Care Support System

Abstract

To provide a care support system that enables even an inexperienced care provider to create a care plan or provide care to realize the wishes of a care recipient. [Solution] The care support device 100 transmits a request including a request to generate desired candidates to the large-scale language model server 200, receives an estimation result output from the large-scale language model server 200 in response to the transmitted request, and displays the desired candidates based on the received estimation result. Also, the care support device 100 transmits a request including the desire input in steps S104 and S106 and a request to generate task candidates to the large-scale language model server 200, receives an estimation result output from the large-scale language model server 200 in response to the request, and displays the task candidates based on the received estimation result. The care provider selects one of the displayed candidates and enters it into the care management table.

Description

[Technical field]

[0001] The present invention relates to a system that supports care providers in caring for care recipients, and in particular to a care support system that enables even inexperienced care providers to create care plans or provide care to realize the wishes of the care recipient. [Background technology]

[0002] 2. Description of the Related Art Conventionally, as a technology for supporting a care provider such as a care manager in caring for a care recipient such as an elderly person, for example, the technology described in Patent Document 1 is known.

[0003] The technology described in Patent Document 1 registers a combination master, a problem specification condition master, and a problem specification master in advance, creates a face sheet and an assessment table for each care recipient, extracts an assessment value corresponding to the judgment period and judgment condition on the problem specification condition master from the assessment table, extracts a problem code of the problem condition corresponding to that assessment value from the combination master, identifies the problem area, problem item, weight, care goal, and problem corresponding to that problem code from the contents of the problem specification master, and performs processing in the following order. This makes it possible to create an assessment table whenever necessary, identify problem areas, problems, and cases, and create a care plan. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 10-334147 Summary of the Invention [Problem to be solved by the invention]

[0005] However, in the technology described in Patent Document 1, the care plan is created based on the problems and goals set by the care provider, so the results of the care provided may not meet the wishes of the care recipient. For example, if the care recipient wishes to return home rather than live in a facility, ideally a care plan should be created to realize that wish. However, as described in Patent Document 1

[0016] to

[0019] , creating a uniform care plan that focuses only on the physical functions and problems of the care recipient will prevent the wish from being realized, leading to a decrease in the satisfaction of the care recipient and their family.

[0006] However, creating a care plan that realizes the wishes of the person being cared for does not simply focus on physical functions and related problems, as mentioned above; the care provider needs to have a wealth of experience, and it is difficult for inexperienced care providers to create a care plan.

[0007] Therefore, the present invention has been made with a focus on the unresolved issues associated with such conventional technology, and aims to provide a care support system that enables even inexperienced care providers to create care plans or provide care to realize the wishes of the care recipient. [Means for solving the problem]

[0008] [Invention 1] In order to achieve the above object, the care support system of Invention 1 comprises an input means for inputting a request including one piece of information among the wishes of a care recipient or his / her family, a problem that needs to be solved in order to realize said wishes, and a goal set for solving said problem, into a large-scale language model, the request including a request to generate one or two pieces of information other than the one piece of information among the wishes, the problem, and the goal, and an acquisition means for acquiring information output from the large-scale language model in response to the request.

[0009] Here, the present system may be realized as a single device, terminal, or other equipment, or may be realized as a network system in which multiple devices, terminals, or other equipment are communicatively connected. In the latter case, each component may belong to any of the multiple devices, etc., as long as they are communicatively connected to each other. The same applies to the care support systems of Inventions 2 to 4 and 7 to 11 below.

[0010] [Invention 2] Furthermore, the care support system of Invention 2 comprises an input means for inputting a request into a large-scale language model, the request including two pieces of information among the wishes of the care recipient or his / her family, a problem that needs to be solved in order to realize the wishes, and a goal that is set for solving the problem, and the request including a request to generate information other than the two pieces of information among the wishes, the problem, and the goal, and an acquisition means for acquiring information output from the large-scale language model in response to the request.

[0011] [Invention 3] Furthermore, the care support system of Invention 3 comprises an input means for inputting a request into a large-scale language model, the request including one piece of information among the wishes of the care recipient or his / her family, a problem that needs to be solved in order to realize the wishes, and action items necessary to solve the problem or to achieve a goal set for solving the problem, and the request including a request to generate one or two pieces of information other than the one piece of information among the wishes, the problem, and the action items, and an acquisition means for acquiring information output from the large-scale language model in response to the request.

[0012] [Invention 4] Furthermore, the care support system of Invention 4 comprises an input means for inputting a request into a large-scale language model, the request including two pieces of information among the wishes of the care recipient or his / her family, a problem that needs to be solved in order to realize the wishes, and action items necessary to solve the problems or to achieve a goal that is set for solving the problems, and the request includes a request to generate information other than the two pieces of information among the wishes, the problems, and the action items, and an acquisition means for acquiring information output from the large-scale language model in response to the request.

[0013] [Invention 5] Furthermore, the care support system of Invention 5 comprises an input means for inputting a request into a large-scale language model, the request including one piece of information selected from the wishes of the care recipient or his / her family, a goal set for solving a problem that needs to be solved in order to realize the wishes, and action items necessary to solve the problem or achieve the goals, and the request including a request to generate one or two pieces of information other than the one piece of information selected from the wishes, the goals, and the action items, and an acquisition means for acquiring information output from the large-scale language model in response to the request.

[0014] [Invention 6] Furthermore, the care support system of Invention 6 comprises an input means for inputting a request into a large-scale language model, the request including two pieces of information among the wishes of the care recipient or his / her family, a goal set for solving a problem that needs to be solved in order to realize the wishes, and action items necessary to solve the problem or achieve the goals, and the request including a request to generate information other than the two pieces of information among the wishes, the goal, and the action items, and an acquisition means for acquiring information output from the large-scale language model in response to the request.

[0015] [Invention 7] Furthermore, the care support system of Invention 7 comprises an input means for inputting a request to a large-scale language model, the request including one piece of information among a problem that needs to be solved in order to realize the wishes of a care recipient or his / her family, a goal set for solving the problem, and an action item necessary to solve the problem or achieve the goal, and the request including a request to generate one or two pieces of information other than the one piece of information among the problem, the goal, and the action item, and an acquisition means for acquiring information output from the large-scale language model in response to the request.

[0016] [Invention 8] Furthermore, the care support system of Invention 8 comprises an input means for inputting a request to a large-scale language model, the request including two pieces of information out of a problem that needs to be solved in order to realize the wishes of a care recipient or his / her family, a goal set for solving the problem, and action items necessary to solve the problem or achieve the goal, and the request including a request to generate information other than the two pieces of information out of the problem, the goal, and the action items, and an acquisition means for acquiring information output from the large-scale language model in response to the request.

[0017] [Invention 9] Furthermore, the care support system of Invention 9 comprises an input means for inputting a request into a large-scale language model, the request including one piece of information among the wishes of the care recipient or his / her family, a problem that needs to be solved in order to realize the wishes, a goal set for solving the problem, and action items necessary to solve the problem or achieve the goal, and the request including a request to generate one, two or three pieces of information other than the one piece of information among the wishes, the problem, the goal, and the action items, and an acquisition means for acquiring information output from the large-scale language model in response to the request.

[0018] [Invention 10] Furthermore, the care support system of Invention 10 comprises an input means for inputting a request into a large-scale language model, the request including two pieces of information selected from the wishes of a care recipient or his / her family, a problem that needs to be solved in order to realize the wishes, a goal set for solving the problem, and action items necessary to solve the problem or achieve the goal, and the request including a request to generate one or two pieces of information other than the wishes, the problem, the goal, and the action items, and an acquisition means for acquiring information output from the large-scale language model in response to the request.

[0019] [Invention 11] Furthermore, the care support system of Invention 11 comprises an input means for inputting a request including three pieces of information among the wish of the care recipient or his / her family, a problem that needs to be solved in order to realize said wish, a goal set for solving said problem, and action items necessary to solve said problem or achieve said goal, into a large-scale language model, the request including a request to generate information other than the three pieces of information among the wish, the problem, the goal, and the action items, and an acquisition means for acquiring information output from the large-scale language model in response to the request.

[0020] [Invention 12] Furthermore, the care support system of Invention 12 is the care support system of any one of Inventions 1 to 11, wherein the request includes attributes of the care recipient or includes a request to generate attributes of the care recipient.

[0021] [Invention 13] Furthermore, the care support system of Invention 13 is a care support system of any one of Inventions 1, 2, 5 to 11, wherein the request includes a deadline for achieving the goal, or includes a request to generate a deadline for achieving the goal.

[0022] [Invention 14] Furthermore, the care support system of Invention 14 is a care support system of any one of Inventions 3 to 11, wherein the request includes a period or frequency for performing the action item, or includes a request to generate a period or frequency for performing the action item. Effect of the Invention

[0023] As described above, according to the care support system of Invention 1, by providing one piece of information from among hopes, challenges, and goals, one or two other pieces of information from among hopes, challenges, and goals can be obtained, so that even an inexperienced care provider can create a care plan or provide care to realize the hopes of the care recipient or their family.

[0024] Furthermore, according to the care support system of Invention 2, by providing two pieces of information out of hopes, issues, and goals, the remaining pieces of information out of hopes, issues, and goals can be obtained, so that even an inexperienced care provider can create a care plan or provide care to realize the hopes of the care recipient or their family.

[0025] Furthermore, according to the care support system of Invention 3, by providing one piece of information from among the wishes, issues, and implementation items, one or two other pieces of information from among the wishes, issues, and implementation items can be obtained, so that even an inexperienced care provider can create a care plan or provide care to realize the wishes of the care recipient or their family.

[0026] Furthermore, according to the care support system of Invention 4, by providing two pieces of information out of the wishes, issues, and implementation items, the remaining information out of the wishes, issues, and implementation items can be obtained, so that even an inexperienced care provider can create a care plan or provide care to realize the wishes of the care recipient or their family.

[0027] Furthermore, according to the care support system of Invention 5, by providing one piece of information from among the wishes, goals, and implementation items, one or two other pieces of information from among the wishes, goals, and implementation items are obtained, so that even an inexperienced care provider can create a care plan or provide care to realize the wishes of the care recipient or their family.

[0028] Furthermore, according to the care support system of Invention 6, by providing two pieces of information out of the wishes, goals, and implementation items, the remaining pieces of information out of the wishes, goals, and implementation items can be obtained, so that even an inexperienced care provider can create a care plan or provide care to realize the wishes of the care recipient or their family.

[0029] Furthermore, according to the care support system of Invention 7, by providing one piece of information among the tasks, goals, and implementation items, one or two other pieces of information among the tasks, goals, and implementation items can be obtained, so that even an inexperienced care provider can create a care plan or provide care to realize the wishes of the care recipient or their family.

[0030] Furthermore, according to the care support system of Invention 8, by providing two pieces of information out of the tasks, goals, and implementation items, the remaining pieces of information out of the tasks, goals, and implementation items can be obtained, so that even an inexperienced care provider can create a care plan or provide care to realize the wishes of the care recipient or their family.

[0031] Furthermore, according to the care support system of Invention 9, by providing one piece of information from among the hopes, issues, goals and implementation items, the remaining one, two or three pieces of information from among the hopes, issues, goals and implementation items can be obtained, so that even an inexperienced care provider can create a care plan or provide care to realize the hopes of the care recipient or their family.

[0032] Furthermore, according to the care support system of Invention 10, by providing two pieces of information from among hopes, issues, goals, and implementation items, one or two other pieces of information from among hopes, issues, goals, and implementation items can be obtained, so that even an inexperienced care provider can create a care plan or provide care to realize the hopes of the care recipient or their family.

[0033] Furthermore, according to the care support system of Invention 11, by providing three pieces of information out of hopes, issues, goals, and implementation items, the remaining information out of hopes, issues, goals, and implementation items can be obtained, so that even an inexperienced care provider can create a care plan or provide care to realize the hopes of the care recipient or their family.

[0034] Furthermore, according to the care support system of Invention 12, attributes or information taking these into consideration can be obtained, so that even care providers with little experience can create care plans or provide care to realize the wishes of the care recipient or their family.

[0035] Furthermore, according to the care support system of Invention 13, deadlines for achievement or information taking these into consideration can be obtained, so that even care providers with little experience can create care plans or provide care to realize the wishes of the care recipient or their family.

[0036] Furthermore, according to the care support system of Invention 14, the period or frequency of carrying out the implementation items, or information taking these into consideration, can be obtained, so that even an inexperienced care provider can create a care plan or carry out care to realize the wishes of the care recipient or their family. [Brief description of the drawings]

[0037] [Figure 1] FIG. 1 is a block diagram showing a configuration of a network system. [Diagram 2] 1 is a diagram showing a hardware configuration of a care support device 100. FIG. [Diagram 3] This is a conceptual diagram showing the connection relationship between hopes, issues, goals, and action items. [Figure 4] 13 is a flowchart showing a care support process. [Diagram 5] This is a screen showing a care management table when preferences are input from multiple candidates. [Figure 6] 13 is a screen showing a care management table when a task is input from a plurality of candidates. [Figure 7] 13 is a screen showing a care management table when a goal is input from a plurality of candidates. [Figure 8] 13 is a screen showing a care management table when action items are input from a plurality of candidates. [Figure 9] A conceptual diagram showing the connection between hopes, challenges and goals. [Figure 10]This is a conceptual diagram showing the connection relationship between hopes, issues, and action items. [Figure 11] FIG. 1 is a conceptual diagram showing the connection between hopes, goals, and actions. [Figure 12] FIG. 1 is a conceptual diagram showing the connection relationship between tasks, goals, and action items. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0038] An embodiment of the present invention will now be described with reference to Figures 1 to 8.

[0039] First, the configuration of this embodiment will be described. FIG. 1 is a block diagram showing the configuration of a network system.

[0040] As shown in FIG. 1, a care support device 100 that supports a care provider in caring for a care recipient, and a large-scale language model server 200 that generates information using a large language model are connected to the Internet 199.

[0041] Next, the configuration of the care support device 100 will be described. FIG. 2 is a diagram showing a hardware configuration of the care support device 100. As shown in FIG.

[0042] As shown in FIG. 2, the care support device 100 is composed of a CPU (Central Processing Unit) 30 that controls calculations and the entire system based on a control program, a ROM (Read Only Memory) 32 in which the control program etc. of the CPU 30 are stored in advance in a specified area, a RAM (Random Access Memory) 34 for storing data read from the ROM 32 etc. and calculation results required in the calculation process of the CPU 30, and an I / F (InterFace) 38 that mediates the input and output of data to and from external devices. These are connected to each other and capable of sending and receiving data by a bus 39, which is a signal line for transferring data.

[0043] Connected to the I / F 38 as external devices are an input device 40 consisting of a keyboard, mouse, etc. capable of inputting data as a human interface, a storage device 42 which stores data, tables, etc. as files, and a display device 44 which displays a screen based on an image signal.

[0044] Next, the relationship between hopes, challenges, goals and implementation items will be explained. The care management table of this embodiment manages in correspondence with (1) the "hopes" of the care recipient, (2) the "issues" (needs) that need to be resolved in order to realize the wishes, (3) the "goals" that are set to resolve the issues, and (4) the "implementation items" necessary to achieve the goals.

[0045] FIG. 3 is a conceptual diagram showing the relationship between hopes, issues, goals, and actions. For each wish, one or more tasks that need to be solved to realize the wish are set, as shown in FIG. 3. In the example of FIG. 3, task 1-1, task 1-2, and other tasks are set for wish 1, and task 2-1, task 2-2, and other tasks are set for wish 2. Since the tasks to be set correspond to each wish, tasks 1-1, 1-2, 2-1, and 2-2 may have the same or similar tendencies or contents, but are basically independent of each other. The care provider hears the wishes of the care recipient and writes the heard wishes in the care management table. Then, the care provider sets the tasks that need to be solved to realize the wish based on his / her own experience and care history, and writes the set tasks in the care management table. One or more tasks may be set as necessary.

[0046] Next, one or more goals are set for each problem. In the example of FIG. 3, goals 1-1-1, 1-1-2, and other goals are set for problem 1-1, goals 1-2-1, 1-2-2, and other goals are set for problem 1-2, goals 2-1-1, 2-1-2, and other goals are set for problem 2-1, and goals 2-2-1, 2-2-2, and other goals are set for problem 2-2. Since the goals to be set correspond to each problem, goals 1-1-1, 1-1-2, 1-2-1, 1-2-2, 2-1-1, 2-1-2, 2-2-1, and 2-2-2 may have the same or similar tendencies or contents, but are basically independent of each other. The care provider sets goals for solving the problems set above based on their own experience and care history, and enters the set goals in the care management table. One or more goals may be set as necessary.

[0047] Next, for each goal, one or more action items necessary to achieve the goal are set. In the example of Fig. 3, action item 1-1-1-1, action item 1-1-1-2 and other action items are set for goal 1-1-1, action item 1-1-2-1, action item 1-1-2-2 and other action items are set for goal 1-1-2, action item 1-2-1-1, action item 1-2-1-2 and other action items are set for goal 1-2-1, action item 1-2-1-2 and other action items are set, and action item 1-2-2-1, action item 1-2-2-2 and other action items are set for goal 1-2-2. In addition, for objective 2-1-1, action item 2-1-1-1, action item 2-1-1-2 and other action items have been set; for objective 2-1-2, action item 2-1-2-1, action item 2-1-2-2 and other action items have been set; for objective 2-2-1, action item 2-2-1-1, action item 2-2-1-2 and other action items have been set; and for objective 2-2-2, action item 2-2-2-1, action item 2-2-2-2 and other action items have been set. Since the action items to be set correspond to each goal, action items 1-1-1-1, 1-1-1-2, 1-1-2-1, 1-1-2-2, 1-2-1-1, 1-2-1-2, 1-2-2-1, 1-2-2-2, 2-1-1-1, 2-1-1-2, 2-1-2-1, 2-1-2-2, 2-2-1-1, 2-2-1-2, 2-2-2-1, 2-2-2-2 may have the same or similar tendencies or contents, but are basically independent of each other. The care provider sets the action items necessary to achieve the above set goals based on their own experience and care history, and enters the set action items in the care management table. One or more action items may be set as necessary.

[0048] Next, the configuration of the large-scale language model server 200 will be described. The large-scale language model server 200 is configured to have the same hardware configuration as the care support device 100. The large-scale language model is a deep learning model that pre-learns from a huge amount of data what is called a language model that models human spoken words based on their occurrence probability. When the large-scale language model server 200 receives a request, it uses the large-scale language model to statistically estimate the generation probability of the next word from the sentence included in the received request, and transmits the estimation result to the request source. As the large-scale language model, for example, known technologies described in the Internet sites "https: / / chatgpt-lab.com / n / n418d3aa56f0b" and "https: / / agirobots.com / chatgpt-mechanism-and-problem / " can be adopted.

[0049] The contents of the hopes, tasks, goals, and actions, as well as the connections between them, as shown in Fig. 3, are publicly known in the home care plan, Tables 1 and 2. This publicly known information is trained in the large-scale language model.

[0050] Next, the operation of this embodiment will be described. The CPU 30 is made up of an MPU (Micro-Processing Unit) or the like, and starts up a predetermined program stored in a predetermined area of ​​the ROM 32, and executes the care support process shown in the flowchart of FIG. 4 in accordance with the program.

[0051] FIG. 4 is a flowchart showing the care support process. The care support process is a process that is started in response to a request from a user such as a care provider, and when executed by the CPU 30, first, the process proceeds to step S100 as shown in FIG.

[0052] In step S100, when input of the name of the care recipient is requested, the name of the care recipient is input from the input device 40.

[0053] FIG. 5 is a screen showing a care management table when preferences are input from multiple candidates. Next, the process proceeds to step S102, and when the input of the care recipient's wish is requested, a display process of the wish candidates is executed. In this display process, the wish candidates are displayed on the display device 44 as follows. In the care support device 100, a request including a request to generate wish candidates is generated and transmitted to the large-scale language model server 200. The request may be, for example, "Please provide the wish candidates of the care recipient when providing care to the care recipient." In the care support device 100, when an estimation result (for example, a text including one or more candidates) output from the large-scale language model server 200 in response to the request is received, the wish candidates of the care recipient are displayed on the display device 44 based on the received estimation result, as shown in FIG. 5. Here, the care provider selects one of the displayed candidates. In the example of FIG. 5, "I want to go home," "I want to continue living at home," and "I want to be able to walk" are displayed as wish candidates, and the care provider selects, for example, "I want to go home." When a wish is selected, the process proceeds to step S104, and the selected wish is input from the input device 40.

[0054] Next, the process proceeds to step S106, where the input of the wishes of the family of the care recipient is requested, and the wishes of the family of the care recipient are input via the input device 40.

[0055] FIG. 6 is a screen showing a care management table when a task is input from multiple candidates. Next, the process proceeds to step S108, and when input of a task is requested, a display process of task candidates is executed. In this display process, task candidates are displayed on the display device 44 as follows. In the care support device 100, a request including the wishes input in steps S104 and S106 and a request to generate task candidates is generated and transmitted to the large-scale language model server 200. The request may be, for example, "The subject's wish in providing care to the subject is XX. The subject's family's wish is XX." or "Please provide candidates of tasks that need to be solved to realize these wishes in providing care to the subject." When the care support device 100 receives the estimation result output from the large-scale language model server 200 in response to the request, candidates of tasks that need to be solved to realize the wishes are displayed on the display device 44 based on the received estimation result, as shown in FIG. 6. Here, the care provider selects one of the displayed candidates. 6, candidate tasks are displayed as "I want to be able to walk by myself," "I want to take a safe bath at home," "I want to continue going to the hospital," and "I want to increase the number of tasks I can do by myself," and the caregiver selects, for example, "I want to be able to walk by myself." When a task is selected, the process proceeds to step S110, and the selected task is input from the input device 40.

[0056] FIG. 7 is a screen showing a care management table when a goal is input from multiple candidates. Next, the process proceeds to step S112, and when a request to input a goal is made, a display process of goal candidates is executed. In this display process, goal candidates are displayed on the display device 44 as follows. In the care support device 100, a request including the task input in step S110 and a request to generate goal candidates is generated and transmitted to the large-scale language model server 200. The request may be, for example, "The nursing task in providing nursing care to the subject is XX." and "Please give a candidate goal to be set to solve this task." In the care support device 100, when an estimation result output from the large-scale language model server 200 in response to the request is received, as shown in FIG. 7, a candidate goal to be set to solve the task is displayed on the display device 44 based on the received estimation result. Here, the care provider selects one of the displayed candidates. In the example of FIG. 7, "Perform daily rehabilitation," "Do what you can by yourself," "Stabilize walking with a cane," and "Increase the amount of physical activity" are displayed as goal candidates, and the care provider selects, for example, "Perform daily rehabilitation." When the target is selected, the process proceeds to step S114, in which the selected target is input from the input device 40.

[0057] FIG. 8 is a screen showing a care management table when action items are input from a number of candidates. Next, the process proceeds to step S116, and when the input of the action item is requested, a display process of the action item candidates is executed. In this display process, the action item candidates are displayed on the display device 44 as follows. In the care support device 100, a request including the goal input in step S114 and a request to generate action item candidates is generated and transmitted to the large-scale language model server 200. The request may have the content, for example, "The goal of care when providing care to the subject is XX." and "Please give candidates of action items necessary to achieve this goal." In the care support device 100, when the estimation result output from the large-scale language model server 200 in response to the request is received, candidates of action items necessary to achieve the goal are displayed on the display device 44 as shown in FIG. 8 based on the received estimation result. Here, the care provider selects one of the displayed candidates. In the example of FIG. 8, "regular medical examination," "medication management," and "provision of meals according to the medical condition" are displayed as action item candidates, and the care provider selects, for example, "regular medical examination." When the action item is selected, the process proceeds to step S118, and the selected action item is input from the input device 40.

[0058] Next, the process proceeds to step S120, and when input of the deadline is requested, a display process of deadline candidates is executed. In this display process, deadline candidates are displayed on the display device 44 as follows. In the care support device 100, a request including the goal input in step S114 and a request to generate deadline candidates is generated and transmitted to the large-scale language model server 200. The request may be, for example, "The goal of care when providing care to the subject is XX." and "Please provide a deadline candidate for achieving this goal." In the care support device 100, when the estimation result output from the large-scale language model server 200 in response to the request is received, deadline candidates for achieving the goal are displayed on the display device 44 based on the received estimation result. Here, the care provider selects one of the displayed candidates. When the deadline is selected, the process proceeds to step S122, and the selected deadline is input from the input device 40.

[0059] Next, the process proceeds to step S124, where input of update contents is requested, and update contents for the previous input are input from the input device 40.

[0060] Next, the process proceeds to step S126, where input of the achievement rate is requested, and the achievement rate (percentage) of the goal is input from the input device 40.

[0061] Next, the process proceeds to step S128, where input of the realization rate is requested, and the desired realization rate (percentage) is input from the input device 40. The realization rate is input based on responses from the care recipient or family members.

[0062] Next, the process proceeds to step S130, where input of the wish realization history is requested, and the wish realization history including the dates when the wishes were realized is input from the input device 40. The wish realization history is input based on responses from the care recipient or family members.

[0063] Next, the process proceeds to step S132, where input of the goal achievement history is requested, and the goal achievement history including the dates on which the goals were achieved is input from the input device 40.

[0064] Next, the process proceeds to step S134, and care management information including the name, wishes of the care recipient, wishes of the family, tasks, goals, action items, deadlines for achievement, update contents, achievement rate, realization rate, wish realization history, and goal achievement history input in steps S100, S104, S106, S110, S114, S118, and S122 to S132 is registered in the storage device 42. Care management information is registered for each care recipient.

[0065] Then, proceeding to step S136, the name, wishes of the care recipient, wishes of the family, tasks, goals, action items, deadline for achievement, update contents, achievement rate, realization rate, wish realization history, and goal achievement history are displayed on the display device 44 for each care recipient based on the care management information in the storage device 42. For example, each item in the care management table of Figs. 5 to 8 is displayed in the corresponding item column of the care management information.

[0066] Next, the effects of this embodiment will be described. In this embodiment, a request including a request to generate a desired candidate is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the sent request is received, and the desired candidate is displayed based on the received estimation result.

[0067] This allows desired candidates to be obtained, so that even a care provider with little experience can create a care plan or provide care to realize the wishes of the care recipient or his / her family.

[0068] Furthermore, in this embodiment, a request including the request entered in steps S104 and S106 and including a request to generate task candidates is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and task candidates are displayed based on the received estimation result.

[0069] This provides candidates for tasks that take the wishes of the care recipient or their family into consideration, so that even care providers with little experience can create a care plan or provide care that realizes the wishes of the care recipient or their family.

[0070] Furthermore, in this embodiment, a request including the task input in step S110 and a request to generate target candidates is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and target candidates are displayed based on the received estimation result.

[0071] This provides candidate goals that take the issues into account, allowing even inexperienced care providers to create care plans or provide care that will realize the wishes of the care recipient or their family.

[0072] Furthermore, in this embodiment, a request including the goal input in step S114 and including a request to generate candidates for action items is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and candidates for action items are displayed based on the received estimation result.

[0073] This provides candidates for actions that take goals into account, allowing even inexperienced care providers to create care plans or provide care that realizes the wishes of the care recipient or their family.

[0074] Furthermore, in this embodiment, a request including the goal input in step S114 and including a request to generate candidates for the achievement deadline is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and candidates for the achievement deadline are displayed based on the received estimation result.

[0075] This provides candidates for deadlines that take goals into consideration, allowing even inexperienced care providers to create care plans or provide care that realizes the wishes of the care recipient or their family.

[0076] In this embodiment, steps S102, S108, S112, S116, or S120 correspond to the input means of inventions 9 to 11, or the acquisition means of inventions 9 to 11.

[0077] [Modifications] In the above embodiment and its modified example, the display process in step S102 generates a request including a request to generate desired candidates, but the request is not limited to this and may include other information. For example, a request including attributes of the care recipient (e.g., gender, age, blood type, level of care required, living environment, disease name, level of cognitive function, details of symptoms related to cognitive function, physical level, excretion status, dietary status, economic level, and information on drug use status; the same applies below) and including a request to generate desired candidates can be generated. This makes it possible to obtain desired candidates that take into account the attributes of the care recipient.

[0078] In the above embodiment and its modified example, the display process in step S108 generates a request including the wishes input in steps S104 and S106 and a request to generate task candidates, but this is not limiting and the request may include other information. For example, a request can be generated that includes the attributes of the care recipient and the wishes input in steps S104 and S106 and includes a request to generate task candidates. This makes it possible to obtain task candidates that take into account the attributes of the care recipient.

[0079] In the above embodiment and its modified example, the display process in step S112 generates a request including the task input in step S110 and including a request to generate goal candidates, but the request is not limited to this and may include other information. For example, a request can be generated that includes the desires input in steps S104 and S106 and the task input in step S110 and includes a request to generate goal candidates. This makes it possible to obtain goal candidates that take the desires into consideration. Also, for example, a request can be generated that includes attributes, desires, and tasks and includes a request to generate goal candidates.

[0080] In the above embodiment and its modified example, in the display process of step S116, a request including the goal input in step S114 and a request to generate candidates for action items is generated, but the request is not limited to this and may include other information. For example, a request including the task input in step S110 and the goal input in step S114 and a request to generate candidates for action items can be generated. This makes it possible to obtain candidates for action items that take the task into consideration. Also, for example, a request including a desire, task, and goal and a request to generate candidates for action items can be generated. Also, for example, a request including an attribute, desire, task, and goal and a request to generate candidates for action items can be generated.

[0081] In addition, in the above embodiment and its variations, information on four items, namely, hopes, issues, goals, and implementation items, is registered, but this is not limited to this, and information on at least one of these items can also be registered.

[0082] In the above embodiment and its modified example, information on four items, hope, task, goal, and implementation, is selectively input, but the present invention is not limited to this, and information on at least one of these items may be selectively input. For example, the following configuration may be adopted.

[0083] [Configuration 1] A request including some of the desires, issues, and goals and including a request to generate candidates for the remaining parts is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and candidates are displayed based on the received estimation result.

[0084] Explain the relationship between hopes, challenges and goals in Structure 1. FIG. 9 is a conceptual diagram showing the connection between hopes, challenges, and goals.

[0085] For each wish, one or more tasks that need to be solved to realize the wish are set, as shown in FIG. 9. In the example of FIG. 9, task 1-1, task 1-2, and other tasks are set for wish 1, and task 2-1, task 2-2, and other tasks are set for wish 2. Since the tasks to be set correspond to each wish, tasks 1-1, 1-2, 2-1, and 2-2 may have the same or similar tendencies or contents, but are basically independent of each other. The care provider hears the wishes of the care recipient and writes the heard wishes in the care management table. Then, the care provider sets the tasks that need to be solved to realize the wish based on his / her own experience, care history, etc., and writes the set tasks in the care management table. One or more tasks may be set as necessary.

[0086] Next, one or more goals are set for each problem. In the example of FIG. 9, goals 1-1-1, 1-1-2, and other goals are set for problem 1-1, goals 1-2-1, 1-2-2, and other goals are set for problem 1-2, goals 2-1-1, 2-1-2, and other goals are set for problem 2-1, and goals 2-2-1, 2-2-2, and other goals are set for problem 2-2. Since the goals to be set correspond to each problem, goals 1-1-1, 1-1-2, 1-2-1, 1-2-2, 2-1-1, 2-1-2, 2-2-1, and 2-2-2 may have the same or similar tendencies or contents, but are basically independent of each other. The care provider sets goals for solving the problems set above based on their own experience and care history, and enters the set goals in the care management table. One or more goals may be set as necessary.

[0087] For cooperation with the large-scale language model server 200, for example, configurations 1A and 1B can be adopted.

[0088] [Configuration 1A] A request including one piece of information among hope, problem, and goal, and including a request to generate one or two pieces of information other than the hope, problem, and goal, is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request, and candidates are displayed based on the received estimation result.

[0089] Hereinafter, the notation "A / B" refers to a configuration in which a request including A and a request to generate B is sent to the large-scale language model server 200, and an inference result B output from the large-scale language model server 200 in response to the request is received. Configuration 1A includes the following configurations: "hope / challenge", "hope / goal", "challenge / hope", "challenge / goal", "goal / hope", "goal / challenge", "hope / challenge and goal", "challenge / hope and goal", "goal / hope and challenge".

[0090] [Configuration 1B] A request including two pieces of information out of hope, problem, and goal, and including a request to generate information other than the hope, problem, and goal, is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request, and candidates are displayed based on the received estimation result.

[0091] Structure 1B includes the following structures: "Hope and challenges / goals," "Hope and goals / challenges," and "Challenges and goals / hopes."

[0092] [Configuration 2] A request including some of the desires, issues, and actions and a request to generate candidates for the remaining parts is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and candidates are displayed based on the received estimation result.

[0093] The relationship between hopes, challenges and implementation items in Structure 2 is explained. FIG. 10 is a conceptual diagram showing the connection relationship between hopes, issues, and action items.

[0094] For each wish, one or more tasks that need to be solved to realize the wish are set, as shown in FIG. 10. In the example of FIG. 10, task 1-1, task 1-2, and other tasks are set for wish 1, and task 2-1, task 2-2, and other tasks are set for wish 2. Since the tasks to be set correspond to each wish, tasks 1-1, 1-2, 2-1, and 2-2 may have the same or similar tendencies or contents, but are basically independent of each other. The care provider hears the wishes of the care recipient and writes the heard wishes in the care management table. Then, the care provider sets the tasks that need to be solved to realize the wish based on his / her own experience, care history, etc., and writes the set tasks in the care management table. One or more tasks may be set as necessary.

[0095] Next, for each task, one or more action items necessary to achieve the goal set for the solution are set. In the example of FIG. 10, action items 1-1-1, 1-1-2, and other action items are set for task 1-1, action items 1-2-1, 1-2-2, and other action items are set for task 1-2, action items 2-1-1, 2-1-2, and other action items are set for task 2-1, and action items 2-2-1, 2-2-2, and other action items are set for task 2-2. Since action items to be set correspond to each task, action items 1-1-1, 1-1-2, 1-2-1, 1-2-2, 2-1-1, 2-1-2, 2-2-1, and 2-2-2 may have the same or similar tendencies or contents, but are basically independent of each other. The care provider sets action items necessary to achieve the goal set for the solution of the above-mentioned set task based on his / her own experience and care history, and enters the set action items in the care management table. One or more implementation items may be set as necessary.

[0096] For cooperation with the large-scale language model server 200, for example, configurations 2A and 2B can be adopted.

[0097] [Configuration 2A] A request including one piece of information among hopes, tasks, and actions, and including a request to generate one or two other pieces of information among hopes, tasks, and actions, is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request, and candidates are displayed based on the received estimation result.

[0098] Structure 2A includes the following structures: "hopes / issues," "hopes / implementations," "issues / hopes," "issues / implementations," "implementations / hopes," "implementations / issues," "hopes / issues and implementation items," "issues / hopes and implementation items," and "implementations / hopes and issues."

[0099] [Configuration 2B] A request including two pieces of information out of hopes, tasks, and actions, and including a request to generate information other than the hopes, tasks, and actions, is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request, and candidates are displayed based on the received estimation result.

[0100] Structure 2B includes the following structures: "Hope and issues / items to be implemented," "Hope and issues / items to be implemented," and "Issues and issues / hopes."

[0101] [Configuration 3] A request including some of the wishes, goals, and actions and a request to generate candidates for the remaining parts is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and candidates are displayed based on the received estimation result.

[0102] This explains the relationship between hopes, goals, and implementation items in Structure 3. FIG. 11 is a conceptual diagram showing the connection relationship between hopes, goals, and actions.

[0103] For one wish, one or more goals are set to solve the problems that need to be solved to realize the wish, as shown in FIG. 11. In the example of FIG. 11, goal 1-1, goal 1-2, and other goals are set for wish 1, and goal 2-1, goal 2-2, and other goals are set for wish 2. Since the goals to be set correspond to each wish, goals 1-1, 1-2, 2-1, and 2-2 may have the same or similar tendencies or contents, but are basically independent of each other. The care provider hears the wishes of the care recipient and writes the heard wishes in the care management table. Then, the care provider sets goals for solving the problems that need to be solved to realize the wish based on his or her own experience and care history, and writes the set goals in the care management table. One or more goals may be set as necessary.

[0104] Next, for each goal, one or more action items necessary to achieve the goal are set. In the example of FIG. 11, action items 1-1-1, 1-1-2, and other action items are set for goal 1-1, action items 1-2-1, 1-2-2, and other action items are set for goal 1-2, action items 2-1-1, 2-1-2, and other action items are set for goal 2-1, and action items 2-2-1, 2-2-2, and other action items are set for goal 2-2. Since action items to be set correspond to each goal, action items 1-1-1, 1-1-2, 1-2-1, 1-2-2, 2-1-1, 2-1-2, 2-2-1, and 2-2-2 may have the same or similar tendencies or contents, but are basically independent of each other. The care provider sets the action items necessary to achieve the above-mentioned set goals based on his / her own experience and care history, and enters the set action items in the care management table. One or more implementation items may be set as necessary.

[0105] For cooperation with the large-scale language model server 200, for example, configurations 3A and 3B can be adopted.

[0106] [Configuration 3A] A request including one piece of information among hopes, goals, and implementation items and including a request to generate one or two other pieces of information among hopes, goals, and implementation items is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and candidates are displayed based on the received estimation result.

[0107] Structure 3A includes the following structures: "hope / goal," "hope / action items," "goal / hope," "goal / action items," "action items / hope," "action items / goal," "hope / goal and action items," "goal / hope and action items," and "action items / hope and goal."

[0108] [Configuration 3B] A request including two pieces of information out of desires, goals, and actions, and including a request to generate information other than the desires, goals, and actions, is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request, and candidates are displayed based on the received estimation result.

[0109] Structure 3B includes the following structures: "Hope and goals / action items," "Hope and action items / goals," and "Goals and action items / hopes."

[0110] [Configuration 4] A request including some of the tasks, goals, and action items and including a request to generate candidates for the remaining parts is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and candidates are displayed based on the received estimation result.

[0111] The relationship between the tasks, goals, and implementation items in Structure 4 is explained. FIG. 12 is a conceptual diagram showing the connection relationship between tasks, goals, and action items.

[0112] For one problem, one or more goals are set for its solution, as shown in FIG. 12. In the example of FIG. 12, goals 1-1, 1-2, and other goals are set for problem 1, and goals 2-1, 2-2, and other goals are set for problem 2. Since the goals to be set correspond to each problem, goals 1-1, 1-2, 2-1, and 2-2 may have the same or similar tendencies or contents, but are basically independent of each other. The care provider hears the wishes of the care recipient, sets the problems that need to be solved to realize the wishes heard based on his / her own experience and care history, and writes the set problems in the care management table. Then, the care provider sets the goals for solving the above problems based on his / her own experience and care history, and writes the set goals in the care management table. One or more goals may be set as necessary.

[0113] Next, for each goal, one or more action items necessary to achieve the goal are set. In the example of FIG. 12, action items 1-1-1, 1-1-2, and other action items are set for goal 1-1, action items 1-2-1, 1-2-2, and other action items are set for goal 1-2, action items 2-1-1, 2-1-2, and other action items are set for goal 2-1, and action items 2-2-1, 2-2-2, and other action items are set for goal 2-2. Since action items to be set correspond to each goal, action items 1-1-1, 1-1-2, 1-2-1, 1-2-2, 2-1-1, 2-1-2, 2-2-1, and 2-2-2 may have the same or similar tendencies or contents, but are basically independent of each other. The care provider sets the action items necessary to achieve the above-mentioned set goals based on his / her own experience and care history, and enters the set action items in the care management table. One or more implementation items may be set as necessary.

[0114] For cooperation with the large-scale language model server 200, for example, configurations 4A and 4B can be adopted.

[0115] [Configuration 4A] A request including one piece of information among tasks, goals, and action items and including a request to generate one or two other pieces of information among tasks, goals, and action items is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and candidates are displayed based on the received estimation result.

[0116] Structure 4A includes the following structures: "issues / goals", "issues / action items", "goals / issues", "goals / action items", "action items / issues", "action items / goals", "issues / goals and action items", "goals / issues and action items", and "action items / issues and goals".

[0117] [Configuration 4B] A request including two pieces of information among tasks, goals, and action items and including a request to generate information other than the tasks, goals, and action items is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and candidates are displayed based on the received estimation result.

[0118] Structure 4B includes the following structures: "Issues and goals / implementations," "Issues and implementation items / goals," and "Goals and implementation items / issues."

[0119] [Configuration 5] A request including some of the desires, issues, goals, and actions and including a request to generate candidates for the remaining parts is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and candidates are displayed based on the received estimation result.

[0120] For example, configurations 5A, 5B, and 5C can be adopted for cooperation with the large-scale language model server 200. Note that configurations 5A, 5B, and 5C include the above-described embodiment and their modifications.

[0121] [Configuration 5A] A request including one piece of information among hopes, tasks, goals, and implementation items and including a request to generate one, two, or three pieces of information other than the hopes, tasks, goals, and implementation items is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and candidates are displayed based on the received estimation result.

[0122] Structure 5A includes the following structures: "Hope / challenges", "Hope / goals", "Hope / implementation items", "Challenges / hopes", "Challenges / goals", "Challenges / implementation items", "Goals / hopes", "Goals / challenges", "Goals / implementation items", "Implementation items / hopes", "Implementation items / challenges", "Implementation items / goals", "Hope / challenges and goals", "Hope / challenges and implementation items", "Hope / goals and implementation items", "Challenges / hopes and goals", "Challenges / hopes and implementation items", "Challenges / goals and implementation items", "Goals / hopes and challenges", "Goals / hopes and implementation items", "Goals / challenges and implementation items", "Implementation items / hopes and challenges", "Implementation items / hopes and goals", "Implementation items / challenges and goals", "Hope / challenges, goals and implementation items", "Challenges / hopes, goals and implementation items", "Goals / hopes, challenges and implementation items", "Implementation items / hopes, challenges and goals".

[0123] [Configuration 5B] A request including two pieces of information among hopes, tasks, goals, and implementation items and including a request to generate one or two pieces of information other than the hopes, tasks, goals, and implementation items is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and candidates are displayed based on the received estimation result.

[0124] Structure 5B includes the following structures: "Hope and issues / goals", "Hope and issues / implementations", "Hope and goals / issues", "Hope and goals / implementations", "Hope and implementation items / issues", "Hope and implementation items / goals", "Issues and goals / hopes", "Issues and goals / implementations", "Issues and implementation items / hopes", "Issues and implementation items / goals", "Goals and implementation items / hopes", "Goals and implementation items / issues", "Hope and issues / goals and implementation items", "Hope and goals / issues and implementation items", "Issues and goals / hopes and implementation items", "Issues and implementation items / hopes and goals", "Goals and implementation items / hopes and issues".

[0125] [Configuration 5C] A request including three pieces of information among hopes, tasks, goals, and implementation items and including a request to generate information other than the hopes, tasks, goals, and implementation items is sent to the large-scale language model server 200, an estimation result output from the large-scale language model server 200 in response to the request is received, and candidates are displayed based on the received estimation result.

[0126] Structure 5C includes the following structures: "Hope, issues, and goals / action items," "Hope, issues, and actions / issues," and "Issues, issues, and goals / hopes."

[0127] [Configuration 6] In any of configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, and 5A to 5C, the request includes an attribute of the care recipient or includes a request to generate an attribute of the care recipient.

[0128] Configurations for sending a request including attributes include (1) a configuration for sending a request including only attributes and including a creation request, and (2) a configuration for sending a request including attributes and other information (e.g., desires, issues, goals, or actions) and including a creation request.

[0129] The configuration for sending a request including a request to generate attributes includes (1) a configuration for sending a request including a request to generate attributes only, and (2) a configuration for sending a request including a request to generate attributes and other information (e.g., preferences, issues, goals, or actions).

[0130] [Configuration 7] In configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, 5A to 5C and 6, the request includes a deadline for achieving the goal, or includes a request for generating a deadline for achieving the goal.

[0131] Configurations for sending a request including a deadline include (1) a configuration for sending a request including only a deadline and a request for creation, and (2) a configuration for sending a request including a deadline and other information (e.g., wishes, issues, goals, or implementation items) and a request for creation.

[0132] The configuration for transmitting a request including a request to generate a deadline includes (1) a configuration for transmitting a request including a request to generate only a deadline, and (2) a configuration for transmitting a request including a request to generate a deadline and other information (e.g., aspirations, challenges, goals, or action items).

[0133] [Configuration 8] In configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, 5A to 5C, 6 and 7, the request includes a period or frequency for performing the action item, or includes a request to generate a period or frequency for performing the action item.

[0134] Configurations for sending a request including a duration or frequency include (1) a configuration for sending a request including a production request that includes only a duration or frequency, and (2) a configuration for sending a request including a production request that includes a duration or frequency and other information (e.g., wishes, issues, goals, or actions).

[0135] The configuration for sending a request including a request to generate a duration or frequency includes (1) a configuration for sending a request including a request to generate only a duration or frequency, and (2) a configuration for sending a request including a request to generate a duration or frequency and other information (e.g., preferences, objectives, goals, or actions).

[0136] [Configuration 9] This is a configuration in which a request is sent that includes one of two combinations of attributes, hopes, issues, goals, action items, deadlines, periods, and frequencies, and includes a request to generate the other. In this case, the connection relationship as shown in Figure 3 has two levels.

[0137] [Configuration 10] A configuration for transmitting a request including a request to generate any one of attributes, hopes, issues, goals, action items, deadlines, periods, and frequencies. In this case, the connection relationship as shown in FIG. 3 does not exist.

[0138] In addition, in the above embodiment and its variations, the terms "issue" and "goal" are used. However, the present invention is not limited to this, and it is equivalent to define "issue" as "short-term goal" and "goal" as "long-term goal".

[0139] In addition, in the above embodiment and its modified examples, the term "implementation items" is used, but this is not limited thereto, and "implementation items" may be defined as "measures," "services," "service menus," "service items," "service contents," etc., which are equivalent in meaning.

[0140] In addition, in the above embodiment and its variations, the term is defined as "items to be implemented that are necessary to achieve a goal," but it is not limited to this and can also be defined as "items to be implemented that are necessary to solve a problem."

[0141] In addition, in the above embodiment and its modified example, one goal is defined, but it is not limited to this, and two or more goals can be defined, for example, a "long-term goal" and a "short-term goal". When there is a connection between the goals, the above embodiment and its modified example can be similarly applied as a configuration in which each goal is selectively input. This also applies to hopes, issues, and implementation items.

[0142] In the above embodiment and its modified example, the care support device 100 is realized as a single device, but the present invention is not limited to this and can also be realized as a network system. A care support server and multiple user terminals are connected to a network such as the Internet. The care support server is configured to have the same functions as the care support device 100. The difference is that the care support server receives information from the user terminal instead of input by the input device 40, and transmits information to the user terminal instead of displaying on the display device 44.

[0143] Furthermore, in the above embodiment and its modified examples, the storage device 42 included in the care support device 100 is used, but the present invention is not limited to this, and an external storage device such as a database server can also be used.

[0144] In addition, in the above embodiment and its modified examples, when executing the process shown in the flowchart of FIG. 4, a case has been described in which a program pre-stored in ROM 32 is executed. However, this is not limited to the above, and the program showing these procedures may be read from a storage medium in which the program is stored, into RAM 34, and executed.

[0145] Here, storage media refers to semiconductor storage media such as RAM and ROM, magnetic storage type storage media such as FD and HD, optically readable storage media such as CD, CDV, LD and DVD, and magnetic storage type / optically readable storage media such as MO, and includes any storage medium that can be read by a computer, regardless of the reading method (electronic, magnetic, optical, etc.).

[0146] Furthermore, the present invention is not limited to the above-mentioned embodiment and its modified examples, and can be applied to other cases without departing from the spirit of the present invention. For example, the present invention can be applied not only to nursing care, but also to cases in which a caregiver supports the care of a care recipient (looking after, protecting, caring for, nursing, etc.) in the fields of medicine (rehabilitation, treatment, etc.) or welfare (physical, intellectual, mental, etc.). [Explanation of symbols]

[0147] 100...care support device, 30...CPU, 32...ROM, 34...RAM, 38...I / F, 40...input device, 42...storage device, 44...display device, 199...Internet, 200...large-scale language model server

Claims

1. an input means for inputting a request including one or two pieces of information among the wishes of a care recipient or his / her family, a problem that needs to be solved in order to realize said wishes, and a goal set for solving said problem, into a large-scale language model, the request including a request to generate a period or frequency for implementing actions required to solve said problem or achieve said goal, or a deadline for achieving said goal; and acquiring information output from the large-scale language model in response to the request.

2. an input means for inputting a request to the large-scale language model, the request including one or two pieces of information among the wishes of a care recipient or his / her family, a problem that needs to be solved in order to realize the wishes, and actions necessary to solve the problems or achieve a goal set for solving the problems, the request including a period or frequency for implementing the actions or a deadline for achieving the goals; and acquiring information output from the large-scale language model in response to the request.

3. an input means for inputting a request including one or two pieces of information among the wishes of a care recipient or his / her family, a goal set for solving a problem that needs to be solved in order to realize said wishes, and actions necessary to solve said problem or achieve said goal, and including a request to generate a period or frequency for implementing said actions or a deadline for achieving said goal, into a large-scale language model; and acquiring information output from the large-scale language model in response to the request.

4. an input means for inputting a request to the large-scale language model, the request including one or two pieces of information among a problem that needs to be solved in order to realize the wishes of a care recipient or his / her family, a goal set for solving the problem, and actions required to solve the problem or achieve the goal, and including a request to generate a period or frequency for implementing the action or a deadline for achieving the goal; and acquiring information output from the large-scale language model in response to the request.

5. an input means for inputting a request including one, two or three pieces of information among the wishes of a care recipient or his / her family, a problem that needs to be solved in order to realize said wishes, a goal set for solving said problem, and actions necessary to solve said problem or achieve said goal, and including a request to generate a period or frequency for implementing said actions or a deadline for achieving said goal, into the large-scale language model; and acquiring information output from the large-scale language model in response to the request.

6. In any one of claims 1 to 5, A care support system, wherein the request includes attributes of the person being cared for.

7. In any one of claims 1 to 5, A care support system, wherein the request includes a period or frequency for carrying out the action item, or a deadline for achieving the goal.

Images