Program, method, information processing device, and system

Abstract

To solve the problem in which it is unable to provide appropriate answers to questions related to laws from users.SOLUTION: In a program to be executed on a computer having a processor and a storage unit, the program executes: a question receiving step in which the processor receives a question from a user; a document retrieval step for, based on the question received in the question receiving step, retrieving one or more documents that describe legal opinions that can be used as a reference when answering the question; and a generation step for generating a prompt based on the question received in the question receiving step and the one or more documents retrieved in the document retrieval step.SELECTED DRAWING: Figure 8

Description

[Technical field]

[0001] The present disclosure relates to a program, a method, an information processing device, and a system. [Background technology]

[0002] 2. Description of the Related Art Web services that provide legal case studies on a website are known. Patent Document 1 discloses a law search system that enables users to search for desired provisions or court cases even if they do not know legal search keywords, enables users to easily and quickly search from combinations of verbs and objects, and further enables users to obtain desired results by sequentially selecting from appropriate options. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2002-140339 A Summary of the Invention [Problem to be solved by the invention]

[0004] There is a problem in that appropriate answers cannot be provided to legal questions from users. Therefore, the present disclosure has been made to solve the above problem, and its purpose is to provide appropriate answers to legal questions from users. [Means for solving the problem]

[0005] A program to be executed by a computer having a processor and a memory unit, the program comprising: a question receiving step in which the processor receives a question from a user; a document search step in which, based on the question received in the question receiving step, the processor searches for one or more documents that contain legal opinions that can be used as reference when answering the question; and a generation step in which the processor generates a prompt based on the question received in the question receiving step and the one or more documents searched for in the document search step. Effect of the Invention

[0006] According to the present disclosure, appropriate answers can be provided to users' legal questions. [Brief description of the drawings]

[0007] [Figure 1] FIG. 2 is a block diagram showing the functional configuration of the system 1. [Diagram 2] FIG. 2 is a block diagram showing the functional configuration of the server 10. [Diagram 3] 2 is a block diagram showing the functional configuration of a user terminal 20. FIG. [Figure 4] FIG. 13 is a diagram showing the data structure of a user table 1012. [Diagram 5] FIG. 13 is a diagram showing the data structure of a document table 1013. [Figure 6] FIG. 13 is a diagram showing the data structure of a question table 1014. [Figure 7] 13 is a flowchart showing the operation of a report presentation process. [Figure 8] 13 is a screen example of a question screen showing the operation of a report presentation process. [Figure 9] 13 is a screen example of a report presentation screen showing the operation of a report presentation process. [Figure 10] FIG. 2 is a block diagram showing the basic hardware configuration of a computer 90. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings. In all the drawings explaining the embodiment, the same reference numerals are given to common components, and repeated explanations are omitted. Note that the following embodiment does not unduly limit the contents of the present disclosure described in the claims. In addition, not all of the components shown in the embodiment are essential components of the present disclosure. In addition, each figure is a schematic diagram and is not necessarily illustrated strictly.

[0009] <System 1 Configuration> System 1 in this disclosure is an information processing system that outputs answers to legal questions. The system 1 includes an information processing device including a server 10, a user terminal 20, and a generating AI 50, which are connected via a network N. FIG. 1 is a block diagram showing the functional configuration of the system 1. FIG. 2 is a block diagram showing the functional configuration of the server 10. As shown in FIG. FIG. 3 is a block diagram showing the functional configuration of the user terminal 20. As shown in FIG.

[0010] Each information processing device is composed of a computer equipped with a calculation device and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the server 10, the user terminal 20, and the generation AI 50, the description overlapping with the basic hardware configuration and the basic functional configuration of the computer described later will be omitted.

[0011] <Server 10 Configuration> The server 10 is an information processing device that provides an information processing service that outputs answers to questions about the law. The server 10 includes a storage unit 101 and a control unit 104 .

[0012] <Configuration of the storage unit 101 of the server 10> The storage unit 101 of the server 10 includes an application program 1011 , a user table 1012 , a document table 1013 , and a question table 1014 .

[0013] The application program 1011 is a program for causing the control unit 104 of the server 10 to function as each functional unit. Application programs 1011 include applications such as a web browser application.

[0014] User table 1012 is a table that stores and manages information about member users (hereinafter, users) who use the service. When a user registers to use the service, the user's information is stored in a new record in user table 1012. This allows the user to use the service according to the present disclosure. The user table 1012 is a table having columns of user ID and user name, with the user ID as the primary key. FIG. 4 is a diagram showing the data structure of the user table 1012. As shown in FIG.

[0015] The user ID is an item for storing user identification information for identifying a user. The user identification information is an item for which a unique value is set for each user. The user name is an item for storing the name of the user. The user name may be set to any character string such as a nickname instead of a name.

[0016] The document table 1013 is a table for storing and managing information relating to documents (document information). The document table 1013 is a table having a document ID as a primary key, and columns of document ID, document type, document data, related document ID, and importance. FIG. 5 is a diagram showing the data structure of the document table 1013. As shown in FIG.

[0017] The document ID is an item for storing document identification information for identifying a document. The document identification information is an item for which a unique value is set for each piece of document information. The document type stores information related to the type of document information (document type). Specifically, the document type is an item that stores character strings indicating "judicial precedent", "commentary on judicial precedent", "legal book", "collection of papers", "paper", etc. In the present disclosure, as an example, document information is managed in document units such as judicial precedent, commentary on judicial precedent, and legal book, but in the case of a book or collection of papers, document information may be managed in partial units such as chapters and sections included in the collection of papers. Furthermore, the relationship between each partial unit may be associated based on the related document ID, etc., which will be described later. The document data is an item that stores the contents of document information. Specifically, the document data is an item that stores the contents of documents in PDF (Portable Document Format), Word, and text formats. The related document ID is an item that stores the document ID of one or more other document information related to the document information. For example, if the document type is a "commentary on legal precedents," the document ID of the document information related to the "legal precedents" that are explained in the commentary is stored. The importance level is an item for storing the importance level of document information. The importance level may be configured to store and reference the importance level for each user. The importance level may be configured to store and reference one or more importance levels common to multiple users.

[0018] The question table 1014 is a table for storing and managing information relating to questions (question information). The question table 1014 is a table having a question ID as a primary key, and columns of a question ID, a question sentence, an answer sentence, a parent question ID, searched document information, a reason for association, and a document summary. FIG. 6 is a diagram showing the data structure of the question table 1014. As shown in FIG.

[0019] The question ID is an item for storing question identification information for identifying a question. The question identification information is an item for which a unique value is set for each piece of question information. The question text is an item for storing a character string of a question text (query) received from a user. The answer sentence is an item for storing a character string of an answer to a question sentence. The answer includes a response regarding a report that includes one or more pieces of document information related to the question. The parent question ID is an item for storing question identification information for identifying a parent question. The searched document information is an item that stores document identification information of one or more pieces of document information related to a question. Specifically, the searched document information is an item that stores document identification information of one or more pieces of document information searched based on a question. The searched document information may include the entire document data of one or more pieces of document information related to the question. The searched document information may include a portion (a part, a snippet) of the document data related to the question. The searched document information may also include information indicating the portion (a part, a snippet) of the document data related to the question (chapter number, section number, paragraph number, identification information such as ID, starting character count, ending character count, etc.). The related reason is an item that stores a character string of information (related reason information) about the reason why one or more pieces of document information related to the question sentence are related. Specifically, the related reason stores the reason why one or more pieces of document information are related to the question sentence in association with each piece of document information. The document summary is an item that stores a character string of information (summary information) indicating a summary of one or more pieces of document information related to the question. Specifically, the document summary includes information related to the summary. The document summary may include summary information based on a portion of the document data of the document information that is related to the question. For example, the document summary may include a summary created based on a portion of the document data of the document information that is related to the question. Specifically, the document summary stores summary information for each of one or more pieces of document information in association with the respective pieces of document information.

[0020] <Configuration of the control unit 104 of the server 10> The control unit 104 of the server 10 includes a user registration control unit 1041 and a presentation unit 1042. The control unit 104 executes an application program 1011 stored in the storage unit 101, thereby realizing each functional unit.

[0021] The user registration control unit 1041 performs processing to store, in the user table 1012, information on users who wish to use the service according to the present disclosure. The information stored in the user table 1012 is generated when a user opens a web page operated by a service provider from any information processing terminal, enters information into a specific input form, and transmits the information to the server 10. The user registration control unit 1041 stores the received information in a new record in the user table 1012, completing the user registration. This allows the user stored in the user table 1012 to use the service. Before the user registration control unit 1041 registers user information in the user table 1012, the service provider may carry out a predetermined examination to restrict whether or not the user is permitted to use the service. The user ID may be any character string or number that can identify the user, any character string or number desired by the user, or an arbitrary character string or number may be automatically set by the user registration control unit 1041.

[0022] The presentation unit 1042 executes a report presentation process, the details of which will be described later.

[0023] <Configuration of User Terminal 20> The user terminal 20 is an information processing device operated by a user who uses a service. The user terminal 20 may be, for example, a mobile terminal such as a smartphone or a tablet, a stationary PC (Personal Computer), or a laptop PC. It may also be a wearable terminal such as an HMD (Head Mount Display) or a wristwatch-type terminal. The user terminal 20 includes a storage unit 201 , a control unit 204 , an input device 206 , and an output device 208 .

[0024] <Configuration of the storage unit 201 of the user terminal 20> The storage unit 201 of the user terminal 20 includes a user ID 2011 and an application program 2012 .

[0025] The user ID 2011 is an account ID of the user. The user transmits the user ID 2011 from the user terminal 20 to the server 10. The server 10 identifies the user based on the user ID 2011 and provides the user with the service according to the present disclosure. The user ID 2011 includes information such as a session ID temporarily assigned by the server 10 when identifying the user who is using the user terminal 20.

[0026] The application program 2012 may be stored in advance in the storage unit 201, or may be configured to be downloaded from a web server operated by a service provider via a communication IF. The application programs 2012 include applications such as a web browser application. The application program 2012 includes an interpreted programming language such as JavaScript™ that runs on a web browser application stored on the user terminal 20 .

[0027] <Configuration of the control unit 204 of the user terminal 20> The control unit 204 of the user terminal 20 includes an input control unit 2041 and an output control unit 2042. The control unit 204 executes an application program 2012 stored in the storage unit 201, thereby realizing each functional unit.

[0028] <Configuration of the input device 206 of the user terminal 20> The input device 206 of the user terminal 20 includes a camera 2061 , a microphone 2062 , a position information sensor 2063 , a motion sensor 2064 , and a touch device 2065 .

[0029] <Configuration of the output device 208 of the user terminal 20> The output device 208 of the user terminal 20 includes a display 2081 and a speaker 2082 .

[0030] <Configuration of generated AI50> The generation AI 50 is a type of artificial intelligence model (deep learning model) that outputs output data such as a character string or an image based on input data such as a character string or an image. In this disclosure, a large-scale language model (LLM) that outputs output data related to a character string based on input data related to a character string is mainly described as an example. Examples of LLMs include OpenAI ChatGPT, Microsoft Bing Chat, and Google Bard.

[0031] <System 1 Operation> Each process of the system 1 will be described below. FIG. 7 is a flowchart showing the operation of the report presentation process. FIG. 8 is an example of a question screen showing the operation of the report presentation process. FIG. 9 is an example of a report presentation screen showing the operation of the report presentation process.

[0032] <Report presentation process> The report presentation process is a process for presenting to a user, in response to a legal question from the user, a report including information indicating documents such as court cases related to the question, explanatory papers on the court cases, legal books, etc.

[0033] <Outline of report presentation process> This is a series of processes that accept a question from the user, search for documents based on the question, present the search results to the user, accept a document selection operation from the user, generate a prompt based on the selected document, input the prompt into a generation AI to obtain the answer, create a report based on the answer, and present the created report.

[0034] <Details of report presentation process> The report presentation process will be described in detail below.

[0035] In step S101, the presentation unit 1042 of the server 10 executes a question receiving step of receiving a question from a user. The user operates the input device 206 of the user terminal 20 to execute a browser application or the like, and opens the report presentation page D1 by inputting the URL of a web page (report presentation page) for executing the report presentation process. The control unit 204 of the user terminal 20 transmits a request including a user ID 2011 for opening the report presentation page to the server 10.

[0036] When the server 10 receives the request, it generates a report presentation page and transmits it to the user terminal 20. The control unit 204 of the user terminal 20 displays the report presentation page on the display 2081 of the user terminal 20 and presents it. 8 is an example of a question screen in the report presentation process. A question page D1 is displayed on the display 2081 of the user terminal 20. The question page D1 includes a question input field D11, a send button D12, documents D131, D132, and D133 related to the search results, check boxes D141, D142, and D143 for selecting each document related to the search results, document summaries D151, D152, and D153 of documents included in the document data, reasons for association with the entered question D161, D162, and D163, and documents related to document information related to the search results D171, D172, and D173.

[0037] The user operates the input device 206 of the user terminal 20 to input a question into the question input field D11. In the present disclosure, it is assumed that the user asks a question about a legal matter. The question may be one of the following: The user can freely input a question in the question input field D11. [Question] -Are there any court cases that discuss whether nail clippers can be considered a weapon under the Minor Offenses Act? -Are there any court cases that address the division of marital property? -Are there any court cases where terminating a rental contract due to non-payment of rent has been deemed legal? -What court cases have there been that have addressed improper termination of rental agreements?

[0038] The user presses the send button D12 by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 transmits the question entered in the question input field D11 to the server 10. The presentation unit 1042 of the server 10 receives and accepts the question. The presentation unit 1042 of the server 10 stores the received question in the question item of the new record (target record) in the question table 1014.

[0039] In step S102, the presentation unit 1042 of the server 10 executes a document search step of searching for one or more documents that describe legal opinions that can be used as a reference when answering the question, based on the question received in the question receiving step. Specifically, the presentation unit 1042 of the server 10 searches for document data items in the document table 1013 based on the received question, and acquires document information including document ID, document type, document data, related document ID, and importance. The presentation unit 1042 of the server 10 may search for document data items in the document table 1013 by partial match based on words extracted by applying morphological analysis processing to the received question. In addition, the presentation unit 1042 of the server 10 can search for document information based on any natural language search technology. In this way, the presentation unit 1042 of the server 10 searches for and identifies multiple pieces of document information related to the question. The presenting unit 1042 of the server 10 stores the identified multiple pieces of document information (including the document ID, the document data, and the related document ID) in the item of searched document information of the target record in the question table 1014.

[0040] The presentation unit 1042 of the server 10 executes an extraction step of extracting a portion related to the question from one or more documents retrieved in the document retrieval step. The presentation unit 1042 of the server 10 extracts a portion (any part of the document data, a paragraph, a line, a sentence, etc., hereinafter referred to as snippet information) containing a word related to the question from the document data of each piece of document information related to the search result. The presentation unit 1042 of the server 10 may also calculate the relevance of each piece of document information related to the search result with the question. The relevance may be a score indicating the relevance between the question and the document information, calculated using any algorithm such as TF-IDF or cosine similarity. The presentation unit 1042 of the server 10 stores the snippet information in the document summary field of the target record in the question table 1014. In the present disclosure, a configuration in which snippet information is stored in the document summary field is taken as an example, but is not limited thereto. For example, documents such as summaries, gist, case summary, commentary, etc. created based on features of document data, not based on questions, may be stored in the document summary. For example, information such as summaries, gist, case summary, commentary, etc. stored in a column not shown in the document table 1013 may be stored in the document summary field of the target record in the question table 1014. The document summary may also include information indicating a section that contains words related to the question, such as a paragraph number, a line number, a sentence number, etc. Along with the snippet information, the user can refer to the paragraph number, the line number, the sentence number, etc., from which the snippet information originates.

[0041] The presenting unit 1042 of the server 10 creates information indicating why the document data of each piece of document information related to the search result is related to the question. Specifically, the presenting unit 1042 of the server 10 creates a sentence indicating why the document information related to the search result is related to the question, based on the question and the snippet information. For example, the presenting unit 1042 of the server 10 may create a sentence indicating why the document information related to the search result is related to the question by transmitting the question and the snippet information of each piece of document information to the generation AI 50. The sentence indicating the related reason can be obtained as an output result by inputting the following prompt (snippet generation) to the generation AI 50. The question received from the user in step S101 is input in the [Question] section. The snippet information of document information A is input in the [Document summary of document information A] section. A prompt is created for each of the multiple document information items (e.g., document information A, document information B, and document information C) related to the search results. [Prompt (snippet generation)] Document information A contains information about [Document summary of document information A]. Please explain why [Question] is related to Document A.

[0042] The presentation unit 1042 of the server 10 associates the multiple document information in the search results with information indicating why the document information in the search results is related to the question text (including sentences indicating the reasons for the relatedness, scores such as the degree of relatedness, etc.) and stores this information in the relatedness reason field of the target record in the question table 1014.

[0043] In step S103, the presenting unit 1042 of the server 10 executes a document presenting step of presenting one or more documents retrieved in the document retrieval step to the user. Specifically, the presentation unit 1042 of the server 10 transmits document information related to the search results searched for in step S102 to the user terminal 20. The presentation unit 1042 of the user terminal 20 displays and presents the received document information in documents D131, D132, and D133 of the question page D1.

[0044] The document presenting step includes a step of controlling a presentation order when presenting one or more documents in response to a selection operation by the user in the document selecting step. Specifically, the control unit 204 of the user terminal 20 may display the documents D131, D132, and D133 on the question page D1 in the order of increasing importance based on the importance included in the received document information. The control unit 204 of the user terminal 20 may display the documents D131, D132, and D133 on the question page D1 in the order of decreasing relevance based on the relevance to the question text calculated for each piece of received document information. The control unit 204 of the user terminal 20 may display the documents D131, D132, and D133 on the question page D1 in the order of decreasing score based on an arbitrary score calculated based on the importance and relevance.

[0045] In step S103, a document presenting step executes a step of presenting to the user one or more documents retrieved in the document retrieval step in association with information indicating a portion related to the question. Specifically, the presentation unit 1042 of the server 10 associates the received document information with each of the documents D131, D132, and D133 on the question page D1, and displays and presents document summaries D151, D152, and D153, such as snippet information, which is a portion of the document data that contains words related to the question.

[0046] In step S103, a document presenting step executes a step of associating information indicating a reason related to the question with each of one or more documents retrieved in the document retrieval step and presenting the document to the user. Specifically, the presentation unit 1042 of the server 10 associates the received document information with each of the documents D131, D132, and D133 on the question page D1, and displays and presents reasons why each piece of document information is related to the question as associated reasons D161, D162, and D163.

[0047] In step S103, a document presenting step executes a step of presenting to the user one or more reference documents related to each of the one or more documents retrieved in the document retrieval step in association with each of the one or more documents. Specifically, the presentation unit 1042 of the server 10 searches the document table 1013 for document IDs based on the related document IDs included in each piece of document information related to the search result, and acquires the document information (related document information). The received document information is associated with each of the documents D131, D132, and D133 on the question page D1, and the related documents related to the related document IDs of each piece of document information are displayed and presented as related reasons D161, D162, and D163.

[0048] In step S103, the document presentation step may include a step of presenting summary information about the search results to the user. The document presentation step may include a document presentation step of presenting the summary information about the search results to the user together with one or more documents retrieved in the document retrieval step. Specifically, the presentation unit 1042 of the server 10 presents to the user summary information showing an overview of the search results, including information on each of one or more documents searched in the document search step. For example, in step S101, in response to the question "What should I pay attention to when switching a full-time employee to a service contract?", the presentation unit 1042 of the server 10 presents to the user a summary statement saying, "The consent of the employee and the contents of the service contract are important. For details, please see the following books and court cases."

[0049] In step S103, the document presentation step may include a step of associating links related to one or more documents retrieved in the document search step with each of the documents and presenting the documents to the user. Specifically, one or more documents retrieved in the document search step may be associated with links for referencing the contents of the documents and presented to the user. For example, when the contents of one or more documents are included in the information processing service according to the present disclosure such as document table 1013 and can be provided, a link for referencing the contents of the documents is associated with the document. On the other hand, when the contents of one or more documents cannot be provided by the information processing service according to the present disclosure, a link to an external information processing service that provides information on purchasing the documents is associated. In other words, the presentation unit 1042 of the server 10 can be configured to selectively associate a first link for referencing a first information processing service and a second link for referencing a second information processing service with each of one or more documents searched for in the document search step. As a result, for documents whose contents can be provided from the information processing service according to the present disclosure, a link for directly referencing the document contents is provided to the user, and for documents whose contents cannot be provided from the information processing service according to the present disclosure, an external link for referencing the document contents or for which a means for referencing is disclosed is provided to the user. The user can conveniently check one or more documents related to the search results.

[0050] In step S104, the presenting unit 1042 of the server 10 executes a document selection step of accepting, from the user, a selection of one or more predetermined documents from among the one or more documents presented in the document presentation step. Specifically, the user checks the contents of documents D131, D132, D133 related to the search results displayed on question page D1 by referring to document summaries, reasons for relevance, related documents, etc. The user operates the input device 206 of the user terminal 20 to select check boxes D141, D142, D143 displayed in association with documents D131, D132, D133 appropriate to the question. The user can select multiple check boxes. The control unit 204 of the user terminal 20 transmits to the server 10 the document information in which the check boxes D141, D142, and D143 are selected (selected document information).

[0051] Also, for document information for which check boxes D141, D142, and D143 are selected, a configuration may be adopted in which an input of a reference level, which is an index showing whether the document information is a document that is useful for the question, is accepted from the user. Alternatively, a configuration may be adopted in which only the input of the reference level is accepted without requiring the user to select a check box, and document information having a reference level equal to or higher than a predetermined value is transmitted to the server 10 as selected document information.

[0052] The presentation unit 1042 of the server 10 stores the received selected document information in the item of searched document information in the question table 1014. As a result, information indicating that the document information has been selected by the user is stored in association with each of the document information related to the search results stored in the item of searched document information.

[0053] The presentation unit 1042 of the server 10 searches the document ID field in the document table 1013 based on the document ID included in the selected document information, and identifies the record of the document information. The presentation unit 1042 changes the importance field of the record of the identified selected document information in response to the selection operation from the user. Specifically, the presentation unit 1042 increases the importance value of the selected document information selected by the user. This makes it possible to control the weighting (importance, score) when presenting multiple patent documents in response to a selection operation by a user. For example, patent documents selected by many users can be presented in a more prioritized position when presenting documents as patent documents with high importance. Patent documents excluded by many users can be presented less likely when presenting documents as patent documents with low importance.

[0054] In step S105, the presentation unit 1042 of the server 10 executes a generating step of generating a prompt based on the question accepted in the question accepting step and one or more documents searched in the document searching step. The generating step executes a step of generating a prompt based on the question accepted in the question accepting step and the predetermined one or more documents selected in the document selecting step. Specifically, the presentation unit 1042 of the server 10 generates a prompt, which is input data to the generation AI, based on at least one of the question sentence of the target record in the question table 1014 and the retrieved document information, the reason for relevance, and the document summary. Note that the prompt may be generated based only on the retrieved document information, the reason for relevance, and the document summary related to the document information selected by the user in step S104, excluding the retrieved document information, the reason for relevance, and the document summary related to the document information not selected by the user. In addition, in this disclosure, an example of generating a prompt based on the document information selected in step S104 has been presented as an example, but it is also possible to omit step S104, in which the user selects document information, and generate a prompt that serves as input data to the generation AI based on the search document information, related reasons, and document summary related to the search results.

[0055] In step S105, the generation step executes a step of generating a prompt based on the question received in the question receiving step and one or more documents searched in the document search step, excluding the specified one or more documents selected in the document selection step. Specifically, in step S104, the user may select a document appropriate for the question, but may also select a document inappropriate for the question. In this case, the prompt may be generated by excluding the search document information, related reasons, and document summary related to the document information selected in step S104.

[0056] In step S105, the generating step executes a step of generating a prompt based on the question accepted in the question accepting step and the part related to the question of one or more documents extracted in the extracting step. Specifically, the presentation unit 1042 of the server 10 generates a prompt that serves as input data to the generation AI based on the question sentence of the target record in the question table 1014 and snippet information included in the document summary.

[0057] The generating step includes a step of generating a prompt for generating a report including a review comparing matches or differences between the documents retrieved in the document retrieval step. Specifically, the presenting unit 1042 of the server 10 generates the following prompt. The question received from the user in step S101 is input in the [Question] section. The document summaries (snippet information) of the document information A to C are input in the [Document summary of document information A], [Document summary of document information B], and [Document summary of document information C] sections. [Prompt (matches / differences)] #Document information A: [Document summary of document information A] #Document information B: [Document summary of document information B] #Document information C: [Document summary of document information C] Regarding [Question], please compare and explain the similarities and differences between Document Information A, Document Information B, and Document Information C.

[0058] The generating step includes generating a prompt for creating a summary outlining the plurality of documents retrieved in the document retrieval step. Specifically, the presenting unit 1042 of the server 10 generates the following prompt. The question received from the user in step S101 is input in the [Question] section. The document summaries (snippet information) of the document information A to C are input in the [Document summary of document information A], [Document summary of document information B], and [Document summary of document information C] sections. [Prompt (matches / differences)] #Document information A: [Document summary of document information A] #Document information B: [Document summary of document information B] #Document information C: [Document summary of document information C] Regarding [question], please create an overall summary of document information A, document information B, and document information C.

[0059] The generating step executes a step of creating a report for a query based on one or more reference documents related to each of the plurality of documents retrieved in the document retrieval step. Specifically, the presenting unit 1042 of the server 10 generates the following prompt: In this disclosure, the document information A to C are court cases. And the related documents D to F are papers or commentaries that explain the court cases of the document information A to C, respectively. The question received from the user in step S101 is input in the [Question] field. The document summaries (snippet information) of the document information A to C are input in the [Document summary of document information A], [Document summary of document information B], and [Document summary of document information C] fields. [Document Information D], [Document Information E], and [Document Information F] are document summaries such as snippet information extracted from related documents D to F that are related to document information A to C. Note that related documents D to F may be stored as their respective document data. They may also be document summaries such as snippet information extracted from parts related to the question. [Prompt (related document)] #Document information A: [Document summary of document information A] #Document information B: [Document summary of document information B] #Document information C: [Document summary of document information C] #Related document D of document information A: [Document summary of document information D] #Related document E of document information B: [Document summary of document information E] #Related document F of document information C: [Document summary of document information F] Regarding [Question], please explain the similarities and differences between Document Information A, Document Information B, and Document Information C, with reference to the explanations in Related Documents D, E, and F.

[0060] The presentation unit 1042 of the server 10 may generate a prompt according to the user's attribute information (user attributes). Specifically, the user's attribute information may include whether the user has legal expertise, occupation, educational background, gender, and age. The user's attribute information may be received via an input field provided on the report presentation page D1, or may be identified based on past questions by the user. Alternatively, a question for the user's attribute information may be asked, and the user's attribute information may be received as a response to the question. The presentation unit 1042 of the server 10 takes user attributes into consideration and includes instructions in the prompt, such as "Please use as simple terms as possible to explain clearly" or "Please use technical terms to provide a concise explanation aimed at experts." Furthermore, by including an instruction sentence according to the user attributes in the prompt (snippet generation), the document summary (snippet information) of the document information can also be made appropriate according to the user attributes. Specifically, non-expert users can get document summaries and responses in simple terms, while expert users can get concise document summaries and responses in technical terms.

[0061] In step S106, the presentation unit 1042 of the server 10 executes an answer acquisition step of acquiring the content of an answer to the prompt by inputting the prompt generated in the generation step to the generation AI. Specifically, the presentation unit 1042 of the server 10 transmits the prompt generated in step S105 as input data to the generation AI 50. The presentation unit 1042 of the server 10 receives the output data (answer content) of the generation AI 50 as a response to the transmitted prompt. The presentation unit 1042 of the server 10 stores the received answer content in the answer text field of the target record in the question table 1014.

[0062] In step S107, the presenting unit 1042 of the server 10 executes a report creating step of creating a report for the question accepted in the question accepting step based on the answer content acquired in the answer acquiring step. Specifically, the presentation unit 1042 of the server 10 creates a report based on the answer content received in step S106. Note that the answer content may be used as the report as is. In other words, the report may include the answer content. For example, the presentation unit 1042 of the server 10 creates a report by combining the question text stored in the question table 1014, the answer text, the document information selected in step S104 included in the searched document information, the related reason, and the document summary. For example, a report may have the following format: The question received from the user in step S101 is input in the [Question] section. The document summaries (snippet information) of document information A, document information B, and document information C are input in the [Document summary of document information A], [Document summary of document information B], and [Document summary of document information C] sections. The reasons why document information A, document information B, and document information C are related are input in the [Reasons why document information A is related], [Reasons why document information B is related], and [Reasons why document information C is related] sections. [Report] Question: [Question] Answer content: [Answer content] Document information A: [Document summary of document information A] [Reasons why document information A is relevant] Document information B: [Document summary of document information B] [Reasons why document information B is relevant] Document information C: [Document summary of document information C] [Reasons why document information C is relevant]

[0063] In step S107, a report creation step creates a report including a review comparing the matching points or differences between the multiple documents retrieved in the document retrieval step. Specifically, the presentation unit 1042 of the server 10 transmits the prompt (matching points / difference points) generated in step S106 as input data to the generation AI 50. The presentation unit 1042 of the server 10 receives the answer content regarding the consideration content comparing the matching points or differences between multiple documents as output data of the generation AI 50. The presentation unit 1042 of the server 10 creates a report based on the answer content received in step S106.

[0064] In step S107, a report creation step executes a step of creating a report for the inquiry based on one or more reference documents related to each of the plurality of documents retrieved in the document retrieval step. Specifically, the presentation unit 1042 of the server 10 transmits the prompt (related document) generated in step S106 as input data to the generation AI 50. The presentation unit 1042 of the server 10 receives the answer content regarding the consideration content for comparing the similarities or differences between multiple documents as output data of the generation AI 50. The presentation unit 1042 of the server 10 creates a report based on the answer content received in step S106.

[0065] In step S108, the presentation unit 1042 of the server 10 executes a report presentation step of presenting the report created in the document creation step to the user. 9 is an example of a report presentation screen in the report presentation process. A report presentation page D3 is displayed on the display 2081 of the user terminal 20. The report presentation page D3 includes a report D31, an additional question input field D32, answers to the additional questions D34, a send button D33, document information D351, D352, D353, document summaries D3511, D3521, D3531 of the document information, and reasons for association with the entered question D3512, D3522, D3532. The control unit 204 of the user terminal 20 transmits the created report to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the received report in report D31 of report presentation page D3. The control unit 204 of the user terminal 20 displays and presents document information A to C in document information D351, D352, and D353, respectively. The control unit 204 of the user terminal 20 displays and presents document summaries of document information A to C in document summaries D3511, D3521, and D3531, respectively. The control unit 204 of the user terminal 20 displays and presents related reasons for document information A to C in related reasons D3512, D3522, and D3532, respectively. This allows the AI ​​to obtain answers to the prompts it has created, and creates a report for the questions received from the user based on the answers. The report can then be presented to the user.

[0066] In step S109, the question receiving step includes a step of receiving a second question from the user after the report is presented to the user in the report presenting step. Specifically, the user can ask an additional question (second question) depending on the contents of the report. The user inputs a question (second question) into the additional question input field D32 by operating the input device 206 of the user terminal 20. For example, the following questions are possible depending on the contents of the report. [Question] -Please explain in more detail the application of the Minor Offences Act to nail clippers. Husband A's assets are... and Wife B's assets are... Please explain how the assets will be divided in this case. · Explain what actions a landlord can take regarding non-payment of rent. · Explain what legal risks I may incur if I terminate my lease.

[0067] The user presses the send button D33 by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 transmits the second question text entered in the additional question input field D32 to the server 10. The presentation unit 1042 of the server 10 receives and accepts the second question text. The presentation unit 1042 of the server 10 stores the received second question sentence in the question sentence field of a new record (second record) in the question table 1014. Also, the presentation unit 1042 stores the question ID of the target record in the parent question ID field of the second record. This indicates that the second question asked in step S109 is a child question of the question asked in step S101.

[0068] In step S109, the generating step includes a step of generating a prompt based on the second question and one or more documents retrieved in the document searching step. The presenting unit 1042 of the server 10 executes an extracting step of extracting a portion related to the second question from the one or more documents retrieved in the document searching step. The generating step executes a step of generating a prompt based on the second question received in the question receiving step and the portion related to the question from the one or more documents extracted in the extracting step. Specifically, the presenting unit 1042 of the server 10 generates the following prompt based on the received second question sentence. The second question sentence is input in the [Second question sentence] section. The document summaries (snippet information) or document data of each of the document information A to C are input in the [Document summary of document information A], [Document summary of document information B], and [Document summary of document information C]. Note that the document summaries of the document information A to C do not need to be document summaries such as snippet information created in step S102, and it is preferable to use document summaries obtained by extracting portions of the document data A to C that contain words related to the second question sentence. This allows the generation AI 50 to obtain a more appropriate answer based on the portions of the document information A to C that are related to the second question sentence. In the present disclosure, a prompt is generated based on the second question sentence and the document information selected in step S104. At this time, the document information that was not selected in step S104 is not included in the prompt. This allows additional questions to be asked of the generation AI 50 regarding the document information A to C selected from the search results for the initially accepted question. 〔prompt〕 #Document information A: [Document summary of document information A] #Document information B: [Document summary of document information B] #Document information C: [Document summary of document information C] Please answer the question [2nd question] based on document information A, document information B, and document information C.

[0069] The presentation unit 1042 of the server 10 transmits the generated prompt as input data to the generation AI 50. The presentation unit 1042 of the server 10 receives the output data (second answer content) of the generation AI 50 as a response to the transmitted prompt. The presenting unit 1042 of the server 10 stores the received answer in the answer text field of the second record in the question table 1014. The presenting unit 1042 of the server 10 may store the related reason and document summary created based on the document information A to C and the second question sentence in the related reason and document summary items of the second record.

[0070] The presentation unit 1042 of the server 10 transmits the received second answer content to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the second answer content in the answer content D34 of the report presentation page D3. This allows the user to ask a follow-up question (second question) based on the contents of the report. The user can generate a prompt that takes into account the contents of the follow-up question, and can obtain an answer to the follow-up question from the generation AI. Specifically, a user can ask follow-up questions about multiple documents retrieved by an initial question, and obtain answers to those multiple documents from the generation AI.

[0071] <Basic computer hardware configuration> 10 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 901, a main storage device 902, an auxiliary storage device 903, and a communication IF 991 (interface). These are electrically connected to each other by a communication bus 921.

[0072] The processor 901 is hardware for executing an instruction set described in a program, and is composed of an arithmetic unit, a register, a peripheral circuit, and the like.

[0073] The main memory device 902 is for temporarily storing programs, data to be processed by the programs, etc. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0074] The auxiliary storage device 903 is a storage device for saving data and programs, such as a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, or a semiconductor memory.

[0075] The communication IF 991 is an interface for inputting and outputting signals for communicating with other computers via a network using a wired or wireless communication standard. The network is composed of the Internet, a LAN, various mobile communication systems constructed by wireless base stations, etc. For example, the network includes 3G, 4G, 5G mobile communication systems, LTE (Long Term Evolution), wireless networks that can connect to the Internet via a specified access point (e.g., Wi-Fi (registered trademark)), etc. In the case of wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), Bluetooth (registered trademark), etc. In the case of wired connection, the network also includes a network that is directly connected by a USB (Universal Serial Bus) cable or the like.

[0076] It should be noted that the computer 90 can be virtually realized by distributing all or part of each hardware configuration among multiple computers 90 and connecting them together via a network. In this way, the computer 90 is a concept that includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.

[0077] <Basic functional configuration of computer 90> A description will now be given of the functional configuration of a computer realized by the basic hardware configuration (FIG. 10) of a computer 90. The computer comprises at least the functional units of a control unit, a storage unit, and a communication unit.

[0078] The functional units of the computer 90 can also be realized by distributing all or part of the functional units among multiple computers 90 connected to each other via a network. The computer 90 is a concept that includes not only a single computer 90 but also a virtualized computer system.

[0079] The control unit is realized by the processor 901 reading out various programs stored in the auxiliary storage device 903, expanding the programs in the main storage device 902, and executing processes according to the programs. The control unit can realize functional units that perform various information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0080] The storage unit is realized by a main storage device 902 and an auxiliary storage device 903. The storage unit stores data, various programs, and various databases. Furthermore, the processor 901 can secure a storage area corresponding to the storage unit in the main storage device 902 or the auxiliary storage device 903 in accordance with a program. Furthermore, the control unit can cause the processor 901 to execute processes of adding, updating, and deleting data stored in the storage unit in accordance with the various programs.

[0081] The term database refers to a relational database, which is used to manage sets of data called masters and tables in a tabular format structurally defined by rows and columns, by associating them with each other. In a database, a table is called a table or master, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables and masters can be set and associated. Usually, a column that serves as a primary key for uniquely identifying a record is set in each table and each master, but setting a primary key in a column is not essential. The control unit can cause the processor 901 to add, delete, or update records in a specific table or master stored in the storage unit according to various programs. Furthermore, by storing data, various programs, and various databases in the storage unit, it can be considered that the information processing device and information processing system according to the present disclosure have been manufactured.

[0082] In addition, the database and master in this disclosure may include any data structure (such as a list, a dictionary, an associative array, or an object) in which information is structurally defined. The data structure also includes data that can be considered as a data structure by combining data with a function, class, method, or the like written in any programming language.

[0083] The communication unit is realized by the communication IF 991. The communication unit realizes a function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input the information to the control unit. The control unit can cause the processor 901 to execute information processing on the received information in accordance with various programs. In addition, the communication unit can transmit information output from the control unit to other computers 90.

[0084] <Additional Notes> The matters described in the above embodiments will be supplemented below.

[0085] (Appendix 1) A program to be executed by a computer having a processor and a memory unit, the program comprising: a question receiving step (S101) in which the processor receives a question from a user; a document search step (S102) in which, based on the question received in the question receiving step, the processor searches for one or more documents that contain legal opinions that can be used as reference in answering the question; and a generation step (S105) in which the processor generates a prompt based on the question received in the question receiving step and the one or more documents searched for in the document search step. This allows the generation of prompts that, in response to a user question, can cause the generative AI to create an appropriate answer to that question based on one or more documents containing legal opinions.

[0086] (Appendix 2) A program described in Appendix 1, in which a processor executes a document presentation step (S103) of presenting to a user one or more documents searched in the document search step, and a document selection step (S104) of accepting from the user a selection of one or more predetermined documents from the one or more documents presented in the document presentation step, and a generation step (S105) of generating a prompt based on the question accepted in the question acceptance step and the one or more predetermined documents selected in the document selection step. This makes it possible to generate prompts that will allow the generative AI to create more appropriate answers in response to user selections made on multiple searched documents.

[0087] (Appendix 3) A program described in Appendix 1, in which a processor executes a document presentation step (S103) of presenting to a user one or more documents searched in the document search step, and a document selection step (S104) of accepting from the user a selection of one or more specific documents from the one or more documents presented in the document presentation step, and a generation step (S105) of generating a prompt based on the question accepted in the question acceptance step and a document from the one or more documents searched in the document search step excluding the one or more specific documents selected in the document selection step. This makes it possible to generate prompts that will allow the generative AI to create more appropriate answers in response to user selections made on multiple searched documents.

[0088] (Appendix 4) A program as described in Appendix 1, in which a processor executes a document presentation step (S103) of presenting one or more documents retrieved in the document search step to a user, the document presentation step (S103) being a step of associating information indicating parts relevant to the question with each of the one or more documents retrieved in the document search step and presenting the document to the user. This allows the user to check multiple documents in the search results as well as information indicating the parts of the documents related to the question, such as paragraphs and line numbers related to the question. The user can select or exclude documents while referring to the related parts of the multiple documents in the search results.

[0089] (Appendix 5) A program as described in Appendix 1, in which a processor executes a document presentation step (S103) of presenting one or more documents retrieved in the document search step to a user, the document presentation step (S103) being a step of associating information indicating reasons related to the question with each of the one or more documents retrieved in the document search step and presenting the document to the user. This allows the user to view multiple documents in the search results along with information about the documents that indicate why they are related to the question. The user can select or exclude documents while referring to the reasons why the documents in the search results are related.

[0090] (Appendix 6) A program described in Appendix 1, in which a processor executes a document presentation step (S103) of presenting one or more documents searched in the document search step to a user, the document presentation step (S103) being a step of associating one or more reference documents related to each of the one or more documents searched in the document search step and presenting them to the user. This allows the user to check the documents in the search results as well as the reference documents related to the documents. The user can select or exclude documents while referring to the reference documents related to the documents in the search results.

[0091] (Appendix 7) A program as described in Appendix 1, in which a processor executes an extraction step (S105) of extracting portions related to the question from one or more documents searched in the document search step, and a generation step (S105) of generating a prompt based on the question received in the question receiving step and the portions related to the question from one or more documents extracted in the extraction step. This allows the system to filter out parts of the search results that are not relevant to the question and generate prompts based only on parts that are relevant to the question. By filtering out parts that are not relevant to the question, the system can improve the quality of answers from the generation AI.

[0092] (Appendix 8) The program of claim 1, wherein the documents include at least one of the following: case law, case law commentaries, and legal texts. This makes it possible to generate prompts that will enable the AI ​​to create appropriate answers to user questions based on documents such as court cases, explanatory papers on court cases, and legal books.

[0093] (Appendix 9) The program described in Appendix 1, in which a processor executes an answer acquisition step (S106) in which the processor inputs the prompt generated in the generation step into a generation AI to acquire an answer to the prompt, a report creation step (S107) in which the processor creates a report for the question received in the question receiving step based on the answer acquired in the answer acquisition step, and a report presentation step (S108) in which the processor presents the report created in the report creation step to a user. This allows the AI ​​to obtain answers to the prompts it has created, and creates a report for the questions received from the user based on the answers. The report can then be presented to the user.

[0094] (Appendix 10) The program according to appendix 9, wherein the report creation step (S107) creates a report including a review comparing the similarities or differences between the multiple documents searched in the document search step. This allows the user to check multiple documents by comparing the documents for matching or differences.

[0095] (Appendix 11) The program according to claim 9, wherein the report creation step (S107) is a step of creating a report for the inquiry based on one or more reference documents related to each of the plurality of documents searched in the document search step. This enables the generative AI to provide higher quality answers that take into account explanations of the multiple documents searched in the reference documents.

[0096] (Appendix 12) The program described in Appendix 9, wherein the question receiving step (S109) includes a step of receiving a second question from the user after presenting the report to the user in the report presentation step, and the generation step (S109) includes a step of generating a prompt based on the second question and one or more documents searched in the document search step. This allows the user to ask a follow-up question (second question) based on the contents of the report. The user can generate a prompt that takes into account the contents of the follow-up question, and can obtain an answer to the follow-up question from the generation AI. Specifically, a user can ask follow-up questions about multiple documents retrieved by an initial question, and obtain answers to those multiple documents from the generation AI.

[0097] (Appendix 13) A program as described in Appendix 12, wherein a processor executes an extraction step (S102) of extracting portions related to the second question from one or more documents searched in the document search step, and a generation step (S109) is a step of generating a prompt based on the second question received in the question receiving step and the portions related to the question in the one or more documents extracted in the extraction step. This makes it possible to exclude parts of the multiple search results that are not related to the follow-up question, and generate prompts based only on parts that are related to the follow-up question. By excluding parts that are not related to the follow-up question, the quality of the answers from the generation AI can be improved.

[0098] (Appendix 14) The program according to claim 2 or 3, wherein the document presenting step (S103) includes a step of controlling a presentation order when presenting one or more documents in response to a selection operation by the user in the document selection step. This makes it possible to control the weighting (importance, score) when presenting multiple patent documents in response to a selection operation by a user. For example, patent documents selected by many users can be presented in a more prioritized position when presenting documents as patent documents with high importance. Patent documents excluded by many users can be presented less likely when presenting documents as patent documents with low importance.

[0099] (Appendix 15) A method implemented on a computer having a processor and a memory, the processor performing all the steps performed in the invention according to any one of claims 1 to 13. This allows the generation of prompts that, in response to a user question, can cause the generative AI to create an appropriate answer to that question based on one or more documents containing legal opinions.

[0100] (Appendix 16) An information processing device comprising a control unit and a memory unit, wherein the control unit executes all of the steps executed in the invention according to any one of Supplementary Note 1 to Supplementary Note 13. This allows the generation of prompts that, in response to a user question, can cause the generative AI to create an appropriate answer to that question based on one or more documents containing legal opinions.

[0101] (Appendix 17) A system comprising means for performing all the steps performed in any of the inventions according to appendix 1 to appendix 13. This allows the generation of prompts that, in response to a user question, can cause the generative AI to create an appropriate answer to that question based on one or more documents containing legal opinions. [Explanation of symbols]

[0102] 1 system, 10 server, 101 memory unit, 104 control unit, 106 input device, 108 output device, 20 user terminal, 201 memory unit, 204 control unit, 206 input device, 208 output device, 50 generation AI, 501 memory unit, 504 control unit, 506 input device, 508 output device

Claims

1. A program to be executed by a computer having a processor and a storage unit, The processor, a question receiving step of receiving a question from a user; a document retrieval step of retrieving one or more documents describing legal opinions that are useful in answering the question based on the question received in the question receiving step; a generating step of generating a prompt based on the question received in the question receiving step and one or more documents retrieved in the document retrieval step; A program that executes.

2. The processor, a document presenting step of presenting one or more documents retrieved in the document retrieval step to the user; a document selection step of accepting, from the user, a selection of one or more predetermined documents from the one or more documents presented in the document presentation step; Run the generating step is a step of generating the prompt based on the question accepted in the question accepting step and the one or more predetermined documents selected in the document selecting step; The program according to claim 1.

3. The processor, a document presenting step of presenting one or more documents retrieved in the document retrieval step to the user; a document selection step of accepting, from the user, a selection of one or more predetermined documents from the one or more documents presented in the document presentation step; Run the generating step is a step of generating the prompt based on the question accepted in the question accepting step and one or more documents retrieved in the document retrieval step, excluding the predetermined one or more documents selected in the document selection step; The program according to claim 1.

4. The processor, a document presenting step of presenting one or more documents retrieved in the document retrieval step to the user; Run the document presenting step is a step of associating information indicating a portion related to the question with each of the one or more documents searched for in the document searching step and presenting the document to the user; The program according to claim 1.

5. The processor, a document presenting step of presenting one or more documents retrieved in the document retrieval step to the user; Run the document presenting step is a step of associating information indicating a reason related to the question with each of the one or more documents searched for in the document searching step and presenting the document to the user; The program according to claim 1.

6. The processor, a document presenting step of presenting one or more documents retrieved in the document retrieval step to the user; Run the document presenting step is a step of associating one or more reference documents related to each of the one or more documents searched in the document searching step with each other and presenting the documents to the user; The program according to claim 1.

7. The processor, an extraction step of extracting a portion related to the question from one or more documents retrieved in the document retrieval step; Run the generating step is a step of generating the prompt based on the question accepted in the question accepting step and parts of the one or more documents extracted in the extracting step that are related to the question; The program according to claim 1.

8. The document includes at least one of a court case, a commentary on a court case, and a law book; The program according to claim 1.

9. The processor, an answer acquisition step of acquiring an answer to the prompt generated in the generating step by inputting the prompt to a generation AI; a report creation step of creating a report on the question received in the question receiving step based on the answer content acquired in the answer acquiring step; a report presentation step of presenting the report created in the report creation step to the user; Execute The program according to claim 1.

10. the report creation step creates the report including a review content comparing the matching points or the differences between the plurality of documents searched in the document search step; The program according to claim 9.

11. the report creation step is a step of creating the report for the question based on one or more reference documents related to each of the plurality of documents searched in the document search step; The program according to claim 9.

12. the question receiving step includes a step of receiving a second question from the user after the report is presented to the user in the report presenting step, the generating step includes a step of generating the prompt based on the second question and one or more documents retrieved in the document retrieval step; The program according to claim 9.

13. The processor, an extraction step of extracting a portion related to the second question from one or more documents retrieved in the document retrieval step; Run the generating step is a step of generating the prompt based on the second question accepted in the question accepting step and a portion of the one or more documents extracted in the extracting step that is related to the question; The program according to claim 12.

14. the document presenting step includes a step of controlling a presentation order when presenting the one or more documents in response to a selection operation by the user in the document selecting step, The program according to claim 2 or 3.

15. A method implemented on a computer having a processor and a memory, the processor performing all of the steps performed in any of the inventions according to claims 1 to 13.

16. 14. An information processing apparatus comprising a control unit and a storage unit, the control unit executing all steps executed in the invention according to any one of claims 1 to 13.

17. A system comprising means for performing all the steps performed in any one of claims 1 to 13.

Images