Method, information processing device, and program

Abstract

To provide a method, an information processing device, and a program which improve a technique for the use of a natural language model.SOLUTION: A method implemented by an information processing device includes steps of: receiving contents of an inquiry from a user; receiving an additional observation item related to the inquiry contents; generating a prompt including the additional observation item and the inquiry contents; and presenting an output according to the inquiry contents, which has been obtained by inputting the prompt into a language model.SELECTED DRAWING: Figure 6

Description

Cross-reference to Related Applications

[0001] This application claims the priority of Japanese Patent Application No. 2023-161769, filed in Japan on September 25, 2023, and incorporates the entire disclosure of the said application herein by reference.

Technical Field

[0002] This disclosure relates to a method, an information processing apparatus, and a program.

Background Art

[0003] Conventionally, as a system for providing answers to questions from users, technologies related to natural language models such as chatbots are known. For example, Patent Document 1 discloses a technology for providing answers to users using a chatbot in an integrated disease management system for patients and the like.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The technology of Patent Document 1 mainly focuses on providing advice on a healthy diabetic lifestyle, and has not studied a method for obtaining highly convincing information from a natural language model. That is, there is room for improvement in the technology of utilizing natural language models.

[0006] In view of such circumstances, an object of the present disclosure is to improve the technology of utilizing natural language models.

Means for Solving the Problems

[0007] (1) The method according to an embodiment of the present disclosure is A method executed by an information processing apparatus, comprising: Receiving an inquiry content from a user; Receiving additional observation items related to the inquiry content; Generating a prompt including the additional observation items and the inquiry content; Presenting an output according to the inquiry content obtained by inputting the second prompt into a language model; Including.

[0008] (2) The method according to an embodiment of the present disclosure is the method described in (1), wherein The additional observation items are items not included in the inquiry content.

[0009] (3) The method according to an embodiment of the present disclosure is the method described in (1) or (2), further comprising Outputting a user interface for prompting the input of the additional observation items.

[0010] (4) The method according to an embodiment of the present disclosure is the method described in any one of (1) to (3), wherein The prompt further includes an index related to any of the additional observation items and the inquiry content.

[0011] (5) The method according to an embodiment of the present disclosure is the method described in any one of (1) to (4), wherein The language model is a large language model.

[0012] (6) An information processing apparatus according to an embodiment of the present disclosure is An information processing apparatus including a control unit, wherein the control unit Receives an inquiry content from a user, Receives additional observation items related to the inquiry content, Generates a prompt including the additional observation items and the inquiry content, Present the output corresponding to the inquiry content obtained by inputting the prompt into the language model.

[0013] (7) A program according to an embodiment of the present disclosure causes a computer to receive an inquiry content from a user, receive additional observation items related to the inquiry content, generate a prompt including the additional observation items and the inquiry content, present the output corresponding to the inquiry content obtained by inputting the prompt into the language model, and execute the above operations.

Advantages of the Invention

[0014] According to an embodiment of the present disclosure, the technology for utilizing natural language models is improved.

Brief Description of the Drawings

[0015]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Mode for Carrying Out the Invention

[0016] Hereinafter, embodiments of the present disclosure will be described.

[0017] (Outline of Embodiment) Referring to FIG. 1, an overview of the system 1 according to an embodiment of the present disclosure will be described. The system 1 according to an embodiment of the present disclosure includes a plurality of terminal devices 10, an information processing device 20, a first server 30, and a second server 40. The plurality of terminal devices 10, the information processing device 20, the first server 30, and the second server 40 are communicably connected to a network 50 including, for example, a mobile communication network and the Internet.

[0018] The plurality of terminal devices 10 are arbitrary devices used by, for example, each of a visiting care worker, a nurse, a care manager, care staff, a facility manager, an administrator, head office staff, etc. (hereinafter also referred to as users). For example, general-purpose electronic devices such as smartphones, PCs, or tablet terminals, or dedicated electronic devices can be adopted as the terminal devices 10. Although FIG. 1 shows an example in which the system 1 includes three terminal devices 10, it is not limited thereto. The system 1 may include less than three terminal devices 10 or may include four or more terminal devices 10.

[0019] The information processing device 20 is, for example, a server device installed in a data center or the like. For example, the information processing device 20 is a server belonging to a cloud computing system or other computing systems. The information processing device 20 can communicate with the terminal devices 10 and the like via the network 50. Although FIG. 1 shows an example in which the system 1 includes one information processing device 20, it is not limited thereto. The system 1 may include two or more information processing devices 20.

[0020] The first server 30 is a server device installed, for example, in a data center or the like. The first server 30 is a server belonging to a cloud computing system or other computing systems. The first server 30 is equipped with a language model. In the present embodiment, the language model includes, for example, any dialogue system such as a Large Language Model (LLM, large-scale language model) or a chatbot. The language model outputs text corresponding to a prompt based on the input of the prompt, which is an instruction from the user. The first server 30 can communicate with the information processing device 20 and the like via the network 50. For example, the information processing device 20 inputs a prompt to the language model of the first server 30 and obtains an output result corresponding to the prompt. Although FIG. 1 shows an example in which there is one first server 30 included in the system 1, it is not limited thereto. The system 1 may include two or more first servers 30.

[0021] The second server 40 is a server device installed, for example, in a data center or the like. For example, the second server 40 is a server belonging to a cloud computing system or other computing systems. The second server 40 is equipped with a database (hereinafter also referred to as an index) that aggregates business manuals, guidelines, past inquiry contents, analysis results thereof, and countermeasures and the like related to specific fields such as care. The second server 40 can communicate with the information processing device 20 and the like via the network 50. Although FIG. 1 shows an example in which there is one second server 40 included in the system 1, it is not limited thereto. The system 1 may include two or more second servers 40.

[0022] First, the overview of this embodiment will be described, and the details will be described later. The information processing apparatus 20 receives inquiry contents in a care site or the like from the user. The information processing apparatus 20 generates a first prompt including the received inquiry contents, inputs the first prompt into a language model, and acquires observation items. The information processing apparatus 20 also receives additional observation items related to the inquiry contents from the user. The additional observation items are additional observation items necessary for answering the inquiry contents. The additional observation items are determined based on the observation items acquired by inputting the first prompt into the language model. Specifically, observation items that are insufficient only with the observation items acquired by inputting the first prompt into the language model are determined as the additional observation items.

[0023] When receiving the acquired additional observation items, the information processing apparatus 20 generates a second prompt including the observation items, the additional observation items, and the inquiry contents. Then, the information processing apparatus 20 presents to the user the countermeasures corresponding to the inquiry contents obtained by inputting the second prompt into the language model.

[0024] As described above, according to this embodiment, when receiving inquiry contents in a care site or the like from the user, first, a first prompt is generated, and the first prompt is input into a language model to acquire observation items. Further, in this embodiment, by generating a second prompt including the additional observation items received from the user and inputting the second prompt into the language model, countermeasures corresponding to the inquiry contents are presented to the user. Therefore, the technology of utilizing the natural language model is improved in that the probability of acquiring the information necessary for presenting the countermeasures is increased.

[0025] Next, each component of the system 1 will be described in detail.

[0026] (Configuration of the terminal device) As shown in FIG. 2, the terminal device 10 includes a control unit 11, a storage unit 12, a communication unit 13, an input unit 14, and an output unit 15.

[0027] The control unit 11 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 a GPU (graphics processing unit), or a dedicated processor specialized for specific processing. The dedicated circuit is, for example, an FPGA (field-programmable gate array) or an ASIC (application specific integrated circuit). While controlling each part of the terminal device 10, the control unit 11 executes processing related to the operation of the terminal device 10.

[0028] The storage unit 12 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of these. The semiconductor memory is, for example, a RAM (random access memory) or a ROM (read only memory). The RAM is, for example, an SRAM (static random access memory) or a DRAM (dynamic random access memory). The ROM is, for example, an EEPROM (electrically erasable programmable read only memory). The storage unit 12 functions as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 12 stores data used for the operation of the terminal device 10 and data obtained by the operation of the terminal device 10.

[0029] The communication unit 13 includes at least one interface for external communication. The communication interface may be either a wired communication interface or a wireless communication interface. In the case of wired communication, the communication interface is, for example, a LAN (Local Area Network) interface or a USB (Universal Serial Bus). In the case of wireless communication, the communication interface is, for example, an interface corresponding to a mobile communication standard such as LTE (Long Term Evolution), 4G (4th generation), or 5G (5th generation), or an interface corresponding to a short-range wireless communication such as WiFi (registered trademark) or Bluetooth (registered trademark). The communication unit 13 receives data used for the operation of the terminal device 10 and transmits data obtained by the operation of the terminal device 10.

[0030] The input unit 14 includes at least one input interface. The input interface is, for example, a physical key, a capacitive key, a pointing device, or a touch screen provided integrally with a display. The input interface may also be, for example, a microphone that receives voice input or a camera that receives gesture input. The input unit 14 receives an operation for inputting data used for the operation of the terminal device 10. Instead of being provided in the terminal device 10, the input unit 14 may be connected to the terminal device 10 as an external input device. As the connection method, for example, any method such as USB (Universal Serial Bus), HDMI (registered trademark) (High-Definition Multimedia Interface), or Bluetooth (registered trademark) can be used.

[0031] The output unit 15 includes at least one output interface. The output interface is, for example, a display that outputs information as video, or a speaker that outputs information as audio, etc. The display is, for example, an LCD (liquid crystal display) or an organic EL (electro luminescence) display. The output unit 15 displays and outputs the data obtained by the operation of the terminal device 10. Instead of being provided in the terminal device 10, the output unit 15 may be connected to the terminal device 10 as an external output device. As the connection method, for example, any method such as USB, HDMI (registered trademark), or Bluetooth (registered trademark) can be used.

[0032] The functions of the terminal device 10 are realized by executing the program according to this embodiment on a processor corresponding to the terminal device 10. That is, the functions of the terminal device 10 are realized by software. The program causes the computer to execute the operations of the terminal device 10, thereby making the computer function as the terminal device 10. That is, the computer functions as the terminal device 10 by executing the operations of the terminal device 10 according to the program.

[0033] 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, and is, for example, a magnetic recording device, an optical disk, a magneto-optical recording medium, or a semiconductor memory. The distribution of the program is performed, for example, by selling, transferring, or lending a portable recording medium such as a DVD (digital versatile disc) or a CD-ROM (compact disc read only memory) on which the program is recorded. Also, the distribution of the program may be performed by storing the program in the storage of an external server and transmitting the program from the external server to other computers. Also, the program may be provided as a program product.

[0034] Some or all of the functions of the terminal device 10 may be realized by a dedicated circuit corresponding to the control unit 11. That is, some or all of the functions of the terminal device 10 may be realized by hardware.

[0035] (Configuration of the information processing device)

[0036] As shown in FIG. 3, the information processing device 20 includes a control unit 21, a storage unit 22, and a communication unit 23.

[0037] The control unit 21 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 or GPU, or a dedicated processor specialized for specific processing. The dedicated circuit is, for example, an FPGA or ASIC. The control unit 21 controls each part of the information processing device 20 and executes processing related to the operation of the information processing device 20.

[0038] The storage unit 22 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of these. The semiconductor memory is, for example, a RAM or ROM. The RAM is, for example, an SRAM or DRAM. The ROM is, for example, an EEPROM. The storage unit 22 functions as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 22 stores data used for the operation of the information processing device 20 and data obtained by the operation of the information processing device 20.

[0039] The communication unit 23 includes at least one interface for external communication. The communication interface may be either a wired communication interface or a wireless communication interface. In the case of wired communication, the communication interface is, for example, a LAN interface or a USB. In the case of wireless communication, the communication interface is, for example, an interface corresponding to a mobile communication standard such as LTE, 4G, or 5G, or an interface corresponding to short-range wireless communication such as WiFi (registered trademark) or Bluetooth (registered trademark). The communication unit 23 receives data used for the operation of the information processing apparatus 20 and transmits data obtained by the operation of the information processing apparatus 20.

[0040] The functions of the information processing apparatus 20 are realized by causing a processor corresponding to the control unit 21 to execute the program according to this embodiment. That is, the functions of the information processing apparatus 20 are realized by software. The program causes a computer to execute the operations of the information processing apparatus 20, thereby causing the computer to function as the information processing apparatus 20. That is, the computer functions as the information processing apparatus 20 by executing the operations of the information processing apparatus 20 according to the program.

[0041] In this embodiment, a computer temporarily stores, for example, a program recorded on a portable recording medium or a program transmitted from a server in a main memory device. Then, the computer reads the program stored in the main memory device with a processor and executes processing according to the read program with the processor. The computer may directly read a program from a portable recording medium and execute processing according to the program. Each time the computer receives a program from an external server, the computer may sequentially execute processing according to the received program. Processing may be executed by a so-called ASP (application service provider) type service that realizes functions only by execution instructions and result acquisition without transmitting a program from the external server to the computer. A program includes information used for processing by an electronic computer that conforms to the program. For example, data that is not a direct instruction to a computer but has a property that defines the processing of the computer corresponds to "what conforms to the program".

[0042] Some or all of the functions of the information processing apparatus 20 may be realized by a dedicated circuit corresponding to the control unit 21. That is, some or all of the functions of the information processing apparatus 20 may be realized by hardware.

[0043] (Configuration of the First Server)

[0044] As shown in FIG. 4, the first server 30 includes a control unit 31, a storage unit 32, and a communication unit 33.

[0045] The control unit 31 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 or a GPU, or a dedicated processor specialized for specific processing. The dedicated circuit is, for example, an FPGA or an ASIC. The control unit 31 controls each unit of the first server 30 and executes processing related to the operation of the first server 30.

[0046] The memory unit 32 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of these. The semiconductor memory is, for example, a RAM or a ROM. The RAM is, for example, an SRAM or a DRAM. The ROM is, for example, an EEPROM. The memory unit 32 functions as, for example, a main memory device, an auxiliary memory device, or a cache memory. The memory unit 32 stores data used for the operation of the first server 30 and data obtained by the operation of the first server 30. For example, the memory unit 32 stores a language model. Also, for example, the language model may be stored in a GPU memory such as the VRAM of the GPU included in the control unit 31. Examples of GPU memory include random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), and other forms of memory known in the art. In an example where the GPU is configured as part of another processor, for example, a host processor, the GPU memory can be accessed by components other than the GPU.

[0047] The communication unit 33 includes at least one external communication interface. The communication interface may be either a wired communication or a wireless communication interface. In the case of wired communication, the communication interface is, for example, a LAN interface, a USB. In the case of wireless communication, the communication interface is, for example, an interface corresponding to a mobile communication standard such as LTE, 4G, or 5G, or an interface corresponding to short-range wireless communication such as WiFi (registered trademark), Bluetooth (registered trademark). The communication unit 33 receives data used for the operation of the first server 30 and transmits data obtained by the operation of the first server 30.

[0048] The functions of the first server 30 are realized by executing the program according to this embodiment on a processor corresponding to the control unit 31. That is, the functions of the first server 30 are realized by software. The program causes a computer to execute the operations of the first server 30, thereby making the computer function as the first server 30. That is, the computer functions as the first server 30 by executing the operations of the first server 30 according to the program.

[0049] Some or all of the functions of the first server 30 may be realized by a dedicated circuit corresponding to the control unit 31. That is, some or all of the functions of the first server 30 may be realized by hardware.

[0050] (Configuration of the second server) As shown in FIG. 5, the second server 40 includes a control unit 41, a storage unit 42, and a communication unit 43.

[0051] The control unit 41 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 or GPU, or a dedicated processor specialized for specific processing. The dedicated circuit is, for example, an FPGA or an ASIC. The control unit 41 executes processing related to the operation of the second server 40 while controlling each part of the second server 40.

[0052] The storage unit 42 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of these. The semiconductor memory is, for example, a RAM or a ROM. The RAM is, for example, an SRAM or a DRAM. The ROM is, for example, an EEPROM. The storage unit 42 functions as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 42 stores data used for the operation of the second server 40 and data obtained by the operation of the second server 40. For example, the storage unit 42 stores an index. Note that the index may be stored in the storage unit 22 of the information processing apparatus 20.

[0053] The communication unit 43 includes at least one interface for external communication. The communication interface may be either a wired communication interface or a wireless communication interface. In the case of wired communication, the communication interface is, for example, a LAN interface or a USB. In the case of wireless communication, the communication interface is, for example, an interface corresponding to a mobile communication standard such as LTE, 4G, or 5G, or an interface corresponding to short-range wireless communication such as WiFi (registered trademark) or Bluetooth (registered trademark). The communication unit 43 receives data used for the operation of the second server 40 and transmits data obtained by the operation of the second server 40.

[0054] The functions of the second server 40 are realized by executing the program according to the present embodiment on a processor corresponding to the control unit 41. That is, the functions of the second server 40 are realized by software. The program causes a computer to execute the operation of the second server 40, thereby causing the computer to function as the second server 40. That is, the computer functions as the second server 40 by executing the operation of the second server 40 according to the program.

[0055] Some or all of the functions of the second server 40 may be realized by a dedicated circuit corresponding to the control unit 41. That is, some or all of the functions of the second server 40 may be realized by hardware.

[0056] (Operation Example 1 of Information Processing Apparatus) With reference to FIG. 6, an operation example of the information processing apparatus 20 according to the present embodiment will be described. FIG. 6 is a flowchart showing an example of a method executed by the information processing apparatus 20 according to the present embodiment.

[0057] Step S100: The control unit 21 of the information processing apparatus 20 receives the inquiry content from the user. As a method for receiving the inquiry content from the user, any method can be adopted. For example, the inquiry content may be acquired by the information processing apparatus 20 via the terminal device 10. In this case, the output unit 15 of the terminal device 10 may prompt the user to input the inquiry content by, for example, outputting a user interface screen related to receiving the inquiry content.

[0058] Step S200: The control unit 21 generates a first prompt including the inquiry content. Here, the first prompt may appropriately include a predetermined prompt template. Thereby, the language model can be made to output according to the predetermined prompt template.

[0059] Step S300: The control unit 21 inputs the first prompt to the language model to acquire observation items. Specifically, the control unit 21 transmits the first prompt generated in Step S200 to the first server 30 via the communication unit 23 and inputs the first prompt to the language model of the first server 30. The language model outputs the observation items corresponding to the first prompt. The control unit 21 acquires the output observation items from the first server 30 via the communication unit 23.

[0060] Step S400: The control unit 21 receives additional observation items related to the inquiry content. As a method for receiving the additional observation items from the user, any method can be adopted. For example, the additional observation items may be acquired by the information processing apparatus 20 via the terminal device 10. In this case, the output unit 15 of the terminal device 10 may prompt the user to input the additional observation items by, for example, outputting a user interface screen related to receiving the additional observation items.

[0061] Step S500: The control unit 21 generates a second prompt including an observation item, an additional observation item, and an inquiry content. Here, the second prompt may appropriately include a predetermined prompt template. Thereby, the language model can be made to output according to the predetermined prompt template.

[0062] Step S600: The control unit 21 presents a countermeasure according to the inquiry content obtained by inputting the second prompt to the language model. Specifically, the control unit 21 transmits the second prompt generated in step S500 to the first server 30 via the communication unit 23, and inputs the second prompt to the language model of the first server 30. The language model outputs a countermeasure corresponding to the second prompt. The control unit 21 acquires the output countermeasure from the first server 30 via the communication unit 23. Then the control unit 21 presents the acquired countermeasure. As a method for presenting the acquired countermeasure, any method can be adopted. For example, the acquired countermeasure may be presented by the information processing apparatus 20 via the terminal apparatus 10. In this case, the output unit 15 of the terminal apparatus 10 outputs, for example, a user interface screen including the content of the acquired countermeasure.

[0063] As described above, according to the operation example 1 of the present embodiment, when receiving an inquiry content in a care site or the like from the user, first, a first prompt is generated, and such a first prompt is input to the language model to acquire an observation item. Further, in the operation example 1, by generating a second prompt including an additional observation item received from the user and inputting the second prompt to the language model, a countermeasure corresponding to the inquiry content is presented to the user. Therefore, the utilization technology of the natural language model is improved in that the probability of obtaining information necessary for presenting the countermeasure is increased.

[0064] (Operation Example 2 of Information Processing Apparatus) Referring to FIG. 7, an operation example 2 of the information processing apparatus 20 according to the present embodiment will be described. FIG. 7 is a flowchart showing an example of a method executed by the information processing apparatus 20 according to the present embodiment. The same operations as those in FIG. 6 are denoted by the same reference numerals. Operation example 2 is different from operation example 1 in that a third prompt is generated and an analysis result is obtained from the language model, and the second prompt includes the analysis result.

[0065] Step S100: The control unit 21 of the information processing apparatus 20 receives the inquiry content from the user. As a method for receiving the inquiry content from the user, any method can be adopted. For example, the inquiry content may be obtained by the information processing apparatus 20 via the terminal device 10. In this case, the output unit 15 of the terminal device 10 may prompt the user to input by, for example, outputting a user interface screen related to receiving the inquiry content to the input unit 14 for the inquiry content.

[0066] Step S200: The control unit 21 generates a first prompt including the inquiry content. Here, the first prompt may appropriately include a predetermined prompt template. Thereby, the language model can be made to output according to the predetermined prompt template.

[0067] Step S300: The control unit 21 inputs the first prompt to the language model to obtain observation items. Specifically, the control unit 21 transmits the first prompt generated in step S200 to the first server 30 via the communication unit 23, and inputs the first prompt to the language model of the first server 30. The language model outputs observation items corresponding to the first prompt. The control unit 21 obtains the output observation items from the first server 30 via the communication unit 23.

[0068] Step S400: The control unit 21 receives additional observation items related to the inquiry content. As a method for receiving additional observation items from the user, any method can be adopted. For example, the additional observation items may be acquired by the information processing device 20 via the terminal device 10. In this case, the output unit 15 of the terminal device 10 may prompt the user to input by, for example, outputting a user interface screen related to the reception of the additional observation items.

[0069] Step S410: The control unit 21 generates a third prompt including the observation items and the inquiry content. Here, the third prompt may appropriately include a predetermined prompt template. Thereby, the language model can be made to output according to the predetermined prompt template.

[0070] Step S420: The control unit 21 inputs the third prompt into the language model to obtain an analysis result. Specifically, the control unit 21 transmits the third prompt generated in Step S410 to the first server 30 via the communication unit 23, and inputs the third prompt into the language model of the first server 30. The language model outputs an analysis result corresponding to the third prompt. The control unit 21 acquires the output analysis result from the first server 30 via the communication unit 23.

[0071] Step S510: The control unit 21 generates a second prompt including the observation items, the additional observation items, the inquiry content, and the analysis result. Here, the second prompt may appropriately include a predetermined prompt template. Thereby, the language model can be made to output according to the predetermined prompt template.

[0072] Step S600: The control unit 21 presents a countermeasure according to the inquiry content obtained by inputting the second prompt into the language model. Specifically, the control unit 21 transmits the second prompt generated in step S500 to the first server 30 via the communication unit 23, and inputs the second prompt into the language model of the first server 30. The language model outputs a countermeasure corresponding to the second prompt. The control unit 21 acquires the output countermeasure from the first server 30 via the communication unit 23. Then the control unit 21 presents the acquired countermeasure. As a method for presenting the acquired countermeasure, any method can be adopted. For example, the acquired countermeasure may be presented by the information processing device 20 via the terminal device 10. In this case, the output unit 15 of the terminal device 10 outputs, for example, a user interface screen including the content of the acquired countermeasure.

[0073] As described above, according to the operation example 2 of the present embodiment, when receiving an inquiry content from a user at a care site or the like, first, a first prompt is generated, and such a first prompt is input into a language model to acquire observation items. Further, in operation example 2, by generating a third prompt including additional observation items received from the user and inputting the third prompt into the language model, an analysis result corresponding to the inquiry content is acquired. And in operation example 2, by generating a second prompt including the observation items, the additional observation items, the inquiry content, and the analysis result and inputting the second prompt into the language model, a countermeasure corresponding to the inquiry content is presented to the user. Therefore, by including the analysis result as information necessary for presenting the countermeasure, a more appropriate countermeasure can be presented.

[0074] (User Interface Example) Hereinafter, an example of a user interface displayed by the terminal device 10 in the above-described operation example 2 is shown. FIGS. 8-11 show an example of a user interface screen related to receiving an inquiry content in step S100. The inquiry content includes a consultation summary, hearing information, and a type of consultation content. The terminal device 10 receives the consultation summary, the hearing information, and the type of consultation content via the user interfaces of FIGS. 8, 10, and 11, respectively.

[0075] The user interface screen shown in FIG. 8 is a screen for receiving input of the consultation summary. The consultation summary includes the consultation content, the information of the care recipient (age, degree of care need, address, etc.), the past medical history of the care recipient, the current medical history, and the medication history. Note that the information of the care recipient (age, degree of care need, address, etc.), the past medical history of the care recipient, the current medical history, the medication history, etc. may also be referred to as the attribute information of the care recipient. As shown in FIG. 8, reference examples may be displayed in each of the fields 81-84 for receiving input of the consultation content, the information of the care recipient, the past medical history of the care recipient, the current medical history, and the medication history. Thereby, it is possible to easily grasp what kind of text should be input in each field. The user interface screen shown in FIG. 9 is a screen indicating a state where the input of the consultation summary is completed. When the button 85 is selected, the screen transitions to a screen for receiving input of the interview information.

[0076] The user interface screen shown in FIG. 10 is a screen for receiving input of the interview information. The interview information includes the interview information from the person himself / herself, the interview information from the relevant person, and other information. Similar to FIG. 8, reference examples may be displayed in each of the fields 101-104 for receiving input of the interview information from the person himself / herself, the interview information from the relevant person, and other information in FIG. 10. When the button 105 is selected, the screen transitions to a screen for receiving input of the interview information. On the other hand, when the button 106 is selected, the screen returns to a screen for receiving input of the consultation summary.

[0077] The user interface screen shown in FIG. 11 is a screen for receiving input of the type of the consultation content. In the example shown in FIG. 11, the types of the consultation content are five types: diet, fall, excretion, dementia, and others. The user interface screen shown in FIG. 11 includes buttons 111-115 corresponding to each of these types. When any one of the buttons 111-115 is selected, the type of the consultation content is selected, and a first prompt including the inquiry content is generated.

[0078] Note that an index regarding the type of inquiry content may be referred to according to the type of consultation content. That is, the first prompt may include the index. In other words, the first prompt may further include the index regarding the inquiry content. Specifically, according to the type of consultation content, the control unit 21 of the information processing apparatus 20 acquires an index regarding the type of inquiry content from the second server 40. The control unit 21 generates the first prompt based on the acquired index. Depending on the type of language model such as a general-purpose language model, it may not be possible to obtain an output with the expected accuracy for a prompt including industry-specific technical terms and expressions. Therefore, by allowing the language model to refer to a predetermined index, it is possible to output a response specialized according to the consultation content. More specifically, the inquiry content includes at least one of inquiries regarding diet, falls, excretion, and dementia, and the first prompt may further include an index regarding the inquiry content. Thereby, desired responses can also be obtained for inquiries in the medical or nursing care fields such as diet, falls, excretion, or dementia. Also, for example, the second prompt may include an index regarding at least one of the observation items, additional observation items, and inquiry content. Thereby, by allowing a general-purpose language model to refer to a predetermined index, it is possible to output a response specialized according to the consultation content. Furthermore, the third prompt may include an index regarding at least one of the observation items, additional observation items, and inquiry content. Thereby, by allowing a general-purpose language model to refer to a predetermined index, it is possible to output a response specialized according to the consultation content. Furthermore, when obtaining an analysis result by the third prompt, the second prompt may further include an index regarding any one of the observation items, additional observation items, inquiry content, and analysis result. A higher-precision output can be obtained. Note that by using an LLM, which is an example of a language model developed for general purposes, the technology according to the present disclosure can be implemented at a nursing care site or the like without newly constructing a model. In this case, by allowing the LLM to refer to an index including information regarding the field to be implemented (such as the nursing care field), an output optimized more for the nursing care field or the like can be obtained.In addition, in the present disclosure, it does not prevent the fine-tuning or transfer learning of a general-purpose language model. For example, even for an additionally trained language model, by inputting information of a predetermined index, a more accurate output can be obtained.

[0079] FIGS. 12 to 14 show an example of the user interface screen related to step S300.

[0080] The user interface screen shown in FIG. 12 is a screen showing an intermediate stage of acquiring observation items after inputting the first prompt into the language model. The observation items to be acquired are controlled based on the above-described predetermined prompt template. The predetermined prompt template may be arbitrary. Here, the case where the predetermined prompt template is based on a framework for specific problem-solving (hereinafter also referred to as PROM) will be described. In PROM, the problem-solving process is divided into five processes. Such five processes are (1) problem identification, (2) situation grasping, (3) analysis, (4) countermeasures, and (5) evaluation. In PROM, these five processes are executed in the order of (1) to (5). Here, the processes of (2) situation grasping and (3) analysis are performed from a phenomenologically multi-faceted perspective. Specifically, the situation grasping or analysis is performed from the perspective of five factors. Such five factors are (1) drug inspection, (2) presence or absence of physical diseases, (3) presence or absence of mental diseases, (4) environmental factors, and (5) psychological factors. Among these, in the situation grasping or analysis regarding (1) drug inspection, (2) presence or absence of physical diseases, and (3) mental diseases, five items become the observation items. The five items are (1) actions and states, (2) complaints from the person himself / herself, (3) vital signs, (4) simple medical tests that can be performed, and (5) tests at medical institutions. On the other hand, in the situation grasping or analysis regarding (5) psychological factors, three or more items (Mental 3+1) become the observation items. The three or more items are (1) life history, (2) action observation, (3) listening to what the person himself / herself says, and (4) what would you do if you were in his / her shoes.

[0081] To implement a problem-solving framework based on a PROM, for example, the first prompt may include a predetermined template along the lines of the PROM. For example, the first prompt may include information regarding at least any one of medicine, physical diseases, mental diseases, environmental factors, and psychological factors. By including this information, an output based on these five factors (5 Reasons) can be obtained from the language model. Also, for example, the first prompt may include information regarding at least any one of actions, states, complaints from the individual, vital signs, and tests. By including this information, these five items (5 Objects) can be output to the language model as observation items. In other words, in the present embodiment, when the first prompt includes information regarding at least any one of medicine, physical diseases, and mental diseases, the observation items may include information regarding at least any one of actions, states, complaints from the individual, vital signs, and tests. Also, when the first prompt includes information regarding mental diseases, the observation items may include information regarding at least any one of life history, action observation, listening to the individual's story, and what would I do if I were in their shoes. By including this information, these three or more items (Mental 3+1) can be output to the language model as observation items.

[0082] As described above, the user interface screen shown in FIG. 12 is a screen showing an intermediate stage of acquiring observation items. Here, the grasping of the state and the confirmation of the observation items are each carried out from the perspective of five factors (5 Reasons): (1) inspection of medicine, (2) presence or absence of physical diseases, (3) presence or absence of mental diseases, (4) environmental factors, and (5) psychological factors, and the progress of each is indicated by icons 121-129. Icons 121, 126, 127, 128, 129 indicate that the processing by the language model is in progress. On the other hand, icons 122-125 indicate that the processing by the language model has been completed. When all of these items are processed, the observation items corresponding to the first prompt are obtained from the language model, and the screen transitions to the next user interface screen.

[0083] The user interface screens shown in FIGS. 13, 14, and 15 are screens that show the observation items corresponding to the first prompt. The observation items corresponding to the first prompt may be listed for each of the five factors (5 Reasons) described above. The user interface screen shown in FIG. 13 includes the observation items related to the drug inspection. Tabs 131-135 are selection objects for selecting the displayed observation items. Tabs 131-135 respectively correspond to (1) drug inspection, (2) presence or absence of physical disease, (3) presence or absence of mental disease, (4) environmental factors, and (5) psychological factors. When tabs 131-135 are selected by the user, the observation items corresponding to each factor are listed. FIG. 13 shows the user interface screen when tab 131 is selected. As shown in FIG. 13, such a user interface screen lists the observation items related to the drug inspection. The information listed includes the result of whether the category of the observation item, the item name, the description, and the inquiry content are included. The category of the observation item corresponds to the above-mentioned 5 Objects or Mental 3+1. The result of whether it is included in the inquiry content is indicated by YES (Y) or NO (N). In the case of Y, it indicates that the observation item is included in the inquiry content. In the case of N, it indicates that the observation item is not included in the inquiry content. The observation items with N attached correspond to the above-mentioned additional observation items.

[0084] The user interface screen shown in FIG. 14 shows the user interface screen when tab 132 is selected. As shown in FIG. 14, such a user interface screen lists the observation items related to the presence or absence of physical disease.

[0085] The user interface screen shown in FIG. 15 shows the user interface screen when tab 135 is selected. As shown in FIG. 15, such a user interface screen lists the observation items related to psychological factors. In the example shown in FIG. 15, the observation items include information related to the items corresponding to the above-mentioned Mental 3+1, that is, life history, behavior observation, listening to the person's own words, and what would you do if you were the person.

[0086] In FIGS. 13, 14, or 15, when button 136 is selected, the screen transitions to the next screen. On the other hand, when button 137 is selected, the screen returns to the consultation summary input screen and the consultation content is corrected. For example, in FIGS. 13, 14, and 15, if it is confirmed that the observation items are included in the consultation content, when button 136 is selected, the screen transitions to the next screen. On the other hand, in FIGS. 13, 14, or 15, if the observation items are insufficient, there is a risk that the presentation of countermeasures will be insufficient. In this case, a user interface screen for prompting the input of the missing observation items (additional observation items) is displayed, and the input of additional observation items from the user is accepted. Any method can be adopted for the mode of input of additional observation items. For example, it may return to the user interface screen shown in FIG. 8 and let the user re-enter all the information. Alternatively, a user interface screen listing only the additional observation items may be displayed, and the additional observation items may be accepted through the user interface screen.

[0087] Here, information related to the advice from the doctor may be input as additional observation items. The user interface screen shown in FIG. 16 is a screen for accepting the input of information related to the advice from the doctor. Field 151 is an object capable of inputting information related to the advice from the doctor. When button 152 is selected with information related to the advice from the doctor input in field 151, a third prompt including the observation items, additional observation items, and consultation content is generated with the information related to the advice from the doctor as additional observation items. On the other hand, when button 152 is selected with no information input in field 151, a third prompt including the observation items and consultation content is generated.

[0088] FIGS. 17 to 19 show an example of the user interface screen related to step S420.

[0089] The user interface screen shown in FIG. 17 is a screen showing an intermediate stage of obtaining analysis results after inputting the third prompt into the language model. The analysis results to be obtained are controlled based on the predetermined prompt template described above. In the present embodiment, the third prompt will be described as including a predetermined template along the PROM. In FIG. 17, the analysis is performed from the viewpoints of five factors: (1) drug inspection, (2) presence or absence of physical diseases, (3) presence or absence of mental diseases, (4) environmental factors, and (5) psychological factors, and the progress of each is indicated by icons 161-165. Icons 161 and 164 indicate that the processing by the language model is in progress. On the other hand, icons 162, 163, and 165 indicate that the processing by the language model has been completed. When all items are processed, the analysis results corresponding to the third prompt are obtained from the language model, and the screen transitions to the next user interface screen.

[0090] The user interface screens shown in FIGS. 18 and 19 are screens showing the analysis results corresponding to the third prompt. The analysis results corresponding to the third prompt may be listed for each of the above five factors (5 Reasons). The user interface screen shown in FIG. 18 includes the analysis results related to drug inspection. Tabs 171-175 are selection objects for selecting the displayed analysis results. Tabs 171-175 correspond to (1) drug inspection, (2) presence or absence of physical diseases, (3) presence or absence of mental diseases, (4) environmental factors, and (5) psychological factors, respectively. When tabs 171-175 are selected by the user, the analysis results corresponding to these factors are listed. FIG. 18 shows the user interface screen when tab 171 is selected. As shown in FIG. 18, the analysis results related to drug inspection are listed on such a user interface screen. The information listed includes the presence or absence of the influence of the drug and the basis for considering that the drug has an influence.

[0091] The user interface screen shown in FIG. 19 shows the user interface screen when tab 172 is selected. As shown in FIG. 18, such a user interface screen lists the analysis results regarding the presence or absence of physical diseases. The information listed includes physical diseases, the presence or absence of the influence of physical conditions, and the basis for considering that physical diseases or physical conditions have an impact. In FIG. 18 or FIG. 19, when button 176 is selected, a second prompt including observation items, additional observation items, inquiry content, and analysis results is generated, and the process proceeds to the user interface screen shown in the next FIG. 20.

[0092] FIGS. 20 and 21 show an example of the user interface screen related to step S600.

[0093] The user interface screen shown in FIG. 20 shows an intermediate stage of obtaining countermeasures according to the inquiry content after inputting the second prompt into the language model. When the processing by the language model is completed, the process proceeds to the user interface screen shown in FIG. 21.

[0094] The user interface screen shown in FIG. 21 is a screen that presents countermeasures according to the inquiry content. The information presented includes the target state and countermeasures. In this way, the target state and countermeasures to be achieved according to the inquiry content are specifically shown. As illustrated in FIG. 21, by selecting button 201 or button 202, it may be possible to start a new analysis or perform a re-analysis with the consultation content changed.

[0095] In the above-described embodiments, the information processing apparatus 20 may be configured or operated to execute part or all of the present disclosure. For example, the information processing apparatus 20 may be configured or operated such that a prompt is configured to include consultation matters regarding the care recipient and the attribute information of the care recipient, and such a prompt is input to the LLM to obtain an answer corresponding to the consultation matter from the LLM. More specifically, information such as the information of the care recipient (age, degree of care required, place of residence, etc.), the medical history, current medical history, and medication history of the care recipient, and the consultation matter may be input to the LLM. Further, information other than the information regarding the consultation matter or the attribute information of the care recipient may be included in the prompt as an index and input to the LLM. Also, 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 each step, etc. can be rearranged so as not to be logically contradictory, and it is possible to combine or divide a plurality of components or steps, etc. into one.

[0096] For example, in the above-described embodiments, an embodiment in which the configuration and operation of the information processing apparatus 20 are distributed to a plurality of computers capable of communicating with each other is also possible. Also, for example, an embodiment in which some or all of the components of the information processing apparatus 20 are provided in the terminal device 10 is also possible.

Description of Reference Numerals

[0097] 1 System 10 Terminal Device 11 Control Unit 12 Storage Unit 13 Communication Unit 14 Input Unit 15 Output Unit 20 Information Processing Apparatus 21 Control Unit 22 Storage Unit 23 Communication Unit 30 First Server 31 Control Unit 32 Memory Unit 33 Communication Unit 40 Second Server 41 Control Unit 42 Memory Unit 43 Communication Unit 50 Network 81, 82, 83, 84 Fields 85 Button 101, 102, 103, 104 Fields 105 Button 111, 112, 113, 114, 115 Buttons 121, 122, 123, 124, 125, 126, 127, 128, 129 Icons 131, 132, 133, 134, 135 Tabs 136, 137 Buttons 151 Field 152 Button 161, 162, 163, 164, 165 Icons 171, 172, 173, 174, 175 Tabs 176 Button 201, 202 Buttons

Claims

1. A method executed by an information processing apparatus, comprising: receiving an inquiry content from a user; receiving additional observation items related to the inquiry content; generating a prompt including the additional observation items and the inquiry content; presenting an output corresponding to the inquiry content obtained by inputting the prompt into a language model. A method including the above.

2. The method according to Claim 1, wherein the additional observation items are items not included in the inquiry content.

3. The method according to Claim 2, further comprising: outputting a user interface for prompting an input of the additional observation items.

4. The method according to Claim 1, further comprising: the prompt further includes an index related to either the additional observation items or the inquiry content.

5. The method according to Claim 1, wherein the language model is a large language model.

6. An information processing apparatus comprising a control unit, wherein the control unit: receives an inquiry content from a user; receives additional observation items related to the inquiry content; generates a prompt including the additional observation items and the inquiry content; presents an output corresponding to the inquiry content obtained by inputting the prompt into a language model.

7. A program for causing a computer to: receive an inquiry content from a user; receive additional observation items related to the inquiry content; generate a prompt including the additional observation items and the inquiry content; present an output corresponding to the inquiry content obtained by inputting the prompt into a language model. ​

Images