Enterprise evaluation processor system

Abstract

The purpose of the present invention is to reduce the answer burden of a vendor in enterprise evaluation. This enterprise evaluation processor system is provided with: a memory that stores, for each given target enterprise, master data in which at least one or more questions and answers are associated, and stores, for each evaluation enterprise, a given score for each question of the master data; a questionnaire and a questionnaire answer which are acquired from a questionnaire distribution source by a target enterprise are accepted, and when any one of questions of the questionnaire and any one of questions of main data related to the target enterprise are similar to each other, the questionnaire answer is stored in a memory as an answer of the main data related to the target enterprise. An answer to the master data of the target enterprise is scored using the score corresponding to the evaluation enterprise.

Description

Technical Field

[0001] The present invention relates to a corporate evaluation processor system. The present invention claims priority to Japanese Patent Application No. 2022-135510 filed on August 29, 2022, and the contents described in the Japanese Patent Application No. 2022-135510 are incorporated by reference into the present application for designated countries that recognize incorporation by reference of documents. Background Art

[0002] In recent years, the ESG (Environment, Social, Governance) investment market has been expanding. In the ESG investment market, investors evaluate companies based on ESG factors and decide on investment targets. This is because companies that value ESG also expect stability in future operations and see a high possibility of growth.

[0003] In recent years, ESG-related evaluations, including environmental issues and child labor issues, have been conducted not only within the company but also throughout the supply chain. As a result, buyers are increasingly requesting ESG evaluations of business entities (also called suppliers) participating in the supply chain system.

[0004] The mainstream of such buyer-oriented supplier ESG evaluation is to obtain information by conducting questionnaire surveys on suppliers.

[0005] On the other hand, the burden of answering questionnaires is heavy for suppliers. This is because the number of questions can sometimes reach tens to hundreds, and depending on the questions, it is necessary to attach proof data to the answers as evidence. In addition, there are multiple evaluation agencies, and each of them sets similar but not completely consistent questions. Furthermore, in addition to the questionnaires from the evaluation agencies, there are also cases where buyers create separate questions and seek answers from suppliers. As a result, the response rate from suppliers is often not active.

[0006] Buyers can sign a contract with a specific evaluation agency to use the evaluation results of suppliers with whom they have transactions. However, it is rare that all suppliers with whom they have transactions participate in the evaluation system of the evaluation agency. Therefore, buyers evaluate suppliers by using multiple evaluation agencies in combination or by using questions that the buyers have prepared individually.

[0007] In addition, regarding the tendency of questions in questionnaires, the underlying standards such as ISO (International Organization for Standardization) 26000, ISO14000 series, and the United Nations Global Compact are mostly common, and the differences in questions are often differences in resolution. Alternatively, although the underlying standards are common between questionnaires, there are often differences in the way the questions are asked. For example, depending on the questionnaire, there are times when asking whether a goal has been set and when asking about the results of the goal.

[0008] In this context, as a prior art from the perspective of ESG evaluation, Patent Document 1 quantitatively collects ESG information in a specific enterprise and outputs information based on the data as data. That is, Patent Document 1 shows a technology for quantitatively analyzing ESG data and visualizing the results to support ESG management in the enterprise.

[0009] In addition, as a technique for identifying the commonality of texts, feature extraction methods such as Bagof Words, TF-IDF, BM-25, and N-gram are generally known in the field of natural language processing.

[0010] There are many machine learning techniques, and in particular, as techniques that are often used as classifiers in natural language processing, support vector machines, decision trees, k-nearest neighbor methods, and the like are generally known.

[0011] As a prior art of natural language processing, there is an inquiry-type learning device shown in Patent Document 2, wherein the inquiry-type learning device constitutes a high-precision classifier for inquiry-type identification using N-gram as a natural language processing technology and support vector machine as a machine learning technology.

[0012] Prior Art Literature

[0013] Patent Literature

[0014] Patent Document 1: Japanese Patent Application Publication No. 2021-009696

[0015] Patent Document 2: JP-A-2004-094521 Summary of the invention

[0016] Problems to be solved by the invention

[0017] In the technology described in the above-mentioned patent document 1, it is possible to collect ESG information of the evaluation target enterprise from the backbone system of the evaluation target enterprise and perform quantitative ESG evaluation. However, in an environment where it is common to conduct separate questionnaires for each evaluation agency as described above, such a mechanism cannot be used as it is. In addition, the answers to the questions in the questionnaire are not necessarily only based on numerical answers, and sometimes it is necessary to accept the results of various data and provide answers including articles using natural language. In addition, in the case where answers using quantitative data are required, it is sometimes necessary to process the obtained quantitative data in conjunction with the questions of each evaluation agency or buyer to prepare answers. In addition, the questions also include qualitative inquiries, and the data required for the answers are not limited to quantitative data. In addition, in order to answer the questionnaire, it is necessary to make the collected huge amount of information into a form suitable for answers to the questions and record it as answers to the corresponding questions.

[0018] An object of the present invention is to reduce the burden of responses on suppliers in corporate evaluation.

[0019] Means for solving problems

[0020] The present application includes a variety of means for solving at least a part of the above-mentioned problems, and the following is provided as an example. A system according to one embodiment of the present invention for solving the above-mentioned problems has one or more memories and one or more processors, the memory stores master data corresponding to at least one question and an answer to the question for each given target enterprise, stores a given score corresponding to each question in the master data for each evaluated target enterprise, and the processor performs the following processing: receiving a questionnaire obtained by the target enterprise from a questionnaire distribution source and the target enterprise's answer to one or more questions contained in the questionnaire, namely, the questionnaire answer, and when any one of the questionnaire questions and any one of the questions in the master data related to the target enterprise are similar to each other, the questionnaire answer is stored in the memory as an answer to the master data related to the target enterprise, and the target enterprise is evaluated and output by scoring the answer to the master data of the target enterprise using the score corresponding to the evaluated enterprise.

[0021] Effects of the Invention

[0022] According to the present invention, a technique for reducing the burden of suppliers' responses in corporate evaluation can be provided. Other problems, configurations, and effects than those described above will become apparent from the following description of the embodiments of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a diagram showing a configuration example of a question answering / evaluation system.

[0024] Figure 2This is a diagram showing an example of supplementary answers from evidence data.

[0025] Figure 3 FIG. 2 is a diagram showing another example of a supplementary answer from evidence data.

[0026] Figure 4 This is a diagram showing an example of a flowchart of the response support process.

[0027] Figure 5 This is a diagram showing an example of the data structure of the question material storage area.

[0028] Figure 6 This is a diagram showing an example of the data structure of the answer history storage area.

[0029] Figure 7 This is a diagram showing an example of the data structure of the main data storage area.

[0030] Figure 8 This is a diagram showing an example of the data structure of master data.

[0031] Fig. 9 This is a diagram showing an example of a flowchart of a business evaluation process.

[0032] Fig.10 This is a diagram showing another example of the flowchart of the response support process.

[0033] Fig.11 This is a diagram showing an example of inter-company evaluation.

[0034] Fig.12 This figure shows an example of factor analysis using master data.

[0035] Fig.13 is a diagram showing an example of the hardware configuration of a processor system. DETAILED DESCRIPTION

[0036] Hereinafter, the embodiments of the present invention will be described with reference to the accompanying drawings. The embodiments are for illustration of the present invention, and are appropriately omitted and simplified for the purpose of clarity of the description. The present invention can also be implemented in various other ways. Unless otherwise specified, each component can be single or multiple.

[0037] The positions, sizes, shapes, ranges, etc. of the components shown in the drawings may not represent actual positions, sizes, shapes, ranges, etc. in order to facilitate understanding of the invention. Therefore, the present invention is not necessarily limited to the positions, sizes, shapes, ranges, etc. disclosed in the drawings.

[0038] As examples of various information, sometimes they are described using expressions such as "table", "list", "queue", etc., but various information can also be expressed in data structures other than these. For example, various information such as "XX table", "XX list", "XX queue" can also be set as "XX information". When describing identification information, expressions such as "identification information", "identifier", "name", "ID", and "number" are used, but these can be interchanged with each other. In addition, the identification information described by these expressions is represented by symbols, numerical values, natural language, or a combination thereof in the embodiments, but the identification information can also be in forms other than these.

[0039] When there are a plurality of components having the same or similar functions, different subscripts may be added to the same reference numerals for description. In addition, when there is no need to distinguish between these plurality of components, the subscripts may be omitted for description.

[0040] In the embodiments, sometimes the processing performed by executing a program is described. Here, the computer executes the program through a processor (such as a CPU, a GPU), and performs the processing determined in the program while using storage resources (such as a memory), an interface device (such as a communication port), etc. Therefore, the subject of the processing performed by executing the program can also be set to a processor. Similarly, the subject of the processing performed by the execution program can be a controller, a device, a system, a computer, or a node with a processor. The subject of the processing performed by the execution program can be a computing unit, and can also include a dedicated circuit for performing specific processing. Here, the so-called dedicated circuit is, for example, an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), a CPLD (Complex Programmable Logic Device), etc.

[0041] The program can be installed to the computer from a program source. The program source can be, for example, a program distribution server or a computer-readable storage medium. In the case where the program source is a program distribution server, the program distribution server can include a processor and a storage resource for storing the program of the distribution object, and the processor of the program distribution server distributes the program of the distribution object to other computers. In addition, in an embodiment, more than two programs can be implemented as one program, and one program can also be implemented as more than two programs.

[0042] Furthermore, although the present invention is a processor system, it can also be realized as a platform having the functions of the present invention.

[0043] Figure 1The diagram shows a configuration example of a question answering / evaluation system. For example, the question answering / evaluation system 10 is a business evaluation system including a processor system 100, a network 50, an evaluation institution D computer 300, an evaluation institution E computer 310, a supplier A computer 400, a supplier B computer 410, a supplier C computer 420, a buyer F computer 800, a buyer G computer 810, and an evaluation client H computer 850.

[0044] The network 50 is, for example, a communication network using a general public line such as a LAN (Local Area Network), a WAN (Wide Area Network), a VPN (Virtual Private Network), the Internet, a mobile phone communication network, or a composite network thereof, in part or in whole. In addition, the network 50 may also be a wireless communication network such as Wi-Fi (registered trademark) or 5G (Generation).

[0045] Evaluation agency D and evaluation agency E are examples of agencies that evaluate suppliers, which are entities that provide parts and products, in a parts supply network such as a supply chain network. Evaluation agencies are not limited to these two agencies, and there are usually more. However, in the example of this embodiment, these two agencies are used as evaluation agencies for simplicity of explanation.

[0046] Supplier A, Supplier B, and Supplier C are examples of suppliers that provide components and products in a component supply network such as a supply chain network. Suppliers are not limited to these three organizations, and there are usually more. However, in the example of this embodiment, these three organizations are set as suppliers for simplicity of explanation.

[0047] Buyer F and Buyer G are examples of buyers who are entities that purchase components and products in a component supply network such as a supply chain network. Buyers are not limited to two organizations, and there are usually more. However, in the example of this embodiment, these two organizations are set as buyers for the sake of simplicity. When the buyer manages and selects suppliers, there are cases where the evaluation organization is used, and there are cases where the buyer does not use the evaluation organization and evaluates the supplier himself. In addition, in the example of this embodiment, in order to simplify the description, suppliers and buyers are recorded separately, but when a supplier purchases components and products, the supplier sometimes becomes a buyer, and when other buyers purchase components and products provided by the buyer, the buyer sometimes becomes a supplier.

[0048] The evaluation client H is an example of an evaluation client who requests the evaluation of the supplier of the processor system for the purpose of managing and selecting the supplier. The evaluation client is considered to be, for example, a buyer, but sometimes an investor or other person other than the buyer becomes the evaluation client. In the example of this embodiment, the evaluation client and the buyer are distinguished for simplicity of description, but as mentioned above, the buyer may become the evaluation client.

[0049] Furthermore, a company with multiple affiliated companies can also use part or all of the functions of this processor system to evaluate and manage the sustainability of the company. In this case, it is considered to perform ESG evaluation within the company by setting the company as the evaluation client H and treating the company's affiliated companies as suppliers.

[0050] The processor system 100 includes a memory 110, a processing unit 120, an input / output interface 130, and a transmission interface 140. The memory 110 includes a question material storage area 111, an answer history storage area 112, and a main data storage area 113. The processing unit 120 includes a question material receiving unit 121, an answer support unit 122, an answer receiving unit 123, an evidence data processing unit 124, a learning / optimization unit 125, an evaluation unit 126, and a comparison analysis unit 127. In addition, the processor system 100 is a system having one or more processors. In addition, the processor system 100 can also be called an enterprise evaluation processor system.

[0051] Figure 2 This is a diagram showing an example of supplementing answers from evidence data by the evidence data processing unit 124, which is one of the functions of the processor system 100. In addition, expressions such as "evidence data", "evidence document", and "proof data" are used to represent the evidence document or data that serves as the basis for the answer, but these can be interchanged with each other. At this time, two modes are considered for the answer support processing. One is a mode in which the processor system 100 receives question materials from an evaluation agency or a buyer, which is called an investigation agent. The other is a mode in which the processor system 100 receives question materials from a supplier, which is called respondent assistance. The difference between the two is whether the processor system 100 acts as an agent from the receipt of question materials to the implementation of the investigation and the sending of answers, or whether the supplier itself actively performs the business from the receipt of question materials to the implementation of the investigation and the sending of answers. Even with these differences in methods, the question answering / evaluation system 10 can reduce the supplier's answer burden. The example of supplementing answers from evidence data shown in this figure is an example of supplementing answers through answer support processing (respondent assistance). Use Figure 2 The following will describe the outline of the respondent-assisted processing. Figure 2 For the sake of simplicity, only the processing unit of Figure 2 , but in reality it is set to have Figure 1 The structure of the record.

[0052] First, supplier A receives a request to answer a question document issued by evaluation organization D from evaluation organization D via network 50. Specifically, supplier A computer 400 receives the question document from evaluation organization D from evaluation organization D computer 300.

[0053] Then, the supplier A sends the evidence data of the question requiring evidence data in the question data and the question data to the processor system 100. Specifically, the evidence data 90 is sent from the supplier A computer 400 to the processor system 100. At this time, the supplier A does not record the answer to the question requiring evidence data in the answer in the question data. In addition, even if the evidence data is not required to be attached as the answer to the question, the same processing can be performed by attaching the evidence data to the question that obtains the answer information from the evidence data.

[0054] The processor system 100 receives the evidence data 90 and the question data from the transmission interface 140. Then, the question data receiving unit 121 of the processing unit 120 receives the question data, and the evidence data processing unit 124 receives the evidence data 90. Next, the evidence data processing unit 124 performs a predetermined process on the evidence data 90, and creates an answer to the question attached with the evidence data 90 in the question data.

[0055] Here, for example, the location (position in the evidence data) of the evidence data 90 used in answering the question is determined in advance by the learning / optimization unit 125. In this case, upon receiving the evidence data 90, the evidence data processing unit 124 extracts the data at the location and generates an answer to the question.

[0056] Alternatively, when the learning / optimizing unit 125 prepares in advance a response plan corresponding to the content of the part used in the answer of the evidence data 90, the evidence data processing unit 124 selects the most suitable response plan for the content of the evidence data 90 and prepares a response to the question.

[0057] In the case of a question that is not an answer based on a free description but an answer is selected from options, the answer to the question can also be prepared by the evidence data processing unit 124. For example, when the learning / optimization unit 125 prepares in advance which option to select according to the content of the part used in the answer of the evidence data 90, the evidence data processing unit 124 selects the most suitable option for the content of the evidence data 90 and prepares the answer to the question. For example, when the evidence data 90 contains data of an appropriate title and data type, the evidence data processing unit 124 selects the option of "measures are being implemented" as the answer to the question.

[0058] Alternatively, in the case where the question is a question to be answered by a numerical value, the answer to the question can also be prepared by the evidence data processing unit 124 in the same manner. For example, in the case where the evidence data 90 is a CSV (Comma Separated Value) file recording numerical values, the evidence data processing unit 124 reads the CSV file, extracts one or more parts required for the answer, and uses them as input variables of a given four arithmetic operations to perform calculations, thereby preparing the answer to the question. In this case, the learning / optimization unit 125 stores the positions of the rows and columns required for the preparation of the answer, the formula required for the calculation, etc. in advance, and prepares the answer to the question by executing the contents. In addition, the positions of the rows and columns required for the preparation of the answer, the formula required for the calculation, etc. are basically unchanged from the previous year, and the past answer contents are stored by the learning / optimization unit 125. In addition, the evidence data processing unit 124 can also extract a plurality of data located at a given position in the read data set and use them as input variables, and use the external data collected by the web crawler process as input variables, perform calculations by a given calculation formula, and use them in supplementing the questionnaire answers.

[0059] The created answer is recorded as an answer to the question data by the answer support unit 122, and sent to the supplier A computer 400 via the transmission interface 140. Then, the supplier A who received the answer plan from the processor system 100 adds necessary corrections to the input answer plan, and the question data of the evaluation agency D whose answer has been recorded again is sent to the processor system 100. The sent data is received by the answer receiving unit 123 of the processing unit 120 via the transmission interface 140, and the learning / optimization unit 125 is updated with respect to the existence of corrections and the correction content of the answer. That is, the learning / optimization unit 125 performs machine learning using the existence of corrections to the questionnaire answer and the corrected answer information, and constructs a learned model (for each target enterprise) of the supplier A.

[0060] Then, the supplier A computer 400 sends the evaluation agency D's question data and evidence data, in which the answers have been recorded, to the evaluation agency D computer 300. In addition, if there is a correction in the answer plan, the answer plan extracted from the evidence data is likely to be wrong. In this case, the learning / optimization unit 125 needs to change the reference part or calculation formula of the evidence data 90. Therefore, the learning / optimization unit 125 re-learns the format of the evidence data 90, re-learns the calculation formula, or re-learns the basis data collected by the web crawler.

[0061] Figure 31 is a diagram showing another example of the answer supplement from the evidence data performed by the evidence data processing unit 124, among the functions of the processor system 100. This example is not an example of the supplier A adding evidence data 90, but an example of the processor system 100 collecting information collected by the information collection unit 401 of the supplier A computer 400. Specifically, the information collection unit 401 collects information from various facilities and equipment owned by the supplier (such as Figure 3 The supplier A equipment computer 400') or the like collects numerical data of the monitoring object in advance. Alternatively, the information collection unit 401 performs a Web crawler or the like to obtain Web information in advance. Then, the evidence data processing unit 124 collects the evidence data 90 collected by the information collection unit 401 at the timing of the response support.

[0062] Furthermore, in Figure 3 In the case where there is insufficient external data 60 in the four arithmetic operations used to calculate the answer, the evidence data processing unit 124 obtains the external data 60. The external data 60 is, for example, the emission unit intensity used in the calculation of CO2 emissions. More specifically, the numerical data corresponding to the monitoring object from the facilities and equipment owned by the supplier is the electricity usage in the target year. The evidence data processing unit 124 calculates the CO2 emissions by multiplying the electricity usage by the emission unit intensity in electricity corresponding to the external data 60.

[0063] Figure 4 This is an example of the processing flow of the answer support process (survey proxy). The answer support process (survey proxy) starts when a start instruction is received from the evaluation agency, the buyer, etc. Alternatively, the answer support process (survey proxy) may also start at a given date and time (for example, 6 a.m. every day) or at a given interval (for example, every 12 hours). The answer support process (survey proxy) is performed when the processor system 100 is acting as a proxy for the work from receiving the question materials to conducting the survey and sending the answer.

[0064] First, the question data receiving unit 121 receives question data from the evaluation agency or the buyer and stores it (step S101). Specifically, the question data receiving unit 121 receives question data from the evaluation agency D computer 300, the evaluation agency E computer 310, the buyer F computer 800, and the buyer G computer 810. The question data receiving unit 121 decomposes the received question data into question units, reconstructs them in the question data storage area 111, and stores them ( Figure 5 ).

[0065] Then, the answer support unit 122 transmits the question data to the supplier through the transmission interface 140 (step S102 ).

[0066] Then, the evidence data processing unit 124 receives evidence documents or data from the suppliers (step S103). Specifically, the evidence data processing unit 124 receives evidence documents or data (sometimes collectively referred to as data sets) related to the answer to the question from the supplier A computer 400, the supplier B computer 410, and the supplier C computer 420.

[0067] If the creation date of the data set received in step S103 is before the evaluation target period, the evidence data processing unit 124 determines that the document or data is insufficient as evidence, and causes the supplier's computer to display a message to that effect.

[0068] Then, the answer support unit 122 uses the delivered data set to implement answer supplement processing (step S104). Specifically, as described above, the answer support unit 122 supplements the answers to the questionnaire by reading out one or more data located at a given position of the delivered data set and transferring them. In addition, in the case where there is master data that has already answered other questionnaires for the same supplier, if there is no answer to any question similar to any of the questions in the master data, the answer support unit 122 supplements the answer to the master data so that the answer to the questionnaire question is used as the answer. In addition, the answer support unit 122 uses the learned model of the learning / optimization unit 125 in the process of supplementing answers for questionnaires that are different in the survey period or the questionnaire distribution source for the same supplier.

[0069] Then, the response support unit 122 sends the response including the response to the supplier (step S105 ).

[0070] Then, the answer receiving unit 123 receives answers from the suppliers (step S106 ). Specifically, the answer receiving unit 123 receives answers, evidence documents or data, and revised contents of the answer plan from the supplier A computer 400 , the supplier B computer 410 , and the supplier C computer 420 .

[0071] The learning / optimization unit 125 stores the received answer as an answer history in the answer history storage area 112 (step S107). Figure 6 ). Then, the learning / optimization unit 125 analyzes the revised content of the answer plan, and corrects the program that records the steps of creating an answer from the evidence document or data and the classifier of the learning / optimization unit 125.

[0072] Then, the answer support unit 122 sends the answer received from the supplier to the evaluation agency or the buyer who requested the investigation (step S108). Specifically, the answer support unit 122 sends the answer received from the supplier to the evaluation agency D computer 300, the evaluation agency E computer 310, the buyer F computer 800, and the buyer G computer 810 through the transmission interface 140.

[0073] The above is an example of a flowchart of the answer support process (survey proxy). According to the answer support process (survey proxy), the burden of answering questions can be reduced. Therefore, the burden of answering suppliers in corporate evaluation can be reduced.

[0074] Figure 5 1 is a diagram showing an example of data structure of a question material storage area. The question material storage area 111 stores information of questions to suppliers. Specifically, the question material storage area 111 has an issuing organization ID 111a, a material name 111b, a response period 111c, a response supplier ID 111d, and a question 111e. The issuing organization ID 111a, the material name 111b, the response period 111c, the response supplier ID 111d, and the question 111e are associated with each other.

[0075] The issuing agency ID 111a stores information that identifies the issuing agency ID, which is identification information for identifying the issuing agency that asks the question. In this embodiment, in the case of the non-financial information questionnaire and the CSR survey report, the issuing agency is set as the evaluation agency D and the evaluation agency E, and in the case of SAQ (self-assessment questionnaire), the issuing agency is set as the buyer F. However, there are cases where the self-assessment questionnaire is provided by the evaluation agency, and there are cases where the non-financial information questionnaire and the CSR survey report are issued by the buyer.

[0076] The name of the document in which the question is recorded is stored in the document name 111b. The document name may be different for each issuing organization, but in this embodiment, it is "non-financial information questionnaire", "CSR (Corporate Social Responsibility) survey report", "self-evaluation questionnaire", etc. However, it is not limited to these, and generally, it is sufficient to ask for answers to non-financial information such as ISO26000 and ISO14000 series. In addition, most of these documents contain questions issued by evaluation organizations or buyers with suppliers as respondents.

[0077] The response period 111c includes information that specifies the period to which the document containing the question is to be answered. Since the evaluation agency often asks suppliers to answer the results of the previous year once a year, the information that specifies the previous year is stored in the response period 111c. However, when the question document is issued at a different frequency, the information that specifies the period corresponding to the response period (previous period, next period, 1Q, etc.) is stored in the response period 111c.

[0078] The answering provider ID 111d stores information identifying a subject that provides a response to the material identified by the material name 111b.

[0079] The question 111e stores a question sentence (natural language, indicator, or mathematical expression) contained in the data specified by the data name 111b. Figure 5 In order to simplify the diagram, the number of questions is reduced to two, but in reality there are several to hundreds of questions.

[0080] Figure 6 1 is a diagram showing an example of data structure of the answer history storage area. The answer history storage area 112 stores the supplier's answer data for each issuing agency and answer period. Specifically, the answer history storage area 112 has an answer supplier ID 112a, an issuing agency ID 112b, an answer period 112c, and an answer data ID 112d. The answer data identified by the answer data ID 112d includes the answer data that was finally answered to the issuing agency and the attached evidence data. However, in the case where there are several answers such as re-submissions in the same period, the answer data 112d may include the answer history.

[0081] Figure 7 11 is a diagram showing an example of a master data storage area. The master data storage area 113 has a reply supplier ID 113a, a reply period 113b, an issuer ID 113c, and a master data ID 113d.

[0082] The answering supplier ID 113a stores information identifying the subject of the answer. The answering period 113b contains information identifying the period to be answered. The issuing agency ID 113c stores information identifying the issuing agency ID, which is identification information for the issuing agency that asked the question. The master data ID 113d contains information identifying the master data to be described later, which is created in each answering period 113b, for each supplier.

[0083] The master data storage area 113 stores, for each supplier, the master data ID 113d created in each response period 113b and the relationship between the evaluation agency or the issuing agency ID 113c of the buyer, which is the setting source of the question used when the master data ID was created. For example, the master data ID 113d with the response period 113b of "2019" for the record with the answer supplier ID 113a of "supplier B" is created based on the answer to the question created by the agency with the issuing agency ID 113c of "evaluation agency D".

[0084] In addition, for the record with the answer supplier ID 113a being "Supplier A", the answer period 113b is "2019" and the issuing organization ID 113c is "Master Data". This means that the master data involved in this record is not a response to a question issued by an external organization such as an evaluation organization or a buyer, but a direct response to the question of the master data itself.

[0085] Figure 8 114a, a benchmark ID 114b, a question 114c, an answer 114d, evidence data 114e, an answer data ID 114f, a score 114g, a scoring benchmark 114h, and a score 114i. The category 114a indicates the category to which the question 114c belongs. For example, the category "E" is a category related to the environment. The benchmark ID 114b is information that is in one-to-one correspondence with the feature vector of the question set as the benchmark. The question 114c is a question from an evaluation agency or a buyer having a feature vector corresponding to the benchmark ID 114b. The answer 114d is an answer from a supplier corresponding to the question determined by the question 114c.

[0086] The evidence data 114e is information identifying data serving as evidence associated with the answer 114d. The answer data ID 114f is the same as the answer data ID 112d in the answer history storage area 112, and is associated with questions and answers from the evaluation organization or the buyer.

[0087] The score 114g is a score for quantitatively evaluating the answer 114d. The scoring standard 114h is a scoring standard for quantitatively evaluating the answer 114d. The score 114i is a score of the result of quantitatively evaluating the answer 114d. The setting of the score 114g and the scoring standard 114h is set by the evaluation client for each answer period. Therefore, the score 114g and the scoring standard 114h can be set in common for all suppliers of the evaluation object. In addition, the suppliers can be divided into specific groups, such as business fields, company sizes, etc., and the score 114g and the scoring standard 114h can be set for each group.

[0088] The master data 114 establishes a correspondence between the questions and answers of the supplier in the response period to the questions from one or more evaluation agencies or buyers and the benchmark ID 114b associated with the benchmark question. That is, when a question asking the same content as the benchmark question is included in the questions from the evaluation agency or buyer, the question and its answer are set as question 114c and answer 114d in the row of the benchmark ID 114b associated with the benchmark question and establish a correspondence. On the other hand, when a question asking the same content as the benchmark question is not included in the questions from the evaluation agency or buyer, the question 114c and answer 114d in the row of the benchmark ID 114b are left blank.

[0089] Fig. 9 This is a diagram showing an example of a flowchart of a business evaluation process. The business evaluation process is a process in which inquiry sheets provided by multiple evaluation agencies and inquiry sheets independently prepared by the buyer are classified according to the content of the questions, and the multiple inquiry sheets are comprehensively displayed by arranging the same questions in a horizontal arrangement. In addition, in the business evaluation process, by using the previously assigned points and scoring criteria in the master data, the evaluations of the suppliers' companies can be displayed comparatively. The business evaluation process starts when a start instruction is received from the evaluation agency, the buyer, etc. Alternatively, the business evaluation process can be started at a given date and time (for example, 6 a.m. every day) or at a given interval (for example, every month).

[0090] First, the evaluation unit 126 receives questions and score settings of the master data of the corresponding year stored in the master data storage area 113 in the memory 110 from the evaluation requester (the evaluation requester H computer 850 ) (step S201 ).

[0091] Suppliers are not necessarily limited to answering questions that the evaluation client wants, such as answering questionnaires from evaluation agencies that are different from the evaluation client. Therefore, by allowing the evaluation client to set the scores for questions in the master data, answers to different questionnaires can also be evaluated on the same basis. Specifically, the evaluation unit 126 accepts the setting of the scores and scoring criteria of the master data 114. At this time, the scores and scoring criteria of the master data 114 can be freely set by the evaluation client. However, considering the trouble of having to set all the scores and evaluation criteria, the evaluation unit 126 can also accept selections from the scoring schemes previously stored in the memory 110 of the processor system 100 according to the needs of the evaluation client. In addition, questions with scores set to 0 are set as questions that are not questions of the corresponding year and are excluded from the evaluation items.

[0092] Next, the evaluation unit 126 receives the registration of the supplier to be evaluated by the evaluation requester (step S202 ). Specifically, the evaluation unit 126 receives the selection of the answering supplier to be evaluated from the answering supplier ID 113 a in the master data storage area 113 .

[0093] Then, the question data receiving unit 121 receives question data from multiple evaluation agencies or buyers and stores them (step S203). Specifically, the question data receiving unit 121 receives question data from the evaluation agency D computer 300, the evaluation agency E computer 310, the buyer F computer 800, and the buyer G computer 810. The question data receiving unit 121 decomposes the received question data into question units, reconstructs them in the question data storage area 111, and stores them.

[0094] Then, the question data receiving unit 121 sends the question data to the supplier registered in step S202 from the transmission interface 140 (step S204). Specifically, the question data receiving unit 121 sends the question data received from the evaluation agency D computer 300, the evaluation agency E computer 310, the buyer F computer 800, and the buyer G computer 810 to the supplier. In addition, the question data receiving unit 121 also sends the question data received from the evaluation agency or the buyer to the supplier who is not registered as the evaluation object by any evaluation client. Only the answer content of the supplier registered as the evaluation object by the evaluation client is used in the evaluation of the evaluation client.

[0095] Then, the answer receiving unit 123 receives answers from the suppliers (step S205 ). Specifically, the answer receiving unit 123 receives question materials, answers, and evidence documents or data from the supplier A computer 400 , the supplier B computer 410 , and the supplier C computer 420 .

[0096] In addition, between step S204 and step S205, in which the supplier answers questions from the evaluation agency or the buyer, or the question 114c of the master data 114, the answer receiving unit 123 may accept the answer by manual input, or may supplement the answer using the evidence document or data using the answer support processing. Or, both are performed. In addition, regarding the processing example of performing the answer supplement, the answer supplement is performed using Fig.10 Then narrate.

[0097] Specifically, the answer receiving unit 123 stores the evaluation agencies or buyers that have received evaluations from the past to the present, the response period for receiving the evaluations, and the response data when receiving the evaluations in a corresponding manner for each supplier in the response history storage area 112. For example, supplier A receives evaluations from evaluation agency D in the response period 2020 and 2021. The answer receiving unit 123 stores the answer data ID of the data in the response period 2020 as "AD-2020" and the answer data ID of the data in the response period 2021 as "AD-2021". The answer data ID is associated with the actual questions stored and the answer data to the questions.

[0098] Then, the answer receiving unit 123 decomposes the received question material, answer, evidence document or data into question units, reconstructs and stores them in the master data 114 of the corresponding year stored in the master data storage area 113 (step S206). At this time, the answer receiving unit 123 stores the data that becomes the original of the received question material, answer, evidence document or data in a given area of ​​the memory.

[0099] As a method of associating questions having the same content as the questions associated with the reference ID 114 b of the master data 114 , for example, a method of obtaining questions from an evaluation organization or a buyer in advance and manually associating them can be adopted.

[0100] Alternatively, when question data is sent from an evaluation organization, a buyer, or a supplier to be evaluated, the question data is divided into questions and each question is automatically assigned to the reference ID 114b of the master data.

[0101] As an example of a method for automatically assigning, there is the following natural language processing. First, in order to identify the commonality between questions, the answer support unit 122 uses various feature extraction techniques such as Bag of Words, TF-IDF, BM-25, N-gram, etc. alone or in combination to generate an appropriate feature vector from the character string of the question. Furthermore, the answer support unit 122 classifies the feature vectors generated from the question as having the same meaning as the original question into the same category and assigns a classification ID.

[0102] Then, the answer support unit 122 performs multimodal learning on the relationship between the feature vector and the classification ID, and constructs a classifier that can predict the classification ID for the feature vector newly created from the unknown question. The classifier in the answer support unit 122 predicts the classification ID using, for example, a support vector machine, a decision tree, a k-nearest neighbor method, etc. That is, when the classifier determines that the classification ID is the same, the answer support unit 122 determines that the meaning of the question is common.

[0103] Alternatively, a method of allocating each question to the reference ID 114 b of the master data using artificial intelligence such as a neural network is also possible.

[0104] Then, the answer accepting unit 123 determines whether there are any unanswered questions (step S207 ). Specifically, the answer accepting unit 123 identifies questions with insufficient answers (no answers) among the questions allocated to the master data in step S206 as unanswered questions.

[0105] If there are unanswered questions (if "yes" in step S207), the answer receiving unit 123 requests the supplier to provide additional information (step S208). Specifically, the answer receiving unit 123 sends a message requesting additional information to the supplier A computer 400, the supplier B computer 410, and the supplier C computer 420. Then, the answer receiving unit 123 returns control to step S205.

[0106] If there are no unanswered questions ("No" in step S207), the evaluation unit 126 uses the master data score 114g set in step S201 to evaluate the company (step S209). Specifically, the evaluation unit 126 evaluates the answer using the master data score 114g and the scoring criteria 114h, and calculates the score 114i.

[0107] Then, the comparison and analysis unit 127 sorts the suppliers according to the evaluation results in step S209 , and transmits information showing the evaluations between companies of the suppliers in comparison to the evaluation requester (step S210 ).

[0108] The above is an example of a flowchart of the enterprise evaluation process. According to the enterprise evaluation process, the evaluation client can evaluate suppliers even when there are multiple suppliers and some or all of the suppliers have not signed a contract with the evaluation organization with which the evaluation client has signed a contract.

[0109] In addition, in the case of a supplier that is not evaluated by any evaluation agency or buyer, if the supplier answers the question 114c of the master data 114, the supplier can be evaluated using the result and compared with other suppliers evaluated by the evaluation agency. In this way, even a supplier that is not evaluated by a buyer can be replaced with the company's evaluation form.

[0110] Furthermore, it is also possible to evaluate suppliers using only the questions 114 c of the master data 114 without using the evaluation results of the evaluation organization or the buyer.

[0111] In the case of using only the question 114c of the master data 114, Figure 4 The answer support process shown is a different answer support process. Fig.10 This is another example of the processing flow of the answer support process. This answer support process can be applied to both the survey agent and the respondent assistance. Fig.10 Indicates an example of application in a survey agent.

[0112] First, the answer support unit 122 transmits the question 114c of the master data 114 to the supplier through the transmission interface 140 (step S301). Then, the answer support unit 122 receives the answer to the question 114c of the master data 114 from the supplier through the transmission interface 140, and the evidence document or data, and stores it in the master data storage area 113 (step S302).

[0113] Then, the question data receiving unit 121 receives the question data from the evaluation agency or the buyer via the transmission interface 140 and stores it (step S303). Specifically, the question data receiving unit 121 receives the question data from the evaluation agency D computer 300, the evaluation agency E computer 310, the buyer F computer 800, and the buyer G computer 810. The question data receiving unit 121 decomposes the received question data into question units, reconstructs them in the question data storage area 111, and stores them ( Figure 5 ).

[0114] Then, the answer support unit 122 supplements questions similar to any of the questions in the master data with answers and evidence documents or data allocated to the master data to form answers and evidence documents or data for questions in the questionnaire of the evaluation organization (step S304 ).

[0115] Then, the answer support unit 122 transmits the question data from the evaluation organization and the answer plan supplemented in step S304 to the supplier through the transmission interface 140 (step S305 ).

[0116] Then, the answer receiving unit 123 receives the answer from the supplier (step S306 ). Specifically, the answer receiving unit 123 receives the answer confirmed by the supplier, the evidence document or data, and the revised content of the answer solution revised as needed via the transmission interface 140 .

[0117] Then, the learning / optimization unit 125 stores the received answer as an answer history in the answer history storage area 112 (step S307). Figure 6 ). Then, the learning / optimization unit 125 analyzes the revised content of the answer plan, and corrects the program recording the steps of creating an answer from the evidence document or data and the classifier of the learning / optimization unit 125.

[0118] Then, the answer support unit 122 sends the answer received from the supplier to the evaluation agency or the buyer who requested the investigation (step S308). Specifically, the answer support unit 122 sends the answer received from the supplier to the evaluation agency D computer 300, the evaluation agency E computer 310, the buyer F computer 800, and the buyer G computer 810 through the transmission interface 140.

[0119] According to the above-mentioned answer support processing, the supplier does not have to answer questions from multiple evaluation agencies and buyers every time, but can answer only the master data in advance. Therefore, if there are questions from multiple evaluation agencies and buyers, the supplier can answer the questions of multiple evaluation agencies and buyers only by confirming the answer plan.

[0120] In addition, when the above-mentioned answer support processing is applied to answerer assistance, in step S303, the supplier receives the question data from the evaluation agency or the buyer. In addition, in the processing of sending the answer and the evidence document or data to the evaluation agency or the buyer in step S308, there is a difference in that the supplier sends it by itself. It can be said that even if there is a difference in the process of sending and receiving these question data, the question answering / evaluation system 10 can reduce the answer burden of the supplier.

[0121] Fig.11It is a diagram showing an example of inter-enterprise evaluation. In the present embodiment, the so-called inter-enterprise evaluation refers to the horizontal evaluation of different suppliers using different questions from different evaluation agencies or buyers. For example, the comparative analysis unit 127 outputs a table in step S210, in which the supplier information (a collection of questions, answers, and scores) is set on the horizontal axis and the benchmark ID 114b, i.e., the questions, is set on the vertical axis, as in the inter-enterprise evaluation diagram 30. In the example of the inter-enterprise evaluation diagram 30, supplier A only answers questions from evaluation agency D. On the other hand, supplier C only answers questions from evaluation agency E. There are more than one common questions in the questions of evaluation agency D and evaluation agency E. By horizontally arranging the common questions according to the benchmark ID 114b, the inter-enterprise evaluation of supplier A and supplier C can be performed using the answers to the questions of different evaluation agencies or buyers.

[0122] Fig.12 is a diagram showing an example of factor analysis using master data. Fig.12 The master data 114 is recorded in a simplified manner. The reference ID 114b is basically not deleted and is added at any time. Therefore, when receiving an instruction from the user, the comparative analysis unit 127 tracks the answer content of the same reference ID 114b stored in the master data 114 of each answer period in a time series. Then, the comparative analysis unit 127 analyzes the factors of the time-dependent changes in the answer content for a specific reference ID 114b based on the correlation with the changes in the answer data for other reference IDs 114b.

[0123] In addition, at this time, the reference ID 114b used by the comparative analysis unit 127 in the analysis may be one or more. For example, when the question to be analyzed is CO2 emission, the comparative analysis unit 127 analyzes the factor by examining the correlation between the number of employees, sales, recyclable material usage rate, emission unit intensity used in calculation, and whether reduction measures are implemented. Fig.12 The diagram 40 is an example of a case where the answers to the questions of the analysis object and the related questions are numerical values. However, the example is not limited to this one, and it is also possible to consider a case where one or both of the questions of the analysis object and the answers to the related questions are, for example, the presence or absence of measures implemented by the enterprise, policies, etc., rather than numerical values. Fig.12 The transition of the answer results shown in the graph is sent from the processor system 100 to a screen of a computer or the like of a user, that is, an evaluation requester, the supplier himself, or another user, and is viewed.

[0124] At this time, the inquiry forms provided by multiple evaluation agencies and the inquiry forms independently prepared by the buyer are integrated to prepare the master data 114. Therefore, whether the evaluation client (buyer, supplier who wants to evaluate its own ESG status, etc.) joins the evaluation agency midway, or the evaluation client changes the evaluation agency to sign a contract midway, the transition of each evaluation period can be evaluated on the same time series data. For example, Fig.12 The master data ID 113d of each recorded master data 114 corresponds to the master data ID 113d of the supplier B whose response period 113b is from 2019 to 2021. Although the issuer ID 113c of the questionnaire is different for the response period of 2019 and after 2020 for supplier B, the comparative analysis unit 127 integrates the questionnaires in the questions of the master data 114 and evaluates them as a series of time series data.

[0125] According to the present invention, even if some or all of the multiple suppliers have not signed a contract with the evaluation agency that the buyer has signed a contract with, the buyer can still conduct supplier evaluation. Furthermore, the supplier can automatically answer the questionnaire for a specific inquiry only by attaching evidence documents or data or collecting through the supplier's computer. Therefore, in this technology, the supplier's answer burden can be reduced. In addition, in this technology, by using the supplier's inherent master data, the factors of changes in the answer content of a specific question can be analyzed, and the buyer's supplier evaluation and management can be smooth.

[0126] In addition, the processor system 100 has the following function: machine learning is performed on the relationship between the answer information to the question and the evidence document or data that confirms the answer information, and the answer to the question is automatically inputted only by attaching the evidence document or data that confirms the answer information, or collecting the document or data through the supplier's computer. In this case, the evidence document or data that confirms the answer information can be an electronic document, or it can be data that is digitized by image recognition, PDF, etc. of a handwritten document. In addition, the form of the evidence document or data also corresponds to any one of documents written in PDF, etc., numerical data such as CSV files, numerical data directly obtained from various facilities and equipment owned by the supplier and collected through the supplier's computer, and information obtained from Web information through Web crawlers, etc.

[0127] Furthermore, in the processor system 100, master data exists for each supplier and each evaluation period, and by using the master data unique to the supplier, the factors of the supplier's answer results for a specific question are determined by using the correlation analysis of the answer results of other questions related to the specific question. Since the master data 114 is created by integrating the inquiry forms provided by multiple evaluation agencies and the inquiry forms independently created by the buyer, even if the buyer joins the evaluation agency midway or changes the evaluation agency to sign a contract with midway, the transition of each evaluation period can be evaluated in time series.

[0128] Fig.13 1 is a diagram showing an example of the hardware structure of a processor system. The processor system 100 can be implemented by a general computer 900 or a network system having a plurality of such computers 900, wherein the computer 900 has: a processor (e.g., a CPU: Central Processing Unit or a GPU: Graphics Processing Unit) 901; a hardware memory 902 such as a RAM (Random Access Memory); an external storage device 903 such as a hard disk device (Hard Disk Drive: HDD) or an SSD (Solid State Drive); a reading device 905 for reading information from a removable storage medium 904 such as a CD (Compact Disk) or a DVD (Digital Versatile Disk); an input device 906 such as a keyboard, a mouse, a barcode reader, or a touch panel; an output device 907 such as a display; and a communication device 908 for communicating with other computers via a communication network such as a LAN or the Internet. In addition, the reading device 905 can not only read from the removable storage medium 904 but also write to it.

[0129] The processor 901 performs various processes by executing various given programs loaded from the external storage device 903 to the memory 902. The program is, for example, an application program that can be executed on an OS (Operating System) program. The program can be installed from a removable storage medium 904 to the external storage device 903 via a reading device 905, or can be downloaded from a network via a communication device 908 and executed by the processor 901.

[0130] For example, the question material receiving unit 121, the answer supporting unit 122, the answer receiving unit 123, the evidence data processing unit 124, the learning / optimization unit 125, the evaluation unit 126, and the comparison and analysis unit 127 can be realized by loading a program stored in the external storage device 903 into the memory 902 and executing it by the processor 901. The input / output interface 130 can be realized by the processor 901 using the input device 906, the output device 907, and the communication device 908. The memory 110 can be realized by the processor 901 using the memory 902 or the external storage device 903. The transmission interface 140 can be realized by the processor 901 using the communication device 908.

[0131] The above is an example of a question answering / evaluation system according to an embodiment of the present invention. In addition, the present invention is not limited to the above-mentioned embodiments, and includes various modified examples. For example, the above-mentioned embodiments are described in detail in order to explain the present invention in an easy-to-understand manner, but are not necessarily limited to all structures described. A part of the structure of the embodiment can be replaced with another structure, and the structure of another embodiment can be added to the structure of the embodiment. In addition, a part of the structure of the embodiment can be deleted.

[0132] The above-mentioned parts, structures, functions, processing parts, etc. may also be implemented in hardware by designing a part or all of them using integrated circuits. In addition, the above-mentioned parts, structures, functions, etc. may also be implemented in software by interpreting and executing programs that implement each function through a processor. Information such as programs, tables, files, etc. that implement each function can be placed in a recording device such as a memory or a hard disk, or a recording medium such as an IC card, an SD card, or a DVD.

[0133] In addition, the control lines and information lines involved in the above-mentioned embodiments are shown as lines that are considered necessary for explanation, but it is not necessarily limited to showing all control lines and information lines in the product. In fact, it can be considered that almost all structures are connected to each other. The above description of the present invention is centered on the embodiment.

[0134] Description of Reference Numerals

[0135] 10: Question answering / evaluation system, 50: Network, 100: Processor system, 110: Memory, 111: Question data storage area, 112: Answer history storage area, 113: Master data storage area, 114: Master data, 120: Processing unit, 121: Question data receiving unit, 122: Answer support unit, 123: Answer receiving unit, 124: Evidence data processing unit, 125: Learning / optimization unit, 126: Evaluation unit, 127: Comparative analysis unit, 130: Input / output interface, 140: Transmission interface, 300: Evaluation agency D computer, 310: Evaluation agency E computer, 400: Supplier A computer, 410: Supplier B computer, 420: Supplier C computer, 800: Buyer F computer, 810: Buyer G computer, 850: Evaluation client H computer.

Claims

1. A business evaluation processor system, comprising one or more memories and one or more processors, wherein the business evaluation processor system is characterized in that: The memory stores master data that establishes a correspondence between at least one question and an answer to the question for each given target enterprise, and stores a given score that establishes a correspondence between each question in the master data for each evaluation enterprise that evaluates the target enterprise. The processor performs the following processing: receiving a questionnaire obtained by the target enterprise from a questionnaire distribution source and a questionnaire answer provided by the target enterprise to one or more questions (questionnaire questions) included in the questionnaire, When any one of the questions in the questionnaire and any one of the questions in the master data related to the target enterprise are similar to each other, the answer to the questionnaire is stored in the memory as the answer to the master data related to the target enterprise. The target enterprise is evaluated by scoring the answers to the master data of the target enterprise using the points corresponding to the evaluation enterprise, and the evaluation is output.

2. The enterprise evaluation processor system according to claim 1, wherein: The processor performs the following processing: receiving a second questionnaire obtained by a second target enterprise different from the target enterprise from the questionnaire distribution source or a second questionnaire distribution source different from the questionnaire distribution source, and receiving second questionnaire answers from the second target enterprise in response to one or more questions included in the second questionnaire, i.e., second questionnaire questions; When any one of the questions in the second questionnaire is similar to any one of the questions in the master data related to the second target enterprise, the answer to the second questionnaire is stored in the memory as the answer to the master data related to the second target enterprise. The answers to the master data of the target enterprise and the answers to the master data of the second target enterprise are scored using the points corresponding to the evaluated enterprise, and evaluations of the target enterprise and the second target enterprise can be outputted in a comparative manner.

3. The enterprise evaluation processor system according to claim 1, wherein: The processor performs the following processing: receiving a data set associated with said questionnaire responses, One or more data located at a given position in the data set is read out and used in supplementing the questionnaire answer.

4. The enterprise evaluation processor system according to claim 1, wherein: The processor performs the following processing: One of a plurality of given scoring schemes is selectively received from the evaluation company and stored in the memory as the scoring, or the evaluation company receives input of the scoring and stores it in the memory.

5. The enterprise evaluation processor system according to claim 1, wherein: The processor performs the following processing: If a second questionnaire is received by the target enterprise from a second questionnaire distribution source different from the questionnaire distribution source, when one or more questions included in the second questionnaire, i.e., any one of the questions in the second questionnaire, and any one of the questions in the master data related to the target enterprise are similar to each other, the answers to the master data related to the target enterprise are used as answers to the questions in the second questionnaire.

6. The enterprise evaluation processor system according to claim 1, wherein: The memory stores the master data for each of the given target companies and for each given period. The processor performs the following processing: Correlation analysis is performed between the plurality of questions on temporal changes in the answers related to the numerical data among the answers of the target enterprise, and factor analysis is performed, and the result is presented to the target enterprise.

7. An enterprise evaluation processor system, comprising one or more memories and one or more processors, characterized in that: The memory stores master data that establishes a correspondence between at least one question and an answer to the question for each given target enterprise. The processor performs the following processing: delivering the master data to the target enterprise, receiving, from the target enterprise, answers to the questions of the master data and data sets associated with the answers, If a questionnaire is received from a questionnaire distribution source obtained by the target enterprise, and if one or more questions contained in the questionnaire, i.e., any one of the questions in the questionnaire, and any one of the questions in the master data related to the target enterprise are similar to each other, the answers to the master data related to the target enterprise and the associated data sets will be used as answers to the questions in the questionnaire.

8. The enterprise evaluation processor system according to claim 7, wherein: The processor performs the following processing: One or more data located at a given position in the associated data set is read out and used to supplement the answer to the question in the questionnaire.

9. An enterprise evaluation processor system, comprising one or more memories and one or more processors, characterized in that: The memory stores master data that establishes a correspondence between at least one question and an answer to the question for each given target enterprise. The processor performs the following processing: receiving a questionnaire obtained by the target enterprise from a questionnaire distribution source, a questionnaire answer provided by the target enterprise to one or more questions contained in the questionnaire, namely, questionnaire questions, and a data set associated with the questionnaire answer, One or more data located at a given position in the data set is read out and used in supplementing the questionnaire answer.

10. The enterprise evaluation processor system according to claim 9, wherein: The processor performs the following processing: Corresponding to the one or more data read out and located at a given position in the data set, an answer is selected from one or more given answer solutions and the supplement is performed.

11. The enterprise evaluation processor system according to claim 9, wherein: The memory stores a given calculation formula having a plurality of input variables. The processor performs the following processing: A plurality of data located at given positions in the data set are extracted and used as the input variables, calculated using the calculation formula, and used to supplement the answers to the questionnaire.

12. The enterprise evaluation processor system according to claim 9, wherein: The memory stores a given calculation formula having a plurality of input variables. The processor performs the following processing: A plurality of data located at a given position in the data set is extracted and used as the input variable, and external data collected by crawler processing is used as the input variable, calculated by the calculation formula, and used to supplement the answers to the questionnaire.

13. The enterprise evaluation processor system according to claim 9, wherein: The data set is data delivered from the target enterprise or data delivered from a given computer of the target enterprise in every given period.

14. The enterprise evaluation processor system according to claim 9, wherein: The processor performs the following processing: Machine learning is performed using the presence or absence of corrections to the answers to the questionnaire and the corrected answer information to construct a learning model for each of the target companies. The learned model is used in a process of supplementing second questionnaire answers to a second questionnaire of the target enterprise different from the questionnaire in one or more of a survey period and a distribution source of the questionnaire.

15. The enterprise evaluation processor system according to claim 9, wherein: The processor performs the following processing: When the data set includes the data whose creation date is before the evaluation target period, an output is output to the effect that the data is insufficient as a proof document.

16. The enterprise evaluation processor system according to any one of claims 1, 7 or 9, wherein: At least one of the questions in the master data is a question about non-financial information related to management.

Images