Care support system

Abstract

To provide a care support system that allows even inexperienced caregivers to create schedules or provide care.SOLUTION: A care support device 100 transmits, to a large-scale language model server 200, a request including information about a caregiver and a demand to generate candidate schedules for implementing care items for a care recipient, receives estimation results output from the large-scale language model server 200 in response to the transmitted request, and displays a schedule based on the received estimation results. This provides candidate schedules, allowing even inexperienced caregivers to create schedules or provide care.SELECTED DRAWING: Figure 9

Description

[Technical Field]

[0001] The present invention relates to a system that supports a caregiver in caring for a care recipient, and more particularly to a care support system that allows even an inexperienced caregiver to create a schedule or provide care. [Background technology]

[0002] BACKGROUND 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 involves inputting at least one piece of information from the hopes of the care recipient or their family, the goals for realizing the hopes, and the tasks for realizing the hopes in achieving the goals, and using a trained model that has been trained based on care management information that corresponds to the hopes, goals or tasks, and the actions necessary to achieve the goals, to estimate the actions to be taken from the input information and present the estimated actions to be taken. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2021-114276 Summary of the Invention [Problem to be solved by the invention]

[0005] However, in the technology described in Patent Document 1, although action items can be obtained by providing a wish, goal, or task, the caregiver must create a schedule for carrying out the action items. The schedule is created based on the period and frequency for carrying out the action items provided, making it difficult for caregivers with little experience to create the schedule.

[0006] Therefore, the present invention has been made with a focus on the unresolved issues of such conventional technology, and aims to provide a care support system that allows even inexperienced care providers to create schedules or provide care. [Means for solving the problem]

[0007] [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 action items for a care recipient and a request to generate a schedule for carrying out the action items into a large-scale language model, and an acquisition means for acquiring information output from the large-scale language model in response to the request.

[0008] Here, the schedule includes, for example, a schedule that associates action items with the time to perform them for a predetermined period (for example, one day, one week, one month), a schedule that associates action items with the time to perform them for each predetermined period, or a schedule that combines these. The same applies to the care support systems of Inventions 4 and 6 below.

[0009] Furthermore, this system may be realized as a single device, terminal, or other equipment, or 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. The same applies to the care support systems of Inventions 4 and 6 below.

[0010] [Invention 2] Furthermore, in the care support system of Invention 2, in the care support system of Invention 1, the request includes a period for carrying out the action item.

[0011] [Invention 3] Furthermore, the care support system of Invention 3 is the care support system of either Invention 1 or 2, wherein the request includes a frequency at which the action item is to be performed.

[0012] [Invention 4] Furthermore, the care support system of Invention 4 comprises an input means for inputting a request including a period for carrying out actions for a care recipient and a request to generate a schedule for carrying out the actions into a large-scale language model, and an acquisition means for acquiring information output from the large-scale language model in response to the request.

[0013] [Invention 5] Furthermore, in the care support system of Invention 5, in the care support system of Invention 4, the request includes a frequency at which the action item is to be performed.

[0014] [Invention 6] Furthermore, the care support system of Invention 6 comprises an input means for inputting a request including a frequency of performing actions for a care recipient and a request to generate a schedule for performing the actions to a large-scale language model, 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 is the care support system of any one of Inventions 1, 2, 4 to 6, wherein the request includes attributes of the care recipient or care provider or information about the care recipient or care provider.

[0016] [Invention 8] Furthermore, the care support system of Invention 8 is the care support system of any one of Inventions 1, 2, 4 to 6, wherein the request includes the wishes of the care recipient or their family, a goal for realizing the wishes, a problem that needs to be solved in order to achieve the goal, or a deadline for achieving the goal.

[0017] [Invention 9] Furthermore, the care support system of Invention 9 is the care support system of any one of Inventions 1, 2, 4 to 6, wherein the request includes the wishes of the care recipient or their family, issues that need to be resolved in order to realize the wishes, goals set for resolving the issues, or a deadline for achieving the goals. [Effects of the Invention]

[0018] As described above, according to the care support system of Invention 1, a schedule can be obtained by providing action items, so even an inexperienced care provider can create a schedule or provide care.

[0019] Furthermore, according to the care support system of Invention 2, a schedule can be obtained that takes into account the period during which the action items are to be carried out.

[0020] Furthermore, according to the care support system of the third or fifth invention, a schedule can be obtained that takes into account the frequency with which the action items are to be performed.

[0021] Furthermore, according to the care support system of Invention 4, a schedule can be obtained by providing a period for carrying out the action items, so even an inexperienced care provider can create a schedule or carry out care.

[0022] Furthermore, according to the care support system of Invention 6, a schedule can be obtained by providing the frequency with which the action items are to be performed, so even an inexperienced care provider can create a schedule or provide care.

[0023] Furthermore, according to the care support system of Invention 7, it is possible to obtain a schedule that takes into consideration the attributes of the care recipient or care provider or information about the care recipient or care provider.

[0024] Furthermore, according to the care support system of Invention 8, a schedule can be obtained that takes into account hopes, goals, challenges, or deadlines for achieving them.

[0025] Furthermore, according to the care support system of Invention 9, a schedule can be obtained that takes into account hopes, challenges, goals, or deadlines for achieving them. [Brief explanation of the drawings]

[0026] [Figure 1] FIG. 1 is a block diagram showing a configuration of a network system. [Figure 2] 1 is a diagram illustrating a hardware configuration of a care support device 100. FIG. [Figure 3] This is a conceptual diagram showing the connection relationship between hopes, goals, tasks, and implementation items. [Figure 4] 10 is a flowchart showing a care plan creation process. [Figure 5] This is a screen showing a care management table when preferences are input from multiple candidates. [Figure 6] 10 is a screen showing a care management table when a goal is input from a plurality of candidates. [Figure 7] 10 is a screen showing a care management table when a task is input from a plurality of candidates. [Figure 8] 10 is a screen showing a care management table when action items are input from a plurality of candidates. [Figure 9] 10 is a flowchart showing a schedule creation process. [Figure 10] This is the screen for inputting the implementation items, implementation period, and implementation frequency. [Figure 11] This is a screen that displays schedule candidates. [Figure 12] This is a screen that displays details of schedule candidates. [Figure 13] This is a conceptual diagram showing the connection between hopes, goals, and challenges. [Figure 14] FIG. 1 is a conceptual diagram showing the connection relationship between hopes, goals, and actions. [Figure 15] FIG. 1 is a conceptual diagram showing the connection relationship between hopes, challenges, and actions. [Figure 16] FIG. 1 is a conceptual diagram showing the connection relationship between goals, tasks, and action items. DETAILED DESCRIPTION OF THE INVENTION

[0027] An embodiment of the present invention will now be described, with reference to Figures 1 to 12.

[0028] First, the configuration of this embodiment will be described. FIG. 1 is a block diagram showing the configuration of a network system.

[0029] As shown in FIG. 1, the Internet 199 is connected to 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.

[0030] Next, the configuration of the care support device 100 will be described. FIG. 2 is a diagram showing the hardware configuration of the care support device 100. As shown in FIG.

[0031] As shown in Figure 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 that stores the control program etc. of the CPU 30 in advance in a specified area, a RAM (Random Access Memory) 34 that stores 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, and 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.

[0032] The I / F 38 is connected to external devices such as an input device 40 consisting of a keyboard, mouse, etc. that can input data as a human interface, a storage device 42 that stores data, tables, etc. as files, and a display device 44 that displays a screen based on an image signal.

[0033] Next, the relationship between hopes, goals, tasks, and implementation items will be explained. The care management table of this embodiment manages (1) the "hopes" of the care recipient, (2) "goals" to realize the wishes, (3) "issues" that need to be resolved to achieve the goals, and (4) "implementations" that are necessary to resolve the issues, in correspondence with each other.

[0034] FIG. 3 is a conceptual diagram showing the connection relationship between hopes, goals, tasks, and implementation items. For each wish, one or more goals are set to realize that wish, as shown in Figure 3. In the example of Figure 3, Goal 1-1, Goal 1-2, and other goals are set for Hope 1, and Goal 2-1, Goal 2-2, and other goals are set for Hope 2. Since goals correspond to each wish, Goals 1-1, 1-2, 2-1, and 2-2 may have common or similar tendencies or contents, but are essentially independent of each other. The care provider hears about the wishes of the care recipient and records the wishes heard in a care management chart. The care provider then sets goals to realize those wishes based on their own experience, care history, etc., and records the set goals in the care management chart. One or more goals may be set as needed.

[0035] Next, for each goal, one or more tasks that need to be resolved to achieve the goal are set. In the example of Figure 3, task 1-1-1, task 1-1-2, and other tasks are set for goal 1-1; task 1-2-1, task 1-2-2, and other tasks are set for goal 1-2; task 2-1-1, task 2-1-2, and other tasks are set for goal 2-1; and task 2-2-1, task 2-2-2, and other tasks are set for goal 2-2. Since tasks correspond to each goal, tasks 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 share or be similar in terms of trend or content, but are essentially independent of each other. Based on their own experience and care history, the care provider sets tasks that need to be resolved to achieve the set goals and records the tasks in the care management chart. One or more tasks may be set as needed.

[0036] Next, for each issue, one or more action items necessary to solve it are set. In the example of Figure 3, action item 1-1-1-1, action item 1-1-1-2, and other action items are set for issue 1-1-1, action item 1-1-2-1, action item 1-1-2-2, and other action items are set for issue 1-1-2, action item 1-2-1-1, action item 1-2-1-2, and other action items are set for issue 1-2-1, and action item 1-2-2-1, action item 1-2-2-2, and other action items are set for issue 1-2-2. Additionally, for task 2-1-1, action item 2-1-1-1, action item 2-1-1-2 and other action items have been set; for task 2-1-2, action item 2-1-2-1, action item 2-1-2-2 and other action items have been set; for task 2-2-1, action item 2-2-1-1, action item 2-2-1-2 and other action items have been set; and for task 2-2-2, action item 2-2-2-1, action item 2-2-2-2 and other action items have been set. Each issue has its own corresponding action item, and although 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, and 2-2-2-2 may share common or similar tendencies or content, they are essentially independent of each other. Based on their own experience and care history, caregivers set the action items necessary to solve the issues set above and record the set action items in the care management chart. One or more action items may be set as needed.

[0037] Next, the configuration of the large-scale language model server 200 will be described. The large-scale language model server 200 has the same hardware configuration as the care support device 100. The large-scale language model is a deep learning model that pre-trains a language model, which models human-spoken language based on its occurrence probability, from a huge amount of data. Upon receiving a request, the large-scale language model server 200 uses the large-scale language model to statistically estimate the probability of generating 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 on the internet sites "https: / / chatgpt-lab.com / n / n418d3aa56f0b" and "https: / / agirobots.com / chatgpt-mechanism-and-problem / " can be adopted.

[0038] The contents of the hopes, goals, tasks, and actions, as well as the connection relationships between them, as shown in Figure 3, are publicly known at least in JP 2020-190818 A. This publicly known information is learned in the large-scale language model.

[0039] Next, the operation of this embodiment will be described. First, the case of creating a care plan will be described.

[0040] The CPU 30 is made up of an MPU (Micro-Processing Unit) or the like, and starts a predetermined program stored in a predetermined area of ​​the ROM 32, and executes the care plan creation process shown in the flowchart of FIG. 4 in accordance with the program.

[0041] FIG. 4 is a flowchart showing the care plan creation process. The care plan creation process is initiated in response to a request from a user such as a care provider, and when executed by the CPU 30, the process first proceeds to step S100 as shown in FIG.

[0042] 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.

[0043] FIG. 5 is a screen showing a care management table when preferences are entered from multiple candidates. Next, the process proceeds to step S102, where input of the care recipient's wishes is requested, and a display process of candidate wishes is executed. In this display process, candidate wishes are displayed on the display device 44 as follows. The care support device 100 generates a request including a request to generate candidate wishes and transmits it to the large-scale language model server 200. For example, the request may read, "Please provide candidate wishes for the care recipient when providing care to the care recipient." When the care support device 100 receives an estimation result (e.g., text including one or more candidates) output from the large-scale language model server 200 in response to the request, the care support device 100 displays candidate wishes for the care recipient on the display device 44 based on the received estimation result, as shown in FIG. 5. The care provider then selects one of the displayed candidates. In the example of FIG. 5, the candidate wishes displayed are "I want to go home," "I want to continue living at home," and "I want to be able to walk," and the care provider selects, for example, "I want to go home." Once a wish is selected, the process proceeds to step S104, where the selected wish is input via the input device 40.

[0044] Next, the process proceeds to step S106, where 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.

[0045] FIG. 6 is a screen showing a care management table when a goal is input from multiple candidates. Next, the process proceeds to step S108, where a request to input a goal is made. A process for displaying candidate goals is executed. In this display process, candidate goals are displayed on the display device 44 as follows. The care support device 100 generates a request including the wishes input in steps S104 and S106 and a request to generate candidate goals, and transmits the request to the large-scale language model server 200. For example, the request may include, "The wish of the subject in providing care to the subject is XX. The wish of the subject's family is XX." "Please provide candidate goals for realizing these wishes in providing care to the subject." When the care support device 100 receives the estimation results output from the large-scale language model server 200 in response to the request, candidate goals for realizing the wishes are displayed on the display device 44 based on the received estimation results, as shown in FIG. 6. The care provider then selects one of the displayed candidates. In the example of FIG. 6, the candidate goals displayed are "perform rehabilitation," "live without anxiety in a facility," "reduce the burden of caregiving on family members," and "become able to go to the toilet." The care provider selects, for example, "perform rehabilitation." Once the target is selected, the process proceeds to step S110, where the selected target is input from the input device 40.

[0046] FIG. 7 is a screen showing a care management table when a task is input from multiple candidates. Next, the process proceeds to step S112, where a task input is requested. A task candidate display process is executed. In this display process, task candidate candidates are displayed on the display device 44 as follows. The care support device 100 generates a request including the goal input in step S110 and a request to generate task candidates, and transmits the request to the large-scale language model server 200. For example, the request may include, "The goal of caregiving for the care recipient is XX." "Please provide candidate tasks that need to be solved to achieve this goal." When the care support device 100 receives the estimation results output from the large-scale language model server 200 in response to the request, the display device 44 displays candidate tasks that need to be solved to achieve the goal based on the received estimation results, as shown in FIG. 7. The care provider then selects one of the displayed candidates. In the example of FIG. 7, the candidate tasks displayed are "insufficient fluid intake," "low dietary intake," and "poor bowel control." The care provider selects, for example, "insufficient fluid intake." Once a task is selected, the process proceeds to step S114, where the selected task is input via the input device 40.

[0047] FIG. 8 is a screen showing a care management table when action items are input from a plurality of candidates. Next, the process proceeds to step S116, where input of an action item is requested. A display process for candidate action items is executed. In this display process, candidate action items are displayed on the display device 44 as follows. The care support device 100 generates a request including the task input in step S114 and a request to generate candidate action items, and transmits the request to the large-scale language model server 200. For example, the request may include, "The care challenge in providing care to the patient is XX." and "Please provide candidate action items necessary to solve this challenge." When the care support device 100 receives the estimation result output from the large-scale language model server 200 in response to the request, candidate action items necessary to solve the challenge are displayed on the display device 44 based on the received estimation result, as shown in FIG. 8. The care provider then selects one of the displayed candidates. In the example of FIG. 8, candidate action items displayed are "regular medical checkups," "medication management," and "providing meals tailored to the patient's condition." The care provider selects, for example, "regular medical checkups." When an action item is selected, the process proceeds to step S118, where the selected action item is input from the input device 40.

[0048] Although not shown, when an action item is input, a period for performing the action item (hereinafter referred to as the "action period") and a frequency for performing the action item (hereinafter referred to as the "action frequency") can also be input. In this case, candidates for the action period and the action frequency can be obtained from the large-scale language model server 200. Specifically, a request including the action item and a request to generate candidates for the action period and the action frequency is generated and transmitted to the large-scale language model server 200. The request may, for example, include the following: "The care action item to be performed for the care recipient is XX." "Please provide candidates for the period and the frequency for performing this action item." When the care support device 100 receives an estimation result output from the large-scale language model server 200 in response to the request, candidates for the action period and the action frequency are displayed on the display device 44 based on the received estimation result. Here, the care provider inputs the action period and the action frequency by selecting one of the displayed candidates. Candidates for only the action period and the action frequency can also be obtained from the large-scale language model server 200, not just for both the action period and the action frequency.

[0049] Next, the process proceeds to step S120, where a request is made to input a deadline for achieving the goal (hereinafter referred to as the "achievement deadline"), and a display process for candidate deadlines is executed. In this display process, candidate deadlines are displayed on the display device 44 as follows. The care support device 100 generates a request including the goal input in step S110 and a request to generate candidate deadlines, and transmits the request to the large-scale language model server 200. The request may, for example, be something like, "The goal of care when providing care to the care recipient is XX." or "Please provide candidate deadlines for achieving this goal." When the care support device 100 receives an estimation result output from the large-scale language model server 200 in response to the request, candidate deadlines for achieving the goal are displayed on the display device 44 based on the received estimation result. The care provider then selects one of the displayed candidates. Once a deadline is selected, the process proceeds to step S122, where the selected deadline is input via the input device 40.

[0050] Next, the process proceeds to step S124, where input of updated content is requested, and the updated content relative to the previous input is input from the input device 40.

[0051] 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.

[0052] 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.

[0053] Next, the process proceeds to step S130, where input of the wish fulfillment history is requested, and the wish fulfillment history, including the dates on which the wishes were fulfilled, is input from the input device 40. The wish fulfillment history is input based on responses from the care recipient or family members.

[0054] 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.

[0055] Next, the process proceeds to step S134, and care management information including the name, wishes of the care recipient, wishes of the family, goals, tasks, implementation items (or implementation period and implementation frequency), achievement deadline, update content, 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.

[0056] Then, the process proceeds to step S136, and for each care recipient, the name, wishes of the care recipient, wishes of the family, goals, tasks, implementation items (or implementation period and implementation frequency), achievement deadline, update details, achievement rate, realization rate, wish realization history, and goal achievement history are displayed on the display device 44 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 its corresponding item column.

[0057] Next, a case where a schedule for carrying out action items (hereinafter referred to as a "schedule") is created will be described.

[0058] The CPU 30 starts a predetermined program stored in a predetermined area of ​​the ROM 32, and executes the schedule creation process shown in the flowchart of FIG. 9 in accordance with the program.

[0059] FIG. 9 is a flowchart showing the schedule creation process. The schedule creation process is initiated in response to a request from a user such as a care provider, and when executed by the CPU 30, the process first proceeds to step S200 as shown in FIG.

[0060] FIG. 10 shows a screen for inputting the implementation items, implementation period, and implementation frequency. In steps S200 to S204, the action items, the action period, and the action frequency (hereinafter collectively referred to as "action items, etc.") are input. For example, when the care provider selects any of the care management information stored in the storage device 42, the selected care management information is read from the storage device 42, and the action items, etc. included in the read care management information are input as initial values ​​into the screen of FIG. 10.

[0061] In the example of Figure 10, three action items are entered. In the first line, the action item is "Regular medical checkups," the implementation period is "April 1, 2024 - April 30, 2024," and the implementation frequency is "Once per month." This indicates that regular medical checkups will be conducted once a month for the care recipient from April 1, 2024 to April 30, 2024. Similarly, the second line indicates that medication management will be conducted once a day for the care recipient from April 1, 2024 to June 30, 2024. The third line indicates that meals tailored to the care recipient's condition will be provided three times a week from April 1, 2024 to May 31, 2024. The action items entered from the care management information can be modified on the screen shown in Figure 10. Furthermore, if the care provider wants to add more action items, they can click the "Add Row" button to add a new row and enter the action items. Then, when the input contents of the implementation items are confirmed, the care provider clicks the "Decide" button.

[0062] FIG. 11 shows a screen displaying schedule candidates. FIG. 12 is a screen displaying details of a schedule candidate.

[0063] Next, the process proceeds to step S206, where a process for displaying schedule candidates is executed. In this display process, schedule candidates are displayed on the display device 44 as follows. The care support device 100 generates a request including the action items and the like input in steps S200 to S204 and a request for generating schedule candidates, and transmits the request to the large-scale language model server 200. The request may include, for example, "The action items, duration, and frequency of care to be performed for the care recipient are XX." "Based on these action items, duration, and frequency, please create multiple weekly schedule candidates for performing these action items. Please output the results in a list." When the care support device 100 receives the estimation results output from the large-scale language model server 200 in response to the request, schedule candidates are displayed on the display device 44 based on the received estimation results, as shown in FIG. 11. A "Details" button is displayed for each candidate. The care provider can click the "Details" button to display and confirm the schedule details, as shown in FIG. 12. Then, the care provider selects one of the displayed candidates and clicks the "Decide" button on the screen of Figure 11. When the "Decide" button is clicked, the process goes through step S208 and the schedule is selected.

[0064] Next, the process proceeds to step S210, where it is determined whether a request to edit the selected schedule has been input. If it is determined that a request to edit the schedule has been input (YES), the process proceeds to step S212, where a screen for editing the selected schedule is displayed. The care provider can edit the schedule on this screen.

[0065] Next, the process proceeds to step S214, where schedule information relating to the selected schedule is registered in the storage device 42. The schedule information is registered in association with the care management information.

[0066] Then, the process proceeds to step S216, where the selected schedule is displayed on the display device 44. If the schedule is for one week, the schedule is displayed as a weekly schedule table as shown in FIG.

[0067] Next, the effects of this embodiment will be described. In this embodiment, a request including action items for the care recipient and a request to generate schedule 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 sent request is received, and a schedule is displayed based on the received estimation result.

[0068] This allows for schedule candidates to be obtained, so that even a caregiver with little experience can create a schedule or provide care.

[0069] Furthermore, in this embodiment, a request including a request to generate desired 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 sent request is received, and the desired candidates are displayed based on the received estimation result.

[0070] This allows desired candidates to be obtained, so even caregivers with little experience can create a care plan or provide care.

[0071] Furthermore, in this embodiment, a request including the desire input in steps S104 and S106 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.

[0072] This allows for the acquisition of goal candidates that take into account the patient's wishes, allowing even inexperienced caregivers to create care plans or provide care.

[0073] Furthermore, in this embodiment, a request including the goal input in step S110 and 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.

[0074] This allows for candidate tasks that take the goal into consideration, so even caregivers with little experience can create care plans or provide care.

[0075] Furthermore, in this embodiment, a request including the task input in step S114 and a request to generate candidate 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 candidate action items are displayed based on the received estimation result.

[0076] This allows for candidates for actions that take the issues into consideration, so even caregivers with little experience can create care plans or provide care.

[0077] Furthermore, in this embodiment, a request including the goal input in step S110 and a request to generate candidate deadlines 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 candidate deadlines are displayed based on the received estimation result.

[0078] This allows for candidate deadlines that take the goal into consideration, so that even caregivers with little experience can create care plans or provide care.

[0079] In this embodiment, step S206 corresponds to the input means of invention 1 or the acquisition means of invention 1.

[0080] [Modification] In the above embodiment and its variations, the display process in step S102 generates a request including a request to generate desired candidates. However, this is not limited to this, and the request may also include other information. For example, a request including the 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 condition, excretion status, dietary status, economic level, and information on medication use; 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.

[0081] In the above embodiment and its variations, the display process in step S108 generates a request including the wishes entered in steps S104 and S106 and a request to generate goal candidates. However, this is not limited to this, and the request may also include other information. For example, a request can be generated that includes the attributes of the care recipient and the wishes entered in steps S104 and S106 and a request to generate goal candidates. This makes it possible to obtain goal candidates that take the attributes of the care recipient into consideration.

[0082] Furthermore, in the above embodiment and its variations, the display process in step S112 generates a request that includes the goal entered in step S110 and a request to generate task candidates, but this is not limited to this, and the request may also include other information. For example, a request can be generated that includes the desires entered in steps S104 and S106 and the goal entered in step S110 and a request to generate task candidates. This makes it possible to obtain task candidates that take the desires into consideration. Also, for example, a request can be generated that includes the attributes, desires, and goals of the care recipient and a request to generate task candidates.

[0083] Furthermore, in the above embodiment and its variations, the display process in step S116 generates a request including the task input in step S114 and a request to generate candidate action items. However, this is not limited to this, and the request may also include other information. For example, a request including the goal input in step S110 and the task input in step S114 and a request to generate candidate action items can be generated. This makes it possible to obtain candidate action items that take the goal into consideration. Also, for example, a request including hopes, goals, and tasks and a request to generate candidate action items can be generated. Also, for example, a request including the attributes, hopes, goals, and tasks of the care recipient and a request to generate candidate action items can be generated.

[0084] Furthermore, in the above embodiment and its variations, information on four items, namely, hopes, goals, tasks, and implementation items, was registered, but this is not limited to this, and information on at least one of these items can also be registered.

[0085] In the above embodiment and its modified example, information on four items, namely, hope, goal, task, and action item, is selectively input, but this is not limiting, and information on at least one of these items may be selectively input. For example, the following configuration may be adopted.

[0086] [Configuration 1] A request including some of the desires, goals, and challenges 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.

[0087] Explain the relationship between hopes, goals, and challenges in Structure 1. FIG. 13 is a conceptual diagram showing the connection between hopes, goals, and challenges.

[0088] For each wish, one or more goals are set to realize that wish, as shown in Figure 13. In the example of Figure 13, Goal 1-1, Goal 1-2, and other goals are set for Hope 1, and Goal 2-1, Goal 2-2, and other goals are set for Hope 2. Since goals correspond to each wish, Goals 1-1, 1-2, 2-1, and 2-2 may have common or similar tendencies or contents, but are basically independent of each other. The care provider hears about the wishes of the care recipient and records the heard wishes in a care management chart. The care provider then sets goals to realize those wishes based on their own experience, care history, etc., and records the set goals in the care management chart. One or more goals may be set as needed.

[0089] Next, for each goal, one or more tasks that need to be resolved to achieve the goal are set. In the example of Figure 13, task 1-1-1, task 1-1-2, and other tasks are set for goal 1-1; task 1-2-1, task 1-2-2, and other tasks are set for goal 1-2; task 2-1-1, task 2-1-2, and other tasks are set for goal 2-1; and task 2-2-1, task 2-2-2, and other tasks are set for goal 2-2. Since tasks correspond to each goal, tasks 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 share or be similar in terms of trend or content, but are essentially independent of each other. Based on their own experience and care history, the care provider sets tasks that need to be resolved to achieve the set goals and records the set tasks in the care management chart. One or more tasks may be set as needed.

[0090] For cooperation with the large-scale language model server 200, for example, configurations 1A and 1B can be adopted.

[0091] [Configuration 1A] A request including one piece of information from among hopes, goals, and challenges, and including a request to generate one or two pieces of information other than hopes, goals, and challenges, 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.

[0092] 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 estimation result B is received from the large-scale language model server 200 in response to the request. Configuration 1A includes the following configurations: "hope / goal," "hope / challenge," "goal / hope," "goal / challenge," "challenge / hope," "challenge / goal," "hope / goal and challenge," "goal / hope and challenge," "challenge / hope and goal."

[0093] [Configuration 1B] A request including two pieces of information from among hope, goal, and problem, and including a request to generate information other than hope, goal, and problem, 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.

[0094] Structure 1B includes the following structures: "Hope and goals / challenges," "Hope and challenges / goals," and "Goals and challenges / hopes."

[0095] [Configuration 2] 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.

[0096] The relationship between hopes, goals, and implementation items in Structure 2 is explained. FIG. 14 is a conceptual diagram showing the connection relationship between hopes, goals, and actions.

[0097] For each wish, one or more goals are set to realize that wish, as shown in Figure 14. In the example of Figure 14, Goal 1-1, Goal 1-2, and other goals are set for Hope 1, and Goal 2-1, Goal 2-2, and other goals are set for Hope 2. Since goals to be set correspond to each wish, Goals 1-1, 1-2, 2-1, and 2-2 may have common or similar tendencies or contents, but are basically independent of each other. The care provider hears about the wishes of the care recipient and records the heard wishes in a care management chart. The care provider then sets goals to realize those wishes based on their own experience, care history, etc., and records the set goals in the care management chart. One or more goals may be set as needed.

[0098] Next, for each goal, one or more action items are set that are necessary to solve the issues that need to be resolved in order to achieve the goal. In the example of Figure 14, action item 1-1-1, action item 1-1-2, and other action items are set for goal 1-1, action item 1-2-1, action item 1-2-2, and other action items are set for goal 1-2, action item 2-1-1, action item 2-1-2, and other action items are set for goal 2-1, and action item 2-2-1, action item 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. Based on their own experience and care history, caregivers will set action items necessary to resolve issues that need to be resolved in order to achieve the set goals, and enter the set action items into the care management chart. One or more action items may be set as needed.

[0099] For cooperation with the large-scale language model server 200, for example, configurations 2A and 2B can be adopted.

[0100] [Configuration 2A] A request including one piece of information from among hopes, goals, and actions, and a request to generate one or two pieces of information other than hopes, 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.

[0101] Structure 2A 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."

[0102] [Configuration 2B] A request including two pieces of information from among hopes, goals, and actions, and including a request to generate information other than the hopes, 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.

[0103] Structure 2B includes the following structures: "Hope and goals / action items," "Hope and action items / goals," and "Goals and action items / hopes."

[0104] [Configuration 3] A request including some of the wishes, 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.

[0105] The relationship between hopes, challenges, and implementation items in Structure 3 is explained. FIG. 15 is a conceptual diagram showing the connection relationship between hopes, issues, and actions.

[0106] For each wish, one or more tasks are set that need to be resolved in order to achieve the goal of realizing that wish, as shown in Figure 15. In the example of Figure 15, 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 tasks to be set correspond to each wish, tasks 1-1, 1-2, 2-1, and 2-2 may have common or similar tendencies or contents, but are basically independent of each other. The care provider hears the wishes of the care recipient and records the wishes heard in a care management chart. Then, based on their own experience, care history, etc., the care provider sets tasks that need to be resolved in order to achieve the goal of realizing that wish, and records the set tasks in the care management chart. One or more tasks may be set as needed.

[0107] Next, for each issue, one or more action items necessary to resolve it are set. In the example of Figure 15, action item 1-1-1, action item 1-1-2, and other action items are set for issue 1-1; action item 1-2-1, action item 1-2-2, and other action items are set for issue 1-2; action item 2-1-1, action item 2-1-2, and other action items are set for issue 2-1; and action item 2-2-1, action item 2-2-2, and other action items are set for issue 2-2. Since action items to be set correspond to each issue, 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 common or similar tendencies or contents, but are essentially independent of each other. The care provider sets the action items necessary to resolve the above-defined issues based on their own experience, care history, etc., and enters the set action items in the care management chart. One or more implementation items may be set as necessary.

[0108] For cooperation with the large-scale language model server 200, for example, configurations 3A and 3B can be adopted.

[0109] [Configuration 3A] A request including one piece of information from among hopes, tasks, and actions, and a request to generate one or two pieces of information other than 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.

[0110] Structure 3A includes the following structures: "Hope / issues," "Hope / implementations," "issues / hopes," "issues / implementations," "implementations / hopes," "implementations / issues," "Hope / issues and implementations," "issues / hopes and implementations," and "implementations / hopes and issues."

[0111] [Configuration 3B] A request including two pieces of information from among hopes, tasks, and actions, and including a request to generate information other than 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.

[0112] Structure 3B includes the following structures: "Hope and issues / implementation items," "Hope and implementation items / issues," and "Issues and implementation items / hopes."

[0113] [Configuration 4] A request including some of the goals, tasks, 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.

[0114] The relationship between the goals, tasks, and implementation items in Structure 4 is explained. FIG. 16 is a conceptual diagram showing the connection relationship between goals, tasks, and action items.

[0115] For each goal, one or more tasks that need to be resolved to achieve the goal are set, as shown in Figure 16. In the example of Figure 16, task 1-1, task 1-2, and other tasks are set for goal 1, and task 2-1, task 2-2, and other tasks are set for goal 2. Since tasks to be set correspond to each goal, tasks 1-1, 1-2, 2-1, and 2-2 may have common or similar tendencies or content, but are essentially independent of each other. The care provider listens to the wishes of the care recipient and sets goals to realize the wishes based on their own experience and care history, etc., and records the set goals in the care management table. Then, the care provider sets challenges that need to be resolved to achieve the above goals based on their own experience and care history, etc., and records the set challenges in the care management table. One or more challenges may be set as needed.

[0116] Next, for each issue, one or more action items necessary to resolve it are set. In the example of Figure 16, action item 1-1-1, action item 1-1-2, and other action items are set for issue 1-1; action item 1-2-1, action item 1-2-2, and other action items are set for issue 1-2; action item 2-1-1, action item 2-1-2, and other action items are set for issue 2-1; and action item 2-2-1, action item 2-2-2, and other action items are set for issue 2-2. Since action items to be set correspond to each issue, 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 common or similar tendencies or contents, but are essentially independent of each other. The care provider sets the action items necessary to resolve the above-defined issues based on their own experience, care history, etc., and enters the set action items in the care management chart. One or more implementation items may be set as necessary.

[0117] For cooperation with the large-scale language model server 200, for example, configurations 4A and 4B can be adopted.

[0118] [Configuration 4A] A request including one piece of information from among the goal, task, and action items and a request to generate one or two pieces of information other than the goal, task, 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.

[0119] Structure 4A includes the following structures: "Goals / Challenges," "Goals / Implementations," "Challenges / Goals," "Challenges / Implementations," "Implementations / Goals," "Implementations / Challenges," "Goals / Challenges and Implementations," "Challenges / Goals and Implementations," and "Implementations / Goals and Issues."

[0120] [Configuration 4B] A request including two pieces of information from among the goal, task, and action items, and including a request to generate information other than the goal, task, 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.

[0121] Structure 4B includes the following structures: "Objectives and Issues / Implementation Items," "Objectives and Implementation Items / Issues," and "Issues and Implementation Items / Objectives."

[0122] [Configuration 5] A request including some of the desires, goals, tasks, and actions, and a request to generate candidates for the remaining parts, is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request, and candidates are displayed based on the received inference result.

[0123] 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.

[0124] [Configuration 5A] A request including one piece of information from among hopes, goals, tasks, and implementation items, and a request to generate one, two, or three pieces of information other than hopes, goals, tasks, 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.

[0125] Structure 5A includes the following structures: "Hope / Goal," "Hope / Challenge," "Hope / Implementation Items," "Goal / Hope," "Goal / Challenge," "Goal / Implementation Items," "Challenges / Hope," "Challenges / Goal," "Challenges / Implementation Items," "Implementation Items / Hope," "Implementation Items / Goal," "Implementation Items / Challenges," "Hope / Goal and Issues," "Hope / Goal and Implementation Items," "Hope / Challenges and Implementation Items," "Goal / Hope and Issues," "Goal / Hope and Implementation Items," "Goal / Issues and Implementation Items," "Issues / Hope and Goal," "Issues / Hope and Goal," "Issues / Goal and Implementation Items," "Implementation Items / Hope and Goal," "Implementation Items / Hope and Issues," "Implementation Items / Goal and Issues," "Hope / Goal, Issues and Implementation Items," "Issues / Hope, Goal and Implementation Items," "Issues / Hope, Goal and Implementation Items," "Implementation Items / Hope and Goal," "Implementation Items / Hope and Goal," "Issues / Goal and Implementation Items," "Issues / Hope, Goal, Issues and Implementation Items," "Issues / Hope, Goal and Implementation Items," "Implementation Items / Hope, Goal and Issues."

[0126] [Configuration 5B] A request including two pieces of information from among hopes, goals, tasks, and implementation items, and including a request to generate one or two pieces of information other than hopes, goals, tasks, 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.

[0127] Structure 5B includes the following structures: "Hope and goals / challenges," "Hope and goals / implementations," "Hope and challenges / goals," "Hope and challenges / implementations," "Hope and implementations / goals," "Hope and implementations / issues," "Goals and challenges / hopes," "Goals and challenges / implementations," "Goals and implementations / hopes," "Goals and implementations / issues," "Issues and implementations / hopes," "Issues and implementations / goals," "Hope and goals / challenges and implementations," "Hope and challenges / goals and implementations," "Hope and implementations / goals and challenges," "Goals and challenges / hopes and implementations," "Goals and implementations / hopes and challenges," "Issues and implementations / hopes and goals."

[0128] [Configuration 5C] A request including three pieces of information among hopes, goals, tasks, and implementation items, and including a request to generate information other than hopes, goals, tasks, and implementation items, is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request, and candidates are displayed based on the received inference result.

[0129] Structure 5C includes the following structures: "Hope, goals and issues / implementations," "Hope, goals and issues / implementations," and "Goals, goals and issues / hopes."

[0130] [Configuration 6A] In any of Configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, and 5A to 5C, the request includes attributes of the care recipient or includes a request to generate attributes of the care recipient.

[0131] Configurations for sending a request including attributes include (1) a configuration for sending a request including only attributes and including a generation request, and (2) a configuration for sending a request including attributes and other information (e.g., wishes, goals, tasks, implementation items, implementation period, implementation frequency, schedule, deadline for achievement, achievement rate or realization rate, information about the care provider (e.g., attributes, daily schedule, information about the means of transportation used; the same applies below), and other information) (hereinafter, this "other information" is the same in (4) and 6A2 to 6A4 below.) and including a generation request.

[0132] The configurations for sending a request including a request to generate attributes include (3) a configuration for sending a request including a request to generate only attributes, and (4) a configuration for sending a request including a request to generate attributes and other information. Note that requests (3) and (4) can include information other than the generation request, as with requests (1) and (2).

[0133] Furthermore, the following configurations can be adopted as application examples of configuration 6A: Of the following configurations, configurations 6A1 to 6A5 do not presuppose configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, and 5A to 5C.

[0134] [Configuration 6A1] This is a configuration combining (1) and (3), in which a request including only the attributes of the care recipient and a request to generate only the attributes of the care recipient is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request is received, and the received inference result is displayed.

[0135] [Configuration 6A2] This is a configuration combining (1) and (4), in which a request including only the attributes of the care recipient and a request to generate the attributes and other information of the care recipient is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request is received, and the received inference result is displayed.

[0136] [Configuration 6A3] This is a configuration combining (2) and (3), in which a request including attributes of the care recipient and other information and a request to generate only the attributes of the care recipient is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request is received, and the received inference result is displayed.

[0137] [Configuration 6A4] This is a configuration combining (2) and (4), namely, a request including attributes and other information of the care recipient and a request to generate the attributes and other information of the care recipient is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request is received, and the received inference result is displayed.

[0138] [Configuration 6A5] In configurations 6A1 to 6A4, instead of the attributes of the care recipient, information about the care recipient (for example, attributes, daily schedule, distance to the facility, travel time to the facility, travel cost to the facility, information on the means of transportation used to get to the facility; the same applies below) is used.

[0139] [Configuration 6A6] This is a configuration in which Configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, 5A to 5C, 6B, 6B1 to 6B6, 7, 7A to 7E, 8, 8A to 8E, 9, and 10 are applied to Configurations 6A1 to 6A5.

[0140] [Configuration 6B] In configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, 5A-5C, 6A, and 6A1-6A6, the request includes attributes of a care provider (e.g., gender, age, years of work experience, and other information on work experience; the same applies below) or a request to generate attributes of a care provider. Here, care providers include, for example, those who have cared for a care recipient (in the past), those who are caring for a care recipient (present), those who plan to care for a care recipient (in the future), and those who have a predetermined relationship with these persons (e.g., those with the same years of work experience, years of experience, number of people in charge, and other achievements, or those within a predetermined range).

[0141] Configurations for sending a request that includes attributes include (1) a configuration for sending a request that includes only attributes and includes a generation request, and (2) a configuration for sending a request that includes attributes and other information (e.g., hopes, goals, tasks, implementation items, implementation period, implementation frequency, schedule, achievement deadline, achievement rate or realization rate, information about the care recipient, and other information) (hereinafter, this "other information" is the same in (4) and 6B2 to 6B4 below), and includes a generation request.

[0142] The configurations for sending a request including a request to generate attributes include (3) a configuration for sending a request including a request to generate only attributes, and (4) a configuration for sending a request including a request to generate attributes and other information. Note that requests (3) and (4) can include information other than the generation request, as with requests (1) and (2).

[0143] Furthermore, the following configurations can be adopted as application examples of configuration 6B. Note that among the following configurations, configurations 6B1 to 6B5 do not presuppose configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, 5A to 5C, 6A, and 6A1 to 6A6.

[0144] [Configuration 6B1] This is a configuration combining (1) and (3), in which a request including only the attributes of a caregiver and a request to generate only the attributes of the caregiver is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request is received, and the received inference result is displayed.

[0145] [Configuration 6B2] This is a configuration combining (1) and (4), in which a request including only the attributes of a caregiver and a request to generate attributes and other information of the caregiver is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request is received, and the received inference result is displayed.

[0146] [Configuration 6B3] This is a configuration combining (2) and (3), in which a request including caregiver attributes and other information and a request to generate only the caregiver attributes is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request is received, and the received inference result is displayed.

[0147] [Configuration 6B4] This is a configuration combining (2) and (4), in which a request including attributes and other information of a caregiver and a request to generate the attributes and other information of a caregiver is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request is received, and the received inference result is displayed.

[0148] [Configuration 6B5] In Configurations 6B1 to 6B4, information about the care provider is used instead of the care provider's attributes.

[0149] [Configuration 6B6] This is a configuration in which Configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, 5A to 5C, 6A, 6A1 to 6A6, 7, 7A to 7E, 8, 8A to 8E, 9, and 10 are applied to Configurations 6B1 to 6B5.

[0150] [Configuration 7] In configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, 5A to 5C, 6A, 6A1 to 6A6, 6B, and 6B1 to 6B6, the request includes an achievement deadline, an achievement rate, or a realization rate, or includes a request to generate an achievement deadline, an achievement rate, or a realization rate.

[0151] Configurations for sending a request including a deadline for achievement include (1) a configuration for sending a request including only the deadline for achievement, the achievement rate, or the realization rate, and including a request for generation; and (2) a configuration for sending a request including the deadline for achievement, the achievement rate, or the realization rate, and other information (e.g., hopes, goals, tasks, implementation items, implementation period, implementation frequency, schedule, information about the care recipient, information about the care provider, and other information) (hereinafter, this "other information" is the same in (4) and 7B to 7D below.) and including a request for generation.

[0152] The configuration of transmitting a request including a request to generate an achievement deadline, achievement rate, or realization rate includes (3) a configuration of transmitting a request including a request to generate only an achievement deadline, achievement rate, or realization rate, and (4) a configuration of transmitting a request including a request to generate an achievement deadline, achievement rate, or realization rate, and other information. Note that requests (3) and (4) can include information other than the generation request, as in requests (1) and (2).

[0153] The following configurations can be adopted as application examples of configuration 7. Note that among the following configurations, configurations 7A to 7D do not presuppose configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, 5A to 5C, 6A, 6A1 to 6A6, 6B, and 6B1 to 6B6.

[0154] [Configuration 7A] This is a configuration combining (1) and (3), namely, a request including only a deadline, an achievement rate, or a realization rate, and including a request to generate only the deadline, the achievement rate, or the realization rate, is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request is received, and the received inference result is displayed.

[0155] [Configuration 7B] This is a configuration combining (1) and (4), namely, a request including only the deadline, achievement rate, or realization rate, and a request to generate the deadline, achievement rate, or realization rate and other information is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request, and the received inference result is displayed.

[0156] [Configuration 7C] This is a configuration combining (2) and (3), in which a request including a deadline, an achievement rate or realization rate, and other information, and a request to generate only the deadline, the achievement rate, or the realization rate, is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request, and the received inference result is displayed.

[0157] [Configuration 7D] This is a configuration combining (2) and (4), namely, a request including a deadline, an achievement rate or realization rate, and other information, and a request to generate the deadline, the achievement rate or realization rate, and other information is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request, and the received inference result is displayed.

[0158] [Configuration 7E] This is a configuration in which Configurations 7A to 7D are applied with Configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, 5A to 5C, 6A, 6A1 to 6A6, 6B, 6B1 to 6B6, 8, 8A to 8E, 9, and 10.

[0159] [Configuration 8] In configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, 5A to 5C, 6A, 6A1 to 6A6, 6B, 6B1 to 6B6, 7, and 7A to 7E, the request includes an action item, an action period, or an action frequency, or includes a request to generate an action item, an action period, or an action frequency.

[0160] Configurations for sending a request including an action item, an implementation period, or an implementation frequency include (1) a configuration for sending a request including only the action item, the implementation period, or the implementation frequency and including a generation request, and (2) a configuration for sending a request including the action item, the implementation period, or the implementation frequency and other information (e.g., hopes, goals, tasks, schedules, deadlines for achievement, achievement rates or realization rates, information about the care recipient, information about the care provider, and other information) (hereinafter, this "other information" is the same in (4) and 8B to 8D below.) and including a generation request.

[0161] The configuration for transmitting a request including a request to generate an action item, an action period, or an action frequency includes (3) a configuration for transmitting a request including a request to generate only an action item, an action period, or an action frequency, and (4) a configuration for transmitting a request including a request to generate an action item, an action period, or an action frequency and other information. Note that the requests in (3) and (4) can include information other than the generation request, as in the requests in (1) and (2).

[0162] The following configurations can be adopted as application examples of configuration 8. Of the following configurations, configurations 8A to 8D do not presuppose configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, 5A to 5C, 6A, 6A1 to 6A6, 6B, 6B1 to 6B6, 7, and 7A to 7E.

[0163] [Configuration 8A] This is a configuration combining (1) and (3), namely, a request including only an action item, an action period, or an action frequency and including a request to generate only the action item, the action period, or the action frequency 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 the received estimation result is displayed.

[0164] [Configuration 8B] This is a configuration combining (1) and (4), namely, a request including only the action item, the action period, or the action frequency, and a request to generate the action item, the action period, or the action frequency and other information is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request, and the received inference result is displayed.

[0165] [Configuration 8C] This is a configuration combining (2) and (3), in which a request including an action item, an action period or an action frequency, and other information, and a request to generate only the action item, the action period or the action frequency, is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request, and the received inference result is displayed.

[0166] [Configuration 8D] This is a configuration combining (2) and (4), namely, a request including an action item, an action period or an action frequency, and other information, and including a request to generate the action item, the action period or the action frequency, and other information, is sent to the large-scale language model server 200, an inference result output from the large-scale language model server 200 in response to the request, and the received inference result is displayed.

[0167] [Configuration 8E] Configurations 8A to 8D are configured by applying Configurations 1A, 1B, 2A, 2B, 3A, 3B, 4A, 4B, 5A to 5C, 6A, 6A1 to 6A6, 6B, 6B1 to 6B6, 7, 7A to 7E, 9, and 10.

[0168] [Configuration 9] This is a configuration in which a request is sent that includes one of two combinations of information about the care recipient, information about the care provider, hopes, goals, tasks, implementation items, implementation period, implementation frequency, achievement deadline, achievement rate, and realization rate, and that includes a request to generate the other combination. In this case, the connection relationship as shown in Figure 3 becomes two-tiered.

[0169] [Configuration 10] A configuration for transmitting a request including a request to generate any one of information about the care recipient, information about the care provider, hopes, goals, tasks, implementation items, implementation period, implementation frequency, achievement deadline, achievement rate, and realization rate. In this case, the connection relationship shown in Figure 3 does not exist.

[0170] In the above embodiment and its variations, the display process in step S206 generates a request including action items and a request to generate schedule candidates, but the request is not limited to this and may include other information. For example, the following configuration can be adopted.

[0171] (1) The request includes an action item and a request to generate a schedule. (2) The request includes an action item and an action period, and includes a request to generate a schedule.

[0172] (3) The request includes an action item and an action frequency, and includes a request to generate a schedule.

[0173] (4) The request includes an action item, an action period, and an action frequency, and includes a request to generate a schedule.

[0174] (5) The request includes an implementation period and a request to generate a schedule. (6) The request includes an execution period and execution frequency, and includes a request to generate a schedule.

[0175] (7) The request includes an execution frequency and a request to generate a schedule. (8) The requests in (1) to (7) may further include attributes of the care recipient, or may include only attributes of the care recipient and a request to generate a schedule.

[0176] (9) The requests in (1) to (8) may further include attributes of a caregiver, or may include only attributes of a caregiver and a request to generate a schedule.

[0177] (10) The requests in (1) to (9) may further include information about the care recipient, or may be requests that include only information about the care recipient and a request to generate a schedule.

[0178] (11) The requests in (1) to (10) may further include information about the caregiver, or may include only information about the caregiver and a request to generate a schedule.

[0179] (12) In the combined relationship of hope, goal, task, and action items shown in Fig. 3, the requests (1) to (11) may further include hope, goal, task, deadline, achievement rate, or realization rate. Alternatively, the requests may include only hope, goal, task, deadline, achievement rate, or realization rate, and may include a request to generate a schedule.

[0180] (13) In the connection relationship between hope, goal, and task shown in Fig. 13, the requests (1) to (11) may further include hope, goal, task, deadline, achievement rate, or realization rate. Alternatively, the requests may include only hope, goal, task, deadline, achievement rate, or realization rate, and may include a request to generate a schedule.

[0181] (14) In the combined relationship between the hope, goal, and action items shown in Fig. 14, the requests (1) to (11) may further include the hope, goal, deadline, achievement rate, or realization rate. Alternatively, the requests may include only the hope, goal, deadline, achievement rate, or realization rate, and may include a request to generate a schedule.

[0182] (15) In the connection relationship between hopes, tasks, and implementation items shown in Fig. 15, the requests (1) to (11) may further include hopes, tasks, or realization rates. Alternatively, the requests may include only hopes, tasks, or realization rates, and may include a request to generate a schedule.

[0183] (16) In the connection relationship between the goal, task, and action items shown in Fig. 16, the requests (1) to (11) may further include the goal, task, deadline, achievement rate, or realization rate. Alternatively, the requests may include only the goal, task, deadline, achievement rate, or realization rate, and may include a request to generate a schedule.

[0184] Furthermore, in the above embodiment and its variations, the display process in step S206 generates a request including the implementation items, implementation period, and implementation frequency, and including a request to generate schedule candidates (one or more schedules), but this is not limited to this, and a request including a request to generate one schedule or a request to generate a predetermined number of schedules can be generated.

[0185] Furthermore, in the above embodiment and its variations, the terms "goal" and "challenge" are used, but this is not limiting, and it is equally valid to define "goal" as "long-term goal" and "challenge" as "short-term goal."

[0186] Furthermore, in the above embodiment and its variations, the term "implementation items" is used, but this is not limiting, and "implementation items" may also be defined as "measures," "services," "service menus," "service items," "service contents," etc., which are synonymous with the term.

[0187] Furthermore, in the above embodiment and its variations, the definition is "items to be implemented that are necessary to solve the problem," but it is not limited to this and can also be defined as "items to be implemented that are necessary to achieve the goal."

[0188] Furthermore, in the above embodiment and its modified examples, one goal is defined, but this is not limiting, and two or more goals can be defined, such as a "long-term goal" and a "short-term goal." If there is a connection between the goals, the above embodiment and its modified examples can be similarly applied as a configuration in which each goal is selectively input. This also applies to hopes, issues, and implementation items.

[0189] Furthermore, in the above embodiment and its variations, "goals to realize one's hopes" and "issues that need to be solved in order to achieve one's goals" are defined, but it is not limited to this, and "goals to realize one's hopes" can also be defined as "issues that need to be solved in order to realize one's hopes," and "issues that need to be solved in order to achieve one's goals" can also be defined as "goals set to solve issues."

[0190] Furthermore, in the above-described embodiment and its modified examples, the schedule is generated by a large-scale language model, but this is not limiting, and the schedule can be estimated by AI (Artificial Intelligence). Specifically, the configuration includes an acquisition means for acquiring input information, and an estimation means for estimating the schedule and other information from the input information acquired by the acquisition means, using a trained model that has been trained based on information of the same type as the input information, the schedule, and other information. For example, the following configuration can be adopted.

[0191] (1) The input information includes the implementation items. (2) The input information includes the implementation items and implementation period. (3) The input information includes the implementation items and implementation frequency.

[0192] (4) The input information includes the implementation items, implementation period, and implementation frequency. (5) Input information includes a request to generate a schedule, including an implementation period.

[0193] (6) Input information includes a request to generate a schedule, including implementation period and implementation frequency. (7) Input information includes a request to generate a schedule, including implementation frequency.

[0194] (8) The input information in (1) to (7) may further include attributes of the care recipient, or may be a request including only attributes of the care recipient and a request to generate a schedule.

[0195] (9) The input information in (1) to (8) may further include attributes of the care provider, or may be a request that includes only attributes of the care provider and a request to generate a schedule.

[0196] (10) The input information in (1) to (9) may further include information about the care recipient, or may be a request that includes only information about the care recipient and a request to generate a schedule.

[0197] (11) The input information in (1) to (10) may further include information about the caregiver, or may be a request that includes only information about the caregiver and a request to generate a schedule.

[0198] (12) In the combined relationship between the hope, goal, task, and action items shown in Fig. 3, the input information (1) to (11) may further include the hope, goal, task, deadline, achievement rate, or realization rate. Alternatively, the input information may include only the hope, goal, task, deadline, achievement rate, or realization rate, and may be a request for generating a schedule.

[0199] (13) In the connection relationship between hope, goal, and task shown in Fig. 13, the input information (1) to (11) further includes hope, goal, task, deadline, achievement rate, or realization rate. Alternatively, it can be a request that includes only hope, goal, task, deadline, achievement rate, or realization rate and includes a request to generate a schedule.

[0200] (14) In the combined relationship between the hope, goal, and action items shown in Fig. 14, the input information (1) to (11) may further include the hope, goal, deadline, achievement rate, or realization rate. Alternatively, the input information may include only the hope, goal, deadline, achievement rate, or realization rate, and may be a request for generating a schedule.

[0201] (15) In the connection relationship between the hope, task, and action items shown in Fig. 15, the input information (1) to (11) may further include the hope, task, or realization rate, or may be a request including only the hope, task, or realization rate and a request to generate a schedule.

[0202] (16) In the connection relationship between the goal, task, and action items shown in Fig. 16, the input information (1) to (11) further includes the goal, task, deadline, achievement rate, or realization rate. Alternatively, it can be a request that includes only the goal, task, deadline, achievement rate, or realization rate and includes a request to generate a schedule.

[0203] (17) In addition, in the above-described embodiment and its variations, information included in a request to a large-scale language model other than a generation request can be used as input information for the AI, and information output from the large-scale language model in response to the request can be used as output information for the AI. In this case, the trained model is trained based on information of the same type as the input information and output information. Then, the input information is acquired, and the trained model is used to estimate the output information from the acquired input information.

[0204] Furthermore, in the above embodiment and its variations, the care support device 100 is realized as a single device, but it 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 inputting it using the input device 40, and transmits information to the user terminal instead of displaying it on the display device 44.

[0205] Furthermore, in the above embodiment and its modifications, the storage device 42 provided in the care support device 100 is used, but this is not limiting, and an external storage device such as a database server can also be used.

[0206] Furthermore, in the above embodiment and its variants, the processing shown in the flowchart of FIG. 4 is executed by executing a program pre-stored in ROM 32, but this is not limiting, and the program showing these procedures may be read into RAM 34 from a storage medium on which the program is stored and executed.

[0207] Here, storage media refers to semiconductor storage media such as RAM and ROM, magnetic storage media such as FD and HD, optically readable storage media such as CD, CDV, LD and DVD, and magnetic storage / optically readable storage media such as MO, and includes all storage media that can be read by a computer, regardless of the reading method (electronic, magnetic, optical, etc.).

[0208] Furthermore, the present invention is not limited to the above-described embodiment and its modifications, and can be applied to other cases within the scope 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 care (looking after, protecting, caring for, nursing, etc.) of a care recipient in the fields of medicine (rehabilitation, treatment, etc.) or welfare (physical, intellectual, mental, etc.). [Explanation of symbols]

[0209] 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 information about a care provider and a request to generate a schedule for performing actions for a care recipient into the large-scale language model; A care support system comprising: an acquisition means for acquiring schedule information output from the large-scale language model in response to the request.

2. In claim 1, A care support system characterized in that the information about the care provider is information about the care provider's attributes, daily schedule, or means of transportation used.

3. an input means for inputting information about a care recipient, the information including a distance to a facility, a travel time to the facility, a travel cost to the facility, or information about a means of transportation to the facility, and a request for generating a schedule for performing actions for the care recipient into the large-scale language model; A care support system comprising: an acquisition means for acquiring schedule information output from the large-scale language model in response to the request.

4. In any one of claims 1 to 3, A care support system characterized in that the request includes the action item, the period or frequency for performing the action item, or a request to generate the action item, the period or frequency for performing the action item.

5. In any one of claims 1 to 3, A care support system characterized in that the request includes a deadline for achieving a goal to realize the wishes of the person being cared for or their family, or a goal to be achieved by solving a problem that needs to be solved to realize the wishes, a rate of achievement of the goal, or a rate of realization of the wishes, or a request to generate the deadline, the rate of achievement, or the rate of realization.

Images