Information processing device, program, and information processing method

Abstract

The present invention improves the efficiency of chats for eliciting know-how. An information processing device 10 is provided with a control unit 15 that acquires a precondition when starting a chat that uses a language model to elicit know-how from a user, and that adjusts the content of a question to be output to the user in the chat in accordance with the precondition.

Description

Information Processing Apparatus, Program, and Information Processing Method

[0001] The present disclosure relates to an information processing apparatus, a program, and an information processing method.

[0002] Conventionally, techniques related to learning systems such as knowledge and know-how have been known. For example, Patent Document 1 discloses creating second-level reference data based on first-level reference data and outputting a lecture including voice that vocalizes the text data of the second-level reference data and video of an avatar instructor.

[0003] Japanese Patent No. 7473270

[0004] Patent Document 1 discloses a learning system that uses machine learning such as generative AI. However, Patent Document 1 does not discuss the efficiency of chats for extracting know-how from experts such as veterans.

[0005] An object of the present disclosure is to improve the efficiency of chats for extracting know-how.

[0006] The information processing apparatus according to the present disclosure includes a control unit that acquires a precondition when starting a chat for extracting know-how from a user using a language model, and adjusts the content of a question to the user output in the chat according to the precondition.

[0007] The program according to the present disclosure causes a computer to execute operations including acquiring a precondition when starting a chat for extracting know-how from a user using a language model, and adjusting the content of a question to the user output in the chat according to the precondition.

[0008] The information processing method according to the present disclosure is an information processing method executed by an information processing apparatus, and includes acquiring a precondition when starting a chat for extracting know-how from a user using a language model, and adjusting the content of a question to the user output in the chat according to the precondition.

[0009] According to the present disclosure, the efficiency of chats for extracting know-how can be improved.

[0010] This figure shows the configuration of the information processing system according to the embodiment of this disclosure. This is a flowchart showing the operation of the information processing system according to the embodiment of this disclosure.

[0011] The embodiments of this disclosure will be described below with reference to the drawings.

[0012] Figure 1 is a diagram showing the configuration of the information processing system 1 according to an embodiment of this disclosure. The configuration and overview of the information processing system 1 according to an embodiment of this disclosure will be described with reference to Figure 1.

[0013] The information processing system 1 comprises an information processing device 10 and a terminal device 20. The information processing device 10 and the terminal device 20 are communicated with each other via a network 30. The network 30 may include a mobile communication network and the internet.

[0014] The information processing device 10 is, for example, a server device installed in a data center or the like. For example, the information processing device 10 is a server belonging to a cloud computing system or other computing system. The information processing device 10 can communicate with a terminal device 20 via a network 30. The information processing device 10 includes a language model. In this embodiment, the language model includes, for example, a Large Language Model (LLM), a chatbot, or any other dialogue system. The information processing device 10 can use the language model to perform a chat to extract know-how from the user. When performing a chat, the information processing device 10 can output questions to the user to extract know-how. For example, the information processing device 10 can output questions to the user via the terminal device 20. Also, for example, the information processing device 10 can obtain the user's answer to the question via the terminal device 20. Note that Figure 1 shows an example in which the information processing system 1 has one information processing device 10, but it is not limited to this. The information processing system 1 may have two or more information processing devices 10.

[0015] The terminal device 20 is any device used by the user. The terminal device 20 may be a general-purpose electronic device such as a smartphone, tablet, wearable device, or PC (Personal Computer), or a dedicated electronic device. Note that Figure 1 shows an example where the information processing system 1 has one terminal device 20, but it is not limited to this. The information processing system 1 may have two or more terminal devices 20.

[0016] First, an overview of this embodiment will be described, and details will be described later. The information processing device 10 can perform a chat to extract know-how from the user. The information processing device 10 can perform a chat using a language model.

[0017] Here, "know-how" refers to specific or specialized knowledge, techniques, methods, or information. For example, know-how may apply to tasks such as screwing or assembling, operating applications or software, or procedures for performing work, but it is not limited to these.

[0018] The information processing device 10 executes a chat to extract know-how from the user. The user may be, for example, a veteran with various knowledge and information. When the information processing device 10 starts a chat to extract know-how from the user, it obtains preconditions for conducting the chat. These preconditions may include, for example, a time limit for the chat, the number of questions that can be asked in the chat, and the technical field that the chat will cover. Once the information processing device 10 obtains the preconditions, it adjusts the content of the questions to be output to the user in the chat according to the preconditions. The information processing device 10 outputs the adjusted questions.

[0019] The device operated by the user is the terminal device 20. Therefore, when the information processing device 10 performs a chat to extract know-how from the user, it outputs questions to the user via the terminal device 20. The information processing device 10 also obtains the user's answers to the questions via the terminal device 20.

[0020] (Configuration of the information processing device) Next, the configuration of the information processing device 10 according to the embodiment of this disclosure will be described.

[0021] As shown in Figure 1, the information processing device 10 comprises a communication unit 11, a storage unit 12, an input unit 13, an output unit 14, and a control unit 15.

[0022] The communication unit 11 includes a communication module that connects to the network 30. For example, the communication unit 11 may include a communication module that corresponds to a LAN (Local Area Network). In one embodiment, the information processing device 10 is connected to the network 30 via the communication unit 11. The communication unit 11 transmits and receives various types of information via the network 30. The communication unit 11 can communicate with the terminal device 20 via the network 30.

[0023] The storage unit 12 is, for example, a semiconductor memory, a magnetic memory, or an optical memory, but is not limited to these. The storage unit 12 may function as, for example, a main memory, an auxiliary memory, or a cache memory. The storage unit 12 stores any information used in the operation of the information processing device 10. For example, the storage unit 12 may store system programs, application programs, and various information received by the communication unit 11. The information stored in the storage unit 12 may be updateable with information received from the network 30 via the communication unit 11, for example. A part of the storage unit 12 may be installed outside the information processing device 10. In that case, the part of the storage unit 12 installed outside may be connected to the information processing device 10 via any interface.

[0024] The input unit 13 includes one or more input interfaces that detect user input and acquire input information based on user operations. For example, the input unit 13 includes, but is not limited to, physical keys, capacitive keys, a touchscreen integrated with the display of the output unit 14, or a microphone that accepts voice input.

[0025] The output unit 14 includes one or more output interfaces for outputting information and notifying the user. For example, the output unit 14 includes, but is not limited to, a display for outputting information as an image, a speaker for outputting information as sound, etc.

[0026] The control unit 15 includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU (Central Processing Unit) or GPU (Graphics Processing Unit), or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). The control unit 15 controls each part of the information processing device 10 and executes processes related to the operation of the information processing device 10.

[0027] The functions of the information processing device 10 are realized by executing the program according to this embodiment on a processor corresponding to the control unit 15. In other words, the functions of the information processing device 10 are realized by software. The program causes the computer to perform the operations of the information processing device 10, thereby causing the computer to function as the information processing device 10. That is, the computer functions as the information processing device 10 by performing the operations of the information processing device 10 according to the program.

[0028] In this embodiment, the program can be recorded on a computer-readable recording medium. The computer-readable recording medium includes non-temporary computer-readable media, such as magnetic recording devices, optical discs, magneto-optical recording media, or semiconductor memory. The program can be distributed, for example, by selling, transferring, or lending portable recording media such as DVDs (Digital Versatile Discs) or CD-ROMs (Compact Disc Read Only Memory) on which the program is recorded. Alternatively, the program may be distributed by storing it on the storage of an external server and transmitting it from the external server to other computers. The program may also be provided as a program product.

[0029] Some or all of the functions of the information processing device 10 may be implemented by a dedicated circuit corresponding to the control unit 15. In other words, some or all of the functions of the information processing device 10 may be implemented by hardware.

[0030] (Operation of the Information Processing System) The operation of the Information Processing System 1 will be explained with reference to the flowchart shown in Figure 2.

[0031] S101: The control unit 15 of the information processing device 10 obtains the preconditions for the chat when starting a chat to extract know-how from the user.

[0032] The user is a veteran with various knowledge and information regarding the know-how being extracted. The memory unit 12 stores a language model. The language model may be, for example, a Large Language Model (LLM). The control unit 15 can use the language model stored in the memory unit 12 to perform a chat to extract know-how from the user. When performing the chat, the control unit 15 may perform the chat using text or voice.

[0033] The prerequisites for a chat designed to extract know-how from users include, for example, a time limit for the chat, the number of questions that can be asked in the chat, and at least one of the technical fields covered by the chat.

[0034] When the information processing device 10 performs a chat to extract know-how from the user, the user may only have a limited amount of time to dedicate to the chat. In such cases, the user can, for example, set a time limit of 10 minutes as a prerequisite. Alternatively, the user can, for example, set a limit of 10 questions as a prerequisite.

[0035] When the information processing device 10 performs a chat to extract know-how from the user, if the technical field is clearly defined, it can efficiently extract the necessary technical field know-how from the user. If the user wants to clarify the technical field, they can, for example, specify the technical field as "screw fastening" as a prerequisite.

[0036] The prerequisites may be entered by the user into the terminal device 20, for example, before the chat starts. In this case, when the terminal device 20 receives the prerequisites from the user, it transmits the prerequisites to the information processing device 10. The control unit 15 of the information processing device 10 obtains the prerequisites transmitted by the terminal device 20 via the communication unit 11.

[0037] Alternatively, the information processing device 10 may obtain the prerequisites by asking for them within the chat at the start of the chat. In this case, the information processing device 10 outputs a question in the chat inquiring about the prerequisites at the start of the chat. The terminal device 20 displays the question in the chat inquiring about the prerequisites obtained from the information processing device 10. When the terminal device 20 receives input from the user's answer to the prerequisite inquiry, it transmits the prerequisites to the information processing device 10. The control unit 15 of the information processing device 10 obtains the prerequisites transmitted by the terminal device 20 via the communication unit 11.

[0038] S102: The control unit 15 of the information processing device 10 adjusts the content of the questions to be output to the user in the chat that extracts know-how from the user, according to the preconditions obtained in S101.

[0039] For example, if the prerequisite includes a time limit, the control unit 15 automatically adjusts the priority of questions according to the time limit. For example, if the time limit is long, the control unit 15 may automatically adjust the priority of questions to include questions from various perspectives so that the content to be extracted as know-how can be comprehensively elicited. Also, for example, if the time limit is short, the control unit 15 may automatically adjust the priority of questions to prioritize questions of high importance so that the important content to be extracted as know-how can be reliably elicited.

[0040] For example, if the prerequisite includes the number of questions, the control unit 15 automatically adjusts the priority of the questions according to the number of questions. For example, if there are many questions, the control unit 15 may automatically adjust the priority of the questions to include questions from various perspectives so that the content to be extracted as know-how can be comprehensively extracted. Also, for example, if there are few questions, the control unit 15 may automatically adjust the priority of the questions to prioritize questions of high importance so that the important content to be extracted as know-how can be reliably extracted.

[0041] For example, if the prerequisites include a technical field, the control unit 15 automatically adjusts the priority of questions according to the technical field. For example, if the technical field is "screw fastening," the control unit 15 may automatically adjust the priority of questions in order to efficiently extract know-how related to "screw fastening."

[0042] If the prerequisite includes a time limit, the control unit 15 may automatically adjust the priority of questions to be asked during the chat, according to the remaining time relative to the time limit. For example, if the prerequisite is a time limit of 10 minutes and there are 3 minutes remaining, the control unit 15 may automatically adjust the priority of questions so that important know-how can be extracted within the remaining 3 minutes.

[0043] During the chat execution, the control unit 15 may automatically adjust the priority of the questions to be asked after the answer according to the user's answer to the question. For example, during the chat execution, the control unit 15 may automatically adjust the priority of the questions to be asked after the user's answer so that the priority of the questions with a higher degree of relevance to the user's answer to the question becomes higher. By prioritizing the questions with a higher degree of relevance to the user's answer in this way, the control unit 15 can have a natural chat with the user and efficiently extract know-how from the user. In addition, since the questions with a higher degree of relevance are prioritized, the user can answer comfortably, so that know-how can be efficiently extracted from the user.

[0044] During the chat execution, when it becomes unnecessary to ask the questions planned according to the user's answer to the question, the control unit 15 may automatically adjust the content of the question to the user to be asked after the user's answer so as to omit the planned question. For example, if three questions are prepared as the remaining questions and in the answer to the first question, the user includes the content that would be the answer to the third question, the control unit 15 may automatically adjust the content of the question to the user so as to omit the planned third question. Thereby, it is possible to prevent the user from being bothered by asking duplicate questions.

[0045] S103: When the control unit 15 of the information processing apparatus 10 adjusts the content of the question to the user, the control unit 15 outputs a question according to the adjusted content.

[0046] The control unit 15 transmits the question to the terminal device 20 via the communication unit 11. The terminal device 20 outputs the question acquired from the information processing apparatus 10.

[0047] As described above, in the information processing apparatus 10 according to the present embodiment, when starting a chat for extracting know-how from the user using a language model, the control unit 15 acquires a precondition, and according to the acquired precondition, adjusts the content of the question to the user to be output in the chat. Thereby, when executing a chat for extracting know-how from the user, the information processing apparatus 10 according to the present embodiment can appropriately adjust the content of the question to the user according to the precondition. Therefore, the information processing apparatus 10 according to the present embodiment can improve the efficiency of the chat for extracting know-how from the user.

[0048] The present disclosure is not limited to the above-described embodiments. For example, a plurality of blocks described in the block diagram may be integrated, or one block may be divided. Instead of executing a plurality of steps described in the flowchart in time series according to the description, they may be executed in parallel or in a different order according to the processing capabilities of the device that executes each step, or as necessary. In addition, modifications can be made without departing from the spirit of the present disclosure.

[0049] For example, some of the processing operations executed in the information processing apparatus 10 in the above-described embodiment may be executed in the terminal device 20. Also, some of the processing operations executed in the terminal device 20 in the above-described embodiment may be executed in the information processing apparatus 10.

[0050] Some embodiments of the present disclosure are illustrated below. However, it should be noted that embodiments of the present disclosure are not limited to these. [Appendix 1] An information processing device comprising: a control unit that acquires preconditions when initiating a chat to extract know-how from a user using a language model, and adjusts the content of the questions to be output to the user in the chat according to the preconditions. [Appendix 2] An information processing device according to Appendix 1, wherein the preconditions include at least one of a time limit, the number of questions, and a technical field. [Appendix 3] An information processing device according to Appendix 1 or 2, wherein the preconditions include a time limit, and the control unit automatically adjusts the priority of the questions according to the time limit. [Appendix 4] An information processing device according to any one of Appendix 1 to 3, wherein the preconditions include a time limit, and the control unit automatically adjusts the priority of the questions to be asked for the remaining time according to the remaining time relative to the time limit. [Appendix 5] An information processing device according to any one of Appendix 1 to 4, wherein the control unit automatically adjusts the priority of subsequent questions according to the user's answer to the question. [Appendix 6] An information processing device according to any one of Appendix 1 to 5, wherein the control unit automatically adjusts the priority of subsequent questions so that questions with a high degree of relevance to the user's answer have a higher priority. [Appendix 7] An information processing device according to any one of Appendix 1 to 6, wherein the control unit automatically adjusts the content of subsequent questions to the user so that the planned questions are omitted when the user's answer to a question makes it unnecessary to ask the planned questions. [Appendix 8] A program that causes a computer to perform an operation including: acquiring preconditions when starting a chat to extract know-how from a user using a language model; and adjusting the content of questions to be output to the user in the chat according to the preconditions. [Appendix 9] A program according to Appendix 8, wherein the preconditions include at least one of a time limit, the number of questions, and a technical field.[Note 10] In the program described in Note 8 or 9, the prerequisite includes a time limit, and the adjustment is a program that automatically adjusts the priority of the questions according to the time limit. [Note 11] In the program described in any one of Notes 8 to 10, the prerequisite includes a time limit, and the adjustment is a program that automatically adjusts the priority of the questions to be asked in the remaining time according to the remaining time relative to the time limit. [Note 12] In the program described in any one of Notes 8 to 11, the adjustment is a program that automatically adjusts the priority of subsequent questions according to the user's answer to the question. [Note 13] In the program described in any one of Notes 8 to 12, the adjustment is a program that automatically adjusts the priority of subsequent questions so that questions with a high degree of relevance to the user's answer have a higher priority. [Note 14] In a program described in any one of Notes 8 to 13, the adjustment is a program that automatically adjusts the content of subsequent questions to the user so that if the user's answer to the question makes it unnecessary to ask the planned question, the planned question is omitted. [Note 15] An information processing method executed by an information processing device, comprising: obtaining preconditions when starting a chat to extract know-how from a user using a language model; and adjusting the content of the questions to be output to the user in the chat according to the preconditions. [Note 16] An information processing method described in Note 15, wherein the preconditions include at least one of a time limit, the number of questions, and a technical field. [Note 17] An information processing method described in Note 15 or 16, wherein the preconditions include a time limit, and the adjustment is an information processing method that automatically adjusts the priority of the questions according to the time limit.[Note 18] An information processing method described in any one of Notes 15 to 17, wherein the preconditions include a time limit, and the adjustment is an information processing method that automatically adjusts the priority of the questions to be asked in the remaining time according to the remaining time relative to the time limit. [Note 19] An information processing method described in any one of Notes 15 to 18, wherein the adjustment is an information processing method that automatically adjusts the priority of subsequent questions according to the user's answer to the question. [Note 20] An information processing method described in any one of Notes 15 to 19, wherein the adjustment is an information processing method that automatically adjusts the priority of subsequent questions so that questions with a high degree of relevance to the user's answer have a higher priority.

[0051] 1 Information Processing System 10 Information Processing Device 11 Communication Unit 12 Storage Unit 13 Input Unit 14 Output Unit 15 Control Unit 20 Terminal Device 30 Network

Claims

1. An information processing device comprising: a control unit that obtains preconditions when initiating a chat to extract know-how from a user using a language model, and adjusts the content of the questions to be output to the user in the chat according to the preconditions.

2. An information processing apparatus according to claim 1, wherein the preconditions include at least one of a time limit, a number of questions, and a technical field.

3. An information processing apparatus according to claim 1, wherein the precondition includes a time limit, and the control unit automatically adjusts the priority of the questions according to the time limit.

4. An information processing apparatus according to claim 1, wherein the precondition includes a time limit, and the control unit automatically adjusts the priority of the questions to be asked for the remaining time according to the remaining time relative to the time limit.

5. An information processing apparatus according to claim 1, wherein the control unit automatically adjusts the priority of subsequent questions in accordance with the user's answer to the question.

6. An information processing device according to claim 5, wherein the control unit automatically adjusts the priority of subsequent questions so that questions that are highly relevant to the user's answers are given higher priority.

7. An information processing apparatus according to claim 1, wherein the control unit automatically adjusts the content of subsequent questions to the user so as to omit the previously scheduled questions when the user's answer to the question makes it unnecessary to ask the previously scheduled questions.

8. A program that causes a computer to perform actions including: obtaining preconditions when initiating a chat to extract know-how from a user using a language model; and adjusting the content of the questions to be output to the user in the chat according to the preconditions.

9. The program according to claim 8, wherein the preconditions include at least one of a time limit, a number of questions, and a field of the technical art.

10. The program according to claim 8, wherein the precondition includes a time limit, and the adjustment is a program that automatically adjusts the priority of the questions according to the time limit.

11. The program according to claim 8, wherein the precondition includes a time limit, and the adjustment is a program that automatically adjusts the priority of the questions to the remaining time according to the remaining time relative to the time limit.

12. The program according to claim 8, wherein the adjustment is an automatic adjustment of the priority of subsequent questions in accordance with the user's answer to the question.

13. The program according to claim 12, wherein the adjustment is an automatic adjustment of the priority of subsequent questions so that questions that are highly relevant to the user's answers have a higher priority.

14. The program according to claim 8, wherein the adjustment is a program that automatically adjusts the content of subsequent questions to the user so that if the user's answer to the question makes it unnecessary to ask the planned question, the planned question is omitted.

15. An information processing method executed by an information processing device, comprising: obtaining preconditions when starting a chat to extract know-how from a user using a language model; and adjusting the content of the questions to be output to the user in the chat according to the preconditions.

16. An information processing method according to claim 15, wherein the preconditions include at least one of a time limit, a number of questions, and a technical field.

17. An information processing method according to claim 15, wherein the precondition includes a time limit, and the adjustment is an information processing method in which the priority of the questions is automatically adjusted according to the time limit.

18. An information processing method according to claim 15, wherein the precondition includes a time limit, and the adjustment is an information processing method in which the priority of the questions to be given to the remaining time is automatically adjusted according to the remaining time relative to the time limit.

19. An information processing method according to claim 15, wherein the adjustment is an information processing method in which the priority of subsequent questions is automatically adjusted according to the user's answer to the question.

20. The information processing method according to claim 19, wherein the adjustment is an information processing method that automatically adjusts the priority of subsequent questions so that questions that are highly relevant to the user's answers have a higher priority.

Images