Information reproduction support system, information reproduction support method, and program
The information processing apparatus addresses the challenge of reproducing non-public information by using a hint-based generation system AI to create and store accurate reproduction candidates, overcoming limitations in existing technologies.
Patent Information
- Application Number
- JP2023084804
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-23
- Publication Date
- 2024-12-05
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing technologies are limited in reproducing non-public information, such as examination questions, due to their focus on simple document or video searching, failing to address the challenge of maintaining privacy and enabling effective reproduction of private information.
An information processing apparatus utilizing a hint receiving unit, generation system AI, and presentation means to generate and present reproduction information candidates, allowing users to input hints for reproducing private information, modify candidates, and store them in a reproduction information pool.
Enables the reproduction of private information, such as examination questions, by generating accurate candidates even when original information is not available, facilitating effective reproduction and storage for review and scoring.
Smart Images

Figure 2024168274000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to a technique for reproducing non-public information. [Background technology]
[0002] There are known technologies for searching document information. For example, Patent Document 1 discloses a technology for a document information search device that can smoothly carry out a series of search actions to search for a desired document from documents stored in a database, quickly determine the validity of the document from the search results, and understand each document.
[0003] Patent document 2 discloses a method of providing a user's terminal with "playback video information" that plays back video footage once filmed at a certain location, as a scene once seen, or "playback video information" that recreates a scene that once existed at that location, as a scene that once existed there. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Patent No. 3356519 [Patent Document 2] JP 2004-070782 A Summary of the Invention [Problem to be solved by the invention]
[0005] In certain fields, there is a demand to reproduce non-public information. However, the invention of Patent Document 1 is limited to simply searching for documents, and the invention of Patent Document 2 is limited to searching a database for matching video information based on information such as the composition of a landscape or the user's standing position.
[0006] In view of the above background, the present invention provides a reproduced information pool in which private information stored in a private information pool is reproduced. [Means for solving the problem]
[0007] One aspect of the present disclosure provides an information reproduction support system having a hint receiving means for receiving input of a hint for reproducing private information belonging to a private information pool from a user, a control means for providing the hint to a generative AI to generate candidates for reproduction information that reproduce the private information, a presentation means for presenting the candidates to the user, a writing means for writing the candidates to the reproduction information pool as reproduction information of the private information in response to an instruction from the user, and a provision means for providing the reproduction information stored in the reproduction information pool in response to a request from another device.
[0008] The apparatus may further include an extracting means for extracting the reproduction information corresponding to the hint from the reproduction information pool, and the presenting means may present the extracted reproduction information to the user.
[0009] The control means may, when the extraction means has not extracted the reproduction information corresponding to the hint, give the hint to the generative AI to generate the candidates for the reproduction information.
[0010] The information processing device may further include a correction receiving means for receiving correction instructions from the user for the extracted reproduction information or the candidate, and the writing means may write the reproduction information or the candidate corrected in accordance with the correction instructions into the reproduction information pool.
[0011] The information processing device may further comprise a determination unit for determining which of the reproduction information corrected in response to the correction instruction and the reproduction information stored in the reproduction information pool before the correction is to be adopted as the reproduction information.
[0012] The control means may provide the hint to the generative AI to generate a plurality of candidates for the reproduction information, and the presentation means may have a selection accepting means for presenting the plurality of candidates to the user and accepting a selection of one candidate from the plurality of candidates from the user.
[0013] The non-public information pool may be a pool in which test questions used in a certain test are stored.
[0014] The test may be a multiple choice test.
[0015] The hint accepting means may accept input of the hint for each of the question sentence and options of the multiple-choice test, and the control means may cause the generative AI to generate the candidates for the reproduction information of the question sentence and the options.
[0016] Another aspect of the present disclosure provides an information reproduction support method, the method including the steps of: a computer receiving, from a user, an input of a hint for reproducing private information belonging to a private information pool; a step of providing the hint to a generative AI to generate candidates for reproduction information that reproduce the private information; a step of presenting the candidates to the user; a step of writing the candidates to the reproduction information pool as the reproduction information of the private information in response to an instruction from the user; and a step of providing the reproduction information stored in the reproduction information pool in response to a request from another device.
[0017] Another aspect of the present disclosure provides a program for causing a computer to execute the steps of: accepting input of a hint for reproducing private information belonging to a private information pool from a user; providing the hint to a generative AI to generate candidates for reproduced information that reproduce the private information; presenting the candidates to the user; writing the candidates to the reproduction information pool as the reproduction information of the private information in response to an instruction from the user; and providing the reproduction information stored in the reproduction information pool in response to a request from another device. Effect of the Invention
[0018] According to the present invention, it is possible to provide a reproduced information pool in which private information stored in a private information pool is reproduced. [Brief description of the drawings]
[0019] [Figure 1] FIG. 1 is a diagram illustrating an example of an overview of a problem in the information reproduction support system 1. [Diagram 2] FIG. 2 is a diagram illustrating an example of an outline of the system operation of the information reproduction support system 1. [Diagram 3] FIG. 1 is a diagram illustrating an example of a system configuration of an information reproduction support system 1. [Figure 4] FIG. 1 is a diagram illustrating an example of a functional configuration of an information reproduction support system 1. [Diagram 5] FIG. 1 is a diagram illustrating an example of a hardware configuration of an information processing device 10. [Figure 6] FIG. 2 is a diagram illustrating an example of the hardware configuration of a user terminal 30. [Figure 7] 1 is a sequence chart illustrating a method for presenting a reproduced problem. [Figure 8] FIG. 4 is a diagram illustrating an example of an input screen on a user terminal 30. [Figure 9] FIG. 2 is a diagram illustrating an example of a database in the information reproduction support system 1. [Figure 10] 1 is a flowchart illustrating a method for selecting a reproduction problem. [Figure 11] FIG. 4 is a diagram illustrating a selection screen on the user terminal 30. [Figure 12] FIG. 4 is a diagram illustrating a selection screen on the user terminal 30. [Figure 13] A sequence chart illustrating how to fix a reproducible problem. [Figure 14] FIG. 13 is a diagram illustrating an example of a correction screen on the user terminal 30. [Figure 15] 11 is a sequence chart illustrating an example of how points are acquired and used. [Figure 16] FIG. 13 is a diagram illustrating a search screen for reproduced questions on a user terminal 30. [Figure 17] FIG. 13 is a diagram illustrating an example of a display screen of a reproduced question on a user terminal 30. [Figure 18] FIG. 13 is a diagram illustrating an example of a viewing screen for reproduced questions on a user terminal 30. [Figure 19]FIG. 13 is a diagram illustrating a modified example of an input screen on the user terminal 30. [Figure 20] FIG. 13 is a diagram illustrating a modified example of a correction screen on the user terminal 30. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0020] 1. Overview 1 is a diagram illustrating an example of an overview of the problem in the information reproduction support system 1. In this example, the problem that the information reproduction support system 1 according to the present invention is intended to solve will be described using, for example, the transition of the examination system for the National Medical Licensing Examination as an example. In this example, the National Medical Licensing Examination refers to the national examination for obtaining a medical license, and the examination system refers to the examination format in which examinees take the examination.
[0021] FIG. 1 is a diagram showing two types of examination systems (A) and (B) as follows. In this example, the examination system (A) includes a form in which, for example, when implementing the National Medical Licensing Examination, an implementing organization issues a question booklet, and examinees take the examination by looking at the published question booklet. On the other hand, the examination system (B) includes the following three systems: (1) online examination, (2) examination question pool system, and (3) non-disclosure of examination questions. In this example, (1) online examination is a system in which examinees answer examination questions stored in a database via an examination terminal. In this example, (2) examination question pool system is a system in which examination questions are randomly asked from a plurality of examination questions (hereinafter referred to as "non-disclosure information") recorded in the implementing organization's database (hereinafter referred to as "non-disclosure information pool"). In this example, (3) non-disclosure of examination questions is a system in which at least a part of the contents of non-disclosure information belonging to the non-disclosure information pool is not disclosed to examinees by limiting the medium for carrying out the examination to examination terminals, not to paper or booklets, etc. These systems (1) to (3) are planned to be combined in a complex manner and implemented, for example, in the national medical examination.
[0022] Here, in the examination system (A), the examinee can take home the distributed question booklet after the examination. Also, the examination institution such as a preparatory school creates a model answer based on the question booklet that the examinee takes home. The examination institution can immediately judge whether the examinee passes or fails based on this model answer and create past questions. On the other hand, in the examination system (B), the above-mentioned systems (1) to (3), especially (1) online examination and (3) non-publication of examination questions, make it impossible for the examinee to take home the question booklet, and it becomes extremely difficult to create model answers, immediately judge whether the examinee passes or fails, and create past questions. In this regard, when information is made private in any field, regardless of the national medical examination, the above-mentioned problems may occur. Therefore, one of the purposes of the information reproduction support system 1 according to the present invention is to reproduce the non-public information even if the information is made private, and to record the reproduced information (hereinafter referred to as "reproduced information") in the system's database (hereinafter referred to as "reproduced information pool"). Therefore, in regard to a method for solving these problems, first, an example of the operation of the information reproduction support system 1 will be simply explained.
[0023] Fig. 2 is a diagram illustrating an example of an outline of the system operation of the information reproduction support system 1. In this example, the information reproduction support system 1 performs the following operations as a means for effectively solving the problem described in Fig. 1. In step S1, a candidate taking the national medical examination stores (extracts) at least a part of the secret questions (an example of the secret information) randomly set from the secret question pool (an example of the secret information pool). This is a process performed by the candidate himself.
[0024] In step S2, the examinee inputs hints for recreating the problem into the information reproduction support system 1. In this example, "hint" represents a concept that includes information that serves as a clue for recreating the closed problem. In this case, the "hint" is information that the examinee extracts from the closed problem. In this example, the examinee recalls as much information as possible for recreating the closed problem and inputs it into the system. This is also a process that is performed by the examinee himself / herself.
[0025] In step S3, the information reproduction support system 1 refers to the hint for reproducing the problem input by the examinee. If the reproduction problem (an example of reproduction information) corresponding to the referenced hint for reproducing the problem is stored in the database of the system, i.e., the reproduction problem pool (an example of the reproduction information pool), the information reproduction support system 1 advances the process to step S4A. On the other hand, if the reproduction problem is not stored in the database, the information reproduction support system 1 advances the process to step S4B.
[0026] In step S4A, the information reproduction support system 1 presents the examinee with a reproduction question corresponding to a hint for reproducing the question from the database.
[0027] In step S4B, the information reproduction support system 1 reproduces the private problem based on the hint for reproducing the problem, and records the reproduced reproduction problem in the database.
[0028] In step S5, the information reproduction support system 1 presents the examinee with a reproduced question reproduced based on the hint for reproducing the question. As described above, even if the exam question has been made private, the information reproduction support system 1 can reproduce the private exam question through cooperation between the system and the examinee. Note that FIG. 2 is merely an overview of an example of the operation for solving the problem, and more specific details of the operation will be explained in Chapter 3. Also, the configuration and operation of the information reproduction support system 1 from this point onwards are explained using an example of the National Medical Licensing Examination.
[0029] 2. Configuration Fig. 3 is a diagram illustrating an example of a system configuration of an information reproduction support system 1. In this example, the information reproduction support system 1 (or simply the system) has an information processing device 10, an AI 20, and a user terminal 30. In this example, the components of the system are compositely connected to each other via a network 9 as shown in Fig. 3. In this example, the network 9 is a computer network such as the Internet.
[0030] In this example, the information processing device 10 is an information processing device / server device in the information reproduction support system 1. In this example, the information processing device 10 presents candidates for reproduction questions corresponding to a hint received from a test-taker for reproducing a closed question.
[0031] In this example, AI20 is a generative AI that generates reproduced questions based on hints received from test-takers to reproduce undisclosed questions. In this example, generative AI is one type of artificial intelligence technology, and includes systems capable of learning large amounts of data and generating new texts and content. In this case, it refers to an AI system capable of generating exam questions for the National Medical Licensing Examination. In this example, AI20 includes a so-called large language model (LLM).
[0032] In this example, the user terminal 30 represents a terminal of an examinee (an example of a user). In this example, the examinee can input a hint to reproduce a non-disclosed question via the user terminal 30, and can receive candidates for reproduced questions corresponding to the hint from the information processing device 10. Note that in this example, multiple user terminals 30 (an example of another device) are illustrated in FIG. 3, and each of these user terminals 30 can be provided with reproduced questions from the information processing device 10.
[0033] 4 is a diagram illustrating an example of a functional configuration of the information reproduction support system 1. In this embodiment, the information processing device 10 has a hint receiving means 11, a control means 12, a presentation means 13, a writing means 14, an extraction means 15, a correction receiving means 16, a decision means 17, a provision means 181, a selection receiving means 182, and a storage means 19. In this example, the storage means 19 stores various data including, for example, a database. In this example, the control means 12 performs various controls.
[0034] In this example, the hint receiving means 11 receives an input of a hint for reproducing a private problem belonging to a private problem pool from a user via the user terminal 30.
[0035] In this example, the control means 12 gives the AI 20 (an example of a generative AI) a hint received by the hint receiving means 11, and causes the AI 20 to generate a candidate reproduction problem that reproduces the private problem. In addition, when the extraction means 15 does not extract a reproduction problem corresponding to the hint, the control means 12 gives a hint to the AI 20 to generate a candidate reproduction problem.
[0036] In this example, the presentation means 13 presents candidates for reproduced questions to the examinee (an example of a user) via the user terminal 30.
[0037] In this example, the writing means 14 writes candidates for reproduction questions as reproduction questions of non-public questions in the storage means 19 (an example of a reproduction question pool) in response to a user's instruction. In this example, the storage means 19 is a database that stores various data. The storage means 19 records and stores data such as the reproduction questions for each national medical examination and attribute information of the reproduction questions.
[0038] In this example, the extraction means 15 extracts a reproduction problem corresponding to the input hint from the storage means 19. Alternatively, the extraction means 15 can narrow down and extract reproduction problems based on search conditions, for example.
[0039] In this example, the correction receiving means 16 receives a correction instruction for the extracted reproduction problem or the candidate reproduction problem from the user. The writing means 14 writes the corrected reproduction problem or the candidate reproduction problem to the storage means 19.
[0040] In this example, the determining means 17 determines which of the information corrected in response to the correction instruction and the information stored in the storage means 19 before the correction is to be adopted as the reproduced problem.
[0041] In this example, the providing means 181 provides a reproduced problem stored in the storage means 19 in response to a request from the user terminal 30 (an example of another device).
[0042] In this example, the selection receiving means 182 receives a selection of one reproduction question candidate from a plurality of reproduction question candidates from the user via the user terminal 30.
[0043] 5 is a diagram illustrating an example of a hardware configuration of the information processing device 10. In this example, the information processing device 10 is a computer or a general-purpose server having a CPU (Central Processing Unit) 101, a memory 102, a storage 103, and a communication IF 104. The CPU 101 is a processor that performs various calculations according to a program. The memory 102 is a main storage device that functions as a work area when the CPU 101 executes a program, and includes, for example, a RAM (Random Access Memory). The storage 103 is an auxiliary storage device that stores various data and programs, and includes, for example, an SSD (Solid State Drive) or an HDD (Hard Disc Drive). The communication IF 104 is a device that communicates with other devices according to a predetermined communication standard, and includes, for example, a NIC (Network Interface Card).
[0044] In this example, the programs stored in the storage 103 include a program (hereinafter referred to as a "server program") for making the computer function as a server in the information reproduction support system 1. When the CPU 101 is executing the server program, the CPU 101, the memory 102, the storage 103, and the communication IF 104 are examples of functions for operating the information processing device 10. The CPU 101 is an example of a control means 12, a writing means 14, an extraction means 15, and a decision means 17. At least one of the memory 102 and the storage 103 is an example of a storage means 19. The communication IF 104 is an example of a hint receiving means 11, a presentation means 13, a correction receiving means 16, a provision means 181, and a selection receiving means 182.
[0045] FIG. 6 is a diagram illustrating a hardware configuration of the user terminal 30. In this example, the user terminal 30 is a computer having a CPU 301, a memory 302, a storage 303, a communication IF 304, an input device 305, and a display device 306, and includes, for example, a smartphone, a tablet, or a personal computer. The CPU 301 is a processor that performs various calculations according to a program. The memory 302 is a main storage device that functions as a work area when the CPU 301 executes a program, and includes, for example, a RAM. The storage 303 is an auxiliary storage device that stores various data and programs, and includes, for example, an SSD or HDD. The communication IF 304 is a device that communicates with other devices according to a predetermined communication standard, and includes, for example, a wireless chip in the case of wireless communication. The input device 305 is a device for inputting information to the user terminal 30, and includes, for example, a touch screen, a keyboard, a mouse, or a pointing device. The display device 306 is a device that displays information, and includes, for example, an organic EL display or a liquid crystal display.
[0046] In this example, the programs stored in the storage 303 include a program (hereinafter referred to as a "client program") for causing the computer to function as a client in the information reproduction support system 1. When the CPU 301 is executing the client program, the CPU 301, memory 302, storage 303, communication IF 304, input device 305, and display device 306 are examples of functions for operating the user terminal 30. Up to this point, the configuration of the information reproduction support system 1 has been described. Next, the operation of the information reproduction support system 1 will be described.
[0047] 3.Operation Here, the operation of the information reproduction support system 1 will be described. The operation of FIG. 2 explained in the overview of Chapter 1 shows an overview of the problem solving process according to the present invention, and merely shows a basic policy. Therefore, more specific operations regarding the functions and processing of the devices etc. included in the information reproduction support system 1 will be explained in four sections. All operations are included in the embodiments of the information reproduction support system 1.
[0048] 3-1. How to present a reproducible problem 7 is a sequence chart illustrating a method of presenting a reproduced question in the information reproduction support system 1. In this example, it is assumed that the user cooperates with the information reproduction support system 1 to reproduce the national medical examination question that the user took.
[0049] In step S101, the information processing device 10 acquires a hint input by the user via the user terminal 30. In this example, the hint receiving means 11 receives an input of a hint for reproducing a private problem belonging to a private problem pool from the user. Here, the input screen for the hint by the user will be described below.
[0050] FIG. 8 is a diagram illustrating an example of a hint input screen. In this example, FIG. 8 shows an example of a display screen displayed by the user terminal 30. In this example, the user inputs hints in each field (an example of the hint receiving means 11) according to the display of the display screen D1. The user inputs as many test question sentences as he can remember in the field F11 displayed on the display screen D1. Furthermore, the user selects either one of the designations (fields) of "correct" or "incorrect" as the answer designation of the true / false question in the fields F121 and F122. In this example, the true / false question is, for example, a question having a question format in which the examinee selects an option corresponding to the answer designation such as "correct" or "incorrect" from among multiple options given for one question. Furthermore, the user inputs the number of options to be selected in the true / false question in the field F13. Then, the user inputs as many options of the true / false question as the user can remember in the fields F141, F142, F143, and the like. Finally, the user enters the identification information (or identification characters) of the option that he or she actually selected into field F15, thereby completing the question answer. In this example, the identification information is information for identifying the option, and includes, for example, letters, numbers, or symbols, particularly alphabets in this case. When the user has completed the input, the information in each field is sent to the information processing device 10.
[0051] Returning to Fig. 7, in step S102, the information processing device 10 refers to the database and determines whether or not there is a reproduced question that corresponds to the input hint. In this example, the database (one example of the storage means 19) records and manages, for example, information related to national medical examination questions, and in this case, particularly, means a reproduced question pool in which a plurality of reproduced questions are stored.
[0052] Here, the following two types of processing are implemented for the subsequent processing. The first is (A) processing when there is a candidate for a reproduction problem in the database. The second is (B) processing when there is no candidate for a reproduction problem in the database and the AI 20 is made to generate a candidate. In this example, the processing of (A) and (B) are both processing for the information processing device 10 to present a reproduction problem based on the hint input by the user. Here, as a result of the processing of the information processing device 10 in step S102, if it is determined that there is a reproduction problem corresponding to the hint input to the database, the information processing device 10 shifts the processing to step SA103. If it is determined that there is no reproduction problem corresponding to the hint input to the database, the information processing device 10 shifts the processing to step SB103. First, the processing (A) will be described.
[0053] In step SA103, the information processing device 10 extracts a reproduction problem corresponding to the hint from the reproduction problem pool. In this example, when there is a reproduction problem corresponding to the input hint in the database, the extraction means 15 extracts a plurality of reproduction problem candidates. Here, the database for recording the reproduction problems will be described.
[0054] FIG. 9 is a diagram illustrating a database in the information reproduction support system 1. In this example, the national medical examination question database 1001 is a database for recording and managing reproduction questions. In this example, the national medical examination question database 1001 records and manages multiple reproduction questions for each classification of examination questions, such as general questions and clinical questions identified by pool IDs. In this example, for multiple reproduction questions classified as general questions, the database comprehensively records candidate question sentences and candidate options included in the components of the reproduction questions. Note that all data recorded in the national medical examination question database 1001 is identified and managed by the information reproduction support system 1 using various IDs. As described above, the information reproduction support system 1 can refer to this database and extract necessary data, for example, a reproduction question corresponding to an input hint. Here, a reproduction question corresponding to a hint refers to a reproduction question whose matching rate (or matching score) with the hint is equal to or higher than a reference value. The matching rate between the hint and the reproduction question is calculated according to a predetermined algorithm. In this example, the extraction means 15 extracts a predetermined number (for example, three) of reproduction problems whose matching rate with the hint is equal to or higher than a reference value, in descending order of matching rate.
[0055] Returning to FIG. 7, in step SA104, the information processing device 10 presents the extracted reproduction problem to the user. In this example, the presenting means 13 presents the extracted reproduction problem candidates to the user via the user terminal 30. As described above, the user can obtain reproduction problem candidates by inputting a hint for the private problem. Next, process (B) will be described.
[0056] Here, process (B) is mainly intended for cases where the extraction means 15 has not extracted a reproduction problem corresponding to the hint. This includes cases where there are no reproduction problem candidates corresponding to the hint in the reproduction problem pool to begin with, or there are too few to present to the user. In other words, in the above-mentioned process (A), for example, when the information processing device 10 refers to the database but does not extract or present reproduction problem candidates, and the user is unable to obtain reproduction problem candidates, the process proceeds to process (B).
[0057] In step SB103, the information processing device 10 uses the hint input by the user to generate a command statement (so-called a prompt) for the AI 20 to generate a reproduction problem, and inputs the generated prompt to the AI 20. This allows the AI 20 to obtain a hint for generating a reproduction problem candidate. In this example, the prompt for generating a reproduction problem includes a command for generating multiple reproduction problem candidates from the same hint. Here, the generation of the prompt will be described.
[0058] In this example, the generation of the prompt includes, for example, a process in which the information processing device 10 estimates the structure of the question sentence from the category of the test question and reflects it in the prompt. The structure of the question sentence refers to a combination of information such as the amount of text, the order of presentation of information, and the presence or absence of a drawing. The category of the test question is, for example, a classification of the test such as general test / clinical test, a classification of organs / organs in the test question sentence, or a classification of the case / attributes (age, sex, etc.) of the clinical patient in the test question sentence. The correspondence between these pieces of information and the structure of the question sentence is predefined in the information processing device 10. In other words, the information processing device 10 can cause the AI 20 to generate a reproduced question with higher reproduction accuracy by instructing the structure of the test question sentence through a prompt based on these categories. Note that all of these categories described above are input, for example, by a user, that is, an examinee. In one example, the hint input screen (FIG. 8) includes an object for specifying a category, and the user specifies the category on this hint input screen. Alternatively, an object for specifying a category may be provided on a screen other than the hint input screen, and the user may specify the category on this screen.
[0059] In step SB104, the AI 20 generates candidates for reproduction problems that reproduce the private problem based on the input prompt. The processes up to this point are performed by the information processing device 10 and the AI 20 working together. That is, in this example, when the extraction means 15 does not extract a reproduction problem that corresponds to the hint, the control means 12 can give a hint to the AI 20 to generate candidates for the reproduction problem.
[0060] In step SB105, the AI 20 outputs the generated candidates for reproduction questions to the information processing device 10. In this way, the information processing device 10 can acquire the candidates for reproduction questions generated by the AI 20.
[0061] In step SB106, the information processing device 10 records the reproduced question candidates generated by the AI 20 in the national medical examination question database 1001.
[0062] In step SB107, the information processing device 10 presents the reproduction problem candidates generated by the AI 20 to the user. In this example, the presenting means 13 presents the generated reproduction problem candidates to the user via the user terminal 30. As described above, by inputting a hint for a private problem, the user can obtain the reproduction problem candidates generated by the AI 20 even if there is no reproduction problem in the reproduction problem pool. So far, the method of presenting reproduction problems in the information reproduction support system 1 has been described.
[0063] 3-2. How to select a reproduction problem 10 is a flowchart illustrating a method for selecting a reproduction problem in the information reproduction support system 1. Here, an example is described in which a user selects reproduction problem candidates presented by the information reproduction support system 1. Here, this flow is started when the information processing device 10 presents the extracted reproduction problem candidates to the user in step SA104 of process (A) described in section 3-1. In step S201, the information processing device 10 presents the reproduction problem candidates extracted from the database to the user via the user terminal 30.
[0064] In step S202, the user judges whether there is a suitable candidate, i.e., a candidate that is thought to be the same (or nearly the same) as the exam question that the user actually took, among the candidates for the reproduction question presented by the information processing device 10. In this example, if the user judges that there is a suitable candidate for the reproduction question (step S202: YES), the information reproduction support system 1 advances the process to step S203. On the other hand, if the user judges that there is no suitable candidate for the reproduction question (step S202: NO), the information reproduction support system 1 advances the process to step S204.
[0065] When it is determined that there is a suitable candidate for the reproduction problem (step S202: YES), in step S203, the user selects one of the candidates for the reproduction problem presented by the information processing device 10 and inputs it to the user terminal 30. At this point, the information reproduction support system 1 ends the processing in Fig. 10. Here, the selection of a reproduction problem by the user will be described.
[0066] FIG. 11 is a diagram illustrating a selection screen in the user terminal 30. In this example, the display screen D21 represents an example of a display screen in the user terminal 30. In this example, fields F211 and F212, etc. represent selection fields including candidates for reproduction problems extracted from the database. In this example, if the user finds a candidate that he / she thinks is suitable as a reproduction problem among the multiple candidates for reproduction problems (step S202: YES), he / she selects it and inputs it to the user terminal 30 (step S203). Alternatively, if the user judges that none of the presented candidates for reproduction problems are suitable as a reproduction problem (step S202: NO), he / she selects "no" in the field F23 indicating that there is no suitable candidate and inputs it to the user terminal 30. This allows the information reproduction support system 1 to obtain information from the user as to whether there is a suitable candidate among the extracted candidates for reproduction problems. Next, a case where there is no suitable candidate among the presented reproduction problems will be described.
[0067] Returning to Fig. 10, in step S204, if the user determines that there are no suitable candidates for the reproduction problem (step S202: NO), the information processing device 10 presents candidates for the reproduction problem generated by the AI 20. This includes the operation of process (B) described in section 3-1.
[0068] In step S205, the user judges whether or not there is a suitable candidate for the reproduction question presented by the information processing device 10, similarly to step S202. In this example, if the user judges that there is a suitable candidate for the reproduction question (step S205: YES), the information reproduction support system 1 advances the process to step S206. On the other hand, if the user judges that there is no suitable candidate for the reproduction question (step S205: NO), the information reproduction support system 1 advances the process to step S207.
[0069] When it is determined that there is a suitable candidate for the reproduction question (step S205: YES), in step S206, the user selects one of the candidates for the reproduction question presented by the information processing device 10 and inputs it to the user terminal 30. At this point, the information reproduction support system 1 ends the processing in Fig. 10. Here, as before, the selection of a reproduction question by the user will be described.
[0070] FIG. 12 is a diagram illustrating a selection screen in the user terminal 30. In this example, the display screen D22 represents an example of a display screen in the user terminal 30. In this example, fields F221 and F222, etc. represent selection fields including candidates for reproduction problems generated by the AI 20. In this example, if the user finds a candidate that the user thinks is suitable as a reproduction problem among the multiple reproduction problem candidates (step S205: YES), the user selects it and inputs it to the user terminal 30 (step S206). Alternatively, if the user determines that none of the presented reproduction problem candidates are suitable as a reproduction problem (step S205: NO), the user selects "Regenerate" in the field F24, which represents a process of having the AI 20 generate a reproduction problem again, and inputs it to the user terminal 30. This allows the information reproduction support system 1 to obtain information from the user as to whether there is a suitable candidate among the reproduction problem candidates generated by the AI 20. Next, a case will be described in which there is no suitable candidate among the presented reproduction problems and the AI 20 is made to generate a reproduction problem again.
[0071] Return to FIG. 10. In step S207, if the user determines that there is no suitable candidate for the reproduction problem (step S205: NO), the information processing device 10 makes the AI 20 generate a reproduction problem candidate again. The information processing device 10 inputs a prompt to the AI 20 to generate a reproduction problem candidate different from the one previously generated. In this example, the information processing device 10 makes the AI 20 regenerate the reproduction problem candidate, and presents the regenerated reproduction problem candidate to the user again. This is the process of returning to the above-mentioned step S204. That is, the information reproduction support system 1 repeats the above-mentioned process until a suitable candidate for the user is selected from the presented reproduction problem candidates (step S205: YES). Finally, in step S206, when the user selects one of the reproduction problem candidates presented by the information processing device 10 and inputs it to the user terminal 30, the information reproduction support system 1 ends the process of FIG. 10 at this point. From the above, the user can select a reproduction problem candidate presented by the information reproduction support system 1. Next, a method for correcting the reproduction problem selected by the user will be described.
[0072] 3-3. How to fix the problem 13 is a sequence chart illustrating a method for correcting a reproduction problem in the information reproduction support system 1. In step S301, the information processing device 10 accepts the above-mentioned user's correction instruction. In this example, the user can correct the reproduction problem candidate selected by the user via the user terminal 30. Here, the correction method by the user will be described.
[0073] FIG. 14 is a diagram illustrating a correction screen in the user terminal 30. In this example, the display screen D3 represents an example of a display screen in the user terminal 30. In this example, each field represents a correction field for correcting a candidate for a reproduced question selected by the user. In this example, the field F31 represents a correction field for correcting the question sentence of the reproduced question. In addition, fields F311, F312, and F313, etc. represent correction fields for correcting the options of the reproduced question. Note that the question sentence and the options to be corrected here are both included in the reproduced question. In this example, the user can correct the information of the reproduced question displayed in each field to make it closer to the exam question that the user actually took. When the user completes the input of the correction of the reproduced question, the user selects "correction completed" in the field F32 and inputs it to the user terminal 30. When the user inputs "correction completed", a correction request is transmitted from the user terminal 30 to the information processing device 10. As described above, the information processing device 10 can accept the correction of the reproduced question from the user.
[0074] Return to FIG. 13. In step S302, the information processing device 10 grants points to the user. In this example, the information reproduction support system 1 is able to reproduce the undisclosed questions by cooperating with the user, that is, the examinees who actually took the exam, and so in return, the information reproduction support system 1 grants points for viewing the reproduced questions recorded in the database. This allows the user to view multiple reproduced questions reproduced by multiple examinees, and use them for grading and review after taking the exam, or as past questions before taking the exam. The number of points granted may be changed depending on the user's cooperation. In this case, the more cooperation a user has, the higher the number of points granted.
[0075] In step S303, information processing device 10 performs a process of comparing the reproduction problem corrected in response to the correction instruction with the reproduction problem before correction to determine which one to adopt as the reproduction problem. In this example, information processing device 10 selects, in accordance with a predetermined program or algorithm, whether to record the reproduction problem corrected in response to the correction instruction or the reproduction problem before correction in the database.
[0076] In step S304, the information processing device 10 writes the reproduction problem that has been adopted into the database. In this example, if the reproduction problem that has been adopted is a reproduction problem that has been corrected in response to a correction instruction, the corresponding reproduction problem before correction in the database is overwritten with the corrected reproduction problem. In this way, the information reproduction support system 1 can cooperate with the user to accumulate data on reproduction problems.
[0077] In addition, by having multiple users, rather than just a single user, involved in the correction of the reproduced problem and the accumulation of the database, it is possible to approach a reproduced problem with higher reproduction accuracy. More specifically, for the same problem, the process of extracting a reproduced problem from the database described in Section 3-1 and presenting it to the user, as well as the process of the user correcting the reproduced problem and writing it to the database described in Section 3-3 (this section), can be repeatedly carried out between multiple users. As a result, the problem can be reproduced by the collective intelligence of multiple users rather than relying on the memory of one person (a single user), and more accurate reproductions are expected.
[0078] 3-4. How to obtain and use points FIG. 15 is a sequence chart illustrating a method of acquiring and using points in the information reproduction support system 1. Here, an example will be described in which the information reproduction support system 1 introduces a point system to more effectively provide reproduction problems to the user. In step S401, the user inputs search conditions for viewing reproduction problems to the information reproduction support system 1 via the user terminal 30 (an example of another device). In this example, the user can request a reproduction problem stored in the database of the information processing device 10. Here, the search for a reproduction problem will be described below.
[0079] FIG. 16 is a diagram illustrating a search screen for reproduction questions on the user terminal 30. In this example, the display screen D4 represents an example of a display screen on the user terminal 30. In this example, each field represents a search field for displaying reproduction questions according to search conditions input by the user. In this example, the fields F41 and F42 represent search fields for inputting search conditions for reproduction questions. In this example, the field F41 allows the user to arbitrarily check the check items of attribute information of the reproduction questions, for example, general questions, clinical questions, cases (themes), and true / false question formats, thereby narrowing down the reproduction questions. In addition, in this example, the field F42 allows the user to narrow down the reproduction questions that match the free words by accepting input of a free word for the reproduction questions from the user. When the user has completed input of all search conditions, the user terminal 30 allows the user to select the field F43 representing a process of searching a database, and transmits the data to the information processing device 10.
[0080] Returning to Fig. 15, in step S402, the information processing device 10 searches the database based on the input search criteria. In this example, the information processing device 10 extracts one or more reproduced questions that match the input search criteria from among the reproduced questions recorded in the national medical examination question database 1001.
[0081] In step S403, information processing device 10 notifies the user of the search results, regardless of whether a reproduction problem that matches the input search conditions exists in the database. In this example, if a reproduction problem that matches the input search conditions exists in the database, user terminal 30 displays one or more reproduction problems extracted by information processing device 10 on the display screen. Alternatively, if a reproduction problem that matches the input search conditions does not exist in the database, user terminal 30 displays the result on the display screen. This allows the user to obtain the search results.
[0082] In step S404, the user purchases points and / or uses the provided points to view the reproduction problems displayed on the user terminal 30. In this example, the points available to the user are managed by the system. The user can use the points to access services such as viewing the reproduction problems. Here, the display of the reproduction problems and the use of points will be described below.
[0083] FIG. 17 is a diagram illustrating a display screen of a reproduced question on the user terminal 30. In this example, the display screen D5 represents an example of a display screen on the user terminal 30. In this example, the field F51 represents a display field for displaying reproduced questions according to the search conditions input by the user. The field F51 displays a list of questions that match the search conditions, and displays, for each of the displayed questions, for example, the classification item, disease item, answer / non-answer item, and viewing item in the search conditions. In this example, when a user views a displayed reproduced question, if the question has already been answered (viewed), the user can freely view it from the viewing item "view". On the other hand, if the question to be viewed is an unanswered (unasked) question, the user can view the reproduced question by consuming the points held by the user. In this example, if the points held by the user do not reach the points required for viewing, the user can purchase the necessary points from the field F52. As described above, the user can view the reproduced question that he or she has searched for by using the points.
[0084] Returning to Fig. 15, in step S405, the information processing device 10 provides the reproduction problem to the user. In this example, the providing means 181 provides the corresponding reproduction problem stored in the database in response to the selection of a viewing item by the user, that is, in response to a request from the user, and can cause the provided problem to be displayed on the user terminal 30.
[0085] In step S406, the user views the selected reproduction problem via the user terminal 30. Here, viewing of the reproduction problem will be described below.
[0086] FIG. 18 is a diagram illustrating a reproduction problem viewing screen on the user terminal 30. In this example, the display screen D6 represents an example of a display screen on the user terminal 30. In this example, the field F61 represents a display field for displaying a reproduction problem selected by the user. The field F62 can accept an answer to the reproduction problem displayed in the field F61 from the user. The field F63 is a field for enabling editing of the reproduction problem displayed in the field F61 when the user edits (or modifies) at least a part of the reproduction problem. Note that viewing and modifying the reproduction problem is a service that can be used by multiple users. That is, in this case, the system can reproduce the problem using the collective intelligence of multiple users, so that more accurate reproduction is expected. When the user has completed all viewing, input, editing, etc., the user can transmit data from the field F64 to the information processing device 10. These data are recorded in the database of the information processing device 10.
[0087] As described above, in the information reproduction support system 1, a user can purchase / use points to view reproduction problems in the database. In addition, with respect to a reproduction problem provided by the information processing device 10, the user can input an answer to the reproduction problem or edit the reproduction problem.
[0088] 4. Variations The present invention is not limited to the above-described embodiment, and various modifications are possible. Some modifications will be described below. Two or more of the following items may be combined and applied.
[0089] (1) Information Reproduction Support System 1 The hardware configuration, network configuration, and functional configuration of the information reproduction support system 1 are not limited to those exemplified in the embodiment. The information reproduction support system 1 may have any hardware configuration, network configuration, and functional configuration as long as the required functions can be realized. For example, a plurality of devices may physically cooperate to function as the information reproduction support system 1. Note that the subjects, configuration, and system structure shown in FIG. 3 are merely an example and merely show an overview of the system. Therefore, for example, the services of the information reproduction support system 1 may be provided in the user terminal 30 by an application or the like constructed in the information processing device 10.
[0090] (2) Information processing device 10 The form of the functional configuration in the information processing device 10 is not limited to that exemplified in the embodiment. The information processing device 10 may have any form of functional configuration as long as the required function can be realized. In addition, a part of the functions of the information processing device 10 may be implemented in another server. This server may be, for example, a physical server or a virtual server (including a so-called cloud). In addition, the correspondence between the functional elements and the hardware is not limited to that exemplified in the embodiment. For example, in the embodiment, at least a part of the functions described as being implemented in the information processing device 10 may be implemented in another device or system, and conversely, at least a part of the functions described as being implemented in the other device or system may be implemented in the information processing device 10. In this example, the information processing device 10 may have at least a part of the functions of the AI 20. In this example, the information processing device 10 may have a function of generating a reproduction problem based on an input hint.
[0091] (3) AI20 AI20 is not limited to the one exemplified in the embodiment. In this example, AI20 may be configured with any model as long as it is a generative AI that generates a sentence from a given prompt. Furthermore, the generative AI is not limited to one that generates a sentence from a prompt, but may also generate an image or generate a sound. Furthermore, the prompt given to AI20 is not limited to a text (character string), but may include a sound or an image.
[0092] The AI 20 has a language model that has been pre-trained using a large amount of text data from various fields. Here, so-called fine tuning may be performed to generate a model specialized for a specific field (e.g., the reproduction of the national medical examination questions) by re-training a dataset of the specific field (e.g., the national medical examination questions) so as to correspond to a specific task (in the example of the embodiment, the reproduction of the national medical examination questions).
[0093] (4) User terminal 30 The user terminal 30 (or other device) is not limited to the one exemplified in the embodiment. In this example, the users who use the terminals use the information reproduction support system 1 through their own terminals, but the above-mentioned configuration and operation may be realized by any display screen, input device, and various UIs (User Interfaces).
[0094] (5) Section 3-1: How to present a reproduction problem The sequence chart shown in Fig. 7 merely shows one example of the operation, and the operation of the information reproduction support system 1 is not limited to this. Some of the operations shown in the figure may be omitted, the order may be changed, or new operations may be added. In this example, the hint that the system prompts the user to input in step S101 may be any information. Here, modified examples of the input screen will be described below.
[0095] FIG. 19 is a diagram illustrating a modified example of the input screen in the user terminal 30. In this example, the display screen D7 represents an example of the display screen in the user terminal 30. In this example, the fields F711 to F713 represent selection fields for allowing the user to select the amount of text in the test question. The fields F721 and F722 represent input fields for allowing the user to input attribute information of the case subject. The bars B731 to B733 represent input bars for allowing the user to input the percentage at which the specified information appeared in the question text. From the above, the system can obtain information necessary for reproducing the reproduction question from multiple angles.
[0096] Furthermore, the hint that the system prompts the user to input may be any information other than those exemplified in Fig. 19. For example, text, numerical values and units (scale), voice (auditory information), and / or images may be input as hints. Furthermore, the input format of the hint may be a description format, a button (item selection format), symbol input, and / or fill-in-the-blank input, etc.
[0097] Also, with regard to process (A), an example has been described in which the process proceeds to process (B) if no reproduction question candidates are extracted or presented even when information processing device 10 refers to the database in steps SA103 and SA104. However, the relationship between process (A) and process (B) is merely an example, and only one of these processes may be implemented, or both may be implemented. Furthermore, when both processes are implemented, the order in which either process is given priority may be determined.
[0098] Furthermore, the trigger for starting process (B) may be, for example, the following specific examples, where no reproduction problem corresponding to the hint input by the extraction means 15 is extracted. These include the case where the system judges that there is no corresponding candidate in the database of the information processing device 10, or the case where the reproduction problem extracted in process (A) is judged to be inappropriate by, for example, the user. Any other case may be applied as the trigger for starting process (B).
[0099] (6) Section 3-2: How to select a reproduction question 10 is merely an example of the operation, and the operation of the information reproduction support system 1 is not limited to this. Some of the operations shown in the figure may be omitted, the order may be changed, or new operations may be added. In this example, when the system causes the AI20 to regenerate candidates for reproduction problems in step S207, the AI20 may regenerate candidates for reproduction problems using a method, program, algorithm, or the like different from the method used to originally generate the reproduction problem to be regenerated.
[0100] (7) Section 3-3: How to fix the reproducible problem The sequence chart shown in Fig. 13 merely shows one example of the operation, and the operation of the information reproduction support system 1 is not limited to this. Some of the operations shown in the figure may be omitted, the order may be changed, or new operations may be added. In this example, the order of step S302 and steps S303 to S304 may be changed. This allows the information reproduction support system 1 to award points to the user after deciding whether or not to adopt the reproduction problem corrected by the correction instruction (depending on whether or not it is adopted).
[0101] In addition, in this example, when the system prompts the user to make corrections in step S301, for example, a function of suggesting correction candidates by the information processing device 10 / AI 20 may be implemented on the correction screen. Here, modified examples of the correction screen will be described below.
[0102] FIG. 20 is a diagram illustrating a modified example of the correction screen in the user terminal 30. In this example, the display screen D8 represents an example of the display screen in the user terminal 30. In this example, each field represents a correction field for correcting a candidate reproduction problem selected by the user, similar to FIG. 14. In this example, in the reproduction problem displayed in the field F81, for example, for a word corresponding to the position where the user places the cursor ("eye movement" in the example of FIG. 20), the information processing device 10 causes the AI 20 to present a predetermined number of words that are correction candidates. The information processing device 10 displays the candidate words presented by the AI 20 in the window W819 on the display screen D8 of the user terminal 30. Such a suggestion function allows the user to more easily correct the reproduction problem.
[0103] (8) Section 3-4: How to obtain and use points The sequence chart shown in Fig. 15 merely shows an example of the operation, and the operation of the information reproduction support system 1 is not limited to this. Some of the operations shown in the figure may be omitted, the order may be changed, or new operations may be added. In this example, in step S401, the system may prompt the user to input any search criteria. For example, it may be attribute information of the case subject (person).
[0104] (9) Database The database of the information reproduction support system 1 shown in Fig. 9 is not limited to the one exemplified in the embodiment. In this example, any type of data may be registered in the database, and may include attribute information of the reproduction problems in addition to the reproduction problems themselves. Alternatively, the relationships between the reproduction problems may be recorded in the database. In addition, the layout of the database is not limited to the one shown in the figure, and data may be managed in any layout.
[0105] (10)Display screen The display screens shown in Figures 8, 11, 12, 14, and 16 to 20 are not limited to those exemplified in the embodiment. In this example, the layout of each field may be defined for the display screen of the user terminal 30 according to the UI of various display screens. In addition, the layout or configuration of the display screen may be set to an optimal display screen according to the UI of a terminal such as a smartphone.
[0106] (11) Confidential information / confidential information pool The private information / private information pool is not limited to those exemplified in the embodiment. In this example, the private information is not limited to the example described for the National Medical Licensing Examination, and may be any examination question. The private information pool may also be a pool in which examination questions used in a certain examination are stored. Furthermore, the private information may be something other than examination questions, such as books in a library that are prohibited from being taken out. In this example, the private information pool does not necessarily have to be a database of information. Here, an application example of the information reproduction support system 1 will be described in more detail.
[0107] The private information / private information pool may be any information / database that is not freely accessible at the time. For example, the private information / private information pool may be information that was freely accessible in the past but is currently restricted in access or practically inaccessible, such as a book that is out of print (hereinafter referred to as an "out-of-print book"). That is, the information reproduction support system 1 may be intended to reproduce (restore) an out-of-print book. In this way, the private information pool may be, for example, an out-of-print book itself that is in existence / not in existence, an out-of-print book itself owned by an individual or various institutions, or a library in which an out-of-print book is secretly kept (prohibited to be taken out or not yet made into a database). For example, the information reproduction support system 1 accepts at least a part of information about the out-of-print book as a hint from a user who has read the out-of-print book. Then, based on the hint accepted from the user, the information reproduction support system 1 reproduces the reproduced information / reproduced information pool of the target out-of-print book. In this example, the out-of-print book is composed of, for example, text (multiple languages, characters, ancient characters), symbols, images, illustrations, and / or information such as ink and paper used in the book. Therefore, the information reproduction support system 1 accepts at least any of these pieces of information as hints from the user and reproduces the out-of-print book. The restoration of out-of-print books described so far may be performed by modifying and optimizing at least a part of the configuration and operation of the information reproduction support system 1. As described above, the information reproduction support system 1 can reproduce and restore information that exists but is not public, including out-of-print books, or information that no longer exists and is relied on people's memories.
[0108] (12) Reproduction information / reproduction information pool The reproduced information / reproduced information pool is not limited to those exemplified in the embodiment. In this example, the reproduced information may be any information that reproduces private information, for example, information that reproduces a part of private information, or information that reproduces private information with supplementary information.
[0109] Furthermore, the form / data format of the reproduction information is not limited to that exemplified in the embodiment. In this example, the reproduction information may have any form / data format, and may include, for example, an image, an audio, a video, and / or a 3D model that reproduces a CT image in 3D. Furthermore, data formats corresponding to these forms may be arbitrarily converted and used within the system.
[0110] (13) Examination questions (National Medical Examination) The test questions are not limited to those exemplified in the embodiment. In this example, the test questions may be multiple-choice tests, that is, a question format in which multiple answer options are given for one question, as in the actual national medical examination, or test questions that adopt other question formats. In this example, the test questions may be test questions that adopt question formats such as multiple choice, descriptive, fill-in-the-blank, or mark sheet format.
[0111] (14) Blockchain Regarding the configuration and operation exemplified in the embodiment, blockchain technology may be applied to the information reproduction support system 1. Regarding the application of blockchain technology to the information reproduction support system 1 in this example, for example, data registered in a database may be recorded in a blockchain network. This makes it possible to protect various types of data in a state where they cannot be deleted or rewritten. In addition, any type of data may be recorded in the blockchain network.
[0112] (15)Other The various programs executed by CPU101, CPU301, etc. may be provided by downloading via a network such as the Internet, or may be provided in a state recorded on a computer-readable non-transitory recording medium such as a DVD-ROM. Each processor may be, for example, an MPU (Micro Processing Unit) or a GPU (Graphics Processing Unit) instead of a CPU. [Explanation of symbols]
[0113] 1...information reproduction support system, 10...information processing device, 20...AI, 30...user terminal, 9...network, 11...hint receiving means, 12...control means, 13...presentation means, 14...writing means, 15...extraction means, 16...correction receiving means, 17...decision means, 181...provision means, 182...selection receiving means, 19...storage means (DB), 101...CPU, 102...memory, 103...storage, 104...communication IF, 301...CPU, 302...memory, 303...storage, 304...communication IF, 305...input device, 306...display device, 1001...national medical examination question database, D...display screen, F...field, B...bar, W...window
Claims
1. a hint receiving means for receiving an input of a hint for reproducing private information belonging to the private information pool from a user; A control means for generating candidates for reproduced information by providing the hint to a generative AI and reproducing the non-public information; a presentation means for presenting the candidates to the user; a writing means for writing the candidate into a reproduction information pool as the reproduction information of the non-public information in response to an instruction from the user; providing means for providing the reproduction information stored in the reproduction information pool in response to a request from another device; An information reproduction support system having the above structure.
2. an extracting means for extracting the reproduction information corresponding to the hint from the reproduction information pool; The presentation means presents the extracted reproduction information to the user.
2. An information reproduction support system according to claim 1.
3. The control means, when the reproduction information corresponding to the hint is not extracted by the extraction means, gives the hint to the generation system AI to generate the candidates for the reproduction information.
3. An information reproduction support system according to claim 2.
4. a correction receiving means for receiving a correction instruction for the extracted reproduction information or the candidate from the user, The writing means writes the reproduction information or the candidate corrected in accordance with the correction instruction into the reproduction information pool.
3. An information reproduction support system according to claim 2.
5. a determination means for determining which of the reproduction information corrected by the correction instruction and the reproduction information stored in the reproduction information pool before the correction is to be adopted as the reproduction information; 5. An information reproduction support system according to claim 4.
6. The control means gives the hint to the generation system AI to generate a plurality of candidates for the reproduction information; The presenting means presents the plurality of candidates to the user, a selection receiving means for receiving a selection of one of the plurality of candidates from the user; 2. An information reproduction support system according to claim 1.
7. The non-public information pool is a pool in which test questions used in a certain test are stored.
2. An information reproduction support system according to claim 1.
8. The test is a multiple choice test.
8. An information reproduction support system according to claim 7.
9. the hint receiving means receives an input of the hint for each of the question sentences and options of the multiple-choice test; The control means causes the generation system AI to generate the candidates for the reproduction information of the question sentence and the options.
9. An information reproduction support system according to claim 8.
10. The computer receiving, from a user, an input of a hint for reproducing private information belonging to a private information pool; A step of generating candidates for reproduced information that reproduces the non-public information by providing the hint to a generative AI; presenting the candidates to the user; writing the candidate into a reproduction information pool as the reproduction information of the non-public information in response to an instruction from the user; providing the reproduction information stored in the reproduction information pool in response to a request from another device; The information reproduction support method includes the steps of:
11. On the computer, receiving, from a user, an input of a hint for reproducing private information belonging to a private information pool; A step of generating candidates for reproduced information that reproduces the non-public information by providing the hint to a generative AI; presenting the candidates to the user; writing the candidate into a reproduction information pool as the reproduction information of the non-public information in response to an instruction from the user; providing the reproduction information stored in the reproduction information pool in response to a request from another device; A program for executing the above.
Citation Information
Patent Citations
Scenery information providing system and method
JP2004070782A
Document information retrieval device
JP3356519B2
