JP7180921B1 - Program, information processing device and information processing method - Google Patents

Abstract

A program, an information processing apparatus, and an information processing method for calculating an evaluation index value for a product provided by a company and an evaluation value for the company itself are provided. In a product score calculation process, a post acquisition step of acquiring posted article information posted by a user, a step of specifying a product related to the posted article information acquired in the post acquisition step, and a and calculating a product score, which is an evaluation index value for the identified product. [Selection drawing] Fig. 10

Description

The present disclosure relates to a program, an information processing device, and an information processing method.

Techniques for evaluating businesses based on information on the Internet are known.
Patent Literature 1 discloses a technique for highly accurately evaluating the creditworthiness of a business operator.
Patent Literature 2 discloses a technique of analyzing text information written about a company to be analyzed and calculating a company evaluation value for use in stock investment.

JP 2016-095729 A Japanese Unexamined Patent Application Publication No. 2007-183796

For start-up companies that provide new products and services to the market and customers, it is difficult to objectively evaluate how well the products provided by the start-up companies are received by the market.

Therefore, the present disclosure has been made to solve the above problems, and its purpose is to provide a technology for calculating an evaluation index value for a product provided by a company and an evaluation value for the company itself.

A program to be executed by a computer comprising a processor and a storage unit, the program comprising: a post acquisition step for acquiring posted article information posted by a user; and a first calculation step of calculating a product score, which is an evaluation index value for the product identified in the first identification step, based on the posted article information. program.

According to the present disclosure, it is possible to calculate an evaluation index value representing how well a product provided by a company is accepted in the market or whether it is likely to be accepted.

1 is a diagram showing an overall configuration of an information processing system 1; FIG. 3 is a block diagram showing the functional configuration of the server 10; FIG. 2 is a block diagram showing a functional configuration of a user terminal 20; FIG. FIG. 10 is a diagram showing the data structure of a user table 1012; FIG. It is a figure which shows the data structure of the company table 1013. FIG. FIG. 10 is a diagram showing the data structure of a product table 1014; FIG. FIG. 10 shows the data structure of a posted article table 1015. FIG. FIG. 10 is a diagram showing the data structure of a posted article table 1016. FIG. FIG. 10 shows the data structure of a media table 1017. FIG. 4 is a flowchart showing the operation of product score calculation processing; It is a flowchart which shows the operation|movement of a comprehensive enterprise score calculation process. 10 is a flow chart showing the operation of company report output processing. It is an example of a screen which shows the operation|movement of a company report output process. 2 is a block diagram showing the basic hardware configuration of computer 90. FIG.

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all the drawings for explaining the embodiments, common constituent elements are given the same reference numerals, and repeated explanations are omitted. It should be noted that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Also, not all the components shown in the embodiments are essential components of the present disclosure. Each figure is a schematic diagram and is not necessarily strictly illustrated.

<Overview of information processing system 1>
FIG. 1 is a diagram showing the overall configuration of an information processing system 1. As shown in FIG. An information processing system 1 according to the present disclosure is an information processing system that provides information (product information) on company information (company information) and products and services (hereinafter referred to as products) provided by the company. In particular, the information processing system 1 is an information processing system for providing information on start-up companies that provide new products and services to markets and customers, and information on products provided by start-up companies.

<Basic Configuration of Information Processing System 1>
FIG. 1 shows an information processing system 1 according to the present disclosure. The information processing system 1 includes a server 10 and a plurality of user terminals 20A, 20B, and 20C, which are connected via a network N. As shown in FIG. FIG. 2 is a block diagram showing the functional configuration of the server 10. As shown in FIG. FIG. 3 is a block diagram showing the functional configuration of the user terminal 20. As shown in FIG.

The server 10 is an information processing device that provides a service of providing company information and a service of providing product information of products provided by companies. A user can post, via the user terminal 20 , articles about companies and products provided by the companies to the server 10 . The server 10 receives posted articles, stores them, accumulates them, and provides them to other users as company information and product information.

The user terminal 20 is an information processing device operated by a user who uses the service. The user terminal 20 may be, for example, a mobile terminal such as a smart phone or tablet, a stationary PC (Personal Computer), or a laptop PC. Moreover, it may be a wearable terminal such as an HMD (Head Mount Display) or a wristwatch type terminal.

Each information processing device is composed of a computer having an arithmetic device and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the server 10 and the user terminal 20, descriptions overlapping with the basic hardware configuration of the computer and the basic functional configuration of the computer, which will be described later, will be omitted.

The configuration and operation of each device will be described below.

<Functional Configuration of Server 10>
A functional configuration realized by the hardware configuration of the server 10 is shown in FIG. The server 10 has a storage unit 101 and a control unit 104 .

<Configuration of Storage Unit of Server 10>
The storage unit 101 of the server 10 includes an application program 1011, a user table 1012, a company table 1013, a product table 1014, a posted article table 1015, a published article table 1016, and a media table 1017.
FIG. 4 is a diagram showing the data structure of the user table 1012. As shown in FIG.
FIG. 5 is a diagram showing the data structure of the company table 1013. As shown in FIG.
FIG. 6 is a diagram showing the data structure of the product table 1014. As shown in FIG.
FIG. 7 is a diagram showing the data structure of the posted article table 1015. As shown in FIG.
FIG. 8 is a diagram showing the data structure of the posted article table 1016. As shown in FIG.
FIG. 9 is a diagram showing the data structure of the media table 1017. As shown in FIG.

The user table 1012 is a table that stores and manages information on member users (hereinafter referred to as users) who use the service. By registering to use the service, the user's information is stored in a new record in the user table. This enables the user to use the service according to the present disclosure.
The user table 1012 is a table having user ID, user name, and user attribute columns with user ID as a primary key.

User ID is an item that stores user identification information for identifying a user. User identification information is an item in which a unique value is set for each user.
The user name is an item that stores the name of the user. Any character string such as a nickname may be set as the user name instead of the full name.
A user attribute is an item that stores user attribute information. User attributes include information such as user data and user rank.
The user data includes information determined based on the user's occupation, work history, place of work, past business experience, and the like. Specifically, it includes information on general users, people with experience of listing, people with experience of selling a company, people with experience of fundraising, venture capitalists, people with experience of high-ranking positions in venture capital, entertainers/influencers, and the like.
The user rank stores an index value based on a user's reliability, credibility, authoritativeness, fame, and the like. Those who have experienced listing, those who have sold a company, and those who have held high positions in venture capital are evaluated as having high user ranks.
Also, in a service that allows users to evaluate and rate each other, user ranks may be determined based on evaluations from other users. Specifically, a statistical value such as an average evaluation rank from other users may be used as the user rank of the user.

The company table 1013 is a table that stores and manages company information to be provided in the information service according to the present disclosure.
The company table 1013 is a table having columns of company ID, company name, company data, investment stage, first company score, second company score, and total company score, with company ID as a primary key.

Company ID is an item that stores company identification information for identifying company information.
The company name is an item that stores the name of the company.
Company data is an item that stores information about a company. Company information includes corporate number, collation, location, trade name, information on directors, information on officers, business description, industry, telephone number, date of establishment, date of establishment, capital, number of employees, shareholders or investors Includes total number, listing category, securities code, accounting period, sales, profits, management information such as capital adequacy ratio, business partners, major suppliers, major customers, affiliates, business objectives, etc.
The investment stage is an item that stores information such as the business development status of the company, the investment phase, and the investment round. The investment stages are seed (stage before starting a business), early (stage immediately after starting a business, so-called "startup"), series A (stage of full-scale start of business), series B (stage where business has started to get on track), Values such as series C (at the stage of becoming profitable and stabilizing management) are stored.
The first company score is an item that stores the first evaluation index value related to the company. The first evaluation index value is an evaluation index value that indicates how positively the company is mentioned in the posted article or published article.
The second company score is an item that stores a second evaluation index value related to the company. The second evaluation index value is an evaluation index value calculated based on the product score, which is the degree of achievement of product market fit of the product provided by the company. In other words, it is an evaluation index value that indicates how well a product provided by a company is accepted in the market and whether it is likely to be accepted.
A comprehensive company score is an item that stores a comprehensive evaluation index value related to a company. A composite company score includes a metric value related to investment eligibility for a company. For example, the overall company score includes an index that indicates the degree of achievement (degree of achievement of product market fit) that the products, services, etc. provided by the company are accepted in an appropriate market that can solve the customer's problem. The degree of achievement of product market fit can be investigated by a customer survey method such as Product/Market Fit Survey (PMFSurvey).
A comprehensive company score is a comprehensive evaluation index value of a company calculated based on the first company score and the second company score.

The product table 1014 is a table for storing and managing product information such as products and services (hereinafter referred to as products) provided by companies.
The product table 1014 is a table having columns of product ID, product name, product score, and company ID, with product ID as a primary key.

Product ID is an item for storing product identification information for identifying product information.
The product name is an item that stores the name of the product.
A product score is an item that stores an evaluation index for a product. For example, the product score includes an indicator that indicates the degree of achievement (degree of achievement of product market fit) that the product is accepted in an appropriate market that can solve the customer's problem. Specifically, the product score is an evaluation index that indicates to what extent the product is accepted in the market and whether it is likely to be accepted.
The company ID is an item that stores the company ID of the company that provides the product.

The posted article table 1015 is a table that stores and manages posted article information posted by users.
The posted article table 1015 is a table having columns of posted article ID, contributor user ID, posted article data, company ID, product ID, posted date and time, with posted article ID as a primary key.

The posted article ID is an item that stores posted article identification information for identifying posted article information.
The posting user ID is an item that stores the user identification information of the user who posted the posted article.
The posted article data is an item that stores information about the content of the posted article. Specifically, posted article data includes various types of data such as posted documents (text), photographs, moving images, and voices posted by users in the information service according to the present disclosure.
The company ID is an item that stores company identification information of a company mentioned or referenced in the posted article information. One piece of posted article information may be associated with a plurality of company IDs.
The product ID is an item for storing product identification information of a product mentioned or referred to in posted article information. One item of posted article information may be associated with a plurality of product IDs.
The posted date and time is an item for storing the date and time when the posted article information was posted.

The posted article table 1016 is a table for storing and managing posted article information posted by various media such as web media, television, radio, newspapers, and magazines.
The posted article table 1016 is a table having columns of posted article ID, posted media ID, posted article data, company ID, product ID, and posted date and time, with the posted article ID as a primary key.

The posted article ID is an item for storing posted article identification information for identifying posted article information.
The published media ID is an item that stores media identification information of the media that published the published article.
The posted article data is an item that stores information about the content of the posted article. Specifically, posted article data includes types of posted articles (document text, images, photographs, video, audio, etc.), posted documents (text) that are data related to the content of posted articles, and various data such as photographs, videos, and audio. including.
The company ID is an item that stores company identification information of a company mentioned or referenced in the posted article information. One piece of posted article information may be associated with a plurality of company IDs.
Product ID is an item for storing product identification information of a product mentioned or referred to in posted article information. One item of posted article information may be associated with a plurality of product IDs.
The published date and time is an item for storing the date and time when the posted article information was published.

The media table 1017 is a table that stores and manages media information related to various media such as web media, television, radio, newspapers, and magazines.
The media table 1017 is a table having media ID, media name, and media attribute columns with media ID as a primary key.

The media ID is an item that stores media identification information for identifying media.
The medium name is an item that stores the name of the medium.
The media attribute is an item that stores media attribute information. Media attributes include information such as media data and media rank.
Media data stores information about media. Information about media includes types of media such as web media, television, radio, newspapers, and magazines, number of copies, number of users, number of accesses, number of viewers, and the like.
The media rank stores index values based on reliability, credibility, authoritativeness, fame, and the like of media. Major newspaper companies, major TV stations, and media with a large number of publications are evaluated as having a high media rank.
In addition, in a service that allows users to evaluate and rate media, the media rank may be determined based on the content of evaluations from users. Specifically, a statistical value such as an average evaluation rank from users may be used as the media rank of the media.

The product evaluation model 1031 uses as input data the posted article data associated with the product, the posted article data, the user attribute of the user who posted the posted article, and the media attribute of the media that posted the posted article, and outputs the product score of the product. It is a learning model that (infers).
The first company evaluation model 1032 uses, as input data, the posted article data associated with the company, the posted article data, the user attribute of the user who posted the posted article, and the media attribute of the media on which the posted article was posted, and the company's first This is a learning model that outputs (infers) company scores.
The second company evaluation model 1033 is a learning model that outputs (infers) the second company score of the company by using the product score of the product provided by the company and the investment stage as input data.
The comprehensive company evaluation model 1034 is a learning model that uses the company's first company score, second company score, and investment stage as input data and outputs (infers) the company's comprehensive company score.

Learning processing of the product evaluation model 1031, the first company evaluation model 1032, the second company evaluation model 1033, and the comprehensive company evaluation model 1034 will be described later.
The product evaluation model 1031, the first company evaluation model 1032, the second company evaluation model 1033, and the comprehensive company evaluation model 1034 models are, for example, machine learning, artificial intelligence, deep learning models, and the like.
As an example of the product evaluation model 1031, the first company evaluation model 1032, the second company evaluation model 1033, and the comprehensive company evaluation model 1034, a deep learning model using a deep neural network in deep learning will be described. The product evaluation model 1031, the first company evaluation model 1032, the second company evaluation model 1033, and the comprehensive company evaluation model 1034 do not necessarily need to be deep learning models, and may be arbitrary machine learning models, artificial intelligence models, or the like.

<Configuration of Control Unit of Server 10>
The control unit 104 of the server 10 includes a user registration control unit 1041 , an analysis unit 1042 , a score calculation unit 1043 , a score output unit 1044 , a report output unit 1045 and a learning unit 1051 . Control unit 104 implements each functional unit by executing application program 1011 stored in storage unit 101 .

The user registration control unit 1041 performs processing for storing information of users who wish to use the service according to the present disclosure in the user table 1012 .
The user ID, user name, and user attribute information stored in the user table 1012 can be obtained by opening a web page or the like operated by a service provider from any information processing terminal, inputting the user ID and user name into a predetermined input form. , the user attribute is input and transmitted to the server 10 . The user registration control unit 1041 of the server 10 stores the received user ID, user name, and user attributes in a new record of the user table 1012, and user registration is completed. As a result, the users stored in the user table 1012 can use the service.
Prior to registration of user information in the user table 1012 by the user registration control unit 1041, the service provider may perform a predetermined examination to limit whether or not the user can use the service.
The user ID may be any character string or number that can identify the user, any character string or number desired by the user, or any character string or number automatically set by the user registration control unit 1041 of the server 10. can be
The user rank, which is included in the user attributes, may be set by the service provider after conducting a predetermined examination.

The analysis unit 1042 executes post analysis processing and posting analysis processing. Details will be described later.
The score calculation unit 1043 executes a product score calculation process, a first company score calculation process, a second company score calculation process, and a comprehensive company score calculation process.
The score output unit 1044 executes comprehensive company score output processing. Details will be described later.
The report output unit 1045 executes company report output processing. Details will be described later.

<Functional Configuration of User Terminal 20>
A functional configuration realized by the hardware configuration of the user terminal 20 is shown in FIG. The user terminal 20 includes a storage unit 201, a control unit 204, a touch panel 206, a touch sensitive device 2061, a display 2062, a microphone 2081, a speaker 2082, a position information sensor 2083, a camera 2084, and a motion sensor 2085.

<Configuration of Storage Unit of User Terminal 20>
The storage unit 201 of the user terminal 20 stores a user ID 2011 for identifying a user who uses the user terminal 20 and an application program 2012 .
The user ID is the user's account ID. The user transmits the user ID 2011 from the user terminal 20 to the server 10 . The server 10 identifies the user based on the user ID 2011 and provides the user with the service according to the present disclosure. The user ID includes information such as a session ID temporarily assigned by the server 10 to identify the user using the user terminal 20 .
The application program 2012 may be stored in the storage unit 201 in advance, or may be downloaded from a web server or the like operated by the service provider via the communication IF. Application program 2012 includes an interpreted programming language such as JavaScript (registered trademark) that runs on a web browser application stored in user terminal 20 .

<Configuration of Control Unit of User Terminal 20>
The control unit 204 of the user terminal 20 has an input control unit 2041 and an output control unit 2042 . By executing the application program 2012 stored in the storage unit 201 , the control unit 204 implements functional units of an input control unit 2041 and an output control unit 2042 .
The input control unit 2041 of the user terminal 20 controls the operation contents of the touch sensitive device 2061 of the touch panel 206 by the user, the voice input to the microphone 2081, the position information sensor 2083, the camera 2084, the motion sensor 2085, and other input devices. acquires information from the client and executes various processes. The input control unit 2041 of the user terminal 20 executes a process of transmitting the information acquired from the input device together with the user ID 2011 to the server 10 .
The output control unit 2042 of the user terminal 20 receives the user's operation on the input device and information from the server 10 , and executes control processing of the display content of the display 2062 and the audio output content of the speaker 2082 .

<Operation of information processing system 1>
Each process of the information processing system 1 will be described below.
FIG. 10 is a flow chart showing the operation of the product score calculation process.
FIG. 11 is a flow chart showing the operation of the comprehensive company score calculation process.
FIG. 12 is a flow chart showing the operation of the company report output process.
FIG. 13 is a screen example showing the operation of the company report output process.

<Post processing>
The posting process is a process of storing posted articles posted by users. Other users can check the stored posted articles and make comments on the posted articles.

<Details of posting process>
A user accesses a predetermined website for posting articles provided by the server 10 using a browser application or the like of the user terminal 20 . By operating the touch panel 206 of the user terminal 20, the user creates a posted article about a company or product in a predetermined input form provided on the website. Posted articles may include various types of data such as document text, images, photographs, moving images, and audio.
By operating the touch panel 206 of the user terminal 20 , the user transmits the user ID 2011 and posted article data related to the input posted article to the server 10 . The server 10 associates the received posted article data with the user ID and stores them in the items of posted article data and contributor user ID of a new record in the posted article table 1015 .
The user accesses a predetermined web server provided by the server 10 using a browser application or the like on his/her own user terminal 20 to confirm the content of the posted articles posted by other users, and read the posted articles. You can post new posts such as comments by

<Posted article acquisition process>
The posted article acquisition process is a process of storing the posted article posted by the media.

<Details of Posted Article Acquisition Processing>
The control unit 104 of the server 10 automatically executes the posted article acquisition process periodically. Note that the control unit 104 of the server 10 may execute the posted article acquisition process in accordance with the instructions of the administrator or the like designated by the service provider.
The control unit 104 of the server 10 collects posted article information posted by various media such as web media, television, radio, newspapers, and magazines, and collects posted article data related to the posted article information and a media table 1017 of the media from which the information is collected. , are stored in the items of posted article data and posted medium ID of a new record in the posted article table 1016 .

<Post analysis processing>
Post analysis processing is processing for analyzing a posted article posted by a user, associating it with a product or company, and storing it. As a result, posted article information is stored in association with product information and company information.

<Overview of post analysis processing>
In the post analysis process, the analysis unit 1042 of the server 10 acquires the posted article data posted by the user, and analyzes the acquired posted article data to obtain the product ID and company name of the product related to the posted article. This is a series of processes for specifying a company ID.

<Details of post analysis processing>
The analysis unit 1042 of the server 10 automatically executes post analysis processing on a regular basis. Note that the analysis unit 1042 of the server 10 may execute the post analysis process in accordance with instructions from an administrator or the like designated by the service provider. Note that the analysis unit 1042 of the server 10 may execute the post analysis process each time a posted article is posted by the user.
In the post analysis process, the analysis unit 1042 of the server 10 refers to the posted article table 1015 and acquires posted article data. The analysis unit 1042 of the server 10 may acquire posted article data for which post analysis processing has already been performed, excluding the posted article data.

The analysis unit 1042 of the server 10 analyzes various types of data such as posted documents (text), photos, videos, and audios included in the acquired posted article data, and analyzes the posted articles referred to, mentioned, quoted, etc. in the posted articles. A product related to the article is specified, and the product ID of the product in the product table 1014 is stored and associated with the product ID item of the posted article information to be analyzed in the posted article table 1015 . One item of posted article information may be associated with a plurality of product IDs.
Specifically, the analysis unit 1042 of the server 10 performs a morphological analysis on the posted document of the posted article data, and if the product name is included in the sentence unit that is separated and written, the product name is found in the posted article table 1015 . The posted article ID and the product ID corresponding to the product name are associated and stored. Alternatively, the analysis unit 1042 of the server 10 may use a product classification model in a machine learning model, a deep learning model, an artificial intelligence model, or the like to associate and store the posted article data and the product ID.

The analysis unit 1042 of the server 10 analyzes various types of data such as posted documents (text), photos, videos, and audios included in the acquired posted article data, and analyzes the posted articles referred to, mentioned, quoted, etc. in the posted articles. A company related to the article is specified, and the company ID of the company in the company table 1013 is stored and associated with the company ID item of the posted article information to be analyzed in the posted article table 1015 . One piece of posted article information may be associated with a plurality of company IDs.
Specifically, the analysis unit 1042 of the server 10 performs morphological analysis on the posted document of the posted article data. The posted article ID and the company ID corresponding to the company name are associated and stored. Alternatively, the analysis unit 1042 of the server 10 may use a company classification model in a machine learning model, a deep learning model, an artificial intelligence model, or the like to store the posted article data and the company ID in association with each other.

<Published analysis processing>
Posting analysis processing is processing for analyzing posted articles posted by the media, and for storing the articles in association with products and companies. As a result, the posted article information is stored in association with the product information and company information.

<Overview of Posting Analysis Processing>
In the posting analysis process, the analysis unit 1042 of the server 10 identifies a posted article posted by an external media, etc., and analyzes the identified posted article data to obtain the product ID and the product ID of the product related to the posted article. This is a series of processes for specifying the company ID of the company.

<Details of posted analysis processing>
The analysis unit 1042 of the server 10 automatically executes publication analysis processing on a regular basis. Note that the analysis unit 1042 of the server 10 may execute the publication analysis process in accordance with instructions from a manager or the like designated by the service provider.
In the posting analysis process, the analysis unit 1042 of the server 10 refers to the posted article table 1016 and acquires posted article data. The analysis unit 1042 of the server 10 may acquire the posted article data that has already been subjected to the posted article data analysis process.

The analysis unit 1042 of the server 10 analyzes various types of data such as posted documents (text), photographs, videos, audio, etc. included in the acquired posted article data, A product related to the article is specified, and the product ID of the product in the product table 1014 is stored and associated with the product ID item of the posted article information to be analyzed in the posted article table 1016 . One item of posted article information may be associated with a plurality of product IDs.
Specifically, the analysis unit 1042 of the server 10 performs morphological analysis on the posted document of the posted article data, and if the product name is included in the sentence unit of the spaced sentence, the product name is found in the posted article table 1016. The posted article ID and the product ID corresponding to the product name are associated and stored. Alternatively, the analysis unit 1042 of the server 10 may use a product classification model in a machine learning model, a deep learning model, an artificial intelligence model, or the like to associate and store the published article data and the product ID.

The analysis unit 1042 of the server 10 analyzes various types of data such as posted documents (text), photographs, videos, and audio contained in the acquired posted article data, A company related to the article is specified, and the company ID of the company in the company table 1013 is stored and associated with the company ID item of the posted article information to be analyzed in the posted article table 1016 . One piece of posted article information may be associated with a plurality of company IDs.
Specifically, the analysis unit 1042 of the server 10 executes a morphological analysis on the posted document of the posted article data, and if a company name is included in the spaced sentence unit, the company name is included in the posted article table 1016. The posted article ID and the company ID corresponding to the company name are associated and stored. In addition, the analysis unit 1042 of the server 10 may store the posted article data and the company ID in association with each other by using a company classification model in a machine learning model, a deep learning model, an artificial intelligence model, or the like.

In the present disclosure, it is configured to execute the posted article data stored in the posted article table 1016, but posted article information posted by various media such as web media, television, radio, newspapers, magazines, etc. It is also possible to adopt a configuration in which the publication analysis process is executed at the time of collection. At this time, the control unit 104 of the server 10 does not store the collected posted article information, but information for specifying the posted article information (information for specifying the posted article, such as headline, program name, broadcast time) only may be stored in the posted article table 1016 of the server 10 . As a result, the posted analysis process can be executed without duplicating the posted article information.

<Product score calculation process>
Product score calculation processing is processing for calculating a product score, which is an evaluation index value for a product. The details of the product score calculation process will be described below with reference to the flowchart of FIG.

<Outline of product score calculation process>
The product score calculation process acquires the posted article information posted by the user, identifies the product referenced by the acquired posted article information, acquires the posted article information posted by the media, and obtains the acquired posted article information. is a series of processes for identifying a product associated with a , and calculating a product score, which is an evaluation index value for the identified product, based on posted article information and published article information. The product score may be calculated from only one of the posted article information and the published article information.

<Details of product score calculation processing>
The score calculation unit 1043 of the server 10 automatically executes product score calculation processing periodically. Note that the score calculation unit 1043 of the server 10 may execute the product score calculation process according to the instructions of the administrator or the like designated by the service provider. Further, in response to a request from a user for a product score regarding a product, the product score calculation processing regarding the product may be executed, and the calculated product score may be transmitted as a response.

In step S101, the score calculation unit 1043 of the server 10 acquires posted article information posted by a user. Specifically, the score calculation unit 1043 of the server 10 refers to the posted article table 1015 to obtain the posted article ID, poster user ID, posted article data, product ID, and posted date and time. The score calculation unit 1043 of the server 10 may acquire posted article information for which the product score calculation process has already been performed, excluding the posted article information.

In step S102, the score calculation unit 1043 of the server 10 identifies products related to the acquired posted article information. In the present disclosure, the product ID of the product to which the posted article is related has already been stored in the item of product ID of the posted article table 1015 by the posted article analysis process.
In step S102, the score calculation unit 1043 of the server 10 may specify the product ID for each piece of posted article information by executing the posted article data acquired in step S101. In this case, execution of post analysis processing in advance may be omitted.

The score calculation unit 1043 of the server 10 searches for the user ID item in the user table 1012 based on the acquired contributor user ID, and acquires the user attribute item. Thereby, the user attribute of the user who posted the acquired posted article information can be acquired.

In step S103, the score calculation unit 1043 of the server 10 acquires information on articles published by media. Specifically, the score calculation unit 1043 of the server 10 refers to the posted article table 1016 to acquire the posted article ID, posted media ID, posted article data, product ID, and posted date and time. The score calculation unit 1043 of the server 10 may acquire information excluding posted article information for which product score calculation processing has already been performed.

In step S104, the score calculation unit 1043 of the server 10 identifies a product for each piece of posted article information obtained. In the present disclosure, the product ID of the product to which the posted article is related has already been stored in the item of product ID of the posted article table 1016 by the posted article analysis process.
In step S104, the score calculation unit 1043 of the server 10 may be configured to specify the product ID for each piece of posted article information by executing the posted article analysis process on the posted article data acquired in step S103. In this case, execution of the publication analysis process in advance may be omitted.

The score calculation unit 1043 of the server 10 searches the media ID item of the media table 1017 based on the acquired posting user ID, and acquires the media attribute item. As a result, it is possible to acquire the media attribute of the media that posted the acquired posted article information.

In step S105, the score calculation unit 1043 of the server 10 calculates the specified product based on the posted article information, the user attributes of the user who posted the posted article information, the posted article information, and the media attributes of the media that posted the posted article information. Calculate the product score, which is the evaluation index value for
Specifically, the score calculation unit 1043 of the server 10 calculates whether the acquired posted article data and published article data refer positively or negatively to the product. The score calculation unit 1043 of the server 10 uses the posted article data and the posted article data as input vectors, respectively, and applies them to an evaluation classification model in a machine learning model, a deep learning model, an artificial intelligence model, etc., so that the posted article and the posted article It is possible to obtain an evaluation value for In the present disclosure, 1 is the most negative and 10 is the most positive, and 10-level evaluation values from 1 to 10 can be obtained. If posted article data or posted article data has an evaluation value such as a rating by a user or media, the evaluation value may be obtained as an evaluation value for posted article data or posted article data.
The score calculation unit 1043 of the server 10 multiplies the evaluation value acquired for the posted article data by the user rank included in the user attribute of the user who posted the posted article, thereby obtaining a product based on the posted article data. Calculate the evaluation index value for the posted article.
The score calculation unit 1043 of the server 10 multiplies the evaluation value acquired for the posted article data by the media rank included in the media attribute of the media that posted the posted article, thereby obtaining a product based on the posted article data. Calculate the evaluation index value for the published article.
The score calculation unit 1043 of the server 10 calculates the sum of the evaluation index value regarding the posted article related to the predetermined product and the evaluation index value regarding the posted article related to the same predetermined product as the product score. Note that the score calculation unit 1043 of the server 10 may use the weighted sum of the evaluation index value for the posted article and the evaluation index value for the posted article as the product score. Specifically, the weighting may be set based on the reliability, credibility, authority, etc., of the evaluation index value for the posted article and the evaluation index value for the posted article.

In step S105, the score calculation unit 1043 of the server 10 uses the acquired posted article data, posted article data, user attribute of the user who posted the posted article, media attribute of the media on which the posted article was posted, etc. as input data to evaluate the product. By applying it to the model 1031, it is good also as a structure which calculates a product score. This makes it possible to calculate the product score without manually designing a detailed algorithm.

The score calculation unit 1043 of the server 10 stores the product score calculated for the predetermined product in the product score item of the record of the product ID of the predetermined product in the product table 1014 . As a result, the product score is stored in association with the product ID, that is, the product information.

<Comprehensive company score calculation process>
Comprehensive company score calculation processing is processing for computing a comprehensive company score, which is an evaluation index value for a company. The details of the comprehensive company score calculation process will be described below with reference to the flowchart of FIG. 11 .

<Outline of Comprehensive Company Score Calculation Processing>
Comprehensive company score calculation processing acquires posted article information posted by users, identifies companies referenced by the acquired posted article information, acquires posted article information posted by media, and obtains posted articles Identify the company to which the information is related, calculate the first company score, which is the evaluation index value for the identified company, based on the posted article information and posted article information, and add the product score calculated in the product score calculation process Based on this, the second company score, which is the evaluation index value for the company that provides the product, is calculated, and based on the first company score and the second company score, the overall company score, which is the evaluation index value for the company, is calculated. processing. The overall company score may be calculated from only one of the posted article information and the published article information.

<Details of Comprehensive Company Score Calculation Processing>
The score calculation unit 1043 of the server 10 automatically executes a comprehensive company score calculation process periodically. Note that the score calculation unit 1043 of the server 10 may execute the comprehensive company score calculation process in accordance with instructions from a manager or the like designated by the service provider. Also, in response to a request from a user for a comprehensive company score regarding a company, a configuration may be adopted in which the comprehensive company score calculation process for the company is executed, and the calculated comprehensive company score is transmitted as a response.

In step S301, the score calculation unit 1043 of the server 10 acquires posted article information posted by the user. Specifically, the score calculation unit 1043 of the server 10 refers to the posted article table 1015 to obtain the posted article ID, poster user ID, posted article data, company ID, and posted date and time. The score calculation unit 1043 of the server 10 may acquire posted article information that has already undergone the comprehensive company score calculation process, excluding it.

In step S302, the score calculation unit 1043 of the server 10 identifies a company associated with each acquired piece of posted article information. In the present disclosure, the company ID of the company to which the posted article is related has already been stored in the column of company ID of the posted article table 1015 by the post analysis process.
In step S302, the score calculation unit 1043 of the server 10 may specify the company ID for each piece of posted article information by executing the posted article data acquired in step S301. In this case, execution of post analysis processing in advance may be omitted.

The score calculation unit 1043 of the server 10 searches for the user ID item in the user table 1012 based on the acquired contributor user ID, and acquires the user attribute item. Thereby, the user attribute of the user who posted the acquired posted article information can be acquired.

The score calculation unit 1043 of the server 10 searches for the company ID item in the company table 1013 based on the specified company ID, and acquires the company stage item for the specified company.

In step S303, the score calculation unit 1043 of the server 10 acquires information on articles published by media. Specifically, the score calculation unit 1043 of the server 10 refers to the posted article table 1016 to obtain the posted article ID, posted media ID, posted article data, company ID, and posted date and time. The score calculation unit 1043 of the server 10 may acquire the published article information for which the comprehensive company score calculation process has already been executed, excluding the published article information.

In step S304, the score calculation unit 1043 of the server 10 identifies a company associated with each acquired posted article information. In the present disclosure, the company ID of the company to which the posted article is related has already been stored in the posted article table 1016 in the column of company ID by the posted article analysis process.
In step S304, the score calculation unit 1043 of the server 10 may be configured to identify the company ID for each piece of posted article information by executing the posted article data acquired in step S303. In this case, execution of the publication analysis process in advance may be omitted.

The score calculation unit 1043 of the server 10 searches the media ID item of the media table 1017 based on the acquired posting media ID, and acquires the media attribute item. As a result, it is possible to acquire the media attribute of the media that posted the acquired posted article information.

The score calculation unit 1043 of the server 10 searches for the company ID item in the company table 1013 based on the specified company ID, and acquires the company stage item for the specified company.

In step S305, the score calculation unit 1043 of the server 10 determines the company specified based on the posted article information, the user attribute of the user who posted the posted article information, the posted article information, and the media attribute of the media that posted the posted article information. Calculate the first company score, which is the evaluation index value for
Specifically, the score calculation unit 1043 of the server 10 calculates whether the acquired posted article data and published article data refer positively or negatively to the company. Specifically, the score calculation unit 1043 of the server 10 uses the posted article data and the posted article data as input vectors, respectively, and applies them to an evaluation classification model in a machine learning model, a deep learning model, an artificial intelligence model, etc. It is possible to obtain evaluation values for each article and posted article. In the present disclosure, 1 is the most negative and 10 is the most positive, and 10-level evaluation values from 1 to 10 can be obtained. If posted article data or posted article data has an evaluation value such as a rating by a user or media, the evaluation value may be obtained as an evaluation value for posted article data or posted article data.
The score calculation unit 1043 of the server 10 multiplies the evaluation value acquired for the posted article data by the user rank included in the user attributes of the user who posted the posted article, thereby obtaining the company based on the posted article data. Calculate the evaluation index value for the posted article.
The score calculation unit 1043 of the server 10 multiplies the evaluation value acquired for the posted article data by the media rank included in the media attribute of the media that posted the posted article, thereby obtaining the company based on the posted article data. Calculate the evaluation index value for the published article.
The score calculation unit 1043 of the server 10 calculates the sum of the evaluation index value regarding the posted article related to the predetermined company and the evaluation index value regarding the posted article related to the same predetermined company as the first company score. Note that the score calculation unit 1043 of the server 10 may use the weighted sum of the evaluation index value for the posted article and the evaluation index value for the posted article as the first company score. Specifically, the weighting may be set based on the reliability, credibility, authority, etc., of the evaluation index value for the posted article and the evaluation index value for the posted article.

In step S305, the score calculation unit 1043 of the server 10 uses the acquired posted article data, posted article data, user attribute of the user who posted the posted article, media attribute of the media on which the posted article data is posted, etc. as input data. The first company score may be calculated by applying it to the one company evaluation model 1032 . Thereby, the first company score can be calculated without manually designing a detailed algorithm.

In step S306, the score calculator 1043 of the server 10 acquires the product score. Specifically, the score calculation unit 1043 of the server 10 searches the item of the company ID in the product table 1014 based on the company ID of the company for which the first company score was calculated, and calculates the product score for each product provided by the company. get.

In step S307, a second company score, which is an evaluation index value relating to the company providing the product, is calculated based on the acquired product score.
Specifically, the score calculation unit 1043 of the server 10 calculates the second company score of the company for which the first company score was calculated by integrating the acquired product scores. A weighted sum of the obtained product scores may be used as the second company score. A product with a newer release date may be calculated by increasing the weight on the product score when calculating the second company score.

In step S307, the score calculation unit 1043 of the server 10 may be configured to calculate the second company score by applying the acquired product score, investment stage, etc. as input data to the second company evaluation model 1033. Thereby, the second company score can be calculated without manually designing a detailed algorithm.

In step S308, the score calculation unit 1043 of the server 10 evaluates the predetermined company based on the first company score calculated for the predetermined company, the second company score calculated for the same predetermined company, and the investment stage of the predetermined company. Calculate the total company score, which is an index value.
Specifically, the score calculation unit 1043 of the server 10 calculates the sum of the first company score calculated for a predetermined company and the second company score calculated for the same predetermined company, calculated as
The score calculation unit 1043 of the server 10 may take the weighted sum of the first company score calculated for a given company and the second company score calculated for the same given company as the total company score. At this time, the ratio of the weight for the first company score (first weight) and the weight for the second company score (second weight) (first weight: second weight, first weight/second weight) is A different value may be set according to the investment stage of the company to be calculated. In other words, the algorithm for calculating the comprehensive corporate score may be changed according to the investment stage of the company.
For example, if the investment stage of the predetermined company acquired in steps S302 and S304 is seed or early, there is a high possibility that the product will pivot to a different product in the future. Let the second weight for the company score be smaller than the first weight. That is, the first weight for the first company score, which is the evaluation index value for the company itself, is made larger than the second weight. This makes it possible to reduce the impact on product-based evaluation index values for companies that have just been founded.
On the other hand, if the investment stage of the predetermined company acquired in steps S302 and S304 is Series A or later, the overall company score is calculated in consideration of the second company score.
In other words, the value of the ratio of the first weight to the second weight when the firm's investment stage is seed or early is the value of the ratio of the first weight to the second weight when the firm's investment stage is Series A or later. shall be greater than
Note that the earlier the investment stage is, the larger the value of the ratio between the first weight and the second weight may be.

In step S308, the score calculation unit 1043 of the server 10 uses the acquired first company score, second company score, investment stage, etc. as input data, and applies them to the comprehensive company evaluation model 1034 to calculate the comprehensive company score. It may be configured. This makes it possible to calculate a comprehensive company score without manually designing a detailed algorithm.

The score calculation unit 1043 of the server 10 converts the first company score, the second company score, and the total company score calculated for a predetermined company to the first company score in the company table 1013 record of the company ID of the predetermined company. It is stored in the items of Score, Second Company Score, and Overall Company Score. As a result, the first company score, the second company score, and the overall company score are stored in association with the company ID, that is, the company information.

<Comprehensive company score output processing>
Comprehensive company score output processing is a process of receiving a request from a user requesting an evaluation of a company and outputting a comprehensive company score.

<Overview of Comprehensive Company Score Output Processing>
The comprehensive company score output process is a series of processes for receiving a request from the user requesting an evaluation of a predetermined company and, in response to the request, outputting the comprehensive company score calculated in the comprehensive company score calculation process as a response.

<Details of Comprehensive Company Score Output Processing>
The user uses a browser application or the like of the user terminal 20 to access a predetermined website for receiving the comprehensive company score provided by the server 10 . By operating the touch panel 206 of the user terminal 20, the user enters a company name, etc. in a predetermined input form provided on the website, and transmits a request to the server 10 to inquire about the overall company score of the company. Send to
The score output unit 1044 of the server 10 searches for the company name item in the company table 1013 based on the company name included in the received request, and specifies the company name and comprehensive company score item of the company. The score output unit 1044 of the server 10 outputs and transmits to the user terminal 20 a response including the specified company name and comprehensive company score.
The display 2062 of the user terminal 20 presents the received company name and the total company score of the company to the user. The overall company score may be presented as ranks such as S, A, B, and C, instead of numerical values. This allows the user to check the total company score for each company.

The user can utilize the presented overall company score for the following purposes.
If the user is a loan officer at a bank, the comprehensive corporate score can be used as a criterion for making a decision on financing the company.
If the user is a person in charge of credit card screening, the overall company score can be used as a basis for determining whether or not the company can issue a credit card.
If the user is a person in charge of examining whether or not to open an account at a financial institution, the comprehensive company score can be used as a criterion for determining whether or not to open an account for that company.
The user can utilize the comprehensive company score as a criterion for deciding whether to invest in the target company when making an investment decision.
When the user is considering employment at the company, the comprehensive company score can be used as a criterion for deciding whether or not to get a job at the company.

<Corporate report output processing>
The company report output process is a process of receiving a request for a company report from the user and outputting an evaluation report on the company. Details of the company report output processing will be described below using the flowchart of FIG. 12 and the display screen example of FIG.

<Outline of company report output processing>
The company score output process accepts a request from the user requesting a report on a specified company, acquires company information on the specified company in response to the request, acquires product information on products provided by the specified company, and posts information on the specified company. Obtain article information and posted article information, obtain posted article information and posted article information about a product, obtain user attributes and media attributes corresponding to posted article information and posted article information, obtain product scores and product score Information used for calculation, 1st company score, information used to calculate 1st company score, 2nd company score, information used to calculate 2nd company score, along with product score and overall company score It is a series of processing to output as.

<Details of company report output processing>
In step S<b>501 , the user designates company information to be executed for company report output processing, and transmits the company information to the server 10 .
Specifically, the user uses a browser application or the like of the user terminal 20 to access a predetermined website for receiving corporate reports provided by the server 10 . By operating the touch panel 206 of the user terminal 20, the user enters a company name, etc., in a predetermined input form provided on the website, and transmits a request to the server 10 to inquire about a company report about the company. Send. The report output unit 1045 of the server 10 accepts the received request.

In step S502, the report output unit 1045 of the server 10 acquires company information based on the company name included in the received request.
Specifically, the report output unit 1045 of the server 10 searches for the company name item in the company table 1013 based on the company name included in the received request, and obtains the company ID, company name, company data, and investment stage of the company. , 1st Company Score, 2nd Company Score, and Overall Company Score.

The report output unit 1045 of the server 10 acquires posted article information and posted article information associated with the company related to the acquired company information.
Specifically, based on the acquired company ID, the report output unit 1045 of the server 10 searches the posted article table 1015 for the item of the company ID, and retrieves the posted article ID, poster user ID, posted article data, company ID, and product. Acquire the items of ID and posted date and time. The report output unit 1045 of the server 10 searches for the user ID item in the user table 1012 based on the contributor user ID, and acquires the user attribute item.
Based on the acquired company ID, the report output unit 1045 of the server 10 searches the items of the company ID in the posted article table 1016, and finds the posted article ID, posted media ID, posted article data, company ID, product ID, and posted date and time. Get an item. The report output unit 1045 of the server 10 searches the media ID item in the media table 1017 based on the publication media ID, and acquires the media attribute item.

In step S503, based on the received request, the report output unit 1045 of the server 10 acquires product information provided by the company based on the company name included in the request.
Specifically, in step S502, the report output unit 1045 of the server 10 searches the product table 1014 for the company ID based on the company ID obtained by searching the company table 1013, and searches for the product provided by the company. Acquire the items of product ID, product name, and product score.

The report output unit 1045 of the server 10 acquires posted article information and published article information associated with the product related to the acquired product information.
Specifically, based on the obtained product ID, the report output unit 1045 of the server 10 searches the posted article table 1015 for the product ID item, and finds the posted article ID, poster user ID, posted article data, company ID, and product. Acquire the items of ID and posted date and time. The report output unit 1045 of the server 10 searches for the user ID item in the user table 1012 based on the contributor user ID, and acquires the user attribute item.
Based on the obtained product ID, the report output unit 1045 of the server 10 searches the item of the product ID in the posted article table 1016, and finds the posted article ID, posted media ID, posted article data, company ID, product ID, posted date and time. Get an item. The report output unit 1045 of the server 10 searches the media ID item in the media table 1017 based on the publication media ID, and acquires the media attribute item.

In step S504, the report output unit 1045 of the server 10 generates report data based on the acquired company information and product information. The report data is object data including company information, product information, posted article information and posted article information regarding the company and the product. Note that the report data may be stored in the storage unit 101 of the server 10 such as an arbitrary table.
The report data includes the product score and the information used to calculate the product score, the first company score and the information used to calculate the first company score, the second company score, and the second company score. Contains information used.

In step S505, the report output unit 1045 of the server 10 outputs report data including the comprehensive company score to the user terminal 20 as a response.
Specifically, the report output unit 1045 of the server 10 transmits the generated report data to the user terminal 20 . The display 2062 of the user terminal 20 generates a formatted report-format document based on the received report data and presents it to the user.

The report data includes the calculated product score, the information used to calculate the product score, the calculated first company score, the information used to calculate the first company score, and the calculated second company Score and information used to calculate the second company score.

The report output unit 1045 of the server 10 publishes the number of influential users who posted the posted articles and the posted articles based on, for example, posted article information of influential users with high user ranks and posted article information of influential media with high media ranks. Even if supplementary information such as the number of leading media, the number of posted articles, the number of posted articles, the frequency of posted articles, the frequency of posted articles, the amount of posted articles, the amount of posted articles, etc. good.

The report output unit 1045 of the server 10 posted the content of the posted article, the content of the posted article, and the posted article based on the posted article information and the posted article information negatively referring to the company and the product provided by the company. Supplementary information such as the number of users, the number of media that posted articles, the number of posted articles, the number of posted articles, the frequency of posted articles, the frequency of posted articles, the amount of posted articles, the amount of posted articles, etc. can be presented.

The report output unit 1045 of the server 10 presents to the user information on the customer segments in which market and customer the product is accepted or expected to be accepted, based on the posted article information and posted article information. good. The extent to which the product is accepted by the market and customers for each market segment and customer segment may be visually presented to the user as a graph.

<Important article presentation processing>
The important article presentation process is a process of identifying and presenting highly influential posted articles and posted articles.

<Overview of important article presentation processing>
The important article presentation process is a series of processes for identifying and presenting posted articles that have a large influence in calculating the product score and the first company score in the company report output process.

<Details of important article presentation processing>
In the report output process, the report output unit 1045 of the server 10 identifies posted articles that have a large influence in calculating the product score and the first company score.

Specifically, the report output unit 1045 of the server 10 acquires an evaluation value by applying an evaluation classification model using the posted article data included in the posted article information about the product acquired in steps S502 and S503 as an input vector. . In the present disclosure, 1 is the most negative and 10 is the most positive, and 10-level evaluation values from 1 to 10 can be obtained.
The report output unit 1045 of the server 10 multiplies the evaluation value acquired for the posted article data by the user rank included in the user attributes of the user who posted the posted article, thereby obtaining a product based on the posted article data. Calculate the evaluation index value for the posted article.
The report output unit 1045 of the server 10 identifies a predetermined number of posted articles with large evaluation index values as posted articles having a large influence in calculating the product score.

Specifically, the report output unit 1045 of the server 10 acquires an evaluation value by applying an evaluation classification model using the posted article data included in the posted article information about the company acquired in steps S502 and S503 as an input vector. . In the present disclosure, 1 is the most negative and 10 is the most positive, and 10-level evaluation values from 1 to 10 can be obtained.
The report output unit 1045 of the server 10 multiplies the evaluation value acquired for the posted article data by the user rank included in the user attributes of the user who posted the posted article, thereby obtaining a company rating based on the posted article data. Calculate the evaluation index value for the posted article.
The report output unit 1045 of the server 10 identifies a predetermined number of posted articles with large evaluation index values as posted articles having a large influence in calculating the first company score.

The report output unit 1045 of the server 10 transmits to the user terminal 20 the posted article information regarding the identified posted article having a large influence. The report output unit 1045 of the server 10 may include the identified posted article with a large influence in the report data in the company report output process.
Based on the received report data, the display 2062 of the user terminal 20 presents to the user posted articles that have a large impact on calculating the product score and the first company score for each product and company.

In the important article presentation process, the report output unit 1045 of the server 10 generates and presents to the user information relating to factors such as why the product was accepted by the market and customers based on the posted article information and posted article information. Also good.

FIG. 13 is an example of a presentation screen of a report-format document presented to the user. A report screen 70 is presented to the user on the display 2062 of the user terminal 20 . A total company score 701, a first company score 702, a second company score 703, company information 705, and product information 707 are displayed on the report screen.
The table of company information 705 includes a list of posted articles 7051 and a list of posted articles 7061 referring to the company. In a list 7051 of posted articles referring to a company, an influence rank 7052 indicating the degree of influence and a user rank 7053 of the user who posted the posted article are visually drawn for each posted article. In the list 7061 of posted articles referring to companies, the impact rank 7062 indicating the degree of influence of each posted article and the media rank 7063 of the media that posted the posted article are visually drawn.
The table of product information 707 includes a list of posted articles 7071 referring to the product, a list of posted articles 7071 and a product score 7074 . In the list 7071 of posted articles referring to the product, an influence rank 7072 indicating the degree of influence and a user rank 7073 of the user who posted the posted article are visually drawn for each posted article. In the list of articles that refer to the product, the degree of influence of each article is visually drawn as the influence rank and the media rank of the media that published the article.
<Learning processing>
Learning processing of the product evaluation model 1031, the first company evaluation model 1032, the second company evaluation model 1033, and the comprehensive company evaluation model 1034 will be described below.

<Learning processing of the product evaluation model 1031>
The learning process of the product evaluation model 1031 is a process of learning the learning parameters of the deep neural network included in the product evaluation model 1031 by deep learning.

<Overview of Learning Processing of Product Evaluation Model 1031>
The learning process of the product evaluation model 1031 uses the posted article data associated with the product, the posted article data, the user attribute of the user who posted the posted article, and the media attribute of the medium on which the posted article was posted as input data (input vector). This is a process of learning the learning parameters of the deep neural network included in the product evaluation model 1031 by deep learning so that the product score of the product becomes output data (teacher data).
User attributes and media attributes may be omitted from the input data of the product evaluation model 1031 .

<Details of the learning process of the product evaluation model 1031>
The service provider sets product scores for some of the product information included in the product table 1014 and creates teacher data. Product scores, which serve as training data, are set based on the opinions of experts.
A product score, which is training data, may be set based on posted article information stored in the posted article table 1015 . A product score, which is training data, may be set based on posted article information by a user with a high user rank.
A product score, which is training data, may be set based on posted article information stored in the posted article table 1016 . The product score, which serves as training data, may be set based on information on articles published by media with a high media rank.
The learning unit 1051 of the server 10 sets the posted article data associated with the product, the posted article data, the user attribute of the user who posted the posted article, and the media attribute of the medium on which the posted article is posted as input data (input vector). Create learning data so that the product score obtained is output data (teacher data).
The learning unit 1051 of the server 10 creates data sets such as training data, test data, and verification data for learning the deep neural network of the product evaluation model 1031 based on the learning data.
The learning unit 1051 of the server 10 learns the learning parameters of the deep neural network included in the product evaluation model 1031 by deep learning based on the created data set.

<Learning processing of the first company evaluation model 1032>
The learning process of the first company evaluation model 1032 is a process of learning the learning parameters of the deep neural network included in the first company evaluation model 1032 by deep learning.

<Outline of learning process of the first company evaluation model 1032>
In the learning process of the first company evaluation model 1032, input data (input vector) is the posted article data associated with the company, the posted article data, the user attribute of the user who posted the posted article, and the media attribute of the medium on which the posted article was posted. , the learning parameters of the deep neural network included in the first company evaluation model 1032 are learned by deep learning so that the first company score of the company is output data (teacher data).
User attributes and media attributes may be omitted from the input data of the first company evaluation model 1032 .

<Details of the learning process of the first company evaluation model 1032>
The service provider sets the first company score for some companies among the company information included in the company table 1013 and creates teacher data. The first company score, which serves as training data, is set based on the opinions of experts.
The first company score, which is training data, may be set based on posted article information stored in the posted article table 1015 . The first company score, which serves as training data, may be set based on posted article information by a user with a high user rank.
The first company score, which serves as training data, may be set based on posted article information stored in the posted article table 1016 . The first company score, which serves as training data, may be set based on published article information by media with a high media rank.
The learning unit 1051 of the server 10 sets the posted article data associated with the company, the posted article data, the user attribute of the user who posted the posted article, and the media attribute of the medium on which the posted article was posted as input data (input vector). Learning data is created so that the obtained first company score becomes output data (teaching data).
The learning unit 1051 of the server 10 creates data sets such as training data, test data, and verification data for learning the deep neural network of the first company evaluation model 1032 based on the learning data.
The learning unit 1051 of the server 10 learns the learning parameters of the deep neural network included in the first company evaluation model 1032 by deep learning based on the created data set.

<Learning processing of the second company evaluation model 1033>
The learning process of the second company evaluation model 1033 is a process of learning the learning parameters of the deep neural network included in the second company evaluation model 1033 by deep learning.

<Overview of Learning Processing of Second Company Evaluation Model 1033>
In the learning process of the second company evaluation model 1033, the product score of the product provided by the company and the investment stage are used as input data (input vector), and the second company score of the company is used as output data (teacher data). This is a process of learning the learning parameters of the deep neural network included in the second company evaluation model 1033 by deep learning.
The investment stage may be omitted from the input data of the second company valuation model 1033 .

<Details of the learning process of the second company evaluation model 1033>
The service provider sets a second company score for some companies among the company information included in the company table 1013 to create training data. The second company score, which serves as training data, is set based on the opinions of experts.
The second company score, which is training data, may be set based on posted article information stored in the posted article table 1015 . The second company score, which serves as training data, may be set based on posted article information by a user with a high user rank.
The second company score, which serves as training data, may be set based on posted article information stored in the posted article table 1016 . The second company score, which serves as training data, may be set based on published article information by media with a high media rank.
The learning unit 1051 of the server 10 creates learning data so that the product score and investment stage of the product provided by the company are used as input data (input vector), and the second company score of the company is used as output data (teacher data). do.
The learning unit 1051 of the server 10 creates data sets such as training data, test data, and verification data for learning the deep neural network of the second company evaluation model 1033 based on the learning data.
The learning unit 1051 of the server 10 learns the learning parameters of the deep neural network included in the second company evaluation model 1033 by deep learning based on the created data set.

<Learning processing of comprehensive company evaluation model 1034>
The learning process of the comprehensive company evaluation model 1034 is a process of learning the learning parameters of the deep neural network included in the comprehensive company evaluation model 1034 by deep learning.

<Overview of learning process of comprehensive company evaluation model 1034>
In the learning process of the comprehensive company evaluation model 1034, the company's first company score, second company score, and investment stage are used as input data (input vector), and the company's comprehensive company score is used as output data (teacher data). , is a process of learning the learning parameters of the deep neural network included in the comprehensive company evaluation model 1034 by deep learning.
The investment stage may be omitted from the input data of the comprehensive company evaluation model 1034 .

<Details of the learning process of the comprehensive company evaluation model 1034>
The service provider sets comprehensive company scores for some companies among the company information included in the company table 1013 and creates training data. Comprehensive company scores, which serve as training data, are set based on the opinions of experts.
The comprehensive company score as training data may be set based on posted article information stored in the posted article table 1015 . The comprehensive company score, which serves as training data, may be set based on posted article information by a user with a high user rank.
The comprehensive company score as training data may be set based on the posted article information stored in the posted article table 1016 . The comprehensive company score, which is used as training data, may be set based on information on articles published by media with a high media rank.
The learning unit 1051 of the server 10 uses the first company score, the second company score, and the investment stage of the company as input data (input vector), and the comprehensive company score of the company as output data (teacher data). to create
The learning unit 1051 of the server 10 creates data sets such as training data, test data, and verification data for learning the deep neural network of the comprehensive company evaluation model 1034 based on the learning data.
The learning unit 1051 of the server 10 learns the learning parameters of the deep neural network included in the comprehensive company evaluation model 1034 by deep learning based on the created data set.

<Basic computer hardware configuration>
FIG. 14 is a block diagram showing the basic hardware configuration of computer 90. As shown in FIG. The computer 90 includes at least a processor 901, a main storage device 902, an auxiliary storage device 903, and a communication IF 991 (Interface). These are electrically connected to each other by a communication bus 921 .

The processor 901 is hardware for executing an instruction set described in a program. The processor 901 is composed of an arithmetic unit, registers, peripheral circuits, and the like.

The main storage device 902 is for temporarily storing programs and data processed by the programs. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

Auxiliary storage device 903 is a storage device for storing data and programs. For example, flash memory, HDD (Hard Disc Drive), magneto-optical disk, CD-ROM, DVD-ROM, semiconductor memory, and the like.

The communication IF 991 is an interface for inputting and outputting signals for communicating with other computers via a network using a wired or wireless communication standard.
The network is composed of various mobile communication systems constructed by the Internet, LAN, wireless base stations, and the like. For example, networks include 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), wireless networks (for example, Wi-Fi (registered trademark)) that can be connected to the Internet through predetermined access points, and the like. When connecting wirelessly, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), Bluetooth (registered trademark), and the like. In the case of wired connection, the network includes direct connection using a USB (Universal Serial Bus) cable or the like.

It should be noted that the computer 90 can be virtually realized by distributing all or part of each hardware configuration to a plurality of computers 90 and connecting them to each other via a network. Thus, the computer 90 is a concept that includes not only the computer 90 housed in a single housing or case, but also a virtualized computer system.

<Basic Functional Configuration of Computer 90>
A functional configuration of the computer realized by the basic hardware configuration (FIG. 14) of the computer 90 will be described. The computer includes at least functional units of a control section, a storage section, and a communication section.

Note that the functional units included in the computer 90 can also be implemented by distributing all or part of each functional unit to a plurality of computers 90 interconnected via a network. The computer 90 is a concept that includes not only a single computer 90 but also a virtualized computer system.

The control unit is implemented by the processor 901 reading out various programs stored in the auxiliary storage device 903, developing them in the main storage device 902, and executing processing according to the programs. The control unit can implement functional units that perform various information processing according to the type of program. Thereby, the computer is implemented as an information processing device that performs information processing.

A storage unit is realized by the main storage device 902 and the auxiliary storage device 903 . The storage unit stores data, various programs, and various databases. Also, the processor 901 can secure a storage area corresponding to the storage unit in the main storage device 902 or the auxiliary storage device 903 according to a program. In addition, the control unit can cause the processor 901 to execute addition, update, and deletion processing of data stored in the storage unit according to various programs.

A database refers to a relational database, and is for managing tabular tables structurally defined by rows and columns, and data sets called masters in association with each other. In a database, a table is called a table, a master is called a column, and a row is called a record. In a relational database, relationships between tables and masters can be set and associated.
Normally, each table and each master has a primary key column for uniquely identifying a record, but setting a primary key to a column is not essential. The control unit can cause the processor 901 to add, delete, and update records in specific tables and masters stored in the storage unit according to various programs.

Note that the database and master in the present disclosure may include any data structure (list, dictionary, associative array, object, etc.) in which information is structurally defined. The data structure also includes data that can be regarded as a data structure by combining data with functions, classes, methods, etc. written in any programming language.

A communication unit is implemented by the communication IF 991 . The communication unit implements a function of communicating with another computer 90 via a network. The communication section can receive information transmitted from another computer 90 and input it to the control section. The control unit can cause the processor 901 to execute information processing on the received information according to various programs. Also, the communication section can transmit information output from the control section to another computer 90 .

<Appendix>
The items described in the above embodiments will be added below.

(Appendix 1)
A program to be executed by a computer comprising a processor and a storage unit, the program comprising: a post acquisition step (S101, S301) for acquiring posted article information posted by a user; A first identification step (S102) of identifying a product related to the obtained posted article information; 1 calculation step (S105);
As a result, it is possible to calculate an evaluation index value representing how well the product provided by the company is accepted in the market and whether it is likely to be accepted.

(Appendix 2)
The program according to appendix 1, wherein the first calculation step is a step of calculating the product score based on the posted article information and the user attributes of the user who posted the posted article information.
As a result, it is possible to calculate a more accurate product score that takes into consideration the user attributes of the user who posted the posted article.

(Appendix 3)
The program provides the processor with a posting acquisition step (S103, S303) of acquiring posted article information posted by media, and a second specifying step ( S104), and the program according to appendix 1 or 2, wherein the first calculation step is a step of calculating a product score for the product identified in the second identification step based on the posted article information.
As a result, it is possible to calculate a more accurate product score that takes into consideration the articles published by the media.

(Appendix 4)
3. The program according to appendix 3, wherein the first calculation step is a step of calculating a product score based on the posted article information and the media attributes of the media that posted the posted article information.
As a result, it is possible to calculate a more accurate product score that takes into consideration the media attributes of the media that posted the article.

(Appendix 5)
The program provides the processor with a third identification step (S302) of identifying a company to which the posted article information acquired in the post acquisition step is related, and an evaluation of the company identified in the third identification step based on the posted article information. 5. The program according to appendix 3 or 4, for executing a second calculation step (S305) of calculating the first company score, which is an index value.
As a result, it is possible to calculate the first company score, which is an evaluation index value representing how positively the company is mentioned in the posted article.

(Appendix 6)
The program causes the processor to execute a fourth identification step (S304) of identifying a company to which the posted article information acquired in the posted article information acquired in the posted article acquisition step is related. 6. The program according to any one of Appendices 3 to 5, which is a step of calculating a first company score, which is an evaluation index value for the company specified in the 4 specifying step.
As a result, it is possible to calculate a more accurate first company score in consideration of the articles published by the media.

(Appendix 7)
The program causes the processor to perform a third calculation step (S306, S307) of calculating a second company score, which is an evaluation index value related to the company providing the product, based on the product score calculated in the first calculation step. The program according to appendix 5 or 6, which causes
As a result, it is possible to calculate the second company score, which is an evaluation index value representing how well the product provided by the company is accepted in the market and whether it is likely to be accepted.

(Appendix 8)
The program provides the processor with an evaluation index value for a given company based on the first company score calculated for the given company in the second calculation step and the second company score calculated for the given company in the third calculation step. The program according to appendix 7, causing execution of a fourth calculation step (S308) of calculating a comprehensive company score.
This makes it possible to calculate a total company score, which is an evaluation index value for the company.

(Appendix 9)
9. The program according to appendix 8, wherein the fourth calculation step is a step of calculating an overall corporate score for the given company based on the investment stage of the given company.
As a result, it is possible to calculate a comprehensive company score with higher accuracy, especially when the evaluation index value is calculated for a start-up company.

(Appendix 10)
In the fourth calculation step, if the investment stage of the given company is seed or early, the overall corporate score for the given company is calculated based on the first calculation method, and if the investment stage of the given company is series A or later. 10. The program according to Appendix 9, which calculates an overall company score for a given company based on the second calculation method.
As a result, it is possible to calculate a comprehensive company score with higher accuracy, especially when the evaluation index value is calculated for a start-up company.

(Appendix 11)
The fourth calculation step is a step of calculating an overall company score for a given company by weighting the sum of the first company score for the given company and the second company score for the given company. 11. The program according to appendix 10, wherein the ratio of the weight of the second company score to the weight of the score is greater than the ratio of the weight of the second company score to the weight of the first company score in the second calculation method.
As a result, especially when the evaluation index value is calculated for startup companies, when the investment stage is seed or early, the company's evaluation index value is calculated with emphasis on the content of the company itself in the article, and this stage is In the case of Series A and later, by calculating the company's evaluation index value with emphasis on the product score of the product provided by the company, it is possible to calculate a more accurate comprehensive company score.

(Appendix 12)
The program provides the processor with a receiving step (S501) for receiving a request from the user requesting an evaluation of a predetermined company, and outputting the comprehensive company score calculated in the fourth step as a response in response to the request received in the receiving step. 12. The program according to any one of appendices 8 to 11, which causes execution of the output step (S505).
Upon user request, a company's overall corporate score can be provided to the user.

(Appendix 13)
The output step includes the product score calculated in the first calculation step, the information used to calculate the product score, the first company score calculated in the second calculation step, and the first company score used to calculate 13. The program according to Supplementary Note 12, including a step of outputting information including the information obtained, the second company score calculated in the third calculation step, and the information used to calculate the second company score.
The user can be provided with a company's overall metric value, including a total company score.

(Appendix 14)
14. The program according to any one of Appendices 1 to 13, wherein the program causes the processor to execute an article presentation step of identifying and presenting posted articles having a large influence in calculating the product score in the first calculation step.
It is possible to provide users with information on posted articles that have had a great influence in calculating the product score of a product.

(Appendix 15)
An information processing apparatus comprising a processor and a storage unit, wherein the processor is provided with a post acquisition step (S101, S301) for acquiring posted article information posted by a user, and a post acquisition step related to the posted article information acquired in the post acquisition step. and a first calculation step (S105) of calculating a product score, which is an evaluation index value for the product identified in the first identification step, based on the posted article information. Information processing device for executing .
As a result, it is possible to calculate an evaluation index value representing how well a product provided by a company is accepted in the market and whether it is likely to be accepted.

(Appendix 16)
An information processing method executed by a computer including a processor and a storage unit, wherein the processor acquires posted article information posted by a user (S101, S301); A first identification step (S102) of identifying a product related to the posted article information, and a first calculation of calculating a product score, which is an evaluation index value for the product identified in the first identification step, based on the posted article information. An information processing method for executing a step (S105).
As a result, it is possible to calculate an evaluation index value representing how well a product provided by a company is accepted in the market and whether it is likely to be accepted.

1 information processing system 10 server 101 storage unit 103 control unit 20A, 20B, 20C user terminal 201 storage unit 204 control unit

Claims (14)

A program to be executed by a computer comprising a processor and a storage unit,
The program causes the processor to:
a post acquisition step for acquiring posted article information posted by a user;
a first identification step of identifying a product related to the posted article information obtained in the post obtaining step;
a first calculation step of calculating a product score, which is an evaluation index value for the product identified in the first identification step, by applying the posted article information to the first learning model;
a third identification step of identifying a company to which the posted article information acquired in the posted article acquisition step is related;
a second calculation step of calculating a first company score, which is an evaluation index value related to the company identified in the third identification step, based on the posted article information;
A third calculation step of calculating a second company score, which is an evaluation index value related to the company that provides the product, by applying the product score calculated in the first calculation step to a third learning model;
Based on the first company score calculated in the second calculation step for a given company and the second company score calculated in the third calculation step for the given company, a total company score, which is an evaluation index value for the given company, is calculated. a fourth calculation step of calculating;
program to run. A fourth calculation step is a step of calculating the overall corporate score for the predetermined company based on the investment stage of the predetermined company.
A program according to claim 1 . The fourth calculation step is
if the investment stage of the given company is seed or early, calculating the overall company score for the given company based on a first calculation method;
If the investment stage of the predetermined company is Series A or later, calculating the overall company score for the predetermined company based on a second calculation method;
3. A program according to claim 2 . A fourth calculation step is a step of calculating the comprehensive company score for the predetermined company by the weighted sum of the first company score for the predetermined company and the second company score for the predetermined company,
The ratio of the weight of the second company score to the weight of the first company score in the first calculation method is greater than the ratio of the weight of the second company score to the weight of the first company score in the second calculation method,
4. A program according to claim 3 . The program causes the processor to:
a receiving step of receiving a request from a user requesting an evaluation of the predetermined company;
an output step of outputting the comprehensive company score calculated in the fourth step as a response in response to the request received in the receiving step;
5. The program according to any one of claims 1 to 4, causing the execution of The output step includes:
The product score calculated in the first calculation step and the information used to calculate the product score;
The first company score calculated in the second calculation step and the information used to calculate the first company score;
The second company score calculated in the third calculation step and the information used to calculate the second company score;
including the step of outputting information containing
6. A program according to claim 5 . The first calculation step is a step of calculating the product score based on the posted article information and a user attribute that is attribute information of an individual user who posted the posted article information.
A program according to any one of claims 1 to 6 . The program causes the processor to:
a posting acquisition step of acquiring information on articles posted by media;
a second specifying step of specifying a product to which the posted article information acquired in the posting acquisition step is related;
and
The first calculation step is a step of calculating the product score for the product identified in the second identification step based on the posted article information.
A program according to any one of claims 1 to 7 . The first calculation step is a step of calculating the product score based on the posted article information and the media attributes of the media that posted the posted article information.
9. A program according to claim 8 . The program causes the processor to:
a fourth identification step of identifying a company to which the posted article information acquired in the posted acquisition step is related;
and run
The second calculation step is a step of calculating a first company score, which is an evaluation index value for the company identified in the fourth identification step, based on the posted article information.
10. A program according to claim 8 or 9 . The program causes the processor to:
an evaluation index value calculated based on a user attribute of a user who posted the posted article or an evaluation value calculated for article content of the posted article, among the plurality of pieces of posted article information acquired in the posted article acquisition step; an article presenting step of identifying and presenting one or more of the posted articles having a predetermined value or more;
11. The program according to any one of claims 1 to 10, causing the execution of An information processing device comprising a processor and a storage unit,
The processor executes the program according to any one of claims 1 to 11 ,
Information processing equipment. An information processing system including an information processing device comprising a processor and a storage unit,
The processor executes the program according to any one of claims 1 to 11 ,
Information processing system. An information processing method executed by a computer comprising a processor and a storage unit,
Cause the computer to execute the program according to any one of claims 1 to 11 ,
Information processing methods.

Images