Method, information processing device, and program

Abstract

Provided is a method executed by an information processing device, the method comprising receiving content of an inquiry from a user, generating a first prompt including the inquiry content, inputting the first prompt into a language model to acquire an observation item, receiving an additional observation item related to the inquiry content, generating a second prompt including the observation item, the additional observation item, and the inquiry content, and presenting a countermeasure corresponding to the inquiry content obtained by inputting the second prompt into the language model.

Description

Method, information processing device, and program CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority from Japanese Patent Application No. 2023-161769, filed on September 25, 2023, the entire disclosure of which is incorporated herein by reference.

[0002] The present disclosure relates to a method, an information processing device, and a program.

[0003] Conventionally, technologies relating to natural language models such as chatbots have been known as systems that provide answers to questions from users. For example, Patent Literature 1 discloses a technology that uses a chatbot to provide answers to users in an integrated disease management system for patients, etc.

[0004] Patent No. 7130633

[0005] The technology in Patent Document 1 is primarily focused on providing advice on healthy lifestyles for people with diabetes, and does not consider a method for obtaining highly convincing information from a natural language model. In other words, there is room for improvement in the technology for utilizing natural language models.

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

[0007] (1) A method according to one embodiment of the present disclosure is a method executed by an information processing device, and includes: accepting an inquiry from a user; generating a first prompt including the inquiry; inputting the first prompt into a language model to obtain an observation item; accepting additional observation items related to the inquiry; generating a second prompt including the observation items, the additional observation items, and the inquiry; and presenting a countermeasure corresponding to the inquiry obtained by inputting the second prompt into the language model.

[0008] (2) A method according to one embodiment of the present disclosure is the method described in (1), further comprising: generating a third prompt including the observation item, the additional observation item, and the inquiry content; inputting the third prompt into the language model to obtain an analysis result; and the second prompt further including the analysis result.

[0009] (3) A method according to one embodiment of the present disclosure is a method according to (1) or (2), wherein the first prompt includes information about any one of medication, physical illness, mental illness, environmental factors, and psychological factors.

[0010] (4) A method according to one embodiment of the present disclosure is a method according to any one of (1) to (3), wherein the first prompt includes information about any one of medication, physical illness, and mental illness, and the observation items include information about at least any one of behavior, condition, complaints from the patient, vital signs, and tests.

[0011] (5) A method according to one embodiment of the present disclosure is a method according to any one of (1) to (4), wherein the first prompt includes information on psychological factors, and the observation items include information on at least one of life history, behavioral observation, listening to the person, and what you would do if you were in their situation.

[0012] (6) A method according to an embodiment of the present disclosure is the method according to any one of (1) to (5), wherein the first prompt further includes an index relating to the inquiry content.

[0013] (7) A method according to one embodiment of the present disclosure is a method according to any one of (1) to (6), wherein the inquiry content includes at least one of inquiries about eating, falls, excretion, and dementia, and the first prompt further includes an index related to the inquiry content.

[0014] (8) A method according to one embodiment of the present disclosure is the method according to any one of (1) to (7), wherein the second prompt further includes an index relating to any of the observation item, the additional observation item, and the inquiry content.

[0015] (9) A method according to one embodiment of the present disclosure is the method according to (2), wherein the third prompt further includes an index relating to any of the observation item, the additional observation item, and the inquiry content.

[0016] (10) A method according to one embodiment of the present disclosure is the method according to (9), wherein the second prompt further includes an index relating to any of the observation item, the additional observation item, the inquiry content, and the analysis result.

[0017] (11) An information processing device according to one embodiment of the present disclosure is an information processing device including a control unit, wherein the control unit: accepts an inquiry from a user; generates a first prompt including the inquiry; inputs the first prompt into a language model to obtain an observation item; accepts additional observation items related to the inquiry; generates a second prompt including the observation item, the additional observation item, and the inquiry; and presents a countermeasure according to the inquiry obtained by inputting the second prompt into the language model.

[0018] (12) A program according to an embodiment of the present disclosure causes a computer to perform the following operations: accept an inquiry from a user; generate a first prompt including the inquiry; input the first prompt into a language model to obtain observation items; accept additional observation items related to the inquiry; generate a second prompt including the observation items, the additional observation items, and the inquiry; and present countermeasures according to the inquiry obtained by inputting the second prompt into the language model.

[0019] According to one embodiment of the present disclosure, techniques for leveraging natural language models are improved.

[0020] 1 is a block diagram showing a schematic configuration of a system according to an embodiment of the present disclosure. FIG. 2 is a block diagram showing a schematic configuration of a terminal device. FIG. 3 is a block diagram showing a schematic configuration of an information processing device. FIG. 4 is a block diagram showing a schematic configuration of a first server. FIG. 5 is a block diagram showing a schematic configuration of a second server. FIG. 6 is a flowchart showing an operation example 1 of the information processing device. FIG. 7 is a flowchart showing an operation example 2 of the information processing device. FIG. 8 is a diagram showing an example of a user interface output by a terminal device. FIG. 9 is a diagram showing an example of a user user interface output by a terminal device. FIG. 10 is a diagram showing an example of a user user interface output by a terminal device. FIG. 11 is a diagram showing an example of a user user interface output by a terminal device. FIG. 12 is a diagram showing an example of a user user interface output by a terminal device. FIG. 13 is a diagram showing an example of a user user interface output by a terminal device. FIG. 14 is a diagram showing an example of a user user interface output by a terminal device.

[0021] Hereinafter, embodiments of the present disclosure will be described.

[0022] (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 according to the 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.

[0023] The multiple terminal devices 10 are any devices used by, for example, care workers, caregivers, care managers, care staff, facility directors, administrators, headquarters 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 used as the terminal devices 10. Note that while FIG. 1 shows an example in which the system 1 is equipped with three terminal devices 10, this is not limiting. The system 1 may be equipped with fewer than three terminal devices 10, or may be equipped with four or more terminal devices 10.

[0024] 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 system. The information processing device 20 is capable of communicating with terminal devices 10 and the like via a network 50. Note that while FIG. 1 shows an example in which the system 1 includes one information processing device 20, this is not limiting. The system 1 may include two or more information processing devices 20.

[0025] The first server 30 is a server device installed in, for example, a data center. The first server 30 is a server belonging to a cloud computing system or other computing system. The first server 30 includes a language model. In this embodiment, the language model includes any dialogue system, such as a Large Language Model (LLM) or a chatbot. The language model outputs text corresponding to a prompt based on a prompt input, which is an instruction from a user. The first server 30 can communicate with the information processing device 20, etc., via the network 50. For example, the information processing device 20 inputs a prompt into the language model of the first server 30 and obtains an output result corresponding to the prompt. Note that while FIG. 1 illustrates an example in which the system 1 includes one first server 30, this is not limiting. The system 1 may include two or more first servers 30.

[0026] The second server 40 is a server device installed in, for example, a data center. For example, the second server 40 is a server belonging to a cloud computing system or other computing system. The second server 40 has a database (hereinafter also referred to as an index) that aggregates business manuals, guidelines, past inquiries, their analysis results, and countermeasures related to a specific field such as nursing care. The second server 40 is capable of communicating with the information processing device 20, etc. via the network 50. Note that while FIG. 1 shows an example in which the system 1 has one second server 40, this is not limiting. The system 1 may have two or more second servers 40.

[0027] First, an overview of this embodiment will be described, and details will be described later. The information processing device 20 receives an inquiry from a user at a care site or the like. The information processing device 20 generates a first prompt including the received inquiry, and inputs the first prompt into a language model to acquire observation items. The information processing device 20 also receives additional observation items related to the inquiry from the user. The additional observation items are additional observation items that are necessary to answer the inquiry. The additional observation items are determined based on the observation items obtained by inputting the first prompt into the language model. Specifically, observation items that are insufficient with just the observation items obtained by inputting the first prompt into the language model are determined as additional observation items.

[0028] When the acquired additional observation item is received, the information processing device 20 generates a second prompt including the observation item, the additional observation item, and the inquiry content. Then, the information processing device 20 inputs the second prompt into a language model and presents to the user a measure corresponding to the inquiry content.

[0029] As described above, according to this embodiment, when an inquiry about a nursing care site or the like is received from a user, a first prompt is first generated and input into a language model to acquire observation items. Furthermore, in this embodiment, a second prompt including the additional observation items received from the user is generated and input into the language model, thereby presenting the user with countermeasures according to the inquiry. Therefore, the technology for utilizing natural language models is improved in that the probability of obtaining the information necessary to present countermeasures is increased.

[0030] Next, each component of the system 1 will be described in detail.

[0031] (Configuration of 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 .

[0032] 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 central processing unit (CPU) or a graphics processing unit (GPU), or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC). The control unit 11 controls each unit of the terminal device 10 and executes processes related to the operation of the terminal device 10.

[0033] 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 random access memory (RAM) or a read-only memory (ROM). The RAM is, for example, a static random access memory (SRAM) or a dynamic random access memory (DRAM). The ROM is, for example, an electrically erasable programmable read-only memory (EEPROM). 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 in the operation of the terminal device 10 and data obtained by the operation of the terminal device 10.

[0034] The communication unit 13 includes at least one external communication interface. The communication interface may be either a wired or 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 compatible with mobile communication standards such as LTE (Long Term Evolution), 4G (4th generation), or 5G (5th generation), or an interface compatible with short-range wireless communication such as WiFi (registered trademark) or Bluetooth (registered trademark). The communication unit 13 receives data used in the operation of the terminal device 10 and transmits data obtained by the operation of the terminal device 10.

[0035] The input unit 14 includes at least one input interface. The input interface may be, for example, a physical key, a capacitive key, a pointing device, or a touch screen integrated with a display. The input interface may also be, for example, a microphone that accepts voice input, or a camera that accepts gesture input. The input unit 14 accepts an operation to input data used in the operation of the terminal device 10. The input unit 14 may be connected to the terminal device 10 as an external input device instead of being provided in the terminal device 10. Any connection method may be used, for example, a Universal Serial Bus (USB), a High-Definition Multimedia Interface (HDMI) (registered trademark), or Bluetooth (registered trademark).

[0036] 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. The display is, for example, an LCD (liquid crystal display) or an organic EL (electro luminescence) display. The output unit 15 displays and outputs data obtained by the operation of the terminal device 10. The output unit 15 may be connected to the terminal device 10 as an external output device instead of being provided in the terminal device 10. Any connection method can be used, for example, USB, HDMI (registered trademark), or Bluetooth (registered trademark).

[0037] The functions of the terminal device 10 are realized by executing a 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 a computer to execute the operations of the terminal device 10, thereby causing the computer to 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 in accordance with the program.

[0038] In this embodiment, the program can be recorded on a computer-readable recording medium. The computer-readable recording medium includes non-transitory computer-readable media, such as a magnetic recording device, an optical disc, a magneto-optical recording medium, or a semiconductor memory. The program can be distributed, 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. The program can also be distributed by storing the program in the storage of an external server and transmitting the program from the external server to another computer. The program can also be provided as a program product.

[0039] Some or all of the functions of the terminal device 10 may be realized by a dedicated circuit equivalent to the control unit 11. In other words, some or all of the functions of the terminal device 10 may be realized by hardware.

[0040] (Configuration of information processing device)

[0041] As shown in FIG. 3, the information processing device 20 includes a control unit 21, a storage unit 22, and a communication unit 23.

[0042] The control unit 21 includes at least one processor, at least one dedicated circuit, or a combination of these. The processor is a general-purpose processor such as a CPU or GPU, or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, an FPGA or an ASIC. The control unit 21 controls each unit of the information processing device 20 and executes processes related to the operation of the information processing device 20.

[0043] 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 a ROM. The RAM is, for example, an SRAM or a 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 in the operation of the information processing device 20 and data obtained by the operation of the information processing device 20.

[0044] The communication unit 23 includes at least one external communication interface. 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 compatible with a mobile communication standard such as LTE, 4G, or 5G, or an interface compatible with short-range wireless communication such as WiFi (registered trademark) or Bluetooth (registered trademark). The communication unit 23 receives data used in the operation of the information processing device 20 and transmits data obtained by the operation of the information processing device 20.

[0045] The functions of the information processing device 20 are realized by executing a program according to this embodiment on a processor corresponding to the control unit 21. That is, the functions of the information processing device 20 are realized by software. The program causes a computer to execute the operations of the information processing device 20, thereby causing the computer to function as the information processing device 20. That is, the computer functions as the information processing device 20 by executing the operations of the information processing device 20 in accordance with the program.

[0046] In this embodiment, a computer temporarily stores a program recorded on a portable recording medium or transmitted from a server in a main storage device. The computer then reads the program stored in the main storage device with a processor and executes processing in accordance with the read program with the processor. The computer may read the program directly from a portable recording medium and execute processing in accordance with the program. The computer may also execute processing in accordance with the received program each time it receives a program from an external server. Processing may also be executed by a so-called ASP (application service provider) type service that realizes functions by issuing execution instructions and obtaining results, rather than transmitting a program from an external server to the computer. Programs include information used for processing by an electronic computer that is equivalent to a program. For example, data that is not a direct instruction to a computer but has properties that define computer processing falls under the category of "equivalent to a program."

[0047] Some or all of the functions of the information processing device 20 may be implemented by a dedicated circuit equivalent to the control unit 21. In other words, some or all of the functions of the information processing device 20 may be implemented by hardware.

[0048] (Configuration of the first server)

[0049] As shown in FIG. 4 , the first server 30 includes a control unit 31 , a storage unit 32 , and a communication unit 33 .

[0050] The control unit 31 includes at least one processor, at least one dedicated circuit, or a combination of these. The processor is a general-purpose processor such as a CPU or GPU, or a dedicated processor specialized for a specific process. 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 processes related to the operation of the first server 30.

[0051] The storage 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 storage unit 32 functions as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 32 stores data used in the operation of the first server 30 and data obtained by the operation of the first server 30. For example, the storage unit 32 stores a language model. Furthermore, for example, the language model may be stored in GPU memory, such as a VRAM of a 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 instances where the GPU is configured as part of another processor, e.g., a host processor, the GPU memory may be accessed by components other than the GPU.

[0052] The communication unit 33 includes at least one external communication interface. 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 compatible with a mobile communication standard such as LTE, 4G, or 5G, or an interface compatible with short-range wireless communication such as Wi-Fi (registered trademark) or Bluetooth (registered trademark). The communication unit 33 receives data used in the operation of the first server 30 and transmits data obtained by the operation of the first server 30.

[0053] The functions of the first server 30 are realized by executing a 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 causing the computer to 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 in accordance with the program.

[0054] Some or all of the functions of the first server 30 may be realized by a dedicated circuit corresponding to the control unit 31. In other words, some or all of the functions of the first server 30 may be realized by hardware.

[0055] (Configuration of 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 .

[0056] The control unit 41 includes at least one processor, at least one dedicated circuit, or a combination of these. The processor is a general-purpose processor such as a CPU or GPU, or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, an FPGA or an ASIC. The control unit 41 controls each part of the second server 40 and executes processes related to the operation of the second server 40.

[0057] The memory 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 memory unit 42 functions as, for example, a main memory device, an auxiliary memory device, or a cache memory. The memory unit 42 stores data used in the operation of the second server 40 and data obtained by the operation of the second server 40. For example, the memory unit 42 stores an index. Note that the index may be stored in the memory unit 22 of the information processing device 20.

[0058] The communication unit 43 includes at least one external communication interface. The communication interface may be either a wired or 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 compatible with a mobile communication standard such as LTE, 4G, or 5G, or an interface compatible with short-range wireless communication such as Wi-Fi (registered trademark) or Bluetooth (registered trademark). The communication unit 43 receives data used in the operation of the second server 40 and transmits data obtained by the operation of the second server 40.

[0059] The functions of the second server 40 are realized by executing a program according to this 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 operations 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 operations of the second server 40 in accordance with the program.

[0060] Some or all of the functions of the second server 40 may be realized by a dedicated circuit corresponding to the control unit 41. In other words, some or all of the functions of the second server 40 may be realized by hardware.

[0061] (Operation Example 1 of Information Processing Apparatus) An operation example of the information processing apparatus 20 according to this embodiment will be described with reference to Fig. 6. Fig. 6 is a flowchart showing an example of a method executed by the information processing apparatus 20 according to this embodiment.

[0062] Step S100: The control unit 21 of the information processing device 20 accepts the inquiry content from the user. Any method can be used to accept the inquiry content from the user. For example, the inquiry content 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 the inquiry content, for example, by outputting a user interface screen related to the acceptance of the inquiry content.

[0063] Step S200: The control unit 21 generates a first prompt including the content of the inquiry. The first prompt may include a predetermined prompt template, as appropriate. This allows the language model to output a message according to the predetermined prompt template.

[0064] Step S300: The control unit 21 inputs the first prompt into 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 into the language model of the first server 30. The language model outputs 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.

[0065] Step S400: The control unit 21 accepts additional observation items related to the inquiry content. Any method can be adopted as a method for accepting additional observation items from the user. 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 the additional observation items, for example, by outputting a user interface screen related to the acceptance of the additional observation items.

[0066] Step S500: The control unit 21 generates a second prompt including the observation item, the additional observation item, and the inquiry. The second prompt may include a predetermined prompt template, as appropriate. This allows the language model to output a message according to the predetermined prompt template.

[0067] Step S600: The control unit 21 presents a countermeasure corresponding 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. The control unit 21 then presents the acquired countermeasure. Any method can be adopted as a method for presenting the acquired countermeasure. 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 a user interface screen including the content of the acquired countermeasure, for example.

[0068] As described above, according to the first operation example of the present embodiment, when an inquiry about a nursing care site or the like is received from a user, a first prompt is first generated and input into a language model to acquire observation items. Furthermore, in the first operation example, a second prompt including the additional observation items received from the user is generated and input into the language model, thereby presenting the user with countermeasures according to the inquiry. Therefore, the technology for utilizing natural language models is improved in that the probability of acquiring the information necessary to present countermeasures is increased.

[0069] (Operation Example 2 of Information Processing Device) Operation Example 2 of the information processing device 20 according to this embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing an example of a method executed by the information processing device 20 according to this embodiment. The same operations as those in Fig. 6 are denoted by the same reference numerals. Operation Example 2 differs 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.

[0070] Step S100: The control unit 21 of the information processing device 20 accepts the inquiry content from the user. Any method can be adopted as a method for accepting the inquiry content from the user. For example, the inquiry content 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 the inquiry content using the input unit 14, for example, by outputting a user interface screen related to the acceptance of the inquiry content.

[0071] Step S200: The control unit 21 generates a first prompt including the content of the inquiry. The first prompt may include a predetermined prompt template, as appropriate. This allows the language model to output a message according to the predetermined prompt template.

[0072] Step S300: The control unit 21 inputs the first prompt into 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 into the language model of the first server 30. The language model outputs 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.

[0073] Step S400: The control unit 21 accepts additional observation items related to the inquiry content. Any method can be adopted as a method for accepting additional observation items from the user. 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 the additional observation items using the input unit 14, for example, by outputting a user interface screen related to the acceptance of the additional observation items.

[0074] Step S410: The control unit 21 generates a third prompt including the observation item and the inquiry. The third prompt may include a predetermined prompt template, so that the language model can output a message according to the predetermined prompt template.

[0075] Step S420: The control unit 21 inputs the third prompt into the language model and acquires 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.

[0076] Step S510: The control unit 21 generates a second prompt including the observation item, the additional observation item, the inquiry, and the analysis result. The second prompt may include a predetermined prompt template, as appropriate. This allows the language model to output according to the predetermined prompt template.

[0077] Step S600: The control unit 21 presents a countermeasure corresponding 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. The control unit 21 then presents the acquired countermeasure. Any method can be adopted as a method for presenting the acquired countermeasure. 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 a user interface screen including the content of the acquired countermeasure, for example.

[0078] As described above, according to Operation Example 2 of this embodiment, when an inquiry about a nursing care site or the like is received from a user, a first prompt is first generated, and the first prompt is input into a language model to acquire observation items. Furthermore, in Operation Example 2, a third prompt including the additional observation items received from the user is generated, and the third prompt is input into the language model to acquire analysis results according to the inquiry. Then, in Operation Example 2, a second prompt including the observation items, the additional observation items, the inquiry, and the analysis results is generated, and the second prompt is input into the language model to present countermeasures according to the inquiry to the user. Therefore, by including the analysis results as information necessary for presenting countermeasures, more appropriate countermeasures can be presented.

[0079] (Example of User Interface) Below, examples of user interfaces displayed by the terminal device 10 in the above-mentioned Operation Example 2 are shown. Figures 8 to 11 show examples of user interface screens related to the acceptance of the inquiry content in step S100. The inquiry content includes a consultation summary, interview information, and the type of consultation content. The terminal device 10 accepts the consultation summary, interview information, and type of consultation content using the user interfaces in Figures 8, 10, and 11, respectively.

[0080] The user interface screen shown in FIG. 8 is a screen for accepting input of a consultation summary. The consultation summary includes the consultation content, information about the care recipient (e.g., age, level of care required, residence), the care recipient's medical history, current illness history, and medication history. The care recipient's information (e.g., age, level of care required, residence), the care recipient's medical history, current illness history, medication history, etc. may also be referred to as the care recipient's attribute information. As shown in FIG. 8 , each of fields 81-84 for accepting input of the consultation content, information about the care recipient, the care recipient's medical history, current illness history, and medication history may display sample sentences. This makes it easy to understand what sentences should be entered in each field. The user interface screen shown in FIG. 9 is a screen showing a state in which input of the consultation summary has been completed. When button 85 is selected, the screen transitions to a screen for accepting input of interview information.

[0081] The user interface screen shown in Figure 10 is a screen for accepting input of interview information. The interview information includes information interviewed from the person in question, information interviewed from related parties, and other information. As in Figure 8, reference examples may be displayed in each of fields 101-104 in Figure 10 for accepting input of information interviewed from the person in question, information interviewed from related parties, and other information. When button 105 is selected, the screen transitions to a screen for accepting input of interview information. On the other hand, when button 106 is selected, the screen returns to a screen for accepting input of a consultation summary.

[0082] The user interface screen shown in Fig. 11 is a screen for receiving input of the type of consultation content. In the example shown in Fig. 11, there are five types of consultation content: diet, falls, excretion, dementia, and other. The user interface screen shown in Fig. 11 includes buttons 111-115 corresponding to each of these types. By selecting one of the buttons 111-115, the type of consultation content is selected and a first prompt including the inquiry content is generated.

[0083] Depending on the type of consultation content, an index related to the type of inquiry content may be referenced. That is, the first prompt may include the index. In other words, the first prompt may further include an index related to the inquiry content. Specifically, depending on the type of consultation content, the control unit 21 of the information processing device 20 acquires an index related to 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 that includes industry-specific terminology or expressions. Therefore, by having the language model refer to a predetermined index, it is possible to output an answer that is more specific to the consultation content. More specifically, the inquiry content may include at least one of inquiries related to eating, falls, excretion, and dementia, and the first prompt may further include an index related to the inquiry content. This allows a desired answer to be obtained even for inquiries in the medical or nursing care fields, such as eating, falls, excretion, or dementia. Furthermore, for example, the second prompt may include an index related to at least one of the observation items, the additional observation items, and the inquiry content. This allows the general-purpose language model to refer to the predetermined index and output an answer that is more specific to the consultation content. Furthermore, the third prompt may include an index related to at least one of the observation items, the additional observation items, and the inquiry content. This allows the general-purpose language model to refer to the predetermined index and output an answer that is more specific to the consultation content. Furthermore, when an analysis result is obtained by the third prompt, the second prompt may further include an index related to any of the observation items, the additional observation items, the inquiry content, and the analysis result. This allows for more accurate output. Note that by using an LLM, which is an example of a language model developed for general purposes, the technology disclosed herein can be implemented in nursing care settings, etc., without building a new model.In this case, by having the LLM refer to an index containing information about the field in which it is implemented (such as the nursing care field), it is possible to obtain output that is more optimized for the nursing care field, etc. Note that this disclosure does not preclude fine-tuning or transfer learning of a general-purpose language model. For example, even with an additionally trained language model, inputting information from a specified index can produce a more accurate output.

[0084] 12 to 14 show examples of the user interface screens related to step S300.

[0085] The user interface screen shown in FIG. 12 shows the intermediate stage of acquiring observation items after inputting the first prompt into the language model. The acquired observation items are controlled based on the predetermined prompt template described above. The predetermined prompt template may be any template. Here, the predetermined prompt template is based on a framework for specific problem solving (hereinafter, also referred to as PROM). In PROM, the problem-solving process is divided into five processes. These five processes are (1) problem identification, (2) understanding the situation, (3) analysis, (4) countermeasures, and (5) evaluation. In PROM, these five processes are executed in order from (1) to (5). Here, the processes of (2) understanding the situation and (3) analysis are performed from a phenomenologically multifaceted perspective. Specifically, the situation is understood or analyzed from the perspective of five reasons. These five factors are (1) medication check, (2) presence or absence of physical illness, (3) presence or absence of mental illness, (4) environmental factors, and (5) psychological factors. Of these, five items (5 Objects) are used for observation when assessing or analyzing the condition of (1) medication check, (2) presence or absence of physical illness, and (3) mental illness. The five items are (1) behavior and condition, (2) complaints from the patient, (3) vital signs, (4) simple medical tests, and (5) tests conducted at a medical institution. On the other hand, when assessing or analyzing the condition of (5) psychological factors, three or more items (Mental 3+1) are used for observation. The three or more items are (1) life history, (2) behavioral observation, (3) listening to the patient, and (4) what I would do if I were in that situation.

[0086] To implement a PROM-based problem-solving framework, for example, the first prompt may include a predetermined template consistent with the PROM. For example, the first prompt may include information on at least one of medication, physical illness, mental illness, 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. For example, the first prompt may include information on at least one of behavior, condition, complaints from the patient, vital signs, and tests. By including this information, these five items (5 Objects) can be output as observation items from the language model. In other words, in this embodiment, if the first prompt includes information on at least one of medication, physical illness, and mental illness, the observation items may include information on at least one of behavior, condition, complaints from the patient, vital signs, and tests. Furthermore, if the first prompt includes information on mental illness, the observation items may include information on at least one of life history, behavioral observation, listening to the patient, and what the patient would do if they were the patient. By including this information, it is possible to output these three or more items (Mental 3+1) as observation items to the language model.

[0087] As described above, the user interface screen shown in FIG. 12 shows the intermediate stage of acquiring observation items. Here, the status is grasped and the observation items are confirmed from the perspective of five reasons: (1) medication check, (2) presence or absence of physical illness, (3) presence or absence of mental illness, (4) environmental factors, and (5) psychological factors. The progress of each is indicated by icons 121-129. Icons 121, 126, 127, 128, and 129 indicate that processing by the language model is in progress. On the other hand, icons 122-125 indicate that processing by the language model is complete. When processing of all of these items is complete, the observation items corresponding to the first prompt are acquired from the language model, and the screen transitions to the next user interface screen.

[0088] The user interface screens shown in FIGS. 13, 14, and 15 are screens showing observation items corresponding to the first prompt. The observation items corresponding to the first prompt may be listed for each of the five reasons described above. The user interface screen shown in FIG. 13 includes observation items related to medication inspection. Tabs 131-135 are selection objects for selecting the observation items to be displayed. Tabs 131-135 correspond to (1) medication inspection, (2) presence or absence of physical illness, (3) presence or absence of mental illness, (4) environmental factors, and (5) psychological factors, respectively. When a user selects one of tabs 131-135, 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, the user interface screen lists observation items related to medication inspection. The listed information includes the category of the observation item, the item name, a description, and a result indicating whether the item is included in the inquiry. The categories of the observation items correspond to the 5 Objects or Mental 3+1 described above. The result of whether or not the observation item is included in the inquiry content is indicated by YES (Y) or NO (N). Y indicates that the observation item is included in the inquiry content. N indicates that the observation item is not included in the inquiry content. Observation items marked with N correspond to the additional observation items described above.

[0089] The user interface screen shown in Fig. 14 is the user interface screen when tab 132 is selected. As shown in Fig. 14, the user interface screen lists observation items related to the presence or absence of physical illnesses.

[0090] The user interface screen shown in Fig. 15 is the user interface screen when tab 135 is selected. As shown in Fig. 15, the user interface screen lists observation items related to psychological factors. In the example shown in Fig. 15, the observation items include information on items corresponding to the above-mentioned Mental 3+1, namely, life history, behavioral observation, listening to the person, and what you would do if you were in that situation.

[0091] In Figures 13, 14, and 15, selecting button 136 transitions to the next screen. On the other hand, selecting button 137 returns the user to the consultation summary input screen, where the consultation content is modified. For example, in Figures 13, 14, and 15, if it is confirmed that the observation items are included in the inquiry content, selecting button 136 transitions to the next screen. On the other hand, if there are insufficient observation items in Figures 13, 14, and 15, the presentation of countermeasures may be insufficient. In this case, a user interface screen is displayed that prompts the user to input the missing observation items (additional observation items), and the user is allowed to input the additional observation items. Any method can be used to input the additional observation items. For example, the user may return to the user interface screen shown in Figure 8 and 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 this user interface screen.

[0092] Here, information related to advice from a doctor may be input as the additional observation item. The user interface screen shown in FIG. 16 is a screen for accepting input of information related to advice from a doctor. A field 151 is an object into which information related to advice from a doctor can be input. When button 152 is selected with the information related to advice from the doctor input in field 151, a third prompt is generated including an observation item, an additional observation item, and an inquiry, with the information related to advice from the doctor as the additional observation item. On the other hand, when button 152 is selected with no information input in field 151, a third prompt is generated including an observation item and an inquiry.

[0093] 17 to 19 show examples of the user interface screens related to step S420.

[0094] The user interface screen shown in FIG. 17 illustrates the intermediate stage of acquiring analysis results after inputting the third prompt into the language model. The acquired analysis results are controlled based on the predetermined prompt template described above. In this embodiment, the third prompt is described as including a predetermined template based on the PROM. In FIG. 17 , the analysis is performed from the perspective of five factors (5 reasons): (1) medication check, (2) presence or absence of physical illness, (3) presence or absence of mental illness, (4) environmental factors, and (5) psychological factors. The progress of each factor is indicated by icons 161-165. Icons 161 and 164 indicate that processing by the language model is in progress. On the other hand, icons 162, 163, and 165 indicate that processing by the language model has been completed. When processing for each item is completed, analysis results corresponding to the third prompt are acquired from the language model, and the screen transitions to the next user interface screen.

[0095] The user interface screens shown in FIGS. 18 and 19 are screens showing analysis results corresponding to the third prompt. The analysis results corresponding to the third prompt may be listed for each of the five reasons described above. The user interface screen shown in FIG. 18 includes analysis results related to medication inspection. Tabs 171-175 are selection objects for selecting the analysis results to be displayed. Tabs 171-175 correspond to (1) medication inspection, (2) presence or absence of physical illness, (3) presence or absence of mental illness, (4) environmental factors, and (5) psychological factors, respectively. When a user selects tabs 171-175, analysis results corresponding to each of these factors are listed. FIG. 18 shows the user interface screen when tab 171 is selected. As shown in FIG. 18, the user interface screen lists analysis results related to medication inspection. The listed information includes whether or not the medication is affecting the patient and the reasons why the medication is believed to be affecting the patient.

[0096] The user interface screen shown in Figure 19 is the user interface screen when tab 172 is selected. As shown in Figure 18, this user interface screen lists analysis results related to the presence or absence of physical illnesses. The listed information includes whether or not a physical illness or physical condition has an effect, and the reasons why a physical illness or physical condition is thought to have an effect. When button 176 is selected in Figure 18 or Figure 19, a second prompt is generated that includes observation items, additional observation items, inquiry content, and analysis results, and the screen transitions to the next user interface screen shown in Figure 20.

[0097] 20 and 21 show examples of the user interface screen related to step S600.

[0098] The user interface screen shown in Fig. 20 is a screen showing the intermediate stage in which a countermeasure corresponding to the inquiry content is being acquired after the second prompt has been input into the language model. Once processing by the language model is complete, the screen transitions to the user interface screen shown in Fig. 21.

[0099] The user interface screen shown in Fig. 21 is a screen that presents countermeasures according to the inquiry content. The presented information includes a target state and countermeasures. In this way, the target state and countermeasures according to the inquiry content are specifically shown. As exemplified in Fig. 21, by selecting button 201 or button 202, a new analysis may be started or a reanalysis may be performed with the consultation content changed.

[0100] In the above-described embodiment, the information processing device 20 may be configured or operated to execute part or all of the present disclosure. For example, the information processing device 20 may be configured or operated to configure a prompt including a consultation item related to a care recipient and attribute information of the care recipient, input such a prompt into the LLM, and obtain an answer corresponding to the consultation item from the LLM. More specifically, information about the care recipient (e.g., age, level of care required, residence), or any of the care recipient's medical history, current medical history, and medication history, along with the consultation item, may be input into the LLM. Furthermore, information about the consultation item or information other than the attribute information of the care recipient may be included as an index in the prompt and input into the LLM. While 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 within the scope of the present disclosure. For example, functions included in each component or step may be rearranged so as not to be logically contradictory, and multiple components or steps may be combined or divided into one.

[0101] 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, for example, an embodiment in which some or all of the components of the information processing device 20 are provided in the terminal device 10 is possible.

[0102] REFERENCE SIGNS LIST 1 System 10 Terminal device 11 Control unit 12 Storage unit 13 Communication unit 14 Input unit 15 Output unit 20 Information processing device 21 Control unit 22 Storage unit 23 Communication unit 30 First server 31 Control unit 32 Storage unit 33 Communication unit 40 Second server 41 Control unit 42 Storage unit 43 Communication unit 50 Network 81, 82, 83, 84 Field 85 Button 101, 102, 103, 104 Field 105 Button 111, 112, 113, 114, 115 Button 121, 122, 123, 124, 125, 126, 127, 128, 129 Icon 131, 132, 133, 134, 135 Tab 136, 137 Button 151 Field 152 Button 161, 162, 163, 164, 165 Icon 171, 172, 173, 174, 175 Tab 176 Button 201, 202 Button

Claims

1. A method executed by an information processing device, comprising: accepting a query from a user; generating a first prompt including the query; inputting the first prompt into a language model to obtain an observation item; accepting additional observation items related to the query; generating a second prompt including the observation items, the additional observation items, and the query; and presenting a countermeasure corresponding to the query obtained by inputting the second prompt into the language model.

2. The method of claim 1, further comprising: generating a third prompt including the observation item, the additional observation item, and the inquiry content; inputting the third prompt into the language model to obtain an analysis result; and the second prompt further including the analysis result.

3. The method of claim 1, wherein the first prompt includes information regarding any one of a medication, a physical illness, a mental illness, an environmental factor, and a psychological factor.

4. The method of claim 1, wherein the first prompt includes information regarding any one of medication, physical illness, and mental illness, and the observation items include information regarding at least any one of behavior, condition, personal complaints, vital signs, and tests.

5. The method of claim 1, wherein the first prompt includes information regarding psychological factors, and the observation items include information regarding at least one of life history, behavioral observation, listening to the person, and what you would do if you were in that situation.

6. The method of claim 1, further comprising: the first prompt further comprising an index relating to the content of the query.

7. The method according to claim 1, further comprising: the inquiry content includes at least one of inquiries regarding eating, falls, excretion, and dementia; and the first prompt further includes an index regarding the inquiry content.

8. The method of claim 1, further comprising: the second prompt further comprising an index relating to any one of the observation item, the additional observation item, and the inquiry content.

9. The method of claim 2, further comprising: the third prompt further comprising an index relating to any one of the observation item, the additional observation item, and the inquiry content.

10. The method of claim 9, wherein the second prompt further includes an index relating to any one of the observation item, the additional observation item, the inquiry, and the analysis result.

11. An information processing device having a control unit, which receives a query from a user, generates a first prompt including the query, inputs the first prompt into a language model to obtain an observation item, receives additional observation items related to the query, generates a second prompt including the observation items, the additional observation items, and the query, and presents a countermeasure corresponding to the query obtained by inputting the second prompt into the language model.

12. A program that causes a computer to perform the following: accepting an inquiry from a user; generating a first prompt including the inquiry; inputting the first prompt into a language model to obtain an observation item; accepting additional observation items related to the inquiry; generating a second prompt including the observation items, the additional observation items, and the inquiry; and presenting a countermeasure corresponding to the inquiry obtained by inputting the second prompt into the language model.

Images