Data processing apparatus, data processing method, and data processing program

Abstract

To provide a data processor, a data processing method, and a program for creating a care plan.SOLUTION: The data processing device includes a reception unit that receives attribute information of a person in need of assistance for creating a care plan, and a processing unit that performs a specifying process using a generation AI model that generates an output result according to an input sentence, and the processing unit generates the care plan as a result of the specifying process by output of the generation AI model when a text instructing a process of generating the care plan from the attribute information received by the reception unit is set as the input sentence.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a data processing device, a data processing method, and a data processing program. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional techniques leave room for improvement in creating care plans. [Means for solving the problem]

[0005] A first aspect of the technology disclosed herein includes a reception unit that receives attribute information of a person requiring support for creating a care plan, and a processing unit that performs specific processing using a generative AI model that generates output results according to an input sentence, wherein the processing unit is a data processing device that generates the care plan as a result of the specific processing based on the output of the generative AI model when the input sentence is text that instructs the processing of generating the care plan from the attribute information received by the reception unit.

[0006] A second aspect of the technology disclosed herein is a data processing method in which a computer receives attribute information of a person requiring support for creating a care plan, performs a specific process using a generative AI model that generates an output result according to an input sentence, and executes a process of generating the care plan as a result of the specific process based on the output of the generative AI model when the input sentence is text that instructs the process of generating the care plan from the received attribute information.

[0007] A third aspect of the technology disclosed herein is a data processing program for causing a computer to perform a process of receiving attribute information of a person requiring support for creating a care plan, performing a specific process using a generative AI model that generates an output result according to an input sentence, and generating the care plan as a result of the specific process based on the output of the generative AI model when the input sentence is text that instructs the process of generating the care plan from the received attribute information. [Brief explanation of the drawings]

[0008] [Figure 1] 1 illustrates an example of the configuration of a data processing system. [Figure 2] 1 shows an example of main functions of a data processing device and a user terminal. [Figure 3] 2 shows a schematic functional configuration of a specific processing unit of the data processing device. [Figure 4] 10 shows an example of an input screen for attribute information. [Figure 5] 10 shows an example of a screen for inputting question information. [Figure 6A] An example of a care plan is shown below. [Figure 6B] An example of a care plan is shown below. [Figure 7] 10 is a diagram illustrating an example of an operational flow of specific processing by a data processing device. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an example of an embodiment of a data processing device, a data processing method, and a program according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), or an APU (Accelerated Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] FIG. 1 shows an example of the configuration of a data processing system 10 according to the embodiment.

[0017] As shown in Fig. 1, the data processing system 10 includes a data processing device 12 and a user terminal 14. An example of the data processing device 12 is a server. An example of the user terminal 14 is a smartphone or a personal computer. In this embodiment, the data processing device 12 is an example of a "data processing device" according to the technology of the present disclosure.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The user terminal 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the person 20 by outputting the data in a form of expression that the person 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the user terminal 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a generative AI model 58. The generative AI model 58 is used by the specific processing unit 290.

[0026] The generative AI model 58 is a so-called generative AI (Artificial Intelligence). An example of the generative AI model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generative AI models. The generative AI model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the generative AI model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The generative AI model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0027] In the user terminal 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 62. The reception output program 62 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 62 from the storage 50 and executes the read reception output program 62 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 62 executed on the RAM 48.

[0028] Next, the processing of the specific processing unit 290 when the data processing device 12 performs the specific processing of generating a care plan for a person requiring support will be described.

[0029] Here, the care plan is a nursing care service plan created according to the situation and wishes of the person requiring care and their family. Furthermore, users of the user terminal 14 include, but are not limited to, the family of the person requiring support and the person requiring support themselves, and may also include a care manager of the person requiring support.

[0030] In the identification process of this embodiment, basic information from the attribute information of the person requiring support is received from the user terminal 14, and question information is generated using a generative AI model. A care plan is generated using the generative AI model based on the attribute information, including the answers to the question information and the basic information. That is, in the past, care plans were generally created by care managers. When creating a care plan, the care manager first interviews the person requiring support and their family and creates an assessment sheet. The care manager then creates the care plan based on the assessment sheet. Therefore, creating a care plan was time-consuming and burdensome for the care manager. Furthermore, due to a labor shortage in the nursing care industry, there was a demand for efficient creation of care plans. In the present disclosure, the use of a generative AI model enables this to be done efficiently.

[0031] As shown in FIG. 3, the specific processing unit 290 includes a receiving unit 292, a processing unit 294, and an output unit 296.

[0032] The receiving unit 292 receives input from the user received at the user terminal 14 . As shown in FIG. 4, first, a screen for inputting basic information from the attribute information of the support-requiring person output from the data processing device 12 is displayed on the user terminal 14. Then, the reception unit 292 receives the basic information of the support-requiring person input by the user through the reception device 38 on this screen. Here, the basic information includes gender, name, age, living situation, prescribed medications, type of allergy, state of physical function, cognitive function, medical history, general life issues to be resolved, and other special notes. For example, "female" is received as the gender. "Hanako Tanaka" is received as the name. "70 years old" is received as the age. "Living alone at home" is received as the living situation. "Insulin injections" is received as the prescribed medication. "Eggs" is received as the type of allergy. "Able to walk, but has difficulty standing for long periods" is received as the state of physical function. "Has mild dementia symptoms" is received as the cognitive function. "High blood pressure, diabetes" is received as the medical history. As for the general problem that people want to solve in their daily lives, they can say, "I tend to stay indoors, so I want to get stronger so I can get out and live a more cheerful life." As for other special notes, they can say, "My children live nearby." Note that the basic information is not limited to the above, and does not have to include all of the above.

[0033] In addition, the receiving unit 292 receives a response from the user to the output of the generative AI model when the input sentence is text that instructs the processing unit 294, described below, to generate question information necessary to receive attribute information.

[0034] The processing unit 294 first inputs text instructing the process of generating question information necessary to accept attribute information to the generation AI model as an input sentence, and outputs the question information output by the generation AI model to the user. Here, the input sentence (prompt) is a predetermined sentence, for example, "Please ask a question in chat format to create a care plan for the person requiring support with this basic information."

[0035] Specifically, as shown in FIG. 5 , the processing unit 294 displays, as question information, question information generated by the generative AI model, such as "Hello, I'm going to create a care plan for Hanako Tanaka. What would be the ideal outcome through care?" on the user terminal 14. In response to the question, the reception unit 292 receives a response from the user, such as "I want to strengthen my legs and be able to go out alone." The processing unit 294 inputs the response to the generative AI model, and further displays, as question information, question information generated by the generative AI model, such as "Got it. In order to strengthen my legs and be able to go out alone, where would you like to go first?" on the user terminal 14. In response to the question, the reception unit 292 receives a response from the user, such as "I want to be able to take a walk in a nearby park." The processing unit 294 inputs the response to the generative AI model, and further displays, as question information, question information generated by the generative AI model, such as "Got it. In order to gather other information necessary for the care plan, I'd like to ask you a few more questions first. Are there any situations in which you need support when going to the hospital or going out?" on the user terminal 14. In response to this question, the reception unit 292 receives the user's response of "Yes." The processing unit 294 then displays on the user terminal 14 the sentence "Thank you. Press the Finish button to create a care plan.", which is generated by the generation AI model when the generation AI model receives the response to the last question information. If the processing unit 294 receives a user operation of the Finish button 60, it generates a care plan. If the processing unit 294 receives a user operation of the Back button 61, it returns to the display for redoing the input of basic information shown in FIG. 4 or the display for redoing the input of the response to the first question information shown in FIG. 5.

[0036] Next, the processing unit 294 generates a care plan. Specifically, the processing unit 294 generates a care plan using the output of the generation AI model when a text instructing a process for generating a care plan from the received attribute information is used as an input sentence. Here, the input sentence (prompt) is a predetermined sentence, for example, "Please generate a care plan for the person requiring support with this attribute information." That is, the processing unit 294 creates attribute information that summarizes the basic information shown in FIG. 4 and the answers shown in FIG. 5, and generates a care plan using the attribute information as part of the input sentence (prompt).

[0037] The output unit 296 transmits the result of the identification process to the user terminal 14. In the user terminal 14, the control unit 46A causes the output device 40 to output the care plan as the result of the identification process.

[0038] A care plan is output for each task of the care plan, as shown in Figures 6A and 6B. For example, as shown in Figure 6A, the following task is generated for the care plan: "We want to improve the situation where the user has few social activities and tends to stay indoors." The long-term goal is generated: "Maintain physical and mental health by going out more and building social connections." The short-term goal is generated: "Improve the mobility required for going out and expand the range of activities at home." The service content is generated: "Support for interaction between users: Plan social gatherings and events for users to provide opportunities for social activities. Support for outdoor activities: Provide support while out and allow users to go out with peace of mind." The implementation period is generated as "one month." The risk management is generated as "Use walking aids and check safe routes to prevent falls and accidents when going out. When holding social gatherings and events, create reasonable programs taking into account the user's physical condition."

[0039] As shown in Figure 6B, the following is generated as the care plan issue: "The patient has difficulty standing for long periods of time, and we would like to suggest ways to strengthen his legs and hips." The following is generated as the long-term goal: "To be able to stand for long periods of time, and to improve his mobility in daily life." The following is generated as the short-term goal: "To strengthen the muscles of the legs and hips, and improve stability when standing up and walking." The following is generated as the service content: "Rehabilitation program: Training to strengthen the muscles of the legs and hips is carried out through individual instruction by specialized rehabilitation staff. Provision of healthy meals: A balanced diet is provided to ensure that the nutrients necessary to maintain physical strength are ingested." The implementation period is "3 months." The following is generated as the risk management: "To prevent injury during training, we will instruct the patient on appropriate posture and movements and create a safe environment. We will provide appropriate consultation on nutrition and health management, taking into account health risks due to dietary restrictions and drug interactions."

[0040] The generated care plan is not limited to the form shown in Figures 6A and 6B. For example, it may be in the form of a "Home Service Plan (1)," "Home Service Plan (2)," "Weekly Service Plan," or the like, which are standard care plans in Japan. In this case, input sentences (prompts) may be created so that the care plan is generated in the form of a "Home Service Plan (1)," "Home Service Plan (2)," "Weekly Service Plan," or the like.

[0041] Next, the operation of the data processing system 10 will be described.

[0042] An example of the flow of the identification process will be described with reference to Fig. 7. The flow of the identification process shown in Fig. 7 is an example of a "data processing method" according to the technique of the present disclosure.

[0043] In step S100, the reception unit 292 receives basic information about the support-requiring person input by the user operating the reception device 38. Then, the process proceeds to the next step, S101.

[0044] In step S101, the processing unit 294 inputs text instructing a process for generating question information necessary to receive attribute information based on the basic information received in step S100 described above as an input sentence (prompt) to the generative AI model. Then, the process proceeds to the next step S102.

[0045] In step S102, the processing unit 294 outputs to the user the question information that is output from the generative AI model as a result of input to the generative AI model in the above-mentioned step S101, and then the process proceeds to the next step S103.

[0046] In step S103, the accepting unit 292 accepts an answer from the user to the question information output in step S102, and then the process proceeds to the next step, S104.

[0047] In step S104, the processing unit 294 further inputs the answer received in step S103 into the generative AI model. Here, the processing from step S101 to step S104 is repeated until an answer to the last question information among the question information necessary to create a care plan is received. Then, the process proceeds to step S105.

[0048] In step S105, the processing unit 294 determines whether or not operation of the Complete button 60 has been accepted, and if it is determined that operation of the Complete button 60 has been accepted, the process proceeds to the next step S106. Note that if it is not determined that operation of the Complete button 60 has been accepted, but rather that operation of the Back button 61 has been accepted, the process returns to step S100 or step S102 described above.

[0049] In step S106, the processing unit 294 inputs text instructing the process of generating a care plan from the attribute information received in steps S100 and S103 as an input sentence (prompt) to the generative AI model, and then proceeds to step S107.

[0050] In step S107, the care plan generated by the generation AI model in step S106 described above is output by being displayed on the user terminal 14. Then, the specification process ends.

[0051] Note that the attribute information is not limited to the information input by the user as described above, but may also include personal health records obtained from other institutions, including medical institutions. The input sentence (prompt) to be input to the generation AI model may be, for example, "Please generate a care plan for the person requiring support whose attribute information includes this personal health record." That is, the processing unit 294 generates a care plan by including the personal health record as part of the input sentence (prompt) in addition to the attribute information that summarizes the basic information shown in FIG. 4 and the answers shown in FIG. 5.

[0052] Furthermore, the attribute information is not limited to the information input by the user as described above, but may also include measurement data received from a measurement device such as a blood pressure monitor or an electrocardiogram monitor. The input sentence (prompt) to be input to the generative AI model may be, for example, "Please generate a care plan for the person requiring support with the attribute information including this measurement data." That is, the processing unit 294 generates a care plan by incorporating the measurement results of the measurement device as part of the input sentence (prompt) in addition to the attribute information that summarizes the basic information shown in FIG. 4 and the answers shown in FIG. 5. The measurement data may be measurement data acquired by the data processing device 12 from a measurement device connected to the data processing system 10 via the network 54, or may be measurement data input by the user to the data processing device 12 using the user terminal 14. The measurement device may also include a device worn by the person requiring support, such as a smartwatch.

[0053] Furthermore, the processing unit 294 may generate materials explaining the generated care plan using the output of the generation AI model when the input sentence is text instructing a process for generating materials explaining the care plan. Here, the materials explaining the care plan include not only text information explaining the care plan but also a video that serves as a model for the person requiring support to act based on the care plan. For example, if the care plan includes exercise such as walking, a video that explains how to walk and serves as a model for the person requiring support to perform the same action may be displayed on the user terminal 14. Furthermore, a video (preview video) that explains the action before the person requiring support acts based on the care plan may be displayed on the user terminal 14.

[0054] Furthermore, the specific processing unit 290 may notify the user at predetermined intervals, for example, every three months, to prompt the user to update the attribute information, and update the care plan based on the new updated attribute information. When updating the care plan, the input sentence (prompt) to be input to the generation AI model may be, for example, "Please generate a care plan that takes into account changes between the previous attribute information and the current attribute information." That is, the processing unit 294 generates a care plan that reflects changes in the attribute information.

[0055] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 290, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[0056] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0057] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0058] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded in response to a request from the data processing device 12 and installed in the computer 22. The present invention may also be applied to a program product.

[0059] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0060] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0061] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[0062] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0063] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0064] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0065] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0066] The following additional notes are provided regarding the above-described embodiments. <Appendix 1> a reception unit that receives attribute information of a person requiring support for creating a care plan; a processing unit that performs specific processing using a generative AI model that generates an output result according to an input sentence, The processing unit A data processing device that generates the care plan as a result of the specified process by outputting the generative AI model when the input sentence is text that instructs the process of generating the care plan from the attribute information received by the reception unit.

[0067] <Appendix 2> The data processing device described in Appendix 1, wherein the attribute information is created using a user's response to the output of the generative AI model when the input sentence is text that instructs a process to generate question information necessary to accept the attribute information.

[0068] <Appendix 3> 3. The data processing device according to claim 1, wherein the attribute information includes a personal health record obtained from another institution, including a medical institution.

[0069] <Appendix 4> 4. The data processing device according to claim 1, wherein the attribute information includes measurement data received from a measurement device including a blood pressure monitor or an electrocardiogram.

[0070] <Appendix 5> The data processing device of any one of Appendix 1 to Appendix 4, wherein the processing unit generates the material using the output of the generative AI model when the input sentence is text that instructs the process of generating a material explaining the care plan based on the generated care plan.

[0071] <Appendix 6> A data processing device as described in Appendix 5, wherein the materials include a video that serves as a model for the person requiring support to act based on the care plan.

[0072] <Appendix 7> The computer Accepts attribute information of individuals requiring assistance to create care plans, Perform specific processing using a generative AI model that generates output results based on the input text, A data processing method that executes a process of generating the care plan as a result of the specified process by outputting the generative AI model when the input sentence is text that instructs the process of generating the care plan from the received attribute information.

[0073] <Appendix 8> On the computer, Accepts attribute information of individuals requiring assistance to create care plans, Perform specific processing using a generative AI model that generates output results based on the input text, A data processing program for executing a process of generating the care plan as a result of the specified process by outputting the generative AI model when the input sentence is text that instructs the process of generating the care plan from the received attribute information. [Explanation of symbols]

[0074] 10 Data Processing System 12 Data Processing Device 14 User terminal 290 Special Processing Department 292 Input section 294 Processing Section 296 Output Section< / url:>

Claims

1. a reception unit that receives attribute information of a person requiring support for creating a care plan; a processing unit that performs specific processing using a generation AI model that generates an output result according to an input sentence, The processing unit A data processing device that generates the care plan as a result of the specified process by outputting the generation AI model when the input sentence is text that instructs the process of generating the care plan from the attribute information received by the reception unit.

2. The data processing device according to claim 1, wherein the attribute information is created using a response from a user to the output of the generative AI model when the input sentence is text instructing a process to generate question information necessary to accept the attribute information.

3. The data processing device according to claim 1 , wherein the attribute information includes a personal health record obtained from another institution, including a medical institution.

4. The data processing device according to claim 1 , wherein the attribute information includes measurement data received from a measurement device including a blood pressure monitor or an electrocardiogram monitor.

5. The data processing device according to claim 1, wherein the processing unit generates the material based on the generated care plan using the output of the generative AI model when the input sentence is text that instructs the process of generating a material explaining the care plan.

6. The data processing device according to claim 5 , wherein the materials include a video that serves as a model for the person in need of support to act according to the care plan.

7. The computer Accepts attribute information of individuals requiring assistance to create care plans, Perform specific processing using a generative AI model that generates output results according to the input text, A data processing method that executes a process of generating the care plan as a result of the specified process by outputting the generative AI model when the input sentence is text that instructs the process of generating the care plan from the received attribute information.

8. On the computer, Accepts attribute information of individuals requiring assistance to create care plans, Perform specific processing using a generative AI model that generates output results according to the input text, A data processing program for executing a process of generating the care plan as a result of the specified process by outputting the generation AI model when the input sentence is text that instructs the process of generating the care plan from the received attribute information.

Images