Answer generation system, answer generation apparatus, and program

Abstract

To answer a question about ESG efficiently.SOLUTION: An answer generating system has one or more computers, and the computer has a reception means that accepts a question related to the evaluation of a user in ESG, an acquisition means that acquires disclosure information disclosed by the user in the past, and an answer generation means that automatically generates an answer to the question using the disclosure information acquired by the acquisition means.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an answer generation system, an answer generation apparatus, and a program.

Background Art

[0002] In recent years, globally, attention has been focused on the environment, society, and corporate governance. Enterprises are required to take measures considering ESG, which is an acronym formed from the initials of these terms. Additionally, third-party institutions (hereinafter referred to as "evaluation institutions") evaluate the efforts of enterprises considering ESG, and there is an ESG score as an indicator.

[0003] For example, in the ESG score, efforts by enterprises considering the environment, such as measures to address environmental problems like reducing carbon dioxide (CO2) emissions, improving water quality pollution caused by wastewater, and microplastics in the ocean, as well as using renewable energy and ensuring biodiversity, are evaluated. Also, in the ESG score, efforts by enterprises to improve the workability of employees belonging to the enterprise and address social human rights issues, such as proper labor conditions, human rights measures in the workplace like gender equality, diversity, work-life balance, child labor issues, and contributions to the local community, are evaluated. Furthermore, in the ESG score, the management system of enterprises, such as establishing a mechanism to avoid scandals directly linked to deteriorating performance, information disclosure for risk management and compliance with laws and regulations, and a high level of awareness regarding capital efficiency, is evaluated.

[0004] Moreover, many investors compare and consider investment targets with reference to the ESG score evaluated by evaluation institutions. Therefore, enterprises considering fundraising, etc., aim to improve their ESG score and respond to requests for answers from evaluation institutions as much as possible. Here, various technologies have been proposed as systems for evaluating and improving the efforts of corporate activities related to ESG (see, for example, Patent Document 1 and Patent Document 2).

Prior Art Documents

Patent Documents

[0005] Patent Document 1 Japanese Unexamined Patent Application Publication No. 2023-025783 Patent Document 2 Japanese Unexamined Patent Application Publication No. 2023-095083 Summary of the Invention Problems to be Solved by the Invention

[0006] By the way, there are multiple evaluation institutions that calculate ESG scores around the world, such as DJSI (The Dow Jones Sustainability Indices) and news agencies. It is very difficult to answer the requests for information disclosure through questionnaires from these evaluation institutions respectively because it takes time, labor, cost, etc. Moreover, a system for reducing the labor and the like for responding to this answering work has not been proposed yet as far as the applicant knows.

[0007] An object of the present invention is to provide a technology that enables efficient answering of questions related to ESG. Means for Solving the Problems

[0008] For this purpose, the technology disclosed in this specification is an answer generation system having one or more computers, wherein the computers include a reception means for receiving questions related to the evaluation of a user in ESG, an acquisition means for acquiring disclosure information disclosed by the user in the past, and an answer generation means for automatically generating an answer to the question using the disclosure information acquired by the acquisition means. The answer generation system is characterized by comprising these.

[0009] Here, the acquisition means may acquire, as the disclosure information, history information associating questions received by the user in the past with answers to the questions. In addition, when generating an answer to one of the questions, the answer generation means may use a plurality of the history information of the user as the disclosure information. Further, the history information may include information on questions in one evaluation institution that conducts ESG evaluations and answers to the questions, as well as questions in another evaluation institution different from the one evaluation institution and answers to the questions. Also, it is preferable to include an association means for associating the history information for each question, and the answer generation means may generate the answer using the history information associated by the association means. Also, the acquisition means may acquire the user's IR information as the disclosure information. Also, it is preferable to include a list display means for displaying a list of a plurality of the questions received by the reception means on a screen. Also, the list display means may display evaluation information regarding evaluation values in ESG for each of the questions in the list. Also, the list display means may display disclosure status information indicating whether or not the user has answered the question for each of the questions in the list. Also, the list display means may display answer non-generation information indicating that the question is a question for which the answer generation means cannot generate an answer for each of the questions in the list. Also, when the user answers the question or corrects the answer generated by the answer generation means, reference information that can be referred to by the user may be individually displayed for each of the questions. Also, the reference information may include explanatory information that is an explanation of the question. Also, the reference information may include the disclosure information for past questions related to the explanatory information.

[0010] Also, for such a purpose, the technology disclosed in this specification is an answer generation device comprising: a reception means for receiving questions related to the evaluation of a user in ESG; an acquisition means for acquiring disclosure information disclosed by the user in the past; and a transmission means for transmitting the questions and the disclosure information to an answer generation means for automatically generating an answer to the questions.

[0011] Also, for the purpose as described above, the technology disclosed in this specification is a program that causes a computer to execute a function of receiving questions related to the evaluation of a user in ESG, a function of acquiring disclosure information disclosed by the user in the past, and a function of transmitting the questions and the disclosure information to an answer generation means that automatically generates answers to the questions.

Advantages of the Invention

[0012] According to the present invention, it is possible to efficiently answer questions regarding ESG.

Brief Description of the Drawings

[0013]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Mode for Carrying Out the Invention

[0014] Hereinafter, as an example of this embodiment, it will be described that a user who has received questions regarding ESG (Environment, Society, Governance) from an evaluation institution automatically generates an answer using this system. Specifically, it will be described with reference to the drawings by taking as an example a user who has received questions regarding the CDP, an international environmental non-governmental organization (NGO), and automatically generates an answer using generative AI in this system.

[0015] The system of this embodiment is configured to automatically generate answers to questions from various evaluation institutions by using generative AI for natural language such as ChatGPT. For example, for answers to questions from evaluation institutions regarding ESG, a plurality of pieces of information regarding ESG that the user has already disclosed are used as a dataset. And since answers are generated using the user disclosure information (for example, an example of the disclosed information) that the user has already disclosed for questions from various evaluation institutions, correct answers can be generated. And in the system of this embodiment, by using generative AI such as ChatGPT, it is possible to reduce time, labor, cost, etc. and efficiently generate answers.

[0016] Note that the embodiments described below are preferred specific examples of this embodiment, and thus are technically subject to various limitations. However, the scope of the present invention is not limited to these embodiments unless otherwise specifically limited in the following description.

[0017] <System Configuration> FIG. 1 is a diagram showing a configuration example of an answer generation system according to the present embodiment.

[0018] As shown in FIG. 1, the answer generation system in the present embodiment includes an answer generation device 10 that automatically generates answers to questions from an evaluation institution, and a user terminal 30 used by a user who is requested to answer questions from the evaluation institution, which are interconnected via a predetermined network N such as the Internet.

[0019] The answer generation device 10 shown in FIG. 1 is a device that stores questions from various evaluation institutions and information related to ESG disclosed by the user, and generates answers to the questions. This answer generation device 10 has arithmetic processing functions and communication functions, and functions as a server in the answer generation system. The answer generation device 10 in the present embodiment is realized by an electronic device such as a personal computer. Therefore, in the following description, the answer generation device 10 may be referred to as a "server".

[0020] The user terminal 30 is a computer operated by a user who is requested to answer questions from an evaluation institution, and is a device having arithmetic processing functions and communication functions. This user terminal 30 is realized by, for example, a desktop or laptop computer, a tablet computer, a smartphone, or the like.

[0021] Also, the network N is constituted by the Internet, but is not particularly limited, and may be a communication network such as a LAN (Local Area Network) or a WAN (Wide Area Network). Also, the communication line of the network N may be wired or wireless, or a combination of these.

[0022] In the example of FIG. 1, only one user terminal 30 is shown, but the number thereof is not particularly limited. Also, although only one answer generation device 10 is shown, the answer generation device 10 is not limited to a device that operates alone, and may be a distributed server system that cooperates by communicating via the network N, or a cloud server. That is, the system of this embodiment can be configured by one or more computers.

[0023] <Hardware Configuration> FIG. 2 is a block diagram showing the hardware configuration of the answer generation device 10 according to this embodiment. The answer generation device 10 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an output unit 16, an input unit 17, a storage unit 18, and a communication unit 19.

[0024] The CPU 11 executes various processes according to a program stored in the ROM 12 or a program loaded from the storage unit 18 into the RAM 13. That is, the CPU 11 is a processor that controls the operation of the entire server 1 and executes various processes according to a program. The program is, for example, an operating system, firmware for operating each part of the server 1, or application software for realizing the functional blocks described later.

[0025] In the RAM 13, data and the like necessary for the CPU 11 to execute various processes are appropriately stored. The CPU 11, ROM 12, and RAM 13 are interconnected via the bus 14. The input / output interface 15 is also connected to this bus 14. Connected to the input / output interface 15 are an output unit 16, an input unit 17, a storage unit 18, and a communication unit 19.

[0026] The output unit 16 is composed of a display, a speaker, etc., and outputs various information as images and sounds. The input unit 17 is composed of a keyboard, a mouse, a microphone, a camera, etc., and inputs various types of information according to the received instruction operations. Note that, for example, the output unit 16 and the input unit 17 may be integrated using a touch panel.

[0027] The storage unit 18 stores various types of data necessary for the server 1 to execute information processing, and is composed of, for example, a hard disk, a DRAM (Dynamic Random Access Memory), etc. The communication unit 19 communicates with other devices via a network N including the Internet.

[0028] Note that the answer generation device 10 may be provided with a drive to which a removable medium made of a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, etc. is appropriately attached. With this drive, the program read from the removable medium can be installed in the storage unit 18. Also, the removable medium can store various types of data stored in the storage unit 18 in the same manner as the storage unit 18.

[0029] <Answer Generation Device 10> FIG. 3 is a block diagram for explaining a configuration example of the answer generation device 10 that functions as a server in the present embodiment. The answer generation device 10 (server) includes an answer generation unit 110 that generates an answer, an answer assistance unit 120 that assists in generating the answer, a question list generation unit 130 that generates a list of questions, and a question individual display generation unit 140 that performs an individual display for each question. Further, the answer generation device 10 includes a reference information display unit 150 that displays reference information, a user public information display unit 160 that displays user public information, and an answer reception unit 170 that receives an answer, and also has a question information DB 210 that manages question information, a user public information DB 220 that manages user public information, and a reference information DB 230 that manages reference information.

[0030] The answer generation unit 110 is a means having a function of automatically generating an answer to a question by using the user public information stored in the user public information DB 220. Then, the answer generation unit 110 transmits the generated answer information to the user terminal 30. For the answer generation unit 110 of the present embodiment, for example, a system that performs natural language processing using a large language model (LLM) can be applied. A large language model is a natural language processing model that is machine-learned using a large amount of text data. In a large language model, when a sentence is input, a sentence is output. When a large language model is applied to a system that performs question and answer, when a question sentence is input to the large language model, an answer sentence is output from the large language model.

[0031] The answer generation unit 110 automatically generates an answer by using, as one of the user public information, the question and answer history information stored in the question and answer history information DB 222. That is, the answer generation unit 110 of the present embodiment uses, as user public information, question and answer history information including questions and answers related to ESG received by the user from the same or different evaluation institutions in the past to automatically generate an answer to a question from the evaluation institution.

[0032] In this way, when generating an answer to a question from an evaluation institution, by using, as user public information, question and answer history information that associates and stores questions and answers received by the user from the same evaluation institution in the past, answers can be generated more efficiently. Also, by using, as user public information, question and answer history information (for example, an example of history information) that associates and stores similar questions and answers received by the user from other different evaluation institutions in the past, answers can be generated more efficiently.

[0033] In addition, the answer generation unit 110 automatically generates an answer using a plurality of questions and their answers as question-and-answer history information. That is, the answer generation unit 110 automatically generates an answer to a single question using a plurality of question-and-answer history information. For example, when generating an answer to a question, instead of using only one answer for one question, a plurality of sets are used with a set of a plurality of questions and their answers of the same evaluation institution or questions and their answers of different other evaluation institutions, etc., with the question and the answer to that question.

[0034] In this way, for a single question from an evaluation institution, instead of using one question and its answer that the user has received in the past from the same evaluation institution or a different other evaluation institution, by using a plurality of questions and their answers, it is possible to generate a more accurate answer considering from multiple perspectives.

[0035] In addition, the answer generation unit 110 automatically generates an answer using the user's IR information stored in the IR information DB 224 (described later) as one of the user public information. Examples of IR information include a securities report, an environmental report, a sustainability report, an integrated report, etc. In this way, the answer generation unit 110 of the present embodiment generates an answer more efficiently by using the user's IR information as user public information when generating an answer to a question from an evaluation institution.

[0036] In addition, the answer generation unit 110 automatically generates an answer using the question-and-answer history information and / or IR information associated by the answer assistance unit 120. That is, by associating in advance the question-and-answer history information and IR information used for generating an answer in the answer generation unit 110, it is possible to efficiently generate an answer to a question from an evaluation institution.

[0037] The answer assistance unit 120 is a means having a function of managing, for each question stored in the question information DB 210, by associating the question-and-answer history information stored in the user public information DB 220. Specifically, as one of the public information, the question and its answer included in the question-and-answer history information stored in the question-and-answer history information DB 222 (described later) are managed by associating them with each question stored in the question information DB 210.

[0038] At this time, the question and its answer included in the question-and-answer history information associated with each question may use not one question and its answer for the question as described above, but a plurality of questions and their answers.

[0039] That is, when using one question and its answer for the question, for example, if an association such as "For question X, use question 1.1a-1 of evaluation institution Q and its answer (Q1.1a-1 = A1.1a-1)" is made, in the answer creation work for question X, the question identified by Q1.1a-1 and the answer identified by A1.1a-1 will be used. In association with question X, the question 1.1a-1 of evaluation institution Q and its answer can be displayed, or an answer to question X can be automatically generated using this question and answer.

[0040] Also, when using multiple questions and their answers for a given question, for example, if an association such as "For question X, use question 1.1a-1 of evaluation institution Q and its answer (Q1.1a-1 = A1.1a-1), question 1.1a-2 of evaluation institution R and its answer (R1.1a-2 = A1.1a-2), and question 1.1a-3 of evaluation institution Z and its answer (Z1.1a-3 = A1.1a-3)" is made, then in the task of answering question X, the three questions and their answers, namely, the question identified by Q1.1a-1 and the answer identified by A1.1a-1, the question identified by R1.1a-2 and the answer identified by A1.1a-2, and the question identified by Z1.1a-3 and the answer identified by A1.1a-3, will be used. In association with question X, it is possible to display the question 1.1a-2 of evaluation institution R and its answer, the question 1.1a-2 of evaluation institution R and its answer, and the question 1.1a-3 of evaluation institution Z and its answer, or to automatically generate an answer to question X using these three questions and their answers.

[0041] In this way, by pre-associating appropriate user public information (for example, question-answer history information that associates and stores one question and its answer received by the user from the same evaluation institution or different other evaluation institutions in the past) for generating answers to questions from evaluation institutions, errors in the selection of information to be used can be avoided, the answer accuracy can be improved, and answers can be generated efficiently.

[0042] Also, the answer assistance unit 120 is a means having a function of associating and managing, for each question stored in the question information DB 210, the IR information stored in the IR information DB 224 together with or in place of the question-answer history information stored in the user public information DB 220.

[0043] That is, when managing by associating IR information with the relevant question, for example, if an association such as "for question X, use the item AAA in the securities report as IR information" is made, in the work of answering question X, the item AAA in the securities report will be used, and the item AAA in the securities report can be displayed in association with question X, or an answer to question X can be automatically generated using the item AAA in the securities report.

[0044] In this way, by pre-associating IR information in addition to the question-and-answer history information as the user public information used when generating an answer to a question from the evaluation institution, more appropriate user public information can be used to improve the answer accuracy and efficiently generate an answer.

[0045] The question list generation unit 130 is a means having a function of generating question display information for list-displaying the question information stored in the question information DB 210 on the user terminal 30, and presenting the generated question display information to the user terminal 30. In this way, by list-displaying the questions from the evaluation institution, the user can visually and easily grasp the questions at a glance and efficiently and appropriately perform the answering work.

[0046] When score information indicating the evaluation value given to the answer to the question is stored for the question stored in the question information DB 210, the question list generation unit 130 generates question display information for list-displaying the score information (for example, an example of evaluation information) associated with the question together with the question information. In this way, by displaying the score for the answer in association with the question from the evaluation institution displayed in the list, the evaluation value for the answer can be visually grasped. In the case of questions related to ESG, the answering motivation can be improved to improve the ESG score, and the answering order can be prioritized to efficiently and appropriately perform the answering work.

[0047] When there is disclosure status information indicating the presence or absence of an answer to a question stored in the question information DB 210 for a question stored in the question list generation unit 130, the question display information is generated to list and display the disclosure status information associated with the question together with the question information in a visually recognizable state. In this way, by displaying the disclosure status in association with the questions from the evaluation institutions listed, it is possible to visually and easily grasp at a glance whether there is an answer, eliminate answer omissions, and efficiently and appropriately perform the answering work. In addition, the disclosure status information is shown only in words such as "answered / unanswered", and by changing the color or size of the characters for "answered / unanswered", the disclosure status information can be made even easier to grasp visually.

[0048] When there is answer non-generation information stored in the question information DB 210 indicating that the answer generation unit 110 cannot automatically generate an answer for a question stored in the question list generation unit 130, the question display information is generated to list and display the answer non-generation information associated with the question together with the question information in a visually recognizable state. That is, in the list display, the question list generation unit 130 uses the answer non-generation information to indicate that the question is one for which the answer generation unit 110 cannot generate an answer. In this way, by displaying the answer non-generation information in association with the questions from the evaluation institutions listed, it is possible to visually and easily grasp at a glance that the answer could not be automatically generated, eliminate answer omissions, and efficiently and appropriately perform the answering work. This answer non-generation information may be text, or may be a figure or symbol such as a star mark or a bullet mark.

[0049] The question individual display generation unit 140 is a means having a function of generating question individual display information for individually displaying the questions stored in the question information DB 210 on the user terminal 30, and presenting the generated question individual display information to the user terminal 30.

[0050] In addition, when there is framework information related to a question stored in the question information DB 210 for the question to be stored in the question information DB 210, the individual question display generation unit 140 generates individual question display information including the predetermined framework information associated with the question stored in the reference information DB 230, and presents the generated individual question display information to the user terminal 30. This framework information is an explanation of the purport of the question using the explanations of other evaluation institutions so that there are no errors in the answer. In this way, for each question from the evaluation institution, by displaying the framework information disclosed by other evaluation institutions for reference, the understanding of the purport of the question can be further deepened, and it can be ensured that there are no errors in the answer.

[0051] When there is reference information (for example, an example of reference information) related to a question stored in the question information DB 210 for the question stored in the question information DB 210, the reference information display unit 150 is a means having a function of receiving an instruction to display the predetermined reference information associated with the question stored in the reference information DB 230 and causing the user terminal 30 to display it together with the individual question display information displayed on the user terminal 30. That is, the reference information display unit 150 is a means having a function of receiving an instruction to display information that helps in understanding the question and causing the user terminal 30 to display it together with the individual question display information displayed on the user terminal 30. Examples of this reference information can include term explanation information (for example, an example of explanation information) that explains terms.

[0052] In this way, by displaying reference information for each question from the evaluation institution, when the user refers to the reference information, for example, the understanding of the question becomes easier. And when the user creates an answer by himself or herself or modifies the automatically generated answer, the work is assisted and the user can answer appropriately.

[0053] The user public information display unit 160 is a means having a function of receiving an instruction to display user public information (for example, an example of disclosed information) for past questions related to the framework information and causing the user terminal 30 to display it together with the question individual display information displayed on the user terminal 30. That is, the user public information for past questions related to the framework information is, for example, questions of other evaluation institutions similar to the said question and the user's answers thereto, and by using the question and answer history information that associates similar questions and their answers received by the user in the past and stores them in the user public information DB 220 (question and answer history information DB 222 described later), it is possible to display the user public information related to the framework information.

[0054] In this way, by providing, for example, a selection button or the like for displaying relevant user public information for each piece of framework information displayed in response to a question from an evaluation institution, the understanding of the question can be further deepened. Note that, as the user public information, in addition to similar questions and their answers received by the user in the past, the full text of the user public information related to ESG related to the said question (disclosed information in ESG) may be displayed.

[0055] The answer reception unit 170 is a means for registering the answer information automatically generated by the answer generation unit 110 or the answer information created by the user himself / herself in the question information DB 210 in association with the question.

[0056] The question information DB 210 is a means for storing questions from evaluation institutions. The latest question information is stored in this question information DB 210. Also, the question information DB 210 is also a means for storing questions from various evaluation institutions for each evaluation institution. That is, it stores questions from multiple evaluation institutions instead of just questions from a single evaluation institution.

[0057] In this question information DB210, before disclosure to the evaluation institution (during the answering process), for each question, the question and its answer, including the answer to the question, are stored in an associated manner. However, after disclosure to the evaluation institution, the newly disclosed questions become the question information stored in the question information DB210, and the previous questions and their answers become the question and answer history information stored in the question and answer history information DB222 as user-public information.

[0058] In addition, the question information DB210 stores, for each question, score information indicating the evaluation value assigned to the answer to the question in an associated manner. In addition, the question information DB210 stores, for each question, disclosure status information indicating the presence or absence of an answer to the question in an associated manner. In addition, the question information DB210 stores, for each question, answer non-generation information indicating that the answer generation unit 110 was unable to automatically generate an answer in an associated manner.

[0059] In addition, the question information DB210 stores, for each question, association information with reference information related to the question. That is, the question information DB210 stores, for each question, association information that enables extraction of the reference information stored in the reference information DB230. The association of reference information with this question may be performed not on the database (DB) but on the program.

[0060] Furthermore, the question information DB210 stores, for each question, association information with framework information related to the question (for example, an example of explanatory information). That is, the question information DB210 stores, for each question, association information that enables extraction of the framework information stored in the reference information DB230. Also, the association with the framework information related to the question may be performed not on the database (DB) but on the program.

[0061] The user disclosure information DB 220 is a means for storing, for each user, the user disclosure information disclosed by the user. In this embodiment, the user disclosure information DB 220 includes a question-and-answer history information DB 222 and an IR information DB 224.

[0062] The question-and-answer history information DB 222 is a means for storing, as one of the user disclosure information, the questions received by the user in the past and their answers in association with each other. The questions received by the user in the past and their answers are not limited to those of the same evaluation institution for which the user requests an answer using this system, but include questions and their answers of different other evaluation institutions. That is, not only the past questions and their answers in the same evaluation institution for which the user has requested an answer using this system are stored, but also the past questions and their answers in a plurality of other evaluation institutions for which the user has requested an answer using this system are stored.

[0063] In addition, the questions and their answers stored in the question-and-answer history information DB 222 may be not only for a single year, but also for multiple years in a plurality of evaluation institutions. Therefore, the question-and-answer history information DB 222 is composed of a plurality of information groups that store, as one of the user disclosure information, the question-and-answer history information disclosed by the user for each of various evaluation institutions.

[0064] Note that the question-and-answer history information DB 222 may manage the past question-and-answer history information disclosed by the user in a summary manner for each user, or may manage it separately for each evaluation institution or each disclosed year.

[0065] The IR information DB 224 is a means for storing, as one of the user disclosure information, the IR information of the user. This IR (Investor Relations) information is information regarding the business situation, financial situation, and performance trends disclosed by the company as the user to investors, and for example, as described above, refers to a securities report, an environmental report, a sustainability report, an integrated report, etc. Therefore, in the IR information DB 224, the IR information disclosed by the user is stored for each user as one of the user disclosure information.

[0066] Note that the IR information DB 224 may manage the IR information such as the aforementioned securities reports, environmental reports, sustainability reports, integrated reports, etc., either by aggregating them for each user or by managing them separately for each piece of information.

[0067] The reference information DB 230 is a means for storing reference information related to the creation of answers to questions or the correction of automatically generated answers. Examples of reference information include glossary information for explaining terms included in questions and framework information related to questions. The reference information DB 230 may manage the glossary information and framework information together for each question stored in the question information DB 210, or may manage them separately in a glossary information DB and a framework information DB.

[0068] Next, the basic processing flow in the answer generation system according to the present embodiment will be described. FIG. 4 is a sequence diagram showing an example of the answer generation process according to the present embodiment.

[0069] In step S301, prior to providing services to the user, the answer generation device 10 registers the latest questions from the evaluation institution in the question information DB 210 for each evaluation institution. Also, in step S302, prior to providing services to the user, the answer generation device 10 registers the user disclosure information already disclosed by the user in the user disclosure information DB 220. More specifically, the answer generation device 10 registers it in the question-answer history information DB 222 and the IR information DB 224. The registration of this user disclosure information in the user disclosure information DB 220 may be performed upon receiving the provision of user disclosure information from the user, or may be performed by acquiring the user disclosure information via the network N.

[0070] In addition, if the user has disclosed answers to the evaluation institution in the past using this system, the question-and-answer history information is registered in the user public information DB220 (question-and-answer history information DB222) as having received the provision of user public information (i.e., question-and-answer history information) from the user.

[0071] When the above-mentioned preliminary preparations are completed, the provision of the answer generation service by this system is implemented, and the user can enjoy the service. In order to receive this service, the user first accesses the answer generation device 10 using the user terminal 30 and completes the login.

[0072] Then, in step S303, the user terminal 30 receives an instruction to request (select) the display of questions and transmits the request to the answer generation device 10. In this embodiment, a request for a question list that displays all questions in a list format is transmitted to the answer generation device 10. In step S304, the answer generation device 10 generates question display information that displays all questions in a list format in response to the request for the question list from the user terminal 30, and transmits the generated question display information to the user terminal 30. At this time, if score information, disclosure status information, answer non-generation information, etc. are stored in association with the question information, question display information including this information is generated.

[0073] In step S305, the user terminal 30 displays the question display information transmitted from the answer generation device 10 on the display screen (monitor), receives an instruction to select (click) one question to answer, and transmits the instruction to the answer generation device 10. In step S306, the answer generation device 10 generates question individual display information that individually displays only the selected question in response to the selection of the question on the user terminal 30, and transmits the generated question individual display information to the user terminal 30. At this time, if framework information is stored in association with the question information, question individual display information including this information is generated.

[0074] In step S307, when the user terminal 30 displays the question display information transmitted from the answer generation device 10 on the display screen (monitor) and receives an instruction to automatically generate an answer to the question, it transmits that request to the answer generation device 10. Note that the user terminal 30 can also receive an input of answer information that the user answers by themselves. In step S308, in response to the request for automatic generation of an answer on the user terminal 30, the answer generation device 10 automatically generates an answer to the question using the user public information, and transmits the generated answer information to the user terminal 30.

[0075] In step S309, the user terminal 30 displays the answer information transmitted from the answer generation device 10 on the display screen (monitor), receives an instruction to answer (disclose) with this content, and transmits that instruction to the answer generation device 10. In step S310, in response to the answer (disclosure) instruction on the user terminal 30, the answer generation device 10 registers the answer information generated by the answer generation device 10 (automatically generated) or the answer information input by the user himself / herself in association with the question in the question information DB210.

[0076] If continuing the answer work for the question, steps S305 to S310 are repeated. Also, after temporarily ending the answer work and performing the answer work again, access and log in to the answer generation device 10 again, and repeat steps S303 to S310.

[0077] Next, the detailed answer generation process flow in the answer generation device 10 will be described. FIG. 5 is a flowchart showing an example of the basic operation of the answer generation process according to this embodiment.

[0078] As shown in FIG. 5, in step S401, the question list generation unit 130 performs a process of determining whether it has received (accepted) a question list request for displaying questions in a list format. If the question list generation unit 130 has received the question list request (YES in S401), the process proceeds to step S402; otherwise (NO in S401), the determination in step S401 is repeated.

[0079] In step S402, the question list generation unit 130 performs a process of generating question display information for displaying all questions in a list format based on the question information DB 210. Also, in step S403, the question list generation unit 130 performs a process of transmitting the generated question display information to the user terminal 30 that has made the request.

[0080] Also, in step S404, the individual question display generation unit 140 performs a process of determining whether it has received (accepted) question selection information for selecting a question to answer. If the individual question display generation unit 140 has received the question selection information (YES in S404), the process proceeds to step S405; otherwise (NO in S404), the determination in step S404 is repeated.

[0081] In step S405, the individual question display generation unit 140 performs a process of generating individual question display information for individually displaying only the selected question. Also, in step S406, the individual question display generation unit 140 performs a process of transmitting the generated individual question display information to the user terminal 30 as instructed.

[0082] Subsequently, in step S407, the answer generation unit 110 performs a process of determining whether it has received (accepted) an instruction (answer generation request) to automatically generate an answer to the question. If the answer generation unit 110 has received the answer generation request (YES in S407), the process proceeds to step S408; otherwise (when receiving the input of answer information for the user to answer by themselves) (NO in S407), the process proceeds to step S410.

[0083] In step S408, the answer generation unit 110 performs a process of automatically generating an answer to the question using the user public information stored in the user public information DB 220. That is, the answer generation unit 110 automatically generates an answer to the question using the question-answer history information stored in the question-answer history information DB 222 and the IR information (for example, securities reports, environmental reports, sustainability reports, integrated reports) stored in the IR information DB 224.

[0084] At this time, when the answer assistance unit 120 manages the association between the question and the user public information (that is, the question-answer history information and the IR information), the answer generation unit 110 efficiently performs a process of automatically generating an answer to the question using the user public information associated by the answer assistance unit 120. Also, in step S409, the answer generation unit 110 performs a process of transmitting the generated answer information to the requested user terminal 30.

[0085] In step S410, the answer reception unit 170 performs a process of determining whether an instruction (answer disclosure request) to request the disclosure of the answer has been received. If the answer reception unit 170 has received the answer disclosure request (YES in S410), the process proceeds to step S411. Otherwise (NO in S410), the determination in step S410 is repeated.

[0086] In step S411, the answer reception unit 170 performs a process of determining whether the answer information has been received. If the answer reception unit 170 has received the answer information (YES in S411), the process proceeds to step S412. Otherwise (NO in S411), the determination in step S407 is repeated. That is, a process of determining whether the input of the answer information automatically generated by the answer generation unit 110 or the answer information created by the user himself / herself has been received is performed. Therefore, if the answer disclosure request is received without receiving the input of the answer information by any method, the process returns to step S407 and the determination of whether the answer generation request has been received is repeated.

[0087] Then, in step S412, the response reception unit 170 performs a process of registering the response information generated by the response generation unit 110 or the response information created by the user himself / herself in association with the question in the question information DB 210. After that, the operation of the response generation device 10 ends (END).

[0088] Here, the method of confirming the question display information generated in step S402 can be shown, for example, in FIG. 6. FIG. 6 is a schematic diagram showing an example of the configuration of a question list screen 300 displayed on the user terminal 30 that displays all questions in a list format.

[0089] In FIG. 6, on this question list screen 300, there are a disclosure No column 301 showing the question number, a score column 302 showing the evaluation value given to the answer to the question, a disclosure status column 303 showing the presence or absence of an answer to the question, a question column 304 showing the content of the question, a difference column 305 from last year showing the presence or absence of changes to the previous question, a response non-generation information 306 indicating that the response cannot be automatically generated, and a "disclosure" button 307 for individually displaying the question.

[0090] Specifically, on the question list screen 300 shown in FIG. 6, five questions shown as "C1.1", "C1.1a", "C1.1b", "C1.1c", and "C1.1d" are listed vertically as part of the questions in the disclosure No column 301.

[0091] Also, in the score column 302, the question with a disclosure No of C1.1 is given a score of "2", the question with a disclosure No of C1.1a is given a score of "5", the question with a disclosure No of C1.1b is given a score of "7", the question with a disclosure No of C1.1c is given a score of "9", and the question with a disclosure No of C1.1d is given a score of "5".

[0092] In addition, in the disclosure status column 303, characters such as "Disclosed" indicating that the answer to the question has been completed or "Not Disclosed" indicating that the answer to the question has not been completed are displayed within the icon image. At this time, in order to visually emphasize that the answer to the question has not been completed, the character "Not Disclosed" is displayed larger than the character "Disclosed", and the size of the horizontally elongated ellipse surrounding the character is also larger, and the color inside the horizontally elongated ellipse may be shown to be different between "Disclosed" and "Not Disclosed".

[0093] In addition, in the question column 304, for example, as a question with a disclosure No. of C1.1, "Is there board-level supervision for climate-related issues within the organization?", as a question with a disclosure No. of C1.1a, "Identify the position", as a question with a disclosure No. of C1.1b, "Please provide more details about the board's supervision of climate-related issues."... and other such contents are displayed.

[0094] In addition, in the difference column 305, characters such as "None" are shown. The difference column 305 is a column that indicates whether there are differences in the content of the questions and the answers, for example, in different years. Furthermore, as the answer non-generation information 306, for a question with a disclosure No. of C1.1a, a star-shaped figure is shown between the difference column 305 and the "Disclose" button 307.

[0095] In addition, the method of checking the question individual display information generated in step S405 can be shown, for example, in FIG. 7. FIG. 7 is a schematic diagram showing an example of the configuration of the question individual display screen 310 displayed on the user terminal 30 after the "Disclose" button 307 is selected (clicked) on the question list screen 300.

[0096] In Fig. 7, on this individual question display screen 310, there are a heading column 311 that simply shows the disclosure No. of the question and its disclosure status in association with each other, a question display column 312 that individually shows the content of the question together with its English translation, a simple answer column 313 for selectively answering the question with "Yes / No", an answer input column 314 for entering the content of the answer in detail, a "Generate Answer Automatically" button 315 that requests to automatically generate an answer, an "Update" button 316 that instructs the disclosure (registration) of the answer, and a "Disclosure Hint" button 317 that requests the display of reference information are displayed.

[0097] When answering the question displayed in the question display column 312 on the individual question display screen 310 shown in Fig. 7, if you want to answer automatically, select (click) the "Generate Answer Automatically" button 315. On the other hand, if the user himself / herself wants to answer, by clicking on the simple answer column 313, a "Yes / No" pull-down menu will be displayed, so select any one of the desired answers and directly enter the answer in the answer input column 314. In addition, when the "Generate Answer Automatically" button 315 is selected, a message "AI is generating an answer..." will be displayed on the screen until the answer shown in Fig. 8 described later is displayed.

[0098] Also, a method for confirming the answer automatically generated in step S408 can be shown in Fig. 8, for example. Fig. 8 is a schematic diagram showing an example of the configuration of an answer display screen 320 displayed on the user terminal 30 after selecting (clicking) the "Generate Answer Automatically" button 315 on the individual question display screen 310.

[0099] In Fig. 8, an answer of "Yes" is automatically entered in the simple answer column 313 of this answer display screen 320, and an answer such as "With the existence of the CSO and the utilization of the ESG promotion department and the AAA system, supervision at the board of directors level is being carried out." is automatically generated and shown as having been entered in the answer input column 314. Further, when it is not desired to automatically generate an answer in step S407 and the user answers by himself / herself, the framework information shown in FIG. 9 can be referred to.

[0100] FIG. 9 is a schematic diagram showing an example of the configuration of framework information displayed by scrolling the question display screen 310 shown in FIG. 7 downward. In FIG. 9, on the question display screen 310, together with the framework information display column 318, a "View Disclosure Information" button 319 is shown which requires displaying the user's answers to questions of other evaluation institutions similar to the said question.

[0101] Next, as a secondary process in the answer generation system according to the present embodiment, the flow when displaying reference information to assist in understanding the gist of the question and inputting the answer will be described based on FIGS. 10 and 11. Both FIGS. 10 and 11 are sequence diagrams showing an example of the reference information display process according to the present embodiment.

[0102] In step S501, when the user terminal 30 receives an instruction from the user to request the display of reference information for disclosure (answer), it transmits that request to the answer generation device 10. That is, after displaying the question display information on the display screen (monitor) of the user terminal 30 in step S307 described above, without immediately requesting automatic answer generation, it requests the answer generation device 10 to disclose the reference information for answering the said question.

[0103] In step S502, the answer generation device 10 transmits the term explanation information included in the said question as reference information to the user terminal 30 in response to the request for disclosure of reference information from the user terminal 30. And in step S503, the user terminal 30 displays the term explanation information transmitted from the answer generation device 10 on the display screen (monitor). Therefore, the user refers to the term explanation information to understand the said question and makes a judgment on whether to answer by himself / herself or to automatically generate an answer (whether to execute step S307).

[0104] Also, in step S601, when the user terminal 30 receives an instruction from the user to request past disclosure information, it transmits the request to the answer generation device 10. That is, after the question individual display information is displayed on the display screen (monitor) of the user terminal 30 in step S307 described above, instead of immediately requesting automatic generation of an answer, the user terminal 30 requests the answer generation device 10 for past disclosure information related to the question.

[0105] In step S602, the answer generation device 10 transmits user public information related to ESG (ESG disclosure information) related to the question to the user terminal 30 as reference information in response to the disclosure request from the user terminal 30. And in step S603, the user terminal 30 displays the ESG disclosure information transmitted from the answer generation device 10 on the display screen (monitor). Therefore, the user understands the purport of the question with reference to the ESG disclosure information, checks the past disclosure information, and determines whether to answer by oneself or generate automatically (whether to execute step S307).

[0106] Next, the flow of secondary processing in the answer generation device 10 will be described. FIG. 12 is a flowchart showing an example of secondary operations of the answer generation process according to the present embodiment.

[0107] As shown in FIG. 12, in step S701, the reference information display unit 150 performs a process of determining whether it has received (received) a reference display request to display reference information related to the question. When the reference information display unit 150 has received the reference display request (YES in S701), the process proceeds to step S702, and when not (NO in S701), the process proceeds to step S801. In step S702, the reference information display unit 150 performs a process of transmitting the reference information related to the question to the user terminal 30 that has made the request. After that, the operation of the answer generation device 10 ends (END).

[0108] Also, in step S801, the user disclosure information display unit 160 performs a process of determining whether or not it has received (accepted) a disclosure information request to display past disclosure information related to the question. If the user disclosure information display unit 160 has received the disclosure information request (YES in S801), the process proceeds to step S802; otherwise (NO in S801), the operation of the answer generation device 10 ends (END). In step S802, the user disclosure information display unit 160 performs a process of transmitting, as disclosure information, past user disclosure information related to ESG related to the question to the user terminal 30 that has made the request.

[0109] Here, the method of checking the reference information transmitted in step S702 can be shown, for example, in FIG. 13. FIG. 13 is a schematic diagram showing an example of the configuration of a reference information display screen 330 displayed on the user terminal 30 after selecting (clicking) the "Disclosure Hint" button 317 on the question individual display screen 310 shown in FIG. 7.

[0110] In FIG. 13, the reference information display screen 330 is displayed so as to overlap the question individual display screen 310, and this reference information display screen 330 is provided with a term explanation display column 321 for explaining terms as reference information.

[0111] Also, the method of checking the disclosure information transmitted in step S802 can be shown, for example, in FIG. 14. FIG. 14 is a schematic diagram showing an example of the configuration of an ESG disclosure information display screen 340 displayed on the user terminal 30 after selecting (clicking) the "View Disclosure Information" button 319 provided in relation to the framework information shown in FIG. 9, which is displayed by scrolling down on the question individual display screen 310.

[0112] In FIG. 14, on the ESG disclosure information display screen 340, an ESG disclosure information display column 331 is provided following the framework information. In this ESG disclosure information display column 331, information related to ESG to assist in understanding the purport of the question, the user's answers to past ESG-related questions similar to the question, etc. are displayed, and past disclosure information related to ESG can be confirmed.

[0113] Note that the "View Disclosure Information" button 319 selected (clicked) when confirming the disclosure information is changed to the "Close Disclosure Information" button 339 on the ESG disclosure information display screen 340 where the ESG disclosure information display column 331 is provided. Therefore, by selecting (clicking) the "Close Disclosure Information" button 339, as shown in FIG. 9, it returns to the question individual display screen 310 where the framework information is displayed.

[0114] As described above, according to this embodiment, for ESG-related questions from various evaluation institutions, an answer text is automatically generated based on various ESG-related information disclosed by the user. Therefore, time, labor, cost, etc. can be reduced, and an answer can be automatically generated efficiently. Moreover, since the various information used for generating the answer is disclosed by the user himself / herself, an error-free and consistent answer can be generated as a whole.

[0115] In addition, since the answer generated using this system ultimately becomes one of the user's public information, the more the system is used to answer questions, the more the user's public information will be accumulated. For questions from other evaluation institutions or questions from the same evaluation institution in the following year, accurate answers can be generated efficiently.

[0116] Note that the above series of processes are merely illustrative and not particularly limited. Therefore, they can be executed by hardware or implemented by software. That is, it suffices that the information processing system is equipped with the function to execute the above series of processes as a whole, and the specific functional blocks used to realize this function are not particularly limited to the above examples.

[0117] Also, in the system configuration example of this embodiment, the answer generation device 10 is provided with, for example, an answer generation unit 110, but it is not limited to this mode. The answer generation unit 110 may be provided in a server device external to the answer generation device 10. In this case, the answer generation device 10 may transmit a question and user public information (an example of disclosure information) to the server device equipped with the answer generation unit 110 and acquire the answer generated by the server device.

[0118] As described above, in the system of this embodiment, since the answer text is automatically generated based on various information of the user disclosed by the user, it is expected to be applied not only to answering questions related to ESG but also to automatically generating appropriate answers for various questions.

[0119] Here, the answer generation device 10 is an example of an answer generation device. The answer generation unit 110 is an example of reception means and answer generation means. The answer assistance unit 120, the question information DB 210, and the user public information DB 220 are examples of acquisition means and related means. The question list generation unit 130 is an example of list display means.

[0120] The above is the description of this embodiment. However, the above-described embodiment is merely an example for facilitating the understanding of the present invention and is not for limiting the interpretation of the present invention. Also, the present invention is not limited to the above-described embodiment, and modifications, improvements, etc. within the scope that can achieve the object of the present invention are included in the present invention.

Explanation of Reference Numerals

[0121] 10... Answer generation device (server), 30... User terminal, 110... Answer generation unit, 120... Answer assistance unit, 130... Question list generation unit, 140... Individual question display generation unit, 150... Reference information display unit, 160... User public information display unit, 170... Answer reception unit, 210... Question information DB, 220... User public information DB, 222... Question and answer history information DB, 224... IR information DB, 230... Reference information DB

Claims

1. An answer generation system having one or more computers, wherein the computer includes reception means for receiving a question related to a user's evaluation in ESG; acquisition means for acquiring disclosure information disclosed by the user in the past; answer generation means for automatically generating an answer to the question using a large language model based on the disclosure information acquired by the acquisition means; and the acquisition means acquires, as the disclosure information, history information associating questions received by the user in the past with answers to the questions, and also acquires the user's IR information as the disclosure information; when the answer generation means inputs the question to the large language model, the answer generation means generates an answer to the question using the disclosure information; An answer generation system characterized by the above.

2. The answer generation system according to claim 1, wherein the answer generation means uses a plurality of the history information of the user as the disclosure information when generating an answer to one question.

3. The history information includes information on questions and answers to the questions in one evaluation institution that conducts ESG evaluations, and questions and answers to the questions in another evaluation institution different from the one evaluation institution. The answer generation system according to claim 2, characterized by this.

4. It is provided with association means for associating the history information for each question, The answer generation system according to any one of claims 1 to 3, wherein the answer generation means generates the answer using the history information associated by the association means.

5. The answer generation system according to claim 1, further comprising list display means for displaying a list of the plurality of questions received by the reception means on a screen.

6. The answer generation system according to claim 5, wherein the list display means displays evaluation information regarding an evaluation value in ESG for each question in the list.

7. The answer generation system according to claim 5, wherein the list display means displays disclosure status information indicating the presence or absence of the user's answer to the question for each question in the list.

8. The list display means displays, for each question, answer non-generation information indicating that the question is a question for which the answer generation means cannot generate an answer, in the list. The answer generation system according to claim 5, characterized in that.

9. When the user answers the question or corrects the answer generated by the answer generation means, reference information that can be referred to by the user is individually displayed for each question. The answer generation system according to claim 1, characterized in that.

10. The reference information includes explanatory information that is an explanation of the question. The answer generation system according to claim 9, characterized in that.

11. The reference information includes the disclosure information for past questions related to the explanatory information. The answer generation system according to claim 10, characterized in that.

12. A reception means for receiving questions related to the evaluation of the user in ESG, An acquisition means for acquiring the disclosure information disclosed by the user in the past, A transmission means for transmitting the question and the disclosure information to an answer generation means that automatically generates an answer to the question using a large language model based on the disclosure information acquired by the acquisition means, Comprising The acquisition means acquires, as the disclosure information, history information associating the questions received by the user in the past with the answers to the questions, and also acquires the user's IR information as the disclosure information, The answer generation means generates an answer to the question using the disclosure information when the question is input to the large language model. An answer generation device, characterized in that.

13. On a computer, A function of receiving questions related to the evaluation of the user in ESG, A function of acquiring the disclosure information disclosed by the user in the past, A function of transmitting the question and the disclosure information to an answer generation means that automatically generates an answer to the question using a large language model based on the acquired disclosure information, A program for executing, The history information associating the questions received by the user in the past with the answers to the questions is acquired as the disclosure information, and the user's IR information is acquired as the disclosure information, The answer generation means generates an answer to the question using the disclosure information when the question is input to the large language model. A program.

Images