Method, non-transitory computer-readable medium, and information processing device
By associating know-how information with provenance information in a database, the system improves dialogue systems by reducing information contamination through origin verification.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-07-16
- Publication Date
- 2026-03-05
AI Technical Summary
Conventional dialogue systems fail to consider the origin of documents used in machine learning, leading to unknown information contamination.
A method and system that associates know-how information with provenance information, storing them together in a database, and outputs answers to questions including both, thereby reducing the likelihood of information contamination.
Enhances the reliability of dialogue systems by allowing users to verify the origin of know-how information, thus minimizing information contamination.
Smart Images

Figure JP2025025519_05032026_PF_FP_ABST
Abstract
Description
Method, non-transitory computer-readable medium and information processing device CROSS-REFERENCE TO RELATED APPLICATIONS
[0001] This application claims priority from Japanese Patent Application No. 2024-150087, filed in Japan on August 30, 2024, the entire disclosure of which is incorporated herein by reference.
[0002] The present disclosure relates to a method, a non-transitory computer-readable medium, and an information processing device.
[0003] Conventionally, there is known a technique for providing a dialogue system that outputs a response to an input sentence. For example, Patent Literature 1 discloses a technique for using documents and queries belonging to a specific domain in machine learning of a search model for a dialogue bot.
[0004] Japanese Patent Application Laid-Open No. 2023-076413
[0005] However, in the conventional dialogue systems, the origin of the documents used in machine learning is not taken into consideration, and the origin of the information on which the answers output from the dialogue systems are based is unknown, which can lead to information contamination. Therefore, there is room for improvement in the technology for providing dialogue systems.
[0006] In view of the above circumstances, an object of the present disclosure is to improve the technology for providing a dialogue system.
[0007] A method according to an embodiment of the present disclosure is a method executed by an information processing device, and includes: when know-how information is input, acquiring provenance information indicating the origin of the know-how information, and storing the know-how information and the provenance information in a database in association with each other; when a question regarding know-how is acquired, acquiring one or more sets of know-how information and provenance information from the database; and outputting an answer to the question that includes the acquired one or more sets of know-how information and provenance information.
[0008] A non-transitory computer-readable medium according to an embodiment of the present disclosure causes a computer to perform operations including: when know-how information is input, acquiring provenance information indicating the origin of the know-how information, and storing the know-how information and the provenance information in a database in association with each other; when a question regarding know-how is acquired, acquiring one or more sets of know-how information and provenance information from the database, and outputting an answer to the question that includes the acquired one or more sets of know-how information and provenance information.
[0009] An information processing device according to an embodiment of the present disclosure is an information processing device including a control unit, wherein when know-how information is input, the control unit acquires provenance information indicating the origin of the know-how information, associates the know-how information with the provenance information, and stores the know-how information and the provenance information in a database; when a question regarding know-how is acquired, the control unit acquires one or more sets of know-how information and provenance information from the database; and outputs an answer to the question that includes the acquired one or more sets of know-how information and provenance information.
[0010] According to one embodiment of the present disclosure, a technique for providing a dialogue system is improved.
[0011] It is a block diagram showing a schematic configuration of a system according to an embodiment of the present disclosure.It is a block diagram showing a schematic configuration of a server.It is a block diagram showing a schematic configuration of an information processing device.It is a flowchart showing an operation of the information processing device.
[0012] Hereinafter, embodiments of the present disclosure will be described.
[0013] (Overview of the embodiment) An overview of a system 1 according to an embodiment of the present disclosure will be described with reference to Fig. 1. The system 1 includes a server 10 and an information processing device 20. The server 10 and the information processing device 20 are capable of communicating with each other via a network 30 such as the Internet. In this embodiment, the system 1 functions as a dialogue system that outputs answers to questions input by a user, for example.
[0014] The server 10 includes one or more computers that can communicate with each other. In this embodiment, the server 10 stores a database (DB) that can store know-how information indicating know-how in a specific field, for example. Know-how refers to specific or specialized knowledge, technology, skills, techniques, or information, and is typically communicated through explanations using words, images, or actions. The subject of know-how includes, but is not limited to, tasks such as screwing or assembly, application or software operation, or business procedures. The "specific field" can be determined arbitrarily depending on the usage manner of the system 1. In one example, if the system 1 is used by a vehicle manufacturer, the "specific field" may include fields such as vehicle manufacturing, maintenance, or sales.
[0015] The information processing device 20 is any computer, such as a smartphone, a tablet terminal, a wearable terminal, or a laptop. In this embodiment, a user can use the information processing device 20 to, for example, input new know-how information or input a question related to know-how.
[0016] An overview of this embodiment will be described below, and details will be provided later. When know-how information is input, the information processing device 20 according to this embodiment acquires provenance information indicating the origin of the know-how information, associates the know-how information with the provenance information, and stores the know-how information and the provenance information in a database. When the information processing device 20 acquires a question about know-how, it acquires one or more sets of know-how information and provenance information from the database. Then, the information processing device 20 outputs a response to the question that includes the acquired one or more sets of know-how information and provenance information.
[0017] According to this embodiment, for example, a user who inputs a question about know-how can check each piece of know-how information output as an answer together with its origin information. Therefore, according to this embodiment, the technology for providing a dialogue system is improved in that the probability of information contamination occurring when using the dialogue system is reduced.
[0018] Next, each component of the system 1 will be described in detail.
[0019] (Configuration of Server) The components of the server 10 will be described in detail with reference to Fig. 2. The server 10 includes a communication unit 11, a storage unit 12, and a control unit 13.
[0020] The communication unit 11 includes one or more communication interfaces that connect to a network 30 such as the Internet. The communication interfaces are compatible with mobile communication standards such as 4G (4th Generation) or 5G (5th Generation), wired LAN (Local Area Network) standards, or wireless LAN standards, but are not limited to these and may be compatible with any communication standard.
[0021] The storage unit 12 includes one or more memories. The memories may be, but are not limited to, semiconductor memories, magnetic memories, or optical memories. Each memory included in the storage unit 12 may function as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 12 stores any information used in the operation of the server 10. For example, the storage unit 12 may store system programs, application programs, databases, and the like.
[0022] The control unit 13 includes one or more processors, one or more programmable circuits, one or more dedicated circuits, or a combination thereof. The processor may be, for example, a general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or a dedicated processor specialized for a specific process, but is not limited to these. The programmable circuit may be, for example, but is not limited to, an FPGA (Field-Programmable Gate Array). The dedicated circuit may be, for example, but is not limited to, an ASIC (Application Specific Integrated Circuit). The control unit 13 controls the overall operation of the server 10.
[0023] (Configuration of Information Processing Device) The components of the information processing device 20 will be described in detail with reference to Fig. 3. The information processing device 20 includes a communication unit 21, an output unit 22, an input unit 23, a storage unit 24, and a control unit 25.
[0024] The communication unit 21 includes one or more communication interfaces that connect to the network 30. The communication interfaces correspond to, for example, a mobile communication standard, a wired LAN standard, or a wireless LAN standard, but are not limited to these and may correspond to any communication standard.
[0025] The output unit 22 includes one or more output devices that output information to notify the user. The output devices may be, for example, but not limited to, a display that outputs information as a video or a speaker that outputs information as a sound. The output unit 22 may also include an interface for connecting an external output device.
[0026] The input unit 23 includes one or more input devices that detect input operations by the user. Examples of the input devices include, but are not limited to, physical keys, capacitive keys, a mouse, a touch panel, a touch screen integrated with the display of the output unit 22, or a microphone. The input unit 23 may also include an interface for connecting an external input device.
[0027] The storage unit 24 includes one or more memories. Each memory included in the storage unit 24 may function as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 24 stores any information used in the operation of the information processing device 20. For example, the storage unit 24 may store system programs, application programs, etc.
[0028] The control unit 25 includes one or more processors, one or more programmable circuits, one or more dedicated circuits, or a combination thereof. The control unit 25 controls the overall operation of the information processing device 20.
[0029] (Operation of Information Processing Apparatus) The operation of the information processing apparatus 20 will be described with reference to FIG.
[0030] S100: The control unit 25 of the information processing device 20 determines whether or not know-how information has been input via the input unit 23. If it is determined that know-how information has been input (S100—Yes), the process proceeds to S101. On the other hand, if it is determined that know-how information has not been input (S100—No), the process proceeds to S102.
[0031] The know-how information is, for example, as described above, information indicating any know-how in a specific field. The know-how information may include, for example, text data, electronic document data, audio data, image data, or a combination thereof. In the know-how information, the know-how may be written in natural language or in accordance with a specific format. In one example, when a user wants to store new know-how in the database, the user can input know-how information indicating the know-how using the information processing device 20.
[0032] S101: If it is determined in S100 that know-how information has been input (S100-Yes), the control unit 25 acquires provenance information indicating the origin of the know-how information, associates the know-how information with the provenance information, and stores the know-how information and the provenance information in a database of the server 10 (storage unit 12). The provenance information may include, but is not limited to, information about the user who input the know-how information, information about the user's attributes, a location indicating the situation in which the know-how information was input, a device used and its parameters, a data type, a data format, or information referred to by the user when inputting the know-how information.
[0033] Specifically, the control unit 25 transmits the know-how information and the corresponding provenance information to the server 10 via the communication unit 21 and the network 30, thereby storing the know-how information and the provenance information in association with each other in the database.
[0034] Any method can be used to acquire the provenance information. For example, the user may input the provenance information when inputting the know-how information. In this case, the control unit 25 acquires the input provenance information.
[0035] Furthermore, for example, the control unit 25 may acquire the origin information by automatically detecting the origin of the input know-how information. Specifically, if the input know-how information includes the name of the creator or the name of the organization to which the creator belongs, the control unit 25 may automatically detect the name as the origin of the know-how information.
[0036] Alternatively, when the input know-how information includes audio data of a conference attended by multiple people and data indicating the names of the multiple people, the control unit 25 may automatically detect the names of the multiple people as the origin of the know-how information. Here, when the audio data is input as know-how information, the control unit 25 may divide the audio data by speaker using a speaker separation function and acquire each divided audio data as an individual piece of know-how information. In such a case, the control unit 25 may store each piece of know-how information (i.e., each divided audio data) in association with origin information indicating the name of the person who spoke the audio data in the database.
[0037] S102: The control unit 25 determines whether or not a question about know-how has been acquired via the input unit 23. If it is determined that a question has been acquired (S102—Yes), the process proceeds to S103. On the other hand, if it is determined that a question has not been acquired (S102—No), the process returns to S100.
[0038] S103: If it is determined in S102 that a question has been acquired (S102-Yes), the control unit 25 acquires one or more pairs of know-how information and provenance information from the database of the server 10 (storage unit 12).
[0039] The acquired question may be, for example, text data written in a natural language. The text data may be, for example, text data directly input by the user via the input unit 23, or text data obtained by converting voice data input by the user into text. Alternatively, the acquired question may be data in a predetermined format written according to a predetermined format.
[0040] In detail, the control unit 25 transmits the acquired question to the server 10 via the communication unit 21 and the network 30. The control unit 13 of the server 10 interprets the content of the question received from the information processing device 20, for example, by natural language processing. Based on the interpreted content, the control unit 13 extracts, for example, one or more pieces of know-how information that may be an answer to the question and provenance information corresponding to each piece of know-how information from a database. For example, a method using a large-scale language model (LLM) and Retrieval-Augmented Generation (RAG) is employed to interpret the question content and extract the know-how information. However, this is not limited to this example, and any method can be employed. The control unit 13 transmits the extracted one or more sets of know-how information and provenance information to the information processing device 20 via the communication unit 11 and the network 30. Here, the control unit 13 may modify the expressions of the extracted one or more pieces of know-how information, for example, by natural language processing. Then, the control unit 25 of the information processing device 20 acquires the one or more sets of know-how information and provenance information by receiving them from the server 10.
[0041] The acquired question may include specification of provenance information. In such a case, the control unit 25 may extract one or more pieces of know-how information that may be an answer to the question from a population of know-how information associated with the specified provenance information among all know-how information stored in the database.
[0042] S104: The control unit 25 outputs, via the output unit 22, an answer including one or more sets of know-how information and provenance information acquired in S103 as an answer to the question acquired in S102.
[0043] Outputting the answer may include, for example, displaying it on the display of the output unit 22 or outputting it as audio through the speaker of the output unit 22 .
[0044] As described above, when know-how information is input, the information processing device 20 according to this embodiment acquires provenance information indicating the origin of the know-how information, associates the know-how information with the provenance information, and stores the know-how information and the provenance information in a database. When the information processing device 20 acquires a question about know-how, it acquires one or more sets of know-how information and provenance information from the database. Then, the information processing device 20 outputs an answer to the question that includes the acquired one or more sets of know-how information and provenance information.
[0045] According to this configuration, as described above, for example, a user who inputs a question about know-how can check each piece of know-how information output as an answer together with its origin information. Therefore, according to this embodiment, the technology for providing a dialogue system is improved in that the probability of information contamination occurring when using the dialogue system is reduced.
[0046] Although the present disclosure has been described based on the drawings and examples, it should be noted that those skilled in the art may make various modifications and alterations based on the present disclosure. Therefore, it should be noted that these modifications and alterations are included in the scope of the present disclosure. For example, the functions included in each component or step can be rearranged so as not to be logically inconsistent, and multiple components or steps can be combined or divided into one.
[0047] For example, in the above-described embodiment, the configuration and operation of the information processing device 20 may be distributed among multiple computers that can communicate with each other. Also, in the above-described embodiment, for example, the configuration and operation of the server 10 may be partially or entirely located in the information processing device 10.
[0048] Also, for example, an embodiment is possible in which a general-purpose computer functions as the information processing device 20 according to the above-described embodiment. Specifically, a program describing the processing content for realizing each function of the information processing device 20 according to the above-described embodiment is stored in the memory of the general-purpose computer, and the program is read and executed by a processor. Therefore, the present disclosure can also be realized as a program executable by a processor or a non-transitory computer-readable medium storing the program.
[0049] In the above-described embodiment, the know-how information and the provenance information are stored in association with each other in the database of the server 10 (storage unit 12). Here, the know-how information may be physically separated and stored in the database for each provenance. In other words, the know-how information may be distributed and stored in different hardware (memory) for each provenance. Alternatively, the know-how information may be logically separated and stored in the database for each provenance. In other words, the know-how information may be distributed and stored in different storage areas for each provenance.
[0050] Some embodiments of the present disclosure are exemplified below. However, it should be noted that the embodiments of the present disclosure are not limited to these. [Supplementary Note 1] A method executed by an information processing device, comprising: when know-how information is input, acquiring provenance information indicating the origin of the know-how information, and storing the know-how information and the provenance information in a database in association with each other; when a question about know-how is received, acquiring one or more sets of know-how information and provenance information from the database; and outputting an answer to the question that includes the acquired one or more sets of know-how information and provenance information. [Supplementary Note 2] The method according to Supplementary Note 1, wherein the know-how information is physically or logically separated and stored in the database for each provenance. [Supplementary Note 3] The method according to Supplementary Note 1 or 2, wherein the know-how information includes text data, electronic document data, audio data, image data, or a combination thereof. [Supplementary Note 4] The method according to any one of Supplements 1 to 3, wherein when the know-how information is input, the information processing device automatically detects the provenance of the know-how information to acquire the provenance information. [Supplementary Note 5] The method according to any one of Supplements 1 to 4, wherein, when the know-how information includes the name of a creator or an organization to which the creator belongs, the information processing device automatically detects the name as the origin of the know-how information. [Supplementary Note 6] The method according to any one of Supplements 1 to 5, wherein, when the know-how information includes audio data of a conference attended by multiple people and data indicating the names of the multiple people, the information processing device automatically detects the names of the multiple people as the origin of the know-how information. [Supplementary Note 7] The method according to any one of Supplements 1 to 6, wherein the question regarding know-how includes specification of origin information, and when the information processing device acquires the question, it acquires from the database one or more pieces of know-how information associated with the specified origin information.[Supplementary Note 8] A non-transitory computer-readable medium that causes a computer to perform operations including: when know-how information is input, acquiring provenance information indicating the origin of the know-how information, and storing the know-how information and the provenance information in a database in association with each other; when a question regarding know-how is received, acquiring one or more sets of know-how information and provenance information from the database, and outputting an answer to the question that includes the acquired one or more sets of know-how information and provenance information. [Supplementary Note 9] The non-transitory computer-readable medium according to Supplementary Note 8, wherein the know-how information is physically or logically separated and stored in the database by provenance. [Supplementary Note 10] The non-transitory computer-readable medium according to Supplementary Note 8 or 9, wherein the know-how information includes text data, electronic document data, audio data, image data, or a combination thereof. [Supplementary Note 11] The non-transitory computer-readable medium according to any one of Supplements 8 to 10, wherein, when the know-how information is input, the computer acquires the origin information by automatically detecting the origin of the know-how information. [Supplementary Note 12] The non-transitory computer-readable medium according to any one of Supplements 8 to 11, wherein, if the know-how information includes the name of a creator or an organization to which the creator belongs, the computer automatically detects the name as the origin of the know-how information. [Supplementary Note 13] The non-transitory computer-readable medium according to any one of Supplements 8 to 12, wherein, if the know-how information includes audio data of a conference attended by multiple people and data indicating the names of the multiple people, the computer automatically detects the names of the multiple people as the origin of the know-how information.[Supplementary Note 14] The non-transitory computer-readable medium according to any one of Supplements 8 to 13, wherein the question regarding know-how includes specification of provenance information, and when the computer acquires the question, it acquires from the database one or more pieces of know-how information associated with the specified provenance information. [Supplementary Note 15] An information processing device including a control unit, wherein when know-how information is input, the control unit acquires provenance information indicating the provenance of the know-how information and associates the know-how information with the provenance information and stores it in a database, and when a question regarding know-how is acquired, the control unit acquires one or more sets of know-how information and provenance information from the database, and outputs a response to the question including the acquired one or more sets of know-how information and provenance information. [Supplementary Note 16] The information processing device according to Supplementary Note 15, wherein the know-how information is physically or logically separated by provenance and stored in the database. [Supplementary Note 17] The information processing device according to Supplementary Note 15 or 16, wherein the know-how information includes text data, electronic document data, audio data, image data, or a combination thereof. [Supplementary Note 18] The information processing device according to any one of Supplements 15 to 17, wherein, when the know-how information is input, the control unit acquires the origin information by automatically detecting the origin of the know-how information. [Supplementary Note 19] The information processing device according to any one of Supplements 15 to 18, wherein, if the know-how information includes the name of a creator or an organization to which the creator belongs, the control unit automatically detects the name as the origin of the know-how information. [Supplementary Note 20] The information processing device according to any one of Supplements 15 to 19, wherein, if the know-how information includes audio data of a conference attended by multiple people and data indicating the names of the multiple people, the control unit automatically detects the names of the multiple people as the origin of the know-how information.
[0051] REFERENCE SIGNS LIST 1 System 10 Server 11 Communication unit 12 Storage unit 13 Control unit 20 Information processing device 21 Communication unit 22 Output unit 23 Input unit 24 Storage unit 25 Control unit 30 Network
Claims
1. A method executed by an information processing device, the method including: when know-how information is input, acquiring provenance information indicating the origin of the know-how information, and storing the know-how information and the provenance information in a database in association with each other; when a question about know-how is received, acquiring one or more sets of know-how information and provenance information from the database; and outputting an answer to the question that includes the acquired one or more sets of know-how information and provenance information.
2. The method according to claim 1, wherein the know-how information is stored in the database in a physically or logically separated manner according to its origin.
3. The method of claim 1, wherein the know-how information includes text data, electronic document data, audio data, image data, or a combination thereof.
4. The method according to claim 1, wherein the information processing device, when the know-how information is input, automatically detects the origin of the know-how information to thereby obtain the origin information.
5. A method according to claim 4, wherein, if the know-how information includes the name of the creator or the name of the organization to which the creator belongs, the information processing device automatically detects the name as the origin of the know-how information.
6. A method according to claim 4, wherein, when the know-how information includes audio data of a conference attended by multiple people and data indicating the names of the multiple people, the information processing device automatically detects the names of the multiple people as the origin of the know-how information.
7. A method according to claim 1, wherein the question regarding know-how includes a specification of provenance information, and when the information processing device acquires the question, it acquires from the database one or more pieces of know-how information associated with the specified provenance information.
8. A non-transitory computer-readable medium that causes a computer to perform the following operations: when know-how information is input, acquire provenance information indicating the origin of the know-how information, and store the know-how information and the provenance information in a database in association with each other; when a question regarding know-how is received, acquire one or more sets of know-how information and provenance information from the database; and output, as a response to the question, a response that includes the acquired one or more sets of know-how information and provenance information.
9. A non-transitory computer-readable medium according to claim 8, wherein the know-how information is physically or logically separated and stored in the database according to its origin.
10. The non-transitory computer-readable medium according to claim 8, wherein the know-how information includes text data, electronic document data, audio data, image data, or a combination thereof.
11. A non-transitory computer-readable medium according to claim 8, wherein the computer, when receiving the know-how information, automatically detects the origin of the know-how information to obtain the origin information.
12. A non-transitory computer-readable medium according to claim 11, wherein, if the know-how information includes the name of a creator or an organization to which the creator belongs, the computer automatically detects the name as the origin of the know-how information.
13. A non-transitory computer-readable medium according to claim 11, wherein, when the know-how information includes audio data of a conference attended by multiple people and data indicating the names of the multiple people, the computer automatically detects the names of the multiple people as the origin of the know-how information.
14. A non-transitory computer-readable medium according to claim 8, wherein the question regarding know-how includes a specification of provenance information, and the computer, upon receiving the question, retrieves from the database one or more pieces of know-how information associated with the specified provenance information.
15. An information processing device having a control unit, wherein the control unit, when know-how information is input, acquires provenance information indicating the origin of the know-how information, associates the know-how information with the provenance information and stores it in a database, acquires one or more sets of know-how information and provenance information from the database when a question about know-how is acquired, and outputs a response to the question that includes the acquired one or more sets of know-how information and provenance information.
16. An information processing device according to claim 15, wherein the know-how information is physically or logically separated according to its origin and stored in the database.
17. An information processing device according to claim 15, wherein the know-how information includes text data, electronic document data, audio data, image data, or a combination thereof.
18. An information processing device according to claim 15, wherein when the know-how information is input, the control unit automatically detects the origin of the know-how information to acquire the origin information.
19. An information processing device according to claim 18, wherein, when the know-how information includes the name of the creator or the name of the organization to which the creator belongs, the control unit automatically detects the name as the origin of the know-how information.
20. An information processing device according to claim 18, wherein, when the know-how information includes audio data recorded from a conference attended by multiple people and data indicating the names of the multiple people, the control unit automatically detects the names of the multiple people as the origin of the know-how information.
Citation Information
Patent Citations
Back-up device for storage of knowhow
JP1991119452A
Method for using know-how information
JP2005157700A
Manufacturing knowledge search system, apparatus for constructing information, apparatus for disclosing / searching information, and program
JP2009087242A
Information processing device, information processing method, program, and information processing system
JP2025077645A