KR102811817B1 - Device and Method for Providing Manufacturer Search Results - Google Patents

Abstract

A device and method for providing manufacturer search results are disclosed.
According to one embodiment of the present invention, a process for receiving search information (S100); a process for generating context information based on the search information (S200); a process for collecting company information (S300); a process for generating a comparison ontology based on the company information (S400); a process for generating a list in which a plurality of manufacturers are arranged in an order corresponding to the order of similarity of each manufacturer's attribute and the context information (S500); and a process for providing a screen including the list and information on each manufacturer included in the list to a user terminal (S600).
A method for providing search results for manufacturers including:

Description

{Device and Method for Providing Manufacturer Search Results}

The present invention relates to a device and method for providing search results for manufacturers. More specifically, the present invention relates to a device and method for providing search results for manufacturers that generate a list in which a plurality of manufacturers are sorted in an order corresponding to the order of similarity between the manufacturers and contextual information.

The material described in this section merely provides background information for the present invention and does not constitute prior art.

While Korea's manufacturing industry is ranked 5th in the world, there is no search engine for finding manufacturers. Therefore, consumers have to search for manufacturers on general search portals to find manufacturers. However, the information provided by general search portals is mixed with noise such as advertisements, and even the information that is not noise often contains content that does not correspond to reality, causing confusion.

In addition, consumers can intuitively understand the manufacturing capabilities or manufactured items of a manufacturer based on the images of products manufactured by the manufacturer, but there is the inconvenience of having to visit the manufacturer's website directly to obtain these images.

delete

Publication of Patent Publication No. 10-2022-0062928 (May 17, 2022)

Accordingly, the present invention has been devised to solve the above-described problems and to provide only information about the manufacturer without noise.

In addition, the present invention seeks to intuitively convey more information about the manufacturer to the user by displaying information such as images of the manufacturer's previously manufactured products along with a list of manufacturers on the user's screen.

According to one embodiment of the present invention, a method for providing search results for a manufacturer comprises: a process in which a manufacturer search result providing device receives search information from a user (S100); a process in which the manufacturer search result providing device generates contextual information corresponding to the search intention of the user based on the search information (S200); a process in which the manufacturer search result providing device collects company information for a plurality of manufacturers (S300); a process in which the manufacturer search result providing device generates a comparison ontology for comparison with the contextual information based on the company information (S400); a process in which the manufacturer search result providing device generates a list in which the plurality of manufacturers are arranged in an order corresponding to the similarity order of each attribute of the manufacturer and the contextual information based on the contextual information and the comparison ontology (S500); and a process in which the manufacturer search result providing device provides a screen including the list and information on each manufacturer included in the list to a user terminal (S600).

Here, the search information includes image data.

Here, process S300 includes a process (S310) in which the manufacturer search result providing device retrieves public data stored in a database.

In addition, process S300 includes a process (S320) in which the manufacturer search result providing device receives search result data for the search information from an external server.

In addition, process S300 includes a process (S330) in which the manufacturer search result providing device receives mining data collected from a website by a crawling bot.

In addition, process S300 includes a process (S341) in which the manufacturer search result providing device generates labeling data corresponding to attributes of at least one manufacturer based on a portfolio of the manufacturer and stores the same in a database; and a process (S342) in which the manufacturer search result providing device retrieves the labeling data from the database.

Here, process S200 includes a process (S210) in which the manufacturer search result providing device separates morphemes of the search information into semantic units when the search information includes language information; and a process (S220) in which the manufacturer search result providing device categorizes each morpheme group separated in process S210, and in process S500, the listing order of the plurality of manufacturers is determined by considering the category of each morpheme group.

Additionally, process S220 categorizes the morpheme groups based on the arrangement order of the plurality of morpheme groups.

Additionally, process S400 includes a process in which the manufacturer search result providing device extracts only data about the manufacturer from the search result data.

According to one embodiment of the present invention, a device for providing search results for a manufacturer comprises: a receiver for receiving search information of a user and company information on a plurality of manufacturers; a first processor for obtaining contextual information corresponding to a search intention of the user based on the search information; a second processor for generating a comparison ontology for comparison with the contextual information based on the company information; a list generator for generating a list in which a plurality of manufacturers are arranged in an order corresponding to an attribute of each of the manufacturers and a similarity order of the contextual information based on the contextual information and the comparison ontology; and a process transmitter for providing screen information including the list and information on each manufacturer included in the list to a user terminal.

In addition, the method further includes a database storing at least one of labeling data generated by labeling information collected from a manufacturer and public data containing information about the manufacturer, and the receiver receives at least one of the labeling data and the public data from the database.

The manufacturer search device and method of the present invention have been devised to solve the above-described problems, and can provide only information about the manufacturer without noise.

In addition, the manufacturer search device and method of the present invention can intuitively convey more information about the manufacturer to the user by displaying information such as images of the manufacturer's previously manufactured products along with a list of manufacturers on the user's screen.

Figure 1 is a flowchart illustrating a method for providing manufacturer search results according to one embodiment of the present invention.
FIG. 2 is a flowchart illustrating process S300 of a method for providing manufacturer search results according to one embodiment of the present invention.
FIG. 3 is a table showing an exemplary calculation formula for a company's expertise score in a method for providing manufacturer search results according to one embodiment of the present invention.
FIG. 4 is a flowchart specifically illustrating a method for providing manufacturer search results according to one embodiment of the present invention.
FIG. 5 is a block diagram schematically showing the configuration of a manufacturer search result providing device according to one embodiment of the present invention.

The advantages and features of the present invention, and the methods for achieving them, will become clear with reference to the embodiments described in detail below together with the accompanying drawings. However, the present invention is not limited to the embodiments invented below, but may be implemented in various different forms, and the present embodiments are provided only to make the invention complete and to fully inform a person having ordinary skill in the art to which the present invention belongs of the scope of the invention, and the present invention is defined only by the scope of the claims. Therefore, in some embodiments, well-known process steps, well-known device structures, and well-known techniques are not specifically described in order to avoid an ambiguity in the interpretation of the present invention. Like reference numerals refer to like elements throughout the specification.

In this specification, the terms first, second, third, etc. may be used to describe various components, but these components are not limited by the terms. The terms are used for the purpose of distinguishing one component from other components. For example, without departing from the scope of the present invention, the first component may be named the second or third component, etc., and similarly, the second or third component may also be named interchangeably.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with a meaning that can be commonly understood by a person of ordinary skill in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries shall not be ideally or excessively interpreted unless explicitly specifically defined.

Hereinafter, a method for providing manufacturer search results according to one embodiment of the present invention will be described with reference to the drawings.

Although the operations are depicted in a particular order in some of the drawings of this disclosure, it should not be understood that the operations must be performed in the particular order depicted or in any sequential order, or that all depicted operations must be performed to achieve a desired result. The method for providing manufacturer search results can be performed by at least one processor.

Figure 1 is a flowchart illustrating a method for providing manufacturer search results according to one embodiment of the present invention.

Referring to Fig. 1, a method for providing manufacturer search results according to one embodiment of the present invention may be initiated by receiving search information from a user (S100). The user may input search information using a user terminal. Here, the search information input by the user may include at least one of language information and image information.

Thereafter, contextual information corresponding to the user's search intent can be generated based on the search information (S200). The contextual information can include, for example, whether a manufacturer with a specific unique name is being searched for, the type of product the user wants to manufacture, and information on the material of the product the user wants to manufacture. The search information can also include information on the manufacturer's professionalism conditions and/or information on the manufacturer's size conditions.

If the search information includes image information, text information displayed in the image can be extracted in process S200. In addition, if image information tagged with text information is input, only the text information can be extracted. However, this process does not necessarily have to be performed if the search information is image information.

In process S300, company information for multiple manufacturers is collected. Although processes S100 and S200 are depicted in the drawing before process S300, process S300 may be performed concurrently with or before processes S100 and S200.

FIG. 2 is a flowchart showing the process S300 of the method for providing manufacturer search results according to one embodiment of the present invention. Although each process of FIG. 2 is illustrated in a specific order, this order does not have to be satisfied, and each process may be performed simultaneously or in a different order from the illustrated order. Referring to FIG. 2, in process S300, public data stored in a database can be called (S310). Here, public data refers to data that public institutions create or acquire and manage for the purposes stipulated in laws and regulations. Since public data includes information investigated by public institutions, it generally contains information that is more consistent with actual facts than information uploaded online, and therefore, by using public data, search results that are consistent with facts can be provided.

In process S300, search result data for search information from an external server may also be received (S320). The search result data may include, for example, information output by entering search information into an Internet portal site. In other words, search results provided by an external server may be utilized. The search result data may include a manufacturer's URL. However, the search result data may often include a URL of an advertising site rather than a manufacturer's URL. In order to exclude such URLs from the search result data, a process of excluding URL information may be performed if the URL of the search result data includes specific texts such as 'blog', 'naver', or 'daum'.

In process S300, the crawling bot may receive mining data collected from a website (S330). Here, the website refers to a site provided by the manufacturer. The mining data collected from the website by the crawling bot may be text data, but is not limited thereto, and the mining data may also include image data.

In process S300, labeling data corresponding to the manufacturer's properties are generated based on at least one manufacturer's portfolio and stored in a database (S341), and the labeling data may be loaded from the database (S342). The manufacturer's portfolio may be obtained from the above-described public data, search result data, or mining data, but is not limited thereto, and may be data directly provided by the manufacturer or directly collected by the provider of the present invention. In process S341, for example, text information on the manufacturer's manufactured goods or materials applicable to the manufactured goods may be labeled as information obtained from the portfolio in an image format.

According to one embodiment of the present invention, the amount of searchable information can be expanded by collecting information about a company from various sources. In addition, since public data, labeling data, etc. are created by the provider or public institution of the present search result provision method, search results with higher reliability can be provided according to one embodiment of the present invention.

After process S300, a comparison ontology for comparison with contextual information can be created based on business information (S400). Process S400 can include a process of extracting only data about the manufacturer from the search result data. In other words, it can include a process of removing data that is not about the manufacturer from the search result data. For example, if the URL of the search result data includes specific texts such as 'blog', 'naver', and 'daum', the URL information can be excluded.

After process S400, a list is generated in which multiple manufacturers are arranged in an order corresponding to the order of similarity between the attributes of each manufacturer and the contextual information based on the contextual information and the comparison ontology (S500). In this process, a similarity score corresponding to the similarity between the information and the contextual information for each manufacturer can be calculated. However, process S400 does not necessarily require the process of calculating the similarity score. In the list of process S500, manufacturers can be listed in order of high similarity with the contextual information.

If the search information is image information, images similar to the image information of the search information can be searched for among the company information in process S500. This search can be performed by an external server, and the search results of the external server can be provided from the external server. For example, the Google image search server can search for image information similar to the image information included in the search information, and the search results obtained by the Google image search server can be provided.

If the search information includes information on the manufacturer's expertise condition and/or information on the manufacturer's size condition, in process S500, an expertise score corresponding to the manufacturer's expertise and/or a size score corresponding to the manufacturer's size can be calculated, and the listing order of the companies can be determined based on the expertise score and/or the size score.

The professionalism score of a given manufacturer can be obtained by adding up, for example, 'a score determined based on the similarity between the manufacturer's name and contextual information', 'a score corresponding to the number of years of service provision by the manufacturer', 'a score corresponding to the similarity between labeling data and contextual information', and 'a score corresponding to the number of times it has been certified by users or public institutions'. The weight of each sub-score can be modified based on the user's satisfaction.

If the 'score corresponding to the similarity between labeling data and contextual information' is calculated based only on the number of similar contextual information among labeling data, then if there is a manufacturer that displays various keywords in its portfolio simply to increase the number of times it is exposed to search engines for advertising purposes, the professionalism score of such a manufacturer is bound to be high.

Therefore, in order to compensate for the expertise score of a manufacturer who has indiscriminately inserted keywords into their portfolio, the 'score corresponding to the similarity between labeling data and contextual information' can be calculated, for example, as '(the number of labeling data of the manufacturer that are similar to contextual information + the number of labeling data for the manufacturer's specialty that are similar to contextual information) / (the number of labeling data of the manufacturer + the number of labeling data for the manufacturer's specialty)'.

Figure 3 (a) is a table showing an exemplary calculation formula for the professionalism score of a company that has been established for 7 years.

Figure 3 (b) is a table showing an exemplary calculation formula for the professionalism score of a company that has not passed 7 years since its establishment.

In the embodiment of Fig. 3, the calculation formula for the scale score is applied differently based on 7 years after the establishment of the company (manufacturer) to reflect the tendency for the government's support scale to expand starting from 7 years after the establishment of the company. However, this starting point is exemplary, and the starting point for changing the calculation formula is not limited to 7 years after the establishment of the company. In order to apply the calculation formula of Fig. 6, the comparison ontology extracted in process S400 includes information on the number of employees and sales of the manufacturer, and a list can be generated based on the information on the number of employees and sales of the manufacturer in process S500. In Fig. 3, sales is a value corresponding to the sales of the manufacturer. According to the calculation formula for the expertise score according to one embodiment of the present invention, even if the legend of the company information provided by each manufacturer is different, for example, even if one manufacturer provides information on the number of employees and another manufacturer provides only information on sales, the scale scores of the manufacturers can be calculated and compared with each other. When calculating the scale score, if the year of establishment of the manufacturer is unknown, it can be assumed that the manufacturer has been established for 7 years.

Thereafter, a screen including a list and information about each manufacturer included in the list is provided to the user terminal (S600). The information about the manufacturer provided in process S600 may be processed from the company information collected in process S300. The information about each manufacturer displayed on the screen provided in process S600 may include at least one of an image of a product manufactured by each manufacturer and an image of the manufacturer's homepage. The user can intuitively understand the information about each manufacturer through these images. To this end, a process of extracting an image of a product manufactured by each manufacturer from the company information may be performed in advance.

In process S600, if both stored data and search result data containing information about an arbitrary manufacturer exist, only the contents of the stored data about that manufacturer can be displayed on the screen of the user terminal. This is because the contents of the stored data are more likely to correspond to reality than the contents of the search result data.

FIG. 4 is a flowchart specifically illustrating a method for providing manufacturer search results according to one embodiment of the present invention.

Referring to Fig. 4, the method for providing manufacturer search results may be initiated by receiving search information from a user (S100). The method for providing manufacturer search results may be initiated by, for example, a user inputting a search term, 'Handsome Handsung Precision' (S100). In process S100, the search term information entered by the user using a user terminal may be received by a processor that performs the method for providing manufacturer search results.

In process S200, if the search information includes language information, the morphemes of the search information can be separated into semantic units (S210), and each morpheme group separated in process S210 can be categorized (S220). For example, if the search information is 'HandsomeHandsomePrecision', the search information can be separated into two morpheme groups of 'HandsomeHandsome' and 'Precision' in process S210. In process S220, the category of 'HandsomeHandsome' can be classified as company-specific information, and the category of 'Precision' can be classified as information on provided services (or information on manufactured goods). Here, each morpheme group and the category information of each morpheme group can be understood as part of contextual information.

In process S220, morpheme groups can be categorized based on the arrangement order of the morpheme groups. For example, if it is known that 'Precision' belongs to the category of provided services, 'Handsome Hanseong' arranged before 'Precision' can be determined to be a proper name of the company.

Thereafter, in process S300 and process S400, company information is collected, and a comparative ontology is extracted from the collected company information. Thereafter, in process S500, the listing order of multiple manufacturers is determined by considering the category of each morpheme group. For example, if the category of the first morpheme group is a company unique name and the category of the second morpheme group is a manufactured product, manufacturers that produce the same manufactured product and have the same company unique name, manufacturers that have company information matching the first morpheme group, and companies that produce manufactured products of the second morpheme group can be listed sequentially.

In the process S500 of the embodiment, a list can be created that sequentially lists a manufacturer whose service is related to 'precision processing' and has the unique name 'Handsome Handsung', a manufacturer whose company information is 'Handsome Handsung', and a manufacturer whose service is precision processing. If there is company information whose unique name is 'Handsome Handsung Precision', 'Handsome Handsung Precision' can be placed at the top of the list.

Thereafter, a screen including a list of process S500 and information on each manufacturer included in the list is provided to the user terminal (S600).

FIG. 5 is a block diagram schematically showing the configuration of a manufacturer search result providing device (100) according to one embodiment of the present invention.

Referring to FIG. 5, a manufacturer search result providing device (100) according to one embodiment of the present invention may include all or part of a crawling bot (110), a database (120), a receiver (130), a first processor (140), a second processor (150), a list generator (160), a screen information generator (170), and a transmitter (180).

The crawling bot (110) is configured to obtain mining data in the form of text information provided by the manufacturer's website (30). The crawling bot (110) can transmit the obtained mining data to a database (120) or a receiver (130).

The database (120) can store at least one of public data containing information about the manufacturer and labeling data created by labeling information collected from the manufacturer. In addition, the database (120) can store mining data collected from the manufacturer's homepage, etc. The search result providing device (100) according to one embodiment of the present invention can provide more reliable search results by using at least one of public data and labeling data to form search results.

The receiver (130) receives the user's search information and company information about multiple manufacturers. The receiver (130) can receive at least one of labeling data and public data from the database (120). The receiver (130) can receive search information input by the user using the user terminal (10). The receiver (130) can receive company information about the properties of the company from the crawling bot (110), the database (120), or the external server (20). Here, the external server (20) can be a server that provides a search engine service.

The first processor (140) obtains contextual information corresponding to the user's search intent based on search information. The second processor (150) creates a comparison ontology for comparison with the contextual information based on company information.

The list generator (160) can generate a list in which multiple manufacturers are arranged in an order corresponding to the order of similarity between the attributes of each manufacturer and the contextual information based on the contextual information and the comparison ontology. The list generator (160) can include a similarity score calculator that calculates, for each manufacturer, a similarity score corresponding to the similarity between the attributes of the contextual information and the multiple manufacturers based on the contextual information and the comparison ontology. The screen information generator (170) generates a list and screen information including information on each manufacturer included in the list. The transmitter (180) provides the screen information generated by the screen information generator (170) to the user terminal (10).

The user terminal (10) receives the screen information transmitted by the transmitter (180) and displays a screen including the list generated by the list generator (160) and the information of each manufacturer included therein. Here, the information of the manufacturer displayed on the screen may include at least one of an image of a manufactured product and an image of the manufacturer's homepage. The user can intuitively understand the information of each manufacturer through these images.

The above-described method and/or various embodiments may be realized by digital electronic circuits, computer hardware, firmware, software, and/or a combination thereof. Various embodiments of the present invention may be implemented as a computer program that is executed by a data processing device, for example, one or more programmable processors and/or one or more computing devices, or stored on a computer-readable recording medium and/or a computer-readable recording medium. The above-described computer program may be written in any form of programming language, including a compiled language or an interpreted language, and may be distributed in any form, such as a standalone program, a module, a subroutine, etc. The computer program may be distributed through a single computing device, a plurality of computing devices connected through the same network, and/or a plurality of computing devices distributed to be connected through a plurality of different networks.

The above-described methods and/or various embodiments may be performed by one or more processors configured to execute one or more computer programs that process, store and/or manage any function, function, etc. by operating on the basis of input data or generating output data. For example, the methods and/or various embodiments of the present invention may be performed by special purpose logic circuits such as a Field Programmable Gate Array (FPGA) or an Application Specific Integrated Circuit (ASIC), and an apparatus and/or system for performing the methods and/or embodiments of the present invention may be implemented as a special purpose logic circuit such as an FPGA or an ASIC.

The one or more processors executing the computer program may include a general purpose or special purpose microprocessor and/or one or more processors of any type of digital computing device. The processor may receive instructions and/or data from each of the read-only memory and the random access memory, or may receive instructions and/or data from the read-only memory and the random access memory. In the present invention, the components of the computing device performing the methods and/or embodiments may include one or more processors for executing instructions, and one or more memory devices for storing instructions and/or data.

In one embodiment, the computing device can communicate data with one or more mass storage devices for storing data. For example, the computing device can receive data from and/or transfer data to a magnetic disc or an optical disc. A computer-readable storage medium suitable for storing instructions and/or data associated with a computer program can include, but is not limited to, any form of non-volatile memory, including semiconductor memory devices such as Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable PROM (EEPROM), flash memory devices, and the like. For example, the computer-readable storage medium can include a magnetic disk, such as an internal hard disk or a removable disk, a magneto-optical disk, a CD-ROM, and a DVD-ROM disk.

To provide interaction with a user, the computing device may include, but is not limited to, a display device (e.g., a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), etc.) for providing or displaying information to the user, and a pointing device (e.g., a keyboard, a mouse, a trackball, etc.) for enabling the user to provide input and/or commands to the computing device. That is, the computing device may further include any other types of devices for providing interaction with the user. For example, the computing device may provide any form of sensory feedback to the user, including visual feedback, auditory feedback, and/or tactile feedback, for interacting with the user. In this regard, the user may provide input to the computing device through various gestures, such as visual, voice, and motion.

In the present invention, various embodiments may be implemented in a computing system including a back-end component (e.g., a data server), a middleware component (e.g., an application server), and/or a front-end component. In this case, the components may be interconnected by any form or medium of digital data communication, such as a communication network. For example, the communication network may include a Local Area Network (LAN), a Wide Area Network (WAN), etc.

A computing device based on the exemplary embodiments described herein may be implemented using hardware and/or software configured to interact with a user, including a user device, a user interface (UI) device, a user terminal, or a client device. For example, the computing device may include a portable computing device, such as a laptop computer. Additionally or alternatively, the computing device may include, but is not limited to, Personal Digital Assistants (PDAs), tablet PCs, game consoles, wearable devices, Internet of Things (IoT) devices, virtual reality (VR) devices, augmented reality (AR) devices, and the like. The computing device may further include other types of devices configured to interact with a user. In addition, the computing device may include a portable communication device (e.g., a mobile phone, a smart phone, a wireless cellular phone, and the like) suitable for wireless communication over a network, such as a mobile communication network. The computing device may be configured to communicate wirelessly with a network server using wireless communication technologies and/or protocols, such as Radio Frequency (RF), Microwave Frequency (MWF), and/or Infrared Ray Frequency (IRF).

10: User Terminal
20: External server
30: Manufacturer's website
110: Crawling bot
120: Database
130: Receiver
140: 1st processor
150: Second processor
160: List Generator
170: Screen information generator
180: Transmitter

Claims (10)

A process for a device providing manufacturer search results to receive search information input by a user (S100);
A process (S200) in which the above manufacturer search result providing device generates contextual information corresponding to the user's search intention based on the above search information;
The above manufacturer search result providing device collects company information on multiple manufacturers (S300);
The process of the above manufacturer search result providing device creating a comparison ontology for comparison with the above contextual information based on the above company information (S400);
The above manufacturer search result providing device generates a list in which multiple manufacturers are sorted in an order corresponding to the order of similarity of each manufacturer's attributes and the context information based on the context information and the comparison ontology (S500); and
The above manufacturer search result providing device includes a process (S600) of providing a screen including the above list and information on each manufacturer included in the above list to a user terminal,
The above process S300,
The above manufacturer search result providing device includes at least one of the steps of loading public data stored in a database (S310) and receiving search result data for the above search information from an external server (S320).
The above manufacturer search result providing device includes a process of excluding URL information including preset text from the above search result data,
The above manufacturer search result providing device generates labeling data corresponding to the attributes of the manufacturer based on the portfolio of at least one manufacturer and stores the same in a database (S341); and
The above manufacturer search result providing device includes a process (S342) of loading the labeling data from the database,
The above process S500,
The above manufacturer search result providing device comprises a process of calculating at least one of a professionalism score corresponding to the professionalism of the manufacturer and a size score corresponding to the size of the manufacturer, and determining the listing order of the companies based on the professionalism score and the size score, when the search information includes at least one of information on the professionalism condition of the manufacturer and information on the size condition of the manufacturer.
The above professionalism score is a score that is the sum of a score determined based on the similarity between the manufacturer's name and the above contextual information, a score corresponding to the number of years of service provision by the manufacturer, a score corresponding to the similarity between the above labeling data and the above contextual information, and a score corresponding to the number of times certification has been received from a user or public institution.
The score corresponding to the similarity between the above labeling data and the above contextual information is calculated based on the number of labeling data of the manufacturer that are similar to the above contextual information, the number of labeling data of the manufacturer's specialty that are similar to the above contextual information, the number of labeling data of the manufacturer, and the number of labeling data of the manufacturer's specialty.
The above process S600,
The above manufacturer search result providing device includes a process of providing only the contents of the storage data for the above manufacturer to the user terminal when both the storage data containing information about the above manufacturer and the search result data exist.
How to provide manufacturer search results. In the first paragraph,
The above search information is a method for providing search results for manufacturers that include image data. delete delete In the first paragraph,
The above process S300,
A method for providing manufacturer search results, wherein the above manufacturer search result providing device includes a process (S330) of receiving mining data collected from a website by a crawling bot. delete In the first paragraph,
The above process S200,
The above manufacturer search result providing device, if the above search information includes language information, separates the morphemes of the above search information into semantic units (S210); and
The above manufacturer search result providing device includes a process (S220) of categorizing each morpheme group separated in the above process S210,
In the above process S500,
A method for providing manufacturer search results that determines the listing order of the multiple manufacturers by considering the categories of each of the above morpheme groups. In Article 7,
In the above process S220,
A method for providing search results for manufacturers by categorizing the morpheme groups based on the arrangement order of the plurality of morpheme groups. In the first paragraph,
The above process S400,
A method for providing manufacturer search results, wherein the manufacturer search result providing device includes a process of extracting only data about the manufacturer from the search result data. delete