Method, information processing device, and program

Abstract

Provided is a method executed by an information processing device 20, the method comprising: receiving, from a user, inquiry details related to a person requiring nursing care; acquiring quantitative information related to the person requiring nursing care from a system used for providing the care service to the person requiring nursing care; generating a prompt including the inquiry details and the quantitative information; and inputting the prompt to a language model to acquire an action item for the inquiry details.

Description

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

[0001] This application claims priority from Japanese Patent Application No. 2024-013609, filed on January 31, 2024, 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 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 in a care system that determines the current state of a user to determine whether the user is in a dangerous state.

[0004] Patent No. 7016499

[0005] The technology in Patent Document 1 mainly focuses on understanding the current state of a user from the content of the user's responses to a chatbot, but does not consider a method for obtaining highly convincing information from a language model. In other words, there is room for improvement in the technology for utilizing language models.

[0006] In view of the above circumstances, an object of the present disclosure is to improve the technology for utilizing 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 regarding a person requiring care; acquiring quantitative information regarding the person requiring care from a system used in providing care services to the person requiring care; generating a prompt including the inquiry and the quantitative information; and inputting the prompt into a language model to acquire an action item for the inquiry.

[0008] (2) A method according to one embodiment of the present disclosure is the method described in (1), wherein the quantitative information is information obtained from the person requiring care via the care service.

[0009] (3) A method according to one embodiment of the present disclosure is a method according to (1) or (2), wherein the quantitative information includes information on at least one of care level, dementia level, medical history, current medical history, and ADL.

[0010] (4) A method according to an embodiment of the present disclosure is the method according to any one of (1) to (3), wherein the quantitative information includes information about an ingested item of the person requiring care.

[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 information regarding the ingested items includes information regarding the intake amount of at least one of medication, fluid, and food ingested by the person requiring care.

[0012] (6) A method according to one embodiment of the present disclosure is a method according to any one of (1) to (5), wherein the quantitative information includes information regarding at least one of the vital signs and amount of sleep of the person requiring care reported by the system.

[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 quantitative information includes information on the number of alerts issued to the person requiring care by the system.

[0014] (8) A method according to an embodiment of the present disclosure is the method according to any one of (1) to (7), wherein the quantitative information includes information indicating changes over time in the care recipient.

[0015] (9) A method according to one embodiment of the present disclosure is a method according to any one of (1) to (8), wherein the quantitative information includes at least one of a schedule and performance information of excretion care for the person requiring care.

[0016] (10) A method according to one embodiment of the present disclosure is a method according to any one of (1) to (9), further comprising: acquiring qualitative information about the person requiring care from the system, and generating a prompt including the inquiry content, the quantitative information, and the qualitative information.

[0017] (11) A method according to one embodiment of the present disclosure is a method according to any one of (1) to (10), further comprising selecting the quantitative information to be obtained from the system depending on the content of the inquiry.

[0018] (12) A method according to one embodiment of the present disclosure is a method according to any one of (1) to (11), further including prioritizing the quantitative information obtained from the system according to the content of the inquiry, and obtaining the quantitative information whose priority is equal to or greater than a predetermined value from the system.

[0019] (13) A method according to one embodiment of the present disclosure is a method according to any one of (1) to (12), further comprising: acquiring qualitative information about the person requiring care from the system in accordance with the content of the inquiry; and generating a prompt including the content of the inquiry, the quantitative information, and the qualitative information.

[0020] (14) A method according to one embodiment of the present disclosure is the method according to any one of (1) to (13), further comprising the step of: the prompt includes an index relating to the query content.

[0021] (15) A method according to one embodiment of the present disclosure is a method according to any one of (1) to (14), further comprising: registering a care schedule recommended by the action item in a scheduler of the system.

[0022] (16) A method according to one embodiment of the present disclosure is a method according to any one of (1) to (15), further comprising storing the query content, the quantitative information, and the action items in an index referenced by the language model.

[0023] (17) A method according to one embodiment of the present disclosure is a method according to any one of (1) to (16), further comprising: receiving a result of implementing the action item on the person requiring care; and storing the result in association with the action item.

[0024] (18) A method according to one embodiment of the present disclosure is the method according to any one of (1) to (17), comprising inputting an output from the language model into the language model to output an additional query.

[0025] (19) An information processing device according to an embodiment of the present disclosure is an information processing device including a processor, wherein the processor executes the method according to any one of (1) to (18).

[0026] (20) A program according to an embodiment of the present disclosure is a program executed by an information processing device, causing a computer to execute the method according to any one of (1) to (18).

[0027] According to a method, an information processing device, and a program according to an embodiment of the present disclosure, a technology for utilizing a language model is improved.

[0028] 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 block diagram showing a schematic configuration of a third server; FIG. 7 is a flowchart showing an operation example 1 of the information processing device; FIG. 8 is a diagram showing an example of a user interface output by the terminal device; FIG. 9 is a flowchart showing an operation example 2 of the information processing device; FIG. 10 is a flowchart showing an operation example 3 of the information processing device; FIG. 11 is a diagram showing an example of a user interface output by the terminal device; FIG. 12 is a diagram showing an example of a user interface output by the terminal device; FIG. 13 is a diagram showing an example of a user interface output by the terminal device;

[0029] Hereinafter, techniques according to embodiments of the present disclosure will be described with reference to the drawings.

[0030] In each drawing, the same or corresponding parts are denoted by the same reference numerals. In the description of this embodiment, the description of the same or corresponding parts will be omitted or simplified as appropriate.

[0031] (Outline of the embodiment) The outline and configuration of a system 1 according to the present embodiment will be described with reference to FIG.

[0032] The system 1 according to this embodiment includes a plurality of terminal devices 10, an information processing device 20, a first server 30, a second server 40, and a third server 50. The plurality of terminal devices 10, the information processing device 20, the first server 30, the second server 40, and the third server 50 are communicably connected to a network 60 including, for example, a mobile communication network and the Internet.

[0033] 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.

[0034] 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 60. 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.

[0035] 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 60. 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.

[0036] The second server 40 is a server device installed in, for example, a data center. The second server 40 is a server belonging to a cloud computing system or other computing system. The second server 40 has a database that aggregates quantitative information, qualitative information, etc. related to persons requiring care. The second server 40 is capable of communicating with the information processing device 20, etc. via the network 60. 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.

[0037] The third server 50 is a server device installed in, for example, a data center. The third server 50 is a server belonging to a cloud computing system or other computing system. The third server 50 has a database (hereinafter also referred to as an index) that aggregates business manuals, guidelines, past inquiries and action items corresponding to each inquiry, implementation results, etc. related to a specific field such as nursing care. The third server 50 is capable of communicating with the information processing device 20, etc. via the network 60. Note that while FIG. 1 shows an example in which the system 1 has one third server 50, this is not limited to this. The system 1 may have two or more third servers 50.

[0038] First, an overview of this embodiment will be described. The information processing device 20 receives an inquiry from a user regarding a care recipient. The information processing device 20 acquires quantitative information regarding the care recipient from a system (hereinafter also referred to as a nursing facility operation support system) used to provide care services to the care recipient related to the inquiry. The information processing device 20 also generates a prompt including the received inquiry and the acquired quantitative information, and inputs the prompt into a language model to acquire an action item for the inquiry.

[0039] Here, a person requiring care refers to a person who requires nursing care. A person requiring care includes a person who has been certified as needing nursing care or support by a city, town, or village. A person requiring care includes a resident of a nursing facility, a nursing home, a housing facility for the elderly with services, a care house, or the like. Furthermore, an inquiry about a person requiring care refers to a matter for which an answer is sought from a language model regarding the person requiring care. The inquiry may include, for example, a question regarding actions such as excretion care, dietary care, and nutritional care for the person requiring care. Furthermore, quantitative information about a person requiring care (hereinafter simply referred to as quantitative information) refers to information regarding the condition, living situation, etc. of the person requiring care that can be recorded when providing care services to the person requiring care, and that can be expressed quantitatively.

[0040] As described above, according to the present embodiment, when the information processing device 20 receives an inquiry about a care recipient from a user, it acquires quantitative information about the care recipient. The information processing device 20 generates a prompt including the inquiry and the quantitative information and inputs the prompt into a language model to acquire action items for the inquiry. Therefore, the technology for utilizing language models is improved in that it is more likely that information required as action items can be acquired.

[0041] Next, each component of the system 1 will be described.

[0042] (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 .

[0043] 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 dedicated processor specialized for a specific process. The dedicated circuit is, for example, a graphics processing unit (GPU), 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.

[0044] 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.

[0045] 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.

[0046] 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).

[0047] 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).

[0048] 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.

[0049] 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.

[0050] 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.

[0051] (Configuration of Information Processing Apparatus) As shown in FIG. 3 , the information processing apparatus 20 includes a control unit 21 , a storage unit 22 , and a communication unit 23 .

[0052] 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 central processing unit (CPU), 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 21 controls each unit of the information processing device 20 and executes processes related to the operation of the information processing device 20.

[0053] 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 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 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.

[0054] The communication unit 23 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 local area network (LAN) interface or a universal serial bus (USB). 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 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.

[0055] 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.

[0056] 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."

[0057] 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.

[0058] (Configuration of First Server) As shown in FIG. 4 , the first server 30 includes a control unit 31 , a storage unit 32 , and a communication unit 33 .

[0059] 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 central processing unit (CPU), or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, a graphics processing unit (GPU), a field-programmable gate array (FPGA), or an application specific integrated circuit (ASIC). The control unit 31 executes processes related to the operation of the first server 30 while controlling each unit of the first server 30.

[0060] 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 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 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.

[0061] For example, the storage unit 32 stores a language model. Also, 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 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.

[0062] The communication unit 33 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 local area network (LAN) interface or a universal serial bus (USB). In the case of wireless communication, the communication interface is, for example, an interface compatible with mobile communication standards such as long term evolution (LTE), 4th generation (4G), or 5th generation (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.

[0063] 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.

[0064] 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.

[0065] (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. The second server 40 is a nursing care facility operation support system.

[0066] 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 a dedicated processor specialized for a specific process. The dedicated circuit is, for example, a GPU, FPGA, or 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.

[0067] 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 quantitative information about the care recipient and qualitative information about the care recipient. Note that this information may be stored in the memory unit 22 of the information processing device 20 and an index of the third server 50.

[0068] 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.

[0069] 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.

[0070] 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.

[0071] (Configuration of Third Server) As shown in FIG. 6 , the third server 50 includes a control unit 51 , a storage unit 52 , and a communication unit 53 .

[0072] The control unit 51 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 a dedicated processor specialized for a specific process. The dedicated circuit is, for example, a GPU, FPGA, or ASIC. The control unit 51 controls each unit of the third server 50 and executes processes related to the operation of the third server 50.

[0073] The memory unit 52 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 52 functions as, for example, a main memory device, an auxiliary memory device, or a cache memory. The memory unit 52 stores data used in the operation of the third server 50 and data obtained by the operation of the third server 50. For example, the memory unit 52 stores an index. Note that the index may be stored in the memory unit 22 of the information processing device 20.

[0074] The communication unit 53 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 53 receives data used in the operation of the third server 50 and transmits data obtained by the operation of the third server 50.

[0075] The functions of the third server 50 are realized by executing a program according to this embodiment on a processor corresponding to the control unit 51. That is, the functions of the third server 50 are realized by software. The program causes a computer to execute the operations of the third server 50, thereby causing the computer to function as the third server 50. That is, the computer functions as the third server 50 by executing the operations of the third server 50 in accordance with the program.

[0076] Some or all of the functions of the third server 50 may be realized by a dedicated circuit corresponding to the control unit 51. In other words, some or all of the functions of the third server 50 may be realized by hardware.

[0077] (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. 7. Fig. 7 is a flowchart showing an example of a method executed by the information processing apparatus 20 according to this embodiment.

[0078] Step S100: The control unit 21 of the information processing device 20 accepts an inquiry from a user regarding the care recipient. Any method can be adopted as a method for accepting the inquiry from the user. For example, the inquiry may be acquired by the information processing device 20 via an input interface of the terminal device 10. In this case, the output unit 15 of the terminal device 10 may prompt the user to input the inquiry, for example, by outputting a user interface screen related to accepting the inquiry.

[0079] Step S200: The control unit 21 acquires quantitative information about a care-requiring person from the care facility operation support system. Specifically, when the control unit 21 receives an inquiry about a care-requiring person from a user in step S100, the control unit 21 acquires quantitative information about the care-requiring person from the storage unit 42 of the second server 40.

[0080] Step S300: The control unit 21 generates a prompt including the inquiry content and quantitative information about the care recipient. The prompt may include a predetermined prompt template as appropriate. This allows the language model to output according to the predetermined prompt template.

[0081] Step S400: The control unit 21 inputs the prompt into the language model and acquires an action item corresponding to the inquiry content. Specifically, the control unit 21 transmits the prompt generated in step S300 to the first server 30 via the communication unit 23 and inputs the prompt into the language model of the first server 30. The language model outputs an action item corresponding to the prompt. The control unit 21 acquires the output action item from the first server 30 via the communication unit 23.

[0082] As described above, according to the first operational example of the present embodiment, when an inquiry about a care recipient from a user is received, quantitative information about the care recipient is first acquired, a prompt is generated, and the prompt is input into a language model to acquire an action item. A language model allows for a high degree of freedom in the content to be input, and the output result is influenced by the input content. By generating a prompt including quantitative information about the care recipient, as in the first operational example of the present embodiment, the objectivity of the input content can be increased, making it easier to obtain accurate output results. Therefore, the technology for utilizing language models is improved in that it increases the probability of acquiring the information necessary as an action item.

[0083] Here, the quantitative information regarding the care recipient may be information acquired from the care recipient through a care service. For example, the quantitative information regarding the care recipient may include information regarding at least one of the care level, dementia level, medical history, current medical history, and ADL. The quantitative information regarding the care recipient may also include information regarding the care recipient's intake. The information regarding the intake may include information regarding the intake amount of at least one of medication, water, and food ingested by the care recipient. A person's physical condition, such as excretion and nutritional status, is affected by what the person ingests. In other words, information regarding the intake or intake amount is useful for allowing a language model to perform a causal analysis of the care recipient's excretion, nutritional status, etc. Appropriate causal analysis is a prerequisite for the language model to output appropriate action items. Therefore, information regarding the intake or intake amount has a significant impact on the action items to be taken. Therefore, by including this information in the quantitative information regarding the care recipient, the probability of acquiring the information necessary as an action item is increased. Note that this quantitative information may be data automatically acquired by various sensors linked to the care facility operation system or data input by a user. The sensor may be an image sensor, a pressure sensor, a mass sensor, a vital sensor, or other sensor for acquiring quantitative information about the care recipient. The quantitative information may also be acquired in real time by the sensor, and by reflecting the quantitative information acquired in real time in the prompt, it is possible to obtain output with higher accuracy.

[0084] In addition, the medication ingested by the person requiring care may be any medication that has been introduced into the body of the person requiring care in some way, and may include medication that has been taken orally by the person requiring care, as well as medication that has been administered to the person requiring care by transdermal absorption, injection, etc.

[0085] The quantitative information about the care recipient may include information about at least one of the vital signs and the amount of sleep of the care recipient reported by the care facility operation support system, and information about the number of alerts for the care recipient reported by the system.

[0086] In addition, the quantitative information related to the care recipient may include information indicating changes in the care recipient over time. Furthermore, the quantitative information related to the care recipient may include at least one of the schedule and performance information of the care recipient's incontinence care. The performance information of the care recipient's incontinence care may include information regarding the time spent incontinence care. The information regarding the time spent incontinence care may include the start time, end time, required time, etc. of the care recipient. By including the performance information of the care recipient's incontinence care, action items can be acquired based on the care recipient's tendency to excrete. Furthermore, by including the schedule of the care recipient's incontinence care, more appropriate action items can be acquired based on the tendency of actual excretion to deviate from the schedule. For example, if actual excretion deviates from the schedule, an action item suggesting a more appropriate time for excretion care can be acquired. In addition, the quantitative information related to the care recipient may include various information that can be recorded related to the care recipient.

[0087] Furthermore, the control unit 21 may acquire qualitative information about the person requiring care from the nursing facility management support system and generate a prompt including the inquiry content, quantitative information about the person requiring care, and qualitative information about the person requiring care.

[0088] Here, qualitative information about a care recipient (hereinafter simply referred to as qualitative information) refers to information that can be recorded when providing care services to a care recipient, such as the condition and living situation of the care recipient, and that can be expressed qualitatively. By including qualitative information in addition to quantitative information in the prompt, the probability of obtaining the information required as an action item is increased.

[0089] The qualitative information about the care recipient may include, for example, information about underwear, type of incontinence, ADL, location of excretion, etc. The underwear may be selected from cloth pants, cloth pants and pads, pant-type diapers, pant-type diapers and pads, tape-on diapers, and tape-on diapers and pads. The underwear may include information about an excretion management support device such as a stoma and the presence or absence of a catheter. The type of incontinence may also be selected from urinary incontinence, fecal incontinence, both, or none. In addition to the above, the qualitative information about the care recipient may include various information that can be recorded about the care recipient, such as complaints from the care recipient, interviews with related parties, and advice from a doctor.

[0090] Furthermore, in step S200, the control unit 21 may select quantitative information to be acquired from the nursing facility management support system according to the inquiry content received in step S100. The control unit 21 may prioritize the quantitative information to be acquired from the system according to the inquiry content, and acquire quantitative information whose priority is equal to or higher than a predetermined value from the system. For example, the inquiry content may include at least one of inquiries regarding soiling incontinence, the number of excretion calls, missed / cancelled excretion care, and the number of excretion care sessions. The control unit 21 may acquire quantitative information with a high priority associated with each type of inquiry content. More specifically, for example, if the inquiry content is regarding soiling incontinence, quantitative information regarding the number of past soiling incontinence events may be associated with a higher priority. The control unit 21 may acquire such quantitative information with a high priority. That is, the quantitative information may be information related to the inquiry content, or more specifically, information related to past performance related to the inquiry content. The predetermined value may be, for example, 3, 5, 7, etc. The predetermined value may be any integer other than these. By narrowing down the quantitative information included in the prompt to those with high priority according to the content of the inquiry, it is possible to reduce erroneous answers (hallucinations). Furthermore, when there is a limit on the number of characters that can be input into a language model prompt, narrowing down the quantitative information included in the prompt to those with high priority makes it possible to generate a prompt with a number of characters that falls within the limit. In this case, the predetermined value may be determined based on the limit on the number of characters that can be input into the language model prompt.

[0091] Furthermore, the control unit 21 may acquire qualitative information about the person requiring care from the nursing facility management support system and generate a prompt including the inquiry content, quantitative information about the person requiring care, and qualitative information about the person requiring care.

[0092] The prompt may include an index related to the inquiry content. For example, the control unit 21 of the information processing device 20 may acquire an index related to the type of inquiry content from the third server 50. The control unit 21 may generate a prompt based on the acquired index. By using an LLM, 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. On the other hand, depending on the type of language model, such as a general-purpose language model, it may not be possible to obtain the expected accuracy in response to a prompt containing industry-specific terminology or expressions. Therefore, by having the language model refer to a predetermined index, it is possible to output a response that is more specific to the inquiry content. More specifically, for example, the inquiry content may include at least one of inquiries regarding soiling incontinence, number of excretion calls, missed / cancelled excretion care attempts, and number of excretion care visits, and the prompt may further include an index related to the inquiry content. This allows desired answers to be obtained even for inquiries in the medical or nursing care fields, such as soiling incontinence and excretion care. In this way, by including an index related to the inquiry content in the prompt, more accurate output can be obtained. Note that the present disclosure does not preclude fine-tuning or transfer learning of a general-purpose language model. For example, even if a language model has undergone additional learning or the like, it is possible to obtain a more accurate output by inputting information on a predetermined index.

[0093] Furthermore, the control unit 21 may acquire multiple action items in step S400. When acquiring multiple action items, the control unit 21 may prioritize the multiple action items and present the action items with the highest priority to the user.

[0094] Furthermore, the control unit 21 may register the care schedule recommended by the action items obtained in step S400 in a scheduler of the care facility operation support system.

[0095] The control unit 21 may display the recommended care schedule for each slot divided into predetermined time periods (e.g., every hour) along with the reason for whether or not care related to the action item should be performed. This allows the control unit 21 to provide the user with information that makes it easier for them to decide whether or not to accept the recommended care schedule. Specifically, as shown in FIG. 8 , the control unit 21 may display for each time slot divided into one hour whether or not excretion care should be performed along with the reason for the same. The control unit 21 may generate a specific care schedule based on the action items obtained in step S400. The control unit 21 may recommend different frequencies of care depending on the time period. For example, the control unit 21 may recommend more actions (care) in a second time period than in a first time period. For example, the control unit 21 may configure the care schedule so that more excretion care schedules are recommended in daytime hours than in nighttime hours.

[0096] The above-described modified example can be applied not only to the first operational example, but also to the second and third operational examples described below.

[0097] (Operation example 2 of information processing device) With reference to Fig. 9, an operation example 2 of the information processing device 20 according to this embodiment will be described. Fig. 9 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. 7 are assigned the same reference numerals. Operation example 2 differs from operation example 1 in that it adds a step of storing the inquiry content, quantitative information about the care recipient, and action items in an index that is referenced by a language model.

[0098] Step S100: The control unit 21 of the information processing device 20 accepts an inquiry from a user regarding the care recipient. Any method can be adopted as a method for accepting the inquiry from the user. For example, the inquiry may be acquired by the information processing device 20 via an input interface of the terminal device 10. In this case, the output unit 15 of the terminal device 10 may prompt the user to input the inquiry, for example, by outputting a user interface screen related to accepting the inquiry.

[0099] Step S200: The control unit 21 acquires quantitative information about a care-requiring person from the care facility operation support system. Specifically, when the control unit 21 receives an inquiry about a care-requiring person from a user in step S100, the control unit 21 acquires quantitative information about the care-requiring person from the storage unit 42 of the second server 40.

[0100] Step S300: The control unit 21 generates a prompt including the inquiry content and quantitative information about the care recipient. The prompt may include a predetermined prompt template as appropriate. This allows the language model to output according to the predetermined prompt template.

[0101] Step S400: The control unit 21 inputs the prompt into the language model and acquires an action item corresponding to the inquiry content. Specifically, the control unit 21 transmits the prompt generated in step S300 to the first server 30 via the communication unit 23 and inputs the prompt into the language model of the first server 30. The language model outputs an action item corresponding to the prompt. The control unit 21 acquires the output action item from the first server 30 via the communication unit 23.

[0102] Step S500: The control unit 21 stores the inquiry content, the quantitative information about the care recipient, and the action items in an index that is referenced by a language model. Specifically, the control unit 21 transmits the inquiry content received in step S100, the quantitative information about the care recipient acquired in step S200, and the action items acquired in step S400 to the third server 50 via the communication unit 23. The control unit 51 of the third server 50 stores this information received via the communication unit 53 in the storage unit 52. In this manner, the control unit 21 stores the inquiry content, the quantitative information about the care recipient, and the action items in an index.

[0103] As described above, according to the second operational example of the present embodiment, when an inquiry about a care recipient from a user is received, quantitative information about the care recipient is first acquired, a prompt is generated, and the prompt is input into a language model to acquire an action item. Then, in the second operational example, the inquiry, the quantitative information about the care recipient, and the action item are stored in an index. This enriches the information contained in the index. Therefore, the technology for utilizing language models is improved in that it is more likely that action items more specific to the inquiry will be obtained for future inquiries.

[0104] (Operation Example 3 of Information Processing Device) With reference to Fig. 10, an operation example 3 of the information processing device 20 according to this embodiment will be described. Fig. 10 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 Figs. 7 and 9 are denoted by the same reference numerals. Operation example 3 differs from operation examples 1 and 2 in that it accepts the results of implementing action items on a person requiring care, and stores the results in association with the action items.

[0105] Step S100: The control unit 21 of the information processing device 20 accepts an inquiry from a user regarding the care-requiring person. Any method can be adopted as a method for accepting the inquiry from the user. For example, the inquiry 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, for example, by outputting a user interface screen related to accepting the inquiry.

[0106] Step S200: The control unit 21 acquires quantitative information about a care-requiring person from the care facility operation support system. Specifically, when the control unit 21 receives an inquiry about a care-requiring person from a user in step S100, the control unit 21 acquires quantitative information about the care-requiring person from the storage unit 42 of the second server 40.

[0107] Step S300: The control unit 21 generates a prompt including the inquiry content and quantitative information about the care recipient. The prompt may include a predetermined prompt template as appropriate. This allows the language model to output according to the predetermined prompt template.

[0108] Step S400: The control unit 21 inputs the prompt into the language model and acquires an action item corresponding to the inquiry content. Specifically, the control unit 21 transmits the prompt generated in step S300 to the first server 30 via the communication unit 23 and inputs the prompt into the language model of the first server 30. The language model outputs an action item corresponding to the prompt. The control unit 21 acquires the output action item from the first server 30 via the communication unit 23.

[0109] Step S410: The control unit 21 accepts the results of implementing the action items on the care recipient (hereinafter simply referred to as the results). Any method can be adopted as a method for accepting the results from the user. For example, the results 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 results, for example, by outputting a user interface screen for accepting the results.

[0110] Step S510: The control unit 21 associates the results with the action items and stores them. Specifically, the control unit 21 associates the results received in step S410 with the action items acquired in step S400. The control unit 21 transmits the inquiry content received in step S100, the quantitative information about the care recipient acquired in step S200, the action items, and the results associated therewith to the third server 50 via the communication unit 23. The control unit 51 of the third server 50 stores this information received via the communication unit 53 in the storage unit 52. In this manner, the control unit 21 associates the results with the action items and stores them in the index.

[0111] As described above, according to the third operational example of the present embodiment, when an inquiry about a care recipient from a user is received, quantitative information about the care recipient is first acquired, a prompt is generated, and the prompt is input into a language model to acquire action items. Then, in the third operational example, the results of implementing the action items on the care recipient are received. In the third operational example, the results are associated with the action items and stored in an index together with the inquiry and quantitative information about the care recipient. The results of implementing the action items on the care recipient can serve as useful reference information not only for the care recipient but also for other care recipients who are similar to the care recipient. Therefore, by further enriching the information included in the index, the likelihood of obtaining action items more specific to the inquiry content for future inquiries is increased, thereby improving the technology for utilizing language models.

[0112] (Example of User Interface) Below, examples of the user interface displayed by the terminal device 10 in the above-mentioned operation examples 1 to 3 are shown. Fig. 11 shows an example of a user interface screen related to the reception of the inquiry content in step S100. The inquiry content includes the type of consultation content. The terminal device 10 receives the type of consultation content through the user interface in Fig. 11.

[0113] The user interface screen shown in Fig. 11 is a screen for accepting input of the type of consultation content. First, the name of the care-requiring person is selected using a pull-down item 81. In the example shown in Fig. 11, there are four types of consultation content: soiling incontinence, number of excretion calls, missed / cancelled excretion care attempts, and number of excretion care attempts. The user interface screen shown in Fig. 11 includes buttons 101-104 corresponding to each of these types. The type of consultation content is selected by selecting one of the buttons 101-104.

[0114] In addition to the above, the terminal device 10 may accept basic information of the care recipient through the user interface of Fig. 12. At least a part of the information input into the input fields of the user interface screen of Fig. 12 may be used as quantitative information about the care recipient.

[0115] The user interface screen shown in Figure 12 is a screen for accepting input of basic information about the care recipient. In the example shown in Figure 12, the basic information about the care recipient includes a care level, a level of independence in daily living, a dementia level, excretion ADL (daytime), excretion ADL (nighttime), underwear (daytime), underwear (nighttime), excretion location (daytime), excretion location (nighttime), ADL for mobility, welfare equipment for mobility, type of incontinence, current medical history, and past medical history. As shown in Figure 12, pull-down items 82-93 for accepting input of the care level, level of independence in daily living, dementia level, excretion ADL (daytime), excretion ADL (nighttime), underwear (daytime), underwear (nighttime), excretion location (daytime), excretion location (nighttime), ADL for mobility, welfare equipment for mobility, and type of incontinence, and fields 94 and 95 for accepting input of the current medical history and past medical history may be provided.

[0116] The user interface screen shown in Fig. 13 is a screen showing an example of action items acquired in response to the inquiry. In the example shown in Fig. 13, the information presented includes the cause, current situation understanding, basis, countermeasures, and points to note. In this way, specific action items are displayed in response to the inquiry. As shown in Fig. 13, a button 105 may be provided so that the action items can be printed. The user interface screen may also be provided with an additional button so that the results of implementing the action items on the person requiring care can be entered.

[0117] Furthermore, the output from the language model may be input to the language model to output an additional inquiry. More specifically, the action items output from the language model may be input to a prompt, and the prompt may include an instruction to cause the language model to output additional inquiry content related to the action items. The additional inquiry content may include, for example, details of the output action items, specific implementation methods, points to note, or other questions or consultation matters that may raise doubts about the user who is presented with the action items. By predicting and generating and presenting matters that the user may want to inquire about (additional consultation), the user's needs can be better met.

[0118] 14 shows an example of a user interface screen that suggests additional consultations. When an action item related to excretion care is output, questions that may motivate the user to seek additional consultations are generated in advance and displayed as suggestions on the user interface screen, thereby more efficiently supporting the user in resolving their issues.

[0119] Although the present disclosure has been described based on the drawings and examples, it should be noted that those skilled in the art can easily make various modifications and alterations based on the present disclosure. Therefore, it should be noted that these modifications and alterations are included in the scope of the present disclosure. For example, the functions included in each component or step can be rearranged so as not to be logically inconsistent, and multiple components or steps can be combined or divided into one.

[0120] 1 System 10 Terminal device 11 Control unit 12 Memory unit 13 Communication unit 14 Input unit 15 Output unit 20 Information processing device 21 Control unit 22 Memory 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 Third server 51 Control unit 52 Memory unit 53 Communication unit 60 Network 81-93 Buttons 94, 95 Fields 101-104 Buttons 105 Button

Claims

1. A method executed by an information processing device, comprising: accepting an inquiry from a user regarding a person requiring care; acquiring quantitative information regarding the person requiring care from a system used in providing care services to the person requiring care; generating a prompt including the inquiry and the quantitative information; and inputting the prompt into a language model to acquire an action item for the inquiry.

2. The method according to claim 1, wherein the quantitative information is information obtained from the care recipient through the care service.

3. The method according to claim 2, wherein the quantitative information includes information on at least one of level of care required, level of dementia, medical history, current medical history, and ADL.

4. The method of claim 2, wherein the quantitative information includes information regarding the intake of the care recipient.

5. The method according to claim 4, wherein the information regarding the intake includes information regarding the intake amount of at least one of medicine, water, and food taken by the person requiring care.

6. A method according to claim 2, wherein the quantitative information includes information relating to at least one of the vital signs and amount of sleep of the person requiring care reported by the system.

7. The method according to claim 2, wherein the quantitative information includes information on the number of alerts issued by the system to the person requiring care.

8. The method according to claim 2, wherein the quantitative information includes information indicating changes over time in the care recipient.

9. A method according to claim 2, wherein the quantitative information includes at least one of a schedule and performance information of excretion care for the person requiring care.

10. The method of claim 2, further comprising: obtaining qualitative information about the person requiring care from the system and generating a prompt including the inquiry content, the quantitative information, and the qualitative information.

11. The method of claim 2, further comprising: selecting the quantitative information to be obtained from the system in response to the content of the inquiry.

12. A method according to claim 11, further comprising prioritizing the quantitative information obtained from the system according to the content of the inquiry, and obtaining from the system the quantitative information whose priority is equal to or greater than a predetermined value.

13. A method according to claim 12, further comprising: obtaining qualitative information about the care recipient from the system in response to the inquiry content, and generating a prompt including the inquiry content, the quantitative information, and the qualitative information.

14. The method of claim 13, further comprising: the prompt including an index related to the query content.

15. The method of claim 2, further comprising: registering the care schedule recommended in the action item in a scheduler.

16. The method of claim 1, further comprising: storing the query content, the quantitative information, and the action items in an index referenced by the language model.

17. The method according to claim 16, further comprising: receiving a result of implementing the action item on the person requiring care; and storing the result in association with the action item.

18. The method of claim 1, wherein the output from the language model is input to the language model to output a further query.

19. An information processing device comprising a processor for executing the method of any one of claims 1 to 18.

20. A program that causes an information processing device to execute the method according to any one of claims 1 to 18.

Images