable reviews for individual users by taking into account the user's past browsing history and rating history. The reliable review providing unit can provide the most suitable reviews for individual users by taking into account the user's past browsing history and rating history. For example, it can prioritize displaying reviews that have received high ratings in the past. The reliable review providing unit can also provide reviews based on the user's interests. For example, it can display highly relevant reviews based on pages viewed in the past and search history. This allows the most suitable reviews to be provided for individual users, making it possible to provide more relevant reviews.

The reliability review providing unit can summarize the content of the review, allowing the user to understand it in a short amount of time. The reliability review providing unit can, for example, summarize the content of the review, allowing the user to understand it in a short amount of time. For example, it can automatically extract the main points of the review. The reliability review providing unit can also highlight important parts of the review. For example, it can display positive and negative comments in different colors. In this way, by summarizing the content of the review, the user can understand the review in a short amount of time.

The reliability review providing unit can visualize the content of the review and display it in a graph or chart. The reliability review providing unit can, for example, visualize the content of the review and display it in a graph or chart. For example, it can display the review rating in a graph. The reliability review providing unit can also display review trends in a chart. For example, it can display the ratio of positive reviews to negative reviews in a pie chart. In this way, by visualizing the content of the review, users can intuitively understand the review.

The reliability review providing unit can increase the credibility of a review by displaying feedback and comments from other users. The reliability review providing unit can increase the credibility of a review by, for example, displaying feedback and comments from other users. For example, it prioritizes reviews that have a lot of positive feedback. The reliability review providing unit can also increase the credibility of a review by displaying comments from other users. For example, it prioritizes reviews that have received high ratings from other users. In this way, the credibility of a review can be increased by displaying feedback and comments from other users.

The continuous learning and improvement unit can automatically detect new malicious review patterns and add them to the learning data. The continuous learning and improvement unit, for example, can automatically detect new malicious review patterns and add them to the learning data. For example, it can detect new spam patterns. The continuous learning and improvement unit can also reflect the detected patterns in subsequent analyses. For example, it can learn new malicious review patterns and reflect them in subsequent analyses. In this way, the accuracy of the system can be improved by automatically detecting new malicious review patterns and adding them to the learning data.

The continuous learning and improvement department can collect feedback from users and reflect it in system improvements. The continuous learning and improvement department can, for example, collect feedback from users and reflect it in system improvements. For example, improve the algorithm based on user opinions. The continuous learning and improvement department can also identify areas for improvement in the system based on user comments and ratings. For example, improve analysis accuracy based on user feedback. In this way, by collecting user feedback and reflecting it in system improvements, the accuracy of the system can be improved.

The Continuous Learning and Improvement Department can integrate data from different review platforms to expand the learning data. The Continuous Learning and Improvement Department can, for example, integrate data from different review platforms to expand the learning data. For example, it can integrate data from Google Maps and Tabelog. The Continuous Learning and Improvement Department can also centralize data from different platforms to improve analysis accuracy. For example, it can integrate reviews from multiple platforms and use them as learning data. In this way, by integrating data from different review platforms, it is possible to expand the learning data and improve the accuracy of the system.

The continuous learning and improvement unit can learn not only from the content of reviews, but also from user behavioral data. The continuous learning and improvement unit can learn not only from the content of reviews, but also from user behavioral data. For example, it can learn from users' browsing history and rating history. The continuous learning and improvement unit can also expand the learning data based on users' click history and purchase history. For example, it can analyze users' behavioral patterns and use this as learning data. In this way, by learning from user behavioral data as well, the accuracy of the system can be improved.

The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows:

The review collection unit can also link with users' social media accounts to collect reviews and comments posted by users on other platforms. For example, it can analyze posts on Twitter and Facebook to collect related reviews. The review collection unit can also prioritize the collection of reliable reviews based on the user's social media activity history. For example, it can prioritize reviews from users with a high number of followers and engagement rate. This makes it possible to collect reviews from a more diverse range of perspectives by utilizing social media data.

The review analysis unit can prioritize analysis of reviews from users who have actually used a product or service, based on the user's purchasing history. For example, it can reference purchase histories on online shopping sites and prioritize reviews from purchasers. The review analysis unit can also compare a user's purchasing history with the content of reviews to identify highly credible reviews. For example, it can prioritize reviews whose content matches reviews left after a purchase. This makes it possible to provide more reliable reviews by placing emphasis on reviews from actual users.

The review collection unit can prioritize collecting reviews from specific devices based on user device information. For example, it can prioritize reviews from smartphones. The review collection unit can also collect reviews in specific device environments by taking into account the device type and OS version. For example, it can prioritize reviews from iOS devices. This makes it possible to collect reviews that prioritize the user experience in a specific device environment.

The review analysis unit takes into account the frequency with which users post reviews and can detect abnormal posting patterns. For example, it can identify users who post a large number of reviews in a short period of time. The review analysis unit can also detect reviews that are posted in large numbers during specific time periods. For example, it can identify reviews that are posted in large numbers late at night. This allows it to detect abnormal posting patterns and provide more reliable reviews.

The review analysis unit learns users' writing habits and styles, and can detect malicious reviews based on individual user characteristics. For example, it analyzes reviews from users who frequently use specific phrases or expressions. The review analysis unit can also detect reviews from unreliable users based on past posting history. For example, it can exclude reviews from users who have posted inappropriate reviews in the past. This allows for more accurate review analysis by detecting malicious reviews based on individual user characteristics.

The review analysis unit can automatically translate reviews in different languages and perform multilingual analysis. For example, when analyzing reviews, it can automatically translate reviews in different languages and perform multilingual analysis. For example, it can translate reviews in English, French, Chinese, etc. The review analysis unit can also use machine translation algorithms to improve translation accuracy. For example, it can translate reviews using Google Translate. This allows for multilingual analysis, making it possible to analyze a wider range of reviews.

The processing flow for Example 1 is briefly explained below.

Step 1: The review aggregator collects reviews from online review platforms. For example, the review aggregator can automatically retrieve reviews from platforms such as Google Maps and Tabelog through APIs. It can also centrally collect reviews for specific restaurants or tourist attractions.
Step 2: The review analysis unit analyzes the collected reviews. For example, it uses generative AI and natural language processing technology to understand the content of each review. It can also perform sentiment analysis and keyword extraction to evaluate the credibility of the reviews.
Step 3: The malicious review filter filters out malicious reviews based on the results of the review analysis. For example, it detects and filters out systematically inflated high ratings and inappropriate posts by bots. It can also filter out unnatural rumors and fake reviews.
Step 4: The reliable review providing unit provides the reliable reviews filtered out by the malicious review filtering unit. For example, it displays only reliable reviews to the user and summarizes the review content so that the user can understand it quickly.

(Example 2)
A review extraction system according to an embodiment of the present invention is a system for extracting true user experiences from online review platforms and providing reliable reviews, thereby filtering out malicious reviews and providing reliable reviews.

The review extraction system according to the embodiment includes a review collection unit, a review analysis unit, a malicious review exclusion unit, and a reliable review providing unit. The review collection unit collects reviews from online review platforms. For example, the review collection unit automatically obtains reviews from platforms such as Google Maps and Tabelog via an API. The review collection unit can also centrally collect reviews related to specific restaurants or tourist attractions. The review analysis unit analyzes the collected reviews. For example, the review analysis unit uses natural language processing technology with generative AI to understand the content of each review. The review analysis unit can also perform sentiment analysis and keyword extraction to evaluate the credibility of reviews. The malicious review exclusion unit excludes malicious reviews based on the results of the analysis by the review analysis unit. For example, the malicious review exclusion unit detects and excludes systematically inflated high ratings and inappropriate posts by bots. The malicious review exclusion unit can also filter out unnatural rumors and fake reviews. The reliable review providing unit provides reliable reviews excluded by the malicious review exclusion unit. For example, the reliable review providing unit displays only reliable reviews to the user. The reliable review providing unit can also summarize the content of the review to allow the user to understand it in a short amount of time. This allows the review extraction system according to the embodiment to filter out malicious reviews and provide reliable reviews. For example, users can obtain accurate information based on reliable reviews. This also improves the reliability of the entire platform.

The review collection unit can prioritize collecting reviews limited to specific regions or time periods based on the user's location information. The review collection unit, for example, obtains the user's location information and prioritizes collecting reviews limited to specific regions. For example, it may concentrate on collecting reviews related to specific cities or tourist destinations. The review collection unit can also prioritize collecting reviews limited to specific time periods. For example, it may collect reviews during peak times or during specific events. In this way, by prioritizing the collection of reviews limited to specific regions or time periods, it is possible to provide more relevant reviews.

The review collection unit can refer to the user's past review history and prioritize collecting reviews from highly reliable users. The review collection unit, for example, analyzes the user's past review history and prioritizes collecting reviews from highly reliable users. For example, it prioritizes reviews from users who have posted many reviews that have received high ratings in the past. The review collection unit can also prioritize collecting reviews from users who have received high ratings from other users. For example, it prioritizes reviews from users who have received a large number of "likes" and comments from other users. In this way, by preferentially collecting reviews from highly reliable users, it is possible to provide more reliable reviews.

The review collection unit can use the emotion estimation function to estimate the user's emotional state when collecting reviews, and prioritize collecting reviews from users with positive emotions. The review collection unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time when collecting reviews, and prioritize collecting reviews from users with positive emotions. For example, reviews that show joy or satisfaction are prioritized. The review collection unit can also use the emotion estimation function to filter reviews from users with negative emotions. For example, reviews that show anger or dissatisfaction are excluded. This allows for the priority collection of reviews from users with positive emotions, making it possible to provide more reliable reviews.

The review collection unit can simultaneously collect not only text but also image and video reviews, and analyze visual information as well. For example, when collecting reviews, the review collection unit can simultaneously collect images and videos posted by users and analyze visual information. For example, it can collect restaurant food photos and video reviews of tourist spots. The review collection unit can also analyze visual information using image recognition technology and video analysis technology. For example, it can analyze the content of images and reflect this in the review rating. In this way, by analyzing visual information as well, more multifaceted review analysis is possible.

The review aggregator can detect duplicate reviews across different review platforms and filter out the duplicate reviews. For example, the review aggregator can compare reviews collected from different review platforms and detect duplicate reviews. For example, it can identify reviews posted by the same user on multiple platforms. The review aggregator can also use an algorithm to filter out duplicate reviews. For example, it can calculate text similarity and filter out duplicate reviews. This can provide more reliable reviews by filtering out duplicate reviews.

The review collection unit can use the emotion estimation function to monitor user emotions in real time when collecting reviews and filter out reviews from users with negative emotions. The review collection unit can, for example, use the emotion estimation function to monitor user emotions in real time when collecting reviews and filter out reviews from users with negative emotions. For example, reviews that show anger or dissatisfaction can be excluded. The review collection unit can also prioritize collecting reviews from users with positive emotions. For example, reviews that show joy or satisfaction can be prioritized. This allows for filtering out reviews from users with negative emotions, making it possible to provide more reliable reviews.

The review analysis unit learns users' writing habits and writing style, and can detect malicious reviews based on individual user characteristics. The review analysis unit, for example, learns users' writing habits and writing style, and can detect malicious reviews based on individual user characteristics. For example, it analyzes reviews from users who frequently use specific phrases or expressions. The review analysis unit can also detect reviews from unreliable users based on past posting history. For example, it can exclude reviews from users who have posted inappropriate reviews in the past. This allows for more accurate review analysis by detecting malicious reviews based on individual user characteristics.

The review analysis unit can take into account the number of "likes" or comments from other users to evaluate the credibility of the review content. The review analysis unit, for example, takes into account the number of "likes" or comments from other users to evaluate the credibility of the review content. For example, it may determine that reviews with many "likes" are highly credible. The review analysis unit can also evaluate reviews with many comments as highly credible. For example, it may prioritize reviews with many positive comments. In this way, by taking feedback from other users into account, the credibility of a review can be evaluated more accurately.

The review analysis unit can use the emotion estimation function to estimate user emotions during review analysis and detect emotionally unnatural reviews. The review analysis unit can, for example, use the emotion estimation function to estimate user emotions during review analysis and detect emotionally unnatural reviews. For example, it can identify reviews with extremely high emotion scores. The review analysis unit can also detect sudden changes in emotion and inconsistent emotional expression. For example, it can detect sudden changes from positive to negative emotions. This makes it possible to provide more reliable reviews by detecting emotionally unnatural reviews.

The review analysis unit can automatically translate reviews in different languages and perform multilingual analysis. For example, when analyzing reviews, the review analysis unit can automatically translate reviews in different languages and perform multilingual analysis. For example, it can translate reviews in English, French, Chinese, etc. The review analysis unit can also use machine translation algorithms to improve translation accuracy. For example, it can translate reviews using Google Translate. This allows for multilingual analysis, making it possible to analyze a wider range of reviews.

The review analysis unit can detect abnormal patterns by taking into account the time and frequency of review posting. The review analysis unit can detect abnormal patterns by taking into account, for example, the time and frequency of review posting. For example, it can identify cases where a large number of reviews are posted in a short period of time. The review analysis unit can also detect reviews that are posted in large concentrations during specific time periods. For example, it can identify reviews that are posted in large concentrations late at night. By detecting abnormal patterns in this way, it is possible to provide more reliable reviews.

The review analysis unit can use the emotion estimation function to monitor user emotions in real time when analyzing reviews, and prioritize classifying reviews that are likely to resonate emotionally. The review analysis unit can, for example, use the emotion estimation function to monitor user emotions in real time when analyzing reviews, and prioritize classifying reviews that are likely to resonate emotionally. For example, reviews with high emotion scores can be prioritized. The review analysis unit can also prioritize classifying reviews that show positive emotions. For example, reviews that show joy or satisfaction can be prioritized. This allows for the provision of more reliable reviews by prioritizing classification of reviews that are likely to resonate emotionally.

The malicious review exclusion unit can take into account reports and feedback from other users. The malicious review exclusion unit, for example, takes into account reports and feedback from other users. For example, it prioritizes excluding reviews reported by multiple users. The malicious review exclusion unit can also identify malicious reviews based on comments and ratings from users. For example, it excludes reviews with a lot of negative feedback. In this way, by taking into account reports and feedback from other users, it is possible to provide more reliable reviews.

The malicious review exclusion unit can use the emotion estimation function to prioritize emotionally unnatural reviews when excluding malicious reviews. The malicious review exclusion unit, for example, uses the emotion estimation function to prioritize emotionally unnatural reviews when excluding malicious reviews. For example, it excludes reviews with extremely high emotion scores. The malicious review exclusion unit can also detect and exclude sudden changes in emotion and inconsistent emotional expressions. For example, it detects sudden changes from positive emotions to negative emotions. This allows for the priority elimination of emotionally unnatural reviews, making it possible to provide more reliable reviews.

The malicious review exclusion unit can consider not only the content of the review, but also the device and IP address from which the review was posted. The malicious review exclusion unit can, for example, consider not only the content of the review, but also the device and IP address from which the review was posted. For example, it can detect large numbers of posts from the same IP address. The malicious review exclusion unit can also identify and exclude posts from specific devices. For example, it can detect posts from specific smartphones or PCs. This makes it possible to provide more reliable reviews by considering the device and IP address from which the review was posted.

The malicious review excluding unit can detect abnormal patterns by taking into account the geographic location information of the review's posting source. The malicious review excluding unit can, for example, detect abnormal patterns by taking into account the geographic location information of the review's posting source. For example, it can detect large numbers of posts from specific regions. The malicious review excluding unit can also identify and exclude posts from specific countries or cities. For example, it can detect spam posts from specific countries. In this way, by taking into account the geographic location information of the posting source, it is possible to provide more reliable reviews.

The malicious review exclusion unit uses the emotion estimation function to monitor user emotions in real time when filtering out malicious reviews, and can prioritize filtering out emotionally unnatural reviews. The malicious review exclusion unit, for example, uses the emotion estimation function to monitor user emotions in real time when filtering out malicious reviews, and can prioritize filtering out emotionally unnatural reviews. For example, it can filter out reviews with extremely high emotion scores. The malicious review exclusion unit can also detect and filter out sudden changes in emotion or inconsistent emotional expressions. For example, it can detect sudden changes from positive to negative emotions. This allows for the priority filtering out of emotionally unnatural reviews, making it possible to provide more reliable reviews.

The reliable review providing unit can provide the most suitable reviews for individual users by taking into account the user's past browsing history and rating history. The reliable review providing unit can provide the most suitable reviews for individual users by taking into account the user's past browsing history and rating history. For example, it can prioritize displaying reviews that have received high ratings in the past. The reliable review providing unit can also provide reviews based on the user's interests. For example, it can display highly relevant reviews based on pages viewed in the past and search history. This allows the most suitable reviews to be provided for individual users, making it possible to provide more relevant reviews.

The reliability review providing unit can summarize the content of the review, allowing the user to understand it in a short amount of time. The reliability review providing unit can, for example, summarize the content of the review, allowing the user to understand it in a short amount of time. For example, it can automatically extract the main points of the review. The reliability review providing unit can also highlight important parts of the review. For example, it can display positive and negative comments in different colors. In this way, by summarizing the content of the review, the user can understand the review in a short amount of time.

The reliable review providing unit can use the emotion estimation function to monitor user emotions in real time when providing reliable reviews, and prioritize providing reviews that are likely to resonate emotionally. The reliable review providing unit can, for example, use the emotion estimation function to monitor user emotions in real time when providing reliable reviews, and prioritize providing reviews that are likely to resonate emotionally. For example, reviews with high emotion scores can be prioritized. The reliable review providing unit can also prioritize providing reviews that show positive emotions. For example, reviews that show joy or satisfaction can be prioritized. This makes it possible to provide more useful reviews to users by prioritizing reviews that are likely to resonate emotionally.

The reliability review providing unit can visualize the content of the review and display it in a graph or chart. The reliability review providing unit can, for example, visualize the content of the review and display it in a graph or chart. For example, it can display the review rating in a graph. The reliability review providing unit can also display review trends in a chart. For example, it can display the ratio of positive reviews to negative reviews in a pie chart. In this way, by visualizing the content of the review, users can intuitively understand the review.

The reliability review providing unit can increase the credibility of a review by displaying feedback and comments from other users. The reliability review providing unit can increase the credibility of a review by, for example, displaying feedback and comments from other users. For example, it prioritizes reviews that have a lot of positive feedback. The reliability review providing unit can also increase the credibility of a review by displaying comments from other users. For example, it prioritizes reviews that have received high ratings from other users. In this way, the credibility of a review can be increased by displaying feedback and comments from other users.

The reliable review providing unit can use the emotion estimation function to monitor user emotions in real time when providing reliable reviews, and prioritize providing reviews that are likely to resonate emotionally. The reliable review providing unit can, for example, use the emotion estimation function to monitor user emotions in real time when providing reliable reviews, and prioritize providing reviews that are likely to resonate emotionally. For example, reviews with high emotion scores can be prioritized. The reliable review providing unit can also prioritize providing reviews that show positive emotions. For example, reviews that show joy or satisfaction can be prioritized. This makes it possible to provide more useful reviews to users by prioritizing reviews that are likely to resonate emotionally.

The continuous learning and improvement unit can automatically detect new malicious review patterns and add them to the learning data. The continuous learning and improvement unit, for example, can automatically detect new malicious review patterns and add them to the learning data. For example, it can detect new spam patterns. The continuous learning and improvement unit can also reflect the detected patterns in subsequent analyses. For example, it can learn new malicious review patterns and reflect them in subsequent analyses. In this way, the accuracy of the system can be improved by automatically detecting new malicious review patterns and adding them to the learning data.

The continuous learning and improvement department can collect feedback from users and reflect it in system improvements. The continuous learning and improvement department can, for example, collect feedback from users and reflect it in system improvements. For example, improve the algorithm based on user opinions. The continuous learning and improvement department can also identify areas for improvement in the system based on user comments and ratings. For example, improve analysis accuracy based on user feedback. In this way, by collecting user feedback and reflecting it in system improvements, the accuracy of the system can be improved.

The Continuous Learning and Improvement Department can integrate data from different review platforms to expand the learning data. The Continuous Learning and Improvement Department can, for example, integrate data from different review platforms to expand the learning data. For example, it can integrate data from Google Maps and Tabelog. The Continuous Learning and Improvement Department can also centralize data from different platforms to improve analysis accuracy. For example, it can integrate reviews from multiple platforms and use them as learning data. In this way, by integrating data from different review platforms, it is possible to expand the learning data and improve the accuracy of the system.

The continuous learning and improvement unit can learn not only from the content of reviews, but also from user behavioral data. The continuous learning and improvement unit can learn not only from the content of reviews, but also from user behavioral data. For example, it can learn from users' browsing history and rating history. The continuous learning and improvement unit can also expand the learning data based on users' click history and purchase history. For example, it can analyze users' behavioral patterns and use this as learning data. In this way, by learning from user behavioral data as well, the accuracy of the system can be improved.

The continuous learning and improvement unit can use the emotion estimation function to monitor user emotions in real time during continuous learning and improvement, and prioritize learning reviews that are likely to resonate emotionally. The continuous learning and improvement unit can, for example, use the emotion estimation function to monitor user emotions in real time during continuous learning and improvement, and prioritize learning reviews that are likely to resonate emotionally. For example, reviews with high emotion scores can be prioritized. The continuous learning and improvement unit can also prioritize learning reviews that show positive emotions. For example, reviews that show joy or satisfaction can be prioritized. This allows the accuracy of the system to be improved by prioritizing learning reviews that are likely to resonate emotionally.

The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows:

The review collection unit can also link with users' social media accounts to collect reviews and comments posted by users on other platforms. For example, it can analyze posts on Twitter and Facebook to collect related reviews. The review collection unit can also prioritize the collection of reliable reviews based on the user's social media activity history. For example, it can prioritize reviews from users with a high number of followers and engagement rate. This makes it possible to collect reviews from a more diverse range of perspectives by utilizing social media data.

The review analysis unit can prioritize analysis of reviews from users who have actually used a product or service, based on the user's purchasing history. For example, it can reference purchase histories on online shopping sites and prioritize reviews from purchasers. The review analysis unit can also compare a user's purchasing history with the content of reviews to identify highly credible reviews. For example, it can prioritize reviews whose content matches reviews left after a purchase. This makes it possible to provide more reliable reviews by placing emphasis on reviews from actual users.

The review collection unit can prioritize collecting reviews from specific devices based on user device information. For example, it can prioritize reviews from smartphones. The review collection unit can also collect reviews in specific device environments by taking into account the device type and OS version. For example, it can prioritize reviews from iOS devices. This makes it possible to collect reviews that prioritize the user experience in a specific device environment.

The review analysis unit can estimate the user's emotions and evaluate the credibility of a review based on the estimated user emotions. For example, reviews that show positive emotions can be determined to be highly credible. The review analysis unit can also evaluate the consistency of emotions and filter out emotionally inconsistent reviews. For example, it can detect cases where emotions change suddenly within a review. This allows for more reliable reviews to be provided by evaluating credibility based on emotions.

The review collection unit can collect users' voice reviews and convert them into text using voice recognition technology. For example, reviews can be collected using the voice input function of a smartphone. The review collection unit can also analyze voice data and evaluate emotions and tone. For example, it can infer a user's emotions from the tone of their voice. This makes it possible to collect reviews in a wider variety of formats by utilizing voice reviews.

The review analysis unit takes into account the frequency with which users post reviews and can detect abnormal posting patterns. For example, it can identify users who post a large number of reviews in a short period of time. The review analysis unit can also detect reviews that are posted in large numbers during specific time periods. For example, it can identify reviews that are posted in large numbers late at night. This allows it to detect abnormal posting patterns and provide more reliable reviews.

The review collection unit can use the emotion estimation function to monitor user emotions in real time as reviews are collected, and filter out reviews from users with negative emotions. For example, reviews that express anger or dissatisfaction can be excluded. The review collection unit can also prioritize collecting reviews from users with positive emotions. For example, reviews that express joy or satisfaction can be prioritized. This allows for filtering out reviews from users with negative emotions, making it possible to provide more reliable reviews.

The review analysis unit learns users' writing habits and styles, and can detect malicious reviews based on individual user characteristics. For example, it analyzes reviews from users who frequently use specific phrases or expressions. The review analysis unit can also detect reviews from unreliable users based on past posting history. For example, it can exclude reviews from users who have posted inappropriate reviews in the past. This allows for more accurate review analysis by detecting malicious reviews based on individual user characteristics.

The review analysis unit uses the emotion estimation function to estimate user emotions during review analysis and detect emotionally unnatural reviews. For example, it can identify reviews with extremely high emotion scores. The review analysis unit can also detect sudden changes in emotion or inconsistent emotional expression. For example, it can detect sudden changes from positive to negative emotions. This allows it to detect emotionally unnatural reviews and provide more reliable reviews.

The review analysis unit can automatically translate reviews in different languages and perform multilingual analysis. For example, when analyzing reviews, it can automatically translate reviews in different languages and perform multilingual analysis. For example, it can translate reviews in English, French, Chinese, etc. The review analysis unit can also use machine translation algorithms to improve translation accuracy. For example, it can translate reviews using Google Translate. This allows for multilingual analysis, making it possible to analyze a wider range of reviews.

The processing flow for Example 2 is briefly explained below.

Step 1: The review aggregator collects reviews from online review platforms. For example, the review aggregator can automatically retrieve reviews from platforms such as Google Maps and Tabelog through APIs. It can also centrally collect reviews for specific restaurants or tourist attractions.
Step 2: The review analysis unit analyzes the collected reviews. For example, it uses generative AI and natural language processing technology to understand the content of each review. It can also perform sentiment analysis and keyword extraction to evaluate the credibility of the reviews.
Step 3: The malicious review filter filters out malicious reviews based on the results of the review analysis. For example, it detects and filters out systematically inflated high ratings and inappropriate posts by bots. It can also filter out unnatural rumors and fake reviews.
Step 4: The reliable review providing unit provides the reliable reviews filtered out by the malicious review filtering unit. For example, it displays only reliable reviews to the user and summarizes the review content so that the user can understand it quickly.

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.

The data generation model 58 is what is known as generative AI (artificial intelligence). An example of a data generation model 58 is generative AI such as ChatGPT (Internet search <URL: https://openai.com/blog/chatgpt>). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing an instruction is input to the data generation model 58, and inference data such as voice data representing speech, text data representing text, and image data representing an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AI other than the generation AI. Examples of AI other than the generation AI include linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes, and can perform a variety of processes, but are not limited to these examples. The AI may also be an AI agent. When the processing of each of the above-mentioned parts is performed by AI, the processing may be performed in part or in whole by AI, but is not limited to these examples. The processing performed by AI, including the generation AI, may be replaced with rule-based processing.

Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, etc., and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device, etc.

Second Embodiment
FIG. 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 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 and/or a LAN.

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, the speaker 240, and the camera 42 are also connected to the bus 52.

The microphone 238 receives instructions and other information from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, 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's surroundings (for example, 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 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. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

In the smart glasses 214, specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain processing results (such as prediction results) using the data generation model 58. The data processing device 12 may also be a server device, or a terminal device owned by a user (for example, a mobile phone, robot, home appliance, etc.).

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.

The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output inference results from prompts that do not include instructions. In this case, the data generation model 58 can output inference results from prompts that do not include instructions. The data processing device 12, etc., includes multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform a variety of processes, but is not limited to these examples. The AI may also be an AI agent. When the processing of each of the above-mentioned parts is performed by AI, the processing may be performed in part or in whole by AI, but is not limited to these examples. The processing performed by AI, including the generative AI, may be replaced with rule-based processing.

The data processing system 210 according to the second embodiment performs processing similar to that of the data processing system 10 according to the first embodiment. Processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device, etc.

[Third embodiment]
FIG. 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 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 and/or a LAN.

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 other information from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, 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's surroundings (for example, 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 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. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

In the headset type terminal 314, the specific processing is performed by the processor 46. A specific program 60 is stored in the storage 50. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain processing results (such as prediction results) using the data generation model 58. The data processing device 12 may also be a server device, or a terminal device owned by a user (for example, a mobile phone, robot, home appliance, etc.).

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.

The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output inference results from prompts that do not include instructions. In this case, the data generation model 58 can output inference results from prompts that do not include instructions. The data processing device 12, etc., includes multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform a variety of processes, but is not limited to these examples. The AI may also be an AI agent. When the processing of each of the above-mentioned parts is performed by AI, the processing may be performed in part or in whole by AI, but is not limited to these examples. The processing performed by AI, including the generative AI, may be replaced with rule-based processing.

The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. Processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[Fourth embodiment]
FIG. 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 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 and/or a LAN.

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, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

The microphone 238 receives instructions and other information from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, 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 image sensor or CCD image sensor, and captures images of the user'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 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. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

In robot 414, specific processing is performed by processor 46. Specific program 60 is stored in storage 50. Processor 46 reads specific program 60 from storage 50 and executes the read specific program 60 on RAM 48. The specific processing is realized by processor 46 operating as control unit 46A in accordance with specific program 60 executed on RAM 48. Note that robot 414 may have a data generation model and emotion identification model similar to data generation model 58 and emotion identification model 59.

Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain processing results (such as prediction results) using the data generation model 58. The data processing device 12 may also be a server device, or a terminal device owned by a user (for example, a mobile phone, robot, home appliance, etc.).

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.

The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output inference results from prompts that do not include instructions. In this case, the data generation model 58 can output inference results from prompts that do not include instructions. The data processing device 12, etc., includes multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform a variety of processes, but is not limited to these examples. The AI may also be an AI agent. When the processing of each of the above-mentioned parts is performed by AI, the processing may be performed in part or in whole by AI, but is not limited to these examples. The processing performed by AI, including the generative AI, may be replaced with rule-based processing.

The data processing system 410 according to the fourth embodiment performs processing similar to that of the data processing system 10 according to the first embodiment. Processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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 on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower 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 sense of calm.

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, and when these balances deviate from the ideal, it indicates discomfort, and when they approach the ideal, it indicates pleasure. Emotion maps can 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.

In the above embodiment, an example was given in which a specific process is performed by a single computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may also be performed by multiple computers, including computer 22.

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.

Furthermore, in the above examples, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. Furthermore, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are only examples, and they may be combined, or other devices may be used. Furthermore, in the above examples, the first and second embodiments have been described separately, but these may also be combined.

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 herein by reference to the same extent as if each individual publication, patent application, and technical standard was specifically and individually indicated to be incorporated by reference.

10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset type terminal 414 Robot

Claims (8)

a review collection unit that collects reviews from an online review platform;
a review analysis unit that analyzes the reviews collected by the review collection unit;
a malicious review exclusion unit that excludes malicious reviews based on the analysis result by the review analysis unit;
A system comprising: a reliable review providing unit that provides reliable reviews excluded by the malicious review excluding unit. The review collection unit
The system according to claim 1, wherein reviews limited to a specific area or time period are preferentially collected based on location information of the user. The review analysis unit
The system according to claim 1, wherein the system learns the writing habits and writing style of users and detects malicious reviews based on individual user characteristics. The malicious review exclusion unit
The system according to claim 1, wherein the system refers to a user's past posting history and preferentially excludes reviews from users with low reliability. The reliability review providing unit
The system according to claim 1, wherein the system provides the most suitable reviews to each individual user by taking into consideration the user's past browsing history and rating history. The review collection unit
The system according to claim 1, further comprising: an emotion estimation function for estimating a user's emotional state when collecting reviews; and a system for preferentially collecting reviews from users with positive emotions. The review analysis unit
The system according to claim 1, wherein an emotion estimation function is used to estimate a user's emotion during review analysis, and emotionally unnatural reviews are detected. The malicious review exclusion unit
The system according to claim 1, wherein, when filtering out malicious reviews, the system uses an emotion estimation function to preferentially filter out emotionally unnatural reviews.