Generation device and generation method

Abstract

A RAG system 20 according to the present disclosure comprises: an attribute acquisition unit 21 that acquires patient attribute information, which is attribute information pertaining to a subject patient including at least information relating to a dementia rank of the subject patient, and caregiver attribute information, which is attribute information pertaining to a subject caregiver; a guideline storage unit 28 in which guideline information indicating guidelines of advice for the caregiver are stored in advance in association with the dementia rank of the patient and the attributes of the caregiver; an information generation unit 26 that reads, from the guideline storage unit 28, the guideline information associated with the information relating to the dementia rank included in the patient attribute information acquired by the attribute acquisition unit 21 and the caregiver attribute information acquired by the attribute acquisition unit 21, and generates a prompt for requesting the generation of subject-patient-care-related advice information for the subject caregiver, the prompt including the guideline information; and an advice acquisition unit 27 that acquires the advice information by inputting the prompt to an interactive AI model 31.

Description

Generation Device and Generation Method 【0001】 One aspect of the present disclosure relates to a generation device and a generation method. 【0002】 In recent years, a dementia diagnosis support system that diagnoses the dementia level of patients and supports doctors has been used (see Patent Document 1 below). This dementia diagnosis support system refers to the electronic medical record information of the patient to identify the symptom level of dementia of the patient, and transmits questions according to the symptom level to the patient-side device. Further, the dementia diagnosis support system receives the information of the patient's answer from the patient-side device, and determines the correctness by comparing it with the correct information. 【0003】 Japanese Patent Application Laid-Open No. 2007-282992 【0004】 According to the above conventional dementia diagnosis support system, the correctness of the information of the patient's answer is determined. On the other hand, recently, an increase in the burden on caregivers of dementia patients has been regarded as a problem. Therefore, it is required to provide appropriate advice information to caregivers. 【0005】 Therefore, an object of the present disclosure is to provide a generation device and a generation method capable of generating appropriate advice information for caregivers of dementia patients. 【0006】 The generation device of the present disclosure includes an attribute acquisition unit that acquires first attribute information, which is attribute information of a target patient including at least information on the progression degree of dementia of the target patient, and second attribute information, which is attribute information of a target caregiver; a pointer storage unit that stores in advance pointer information indicating the advice guidelines for the caregiver in association with the progression degree of the patient's dementia and the attributes of the caregiver; an information generation unit that reads out the pointer information associated with the information on the progression degree of dementia included in the first attribute information acquired by the attribute acquisition unit and the second attribute information acquired by the attribute acquisition unit from the pointer storage unit, and generates input information that includes the pointer information and requests the generation of advice information regarding the care of the target patient for the target caregiver; and an advice acquisition unit that acquires advice information by inputting the input information into a generation AI model. 【0007】Alternatively, the generation method of the present disclosure is a generation method performed by a generation device, comprising: an attribute acquisition step of acquiring first attribute information which is attribute information of a target patient and which includes at least information regarding the progression of dementia of the target patient, and second attribute information which is attribute information of a target caregiver; a guideline storage step of pre-storing guideline information which indicates guidelines for advice to the caregiver, associating the progression of dementia of the patient with the attributes of the caregiver; an information generation step of reading from the information stored by the guideline storage step the guideline information which is associated with the information regarding the progression of dementia included in the first attribute information acquired by the attribute acquisition step and the second attribute information acquired by the attribute acquisition step, and generating input information which includes the guideline information and requests the generation of advice information regarding the care of the target patient to the target caregiver; and an advice acquisition step of acquiring advice information by inputting the input information into a generation AI model. 【0008】 According to one aspect of this disclosure, it is possible to generate appropriate advice information for caregivers of dementia patients. 【0009】 Figure 1 is a block diagram showing the configuration of the generation system of the present disclosure. Figure 2 is a diagram showing the data structure of the guideline information stored in the guideline storage unit 28 of Figure 1. Figure 3 is a flowchart showing the procedure for rank determination processing by the RAG system 20. Figure 4 is a flowchart showing the procedure for information provision processing by the RAG system 20. Figure 5 is a diagram showing an example of the hardware configuration of the RAG system 20 according to one embodiment of the present disclosure. Figure 6 is a block diagram showing the configuration of the generation system according to a modified example of the present disclosure. Figure 7 is a diagram showing the data structure of the history information stored in the history storage unit 29 of Figure 6. 【0010】 Embodiments of this disclosure will be described with reference to the attached drawings. Where possible, the same parts will be denoted by the same reference numerals, and redundant descriptions will be omitted. 【0011】Figure 1 is a diagram showing the device configuration of the generation system according to this embodiment. The generation system shown in Figure 1 includes terminals 10A and 10B, a RAG (Retrieval-Augmented Generation) system 20, and a server device 30, all configured to communicate with each other via a network including a wireless communication network and a fixed communication network. The RAG system 20 constitutes a generation device that provides care-related advice information to the user of terminal 10A. 【0012】 Terminal 10A is a device used by the user of the care recipient who seeks to obtain advice information using an interactive AI model. Terminal 10A can be, for example, a personal computer, smartphone, tablet, feature phone, server device, or game console. Although only one terminal 10A is shown in Figure 1, the generation system may include two or any number of terminals 10A. 【0013】 Terminal 10B is a device used by the user of the target patient who is being cared for by the target caregiver, who is also the user of Terminal 10A. Terminal 10B is a device similar to Terminal 10A, and any number of Terminal 10B may be included in the generation system. Also, Terminal 10A may also perform the functions of Terminal 10B. 【0014】 The server device 30 is a device that enables the provision of content using a generative AI model. A generative AI model is a model that, in response to input from a prompt containing input information, generates content according to one or a combination of the instructions, context, questions, and output format indicated by the prompt, and returns that content as response information. The prompt can also include input information, in which case the generative AI model generates response information targeting the input information. The generative AI model may be, for example, an interactive AI model that includes a Large Language Model (LLM) and a user interface (UI) for interaction with the user, enabling text chat or voice chat with the user. 【0015】The generative AI model used in this embodiment returns text-based response information in response to text-based prompt input. Examples of such generative AI models include ChatGPT, GPT®-3.5, GPT-3.5 Turbo, GPT-4.0, GPT-4.0 Turbo, Azure OpenAI Service, tsuzumi, GPT-4V, PaLM2, and the like. 【0016】 In this embodiment, the server device 30 enables the provision of content using an interactive AI model 31. This interactive AI model 31 may be stored within the server device 30, or it may be stored in another device connected to the server device 30 via a network, and configured to allow information exchange with the user via the server device 30. The interactive AI model 31 may also be stored within terminal 10A or terminal 10B. Although only one server device 30 is shown in Figure 1, the generation system may include multiple server devices 30. Furthermore, while the above description uses a large-scale language model as an example, other AI models may be used. In addition, the generation system may use an AI model selected from among multiple types of AI models. 【0017】 The RAG system 20 is composed of functional components including an attribute acquisition unit 21, a question generation unit 22, a dialogue control unit 23, a symptom determination unit 24, a guideline identification unit 25, an information generation unit 26, an advice acquisition unit 27, and a guideline storage unit 28. The RAG system 20 has a rank determination function that controls the dialogue with the target patient, who is the user of terminal 10B, to determine the degree of progression of the patient's dementia (dementia rank), and an information provision function that provides advice information to the target caregiver, who is the user of terminal 10A. The functions of each functional unit of the RAG system 20 will be described in detail below. 【0018】When the rank determination function is activated, the attribute acquisition unit 21 acquires patient attribute information (first attribute information) representing the attributes of the target patient from terminal 10A or terminal 10B, and passes the acquired patient attribute information to the question generation unit 22. The patient attribute information includes age, personality, past medical history, information on the degree of dementia progression (dementia rank) determined at a past point in time, and determination information used to determine the dementia rank at a past point in time (such as question information generated in the past). The attribute acquisition unit 21 may also acquire a part of the patient attribute information (for example, information on the dementia rank, question information, etc.) by reading history information stored in the RAG system 20 by the question generation unit 22 or the symptom determination unit 24. 【0019】 Furthermore, when the information provision function is activated, the attribute acquisition unit 21 acquires patient attribute information in the same manner as described above and passes the acquired patient attribute information to the guideline identification unit 25. In addition, when the information provision function is activated, the attribute acquisition unit 21 acquires caregiver attribute information (second attribute information) representing the attributes of the target caregiver from the terminal 10A and passes the acquired caregiver attribute information to the guideline identification unit 25. The caregiver attribute information includes information indicating the relationship between the target patient and the target caregiver (such as whether they live together or far away), personality, number of days the caregiver visits to care for the target patient, occupation, etc. The attribute acquisition unit 21 may also use the patient attribute information acquired when the rank determination function is activated when the information provision function is activated. 【0020】The question generation unit 22 generates question information for the target patient based on the patient attribute information received from the attribute acquisition unit 21 when the rank determination function is activated. The question generation unit 22 then stores the question information generated for the target patient as history information in the RAG system 20. For example, the question generation unit 22 creates a prompt that includes all or part of the patient attribute information and requests the generation of question information to be used when determining the dementia rank, inputs the created prompt to the interactive AI model 31, and obtains the question information as response information from the interactive AI model 31. The question information may be in text format, audio format, or image format. The prompt input to the interactive AI model 31 includes at least information regarding the target patient's dementia rank as input information. At this time, the question generation unit 22 may include in the prompt input to the interactive AI model 31 question information previously sent to the target patient from the dialogue control unit 23, and may also include information instructing the AI ​​model 31 to generate the same question information as previously sent for target patients with a high dementia rank. 【0021】 In addition to generating question information using the interactive AI model 31, the question generation unit 22 may also obtain question information corresponding to patient attribute information (such as information regarding dementia rank) from the database by referring to the database within the RAG system 20. 【0022】 When the rank determination function is activated, the dialogue control unit 23 controls the dialogue between the terminal 10B used by the target patient and the RAG system 20 using the question information generated by the question generation unit 22. The dialogue control may be performed by controlling the transmission and reception of text data, by controlling the transmission and reception of voice data, or by transmitting and receiving image data via video call, etc. Through the dialogue control, the dialogue control unit 23 acquires response information from the target patient in response to the question information, and passes the combination of the acquired response information and the question information to which the response information was based to the symptom determination unit 24. The response information, like the question information, may be in text format, voice format, or image format. 【0023】 The symptom determination unit 24 determines the dementia rank of the target patient based on the combination of question information and response information received from the dialogue control unit 23 when the rank determination function is activated. This determination function is implemented using a publicly known application program for dementia diagnosis using AI (Artificial Intelligence), etc. (see, for example, Internet URL: https: / / systems.nippontect.co.jp / products / onsei / , or Internet URL: https: / / prtimes.jp / main / html / rd / p / 000000011.000009514.html, etc.). The symptom determination unit 24 then stores the dementia rank (e.g., "I", "II", etc.) determined for the target patient as history information in the RAG system 20. 【0024】When the information provision function is activated, the guideline identification unit 25 reads out guideline information that indicates guidelines for generating advice for the target caregiver by referring to the guideline storage unit 28 based on the patient attribute information and caregiver attribute information acquired by the attribute acquisition unit 21. Figure 2 shows the data structure of the guideline information pre-stored in the guideline storage unit 28. The guideline storage unit 28 stores example advice sentences, which are guideline information, associated with information on dementia rank, which is one of the patient's attributes, information on dementia symptoms, which is another of the patient's attributes, and information indicating the caregiver's attributes. For example, the advice sentence example "Please try to be supportive and not deny what the patient is seeing. Also, please create an environment that is less likely to cause hallucinations, such as increasing the lighting in the patient's room..." is stored, associated with the dementia rank information "I", the symptom information "visual hallucinations", and the information indicating the caregiver's relationship with the patient "family member or friend living together". If the patient attribute information and caregiver attribute information acquired by the attribute acquisition unit 21 contain information that matches or is similar to the dementia rank information "I", the symptom information "visual hallucinations", and the information indicating the caregiver's relationship with the patient "living together", the guideline identification unit 25 reads out an example of advice text from the guideline storage unit 28 that corresponds to that information: "Please try to respond in a supportive manner without denying what the patient is seeing. Also, please create an environment that is less likely to cause visual hallucinations, such as increasing the lighting in the patient's room..." Then, the guideline identification unit 25 hands over the read-out example of advice text to the information generation unit 26. 【0025】When the information provision function is activated, the information generation unit 26 generates a prompt requesting the target caregiver to generate advice information regarding the care of the target patient, based on the patient attribute information and caregiver attribute information acquired by the attribute acquisition unit 21, and the example advice text, which is the guideline information read by the guideline identification unit 25. For example, the input information to be included in the prompt by the information generation unit 26 includes information indicating who the advice information is for, instructions to generate advice information by referring to the example advice text, and information specifying the granularity of the advice information. Below is an example of a prompt generated by the information generation unit 26. <Prompt Example> Role: Doctor diagnosing dementia Task: Generate advice text regarding dementia care according to the conditions. Conditions: The target caregiver is a family member living together, and the target patient is currently dementia rank I. Example Advice Text: Please generate advice text referring to "Please be mindful of responding in a supportive manner without denying what the patient is seeing. Also, please create an environment that is less likely to cause hallucinations, such as increasing the lighting in the patient's room..." Please generate the advice text so that the granularity of the information is between 200 and 300 characters. <End of Prompt Example> 【0026】 As shown in the prompt above, the information generation unit 26 generates a prompt that includes information specifying the granularity of the advice information. That is, the information generation unit 26 refers to the history information regarding dementia rank stored in the RAG system 20 to detect the change from past dementia rank information to current dementia rank information for the target patient, and includes an instruction in the prompt to change the granularity of the information according to that change. More specifically, if the dementia rank changes from "II" to "III", the information generation unit 26 includes an instruction in the prompt to set the granularity of the information to "200 characters or more and 300 characters or less". 【0027】The advice acquisition unit 27 inputs the prompt generated by the information generation unit 26 to the interactive AI model 31 and acquires advice information as response information from the interactive AI model 31. The advice acquisition unit 27 then transmits the acquired advice information to the terminal 10A. The advice acquisition unit 27 may also store the acquired advice information in the RAG system 20 so that it can be accessed by external devices such as the terminal 10A. 【0028】 The procedure for rank determination processing and information provision processing by the RAG system 20 configured as described above, that is, the flow of the generation method according to this embodiment, will now be explained. Figure 3 is a flowchart showing the procedure for rank determination processing by the RAG system 20, and Figure 4 is a flowchart showing the procedure for information provision processing by the RAG system 20. 【0029】 In response to receiving instruction information from an external device such as terminal 10A, the rank determination function is activated and the rank determination process is executed. Referring to Figure 3, when the rank determination process is started, first, the attribute acquisition unit 21 of the RAG system 20 acquires patient attribute information representing the attributes of the target patient (step S101). Next, the question generation unit 22 generates question information targeting the target patient based on the patient attribute information (step S102). 【0030】 Subsequently, the dialogue control unit 23 controls the dialogue with the target patient using the question information, and the symptom determination unit 24 determines the dementia rank of the target patient based on the results of the dialogue (step S103). As a result, the symptom determination unit 24 stores the dementia rank determination history as history information in the RAG system 20 (step S104). 【0031】 Referring to Figure 4, when information provision processing is started in response to the receipt of instruction information from an external device, first, the attribute acquisition unit 21 acquires patient attribute information and caregiver attribute information representing the attributes of the caregiver (step S201). Next, the guideline identification unit 25 reads out example advice sentences corresponding to the dementia rank information and caregiver attribute information from the guideline storage unit 28 (step S202). 【0032】Subsequently, the information generation unit 26 generates a prompt including an example of advice text using patient attribute information and caregiver attribute information (step S203). Furthermore, the advice acquisition unit 27 inputs the prompt generated by the information generation unit 26 to the interactive AI model 31 (step S204). Accordingly, the advice acquisition unit 27 acquires response information including advice text from the interactive AI model 31 (step S205). Finally, the advice acquisition unit 27 outputs the acquired response information to the terminal 10A (step S206). 【0033】 Next, the effects of the generation device of this disclosure will be explained. According to the RAG system 20 of this disclosure, a guideline is determined that is suitable for the combination of the dementia rank of the target patient and the attributes of the target caregiver, and advice information for the target caregiver is generated based on that guideline. As a result, it is possible to generate advice information that corresponds to the symptoms of dementia and the attributes of the caregiver, and appropriate advice information can be generated for caregivers of dementia patients. 【0034】 In the RAG system 20 of this disclosure, the attribute acquisition unit 21 acquires information regarding the dementia rank determined based on response information from the target patient. This makes it possible to acquire information regarding the progression of dementia without burdening the target patient, and as a result, it is possible to generate appropriate advice information for the caregiver of the dementia patient without burdening the target patient. 【0035】 Furthermore, the RAG system 20 of this disclosure is further equipped with a question generation unit 22 that generates question information for the target patient, and an attribute acquisition unit 21 acquires information on the dementia rank determined based on the response information received from the target patient in response to the question information. In this case, information on the progression of dementia can be obtained without burdening the system operator, and as a result, appropriate advice information can be generated for the caregiver of the dementia patient without burdening the system operator. 【0036】Furthermore, in the RAG system 20 of this disclosure, the question generation unit 22 generates question information based on the attributes of the target patient. This allows for efficient acquisition of information regarding dementia rank, and as a result, more appropriate advice information can be generated for caregivers of dementia patients. 【0037】 Furthermore, in the RAG system 20 of this disclosure, the information generation unit 26 detects changes in the current dementia rank information from information on the dementia rank of the target patient acquired in the past, and includes a prompt that instructs the system to change the granularity of the information according to the change. With this configuration, it is possible to generate advice information for caregivers with varying amounts of information according to changes in the patient's dementia rank, thereby providing caregivers with useful advice information. 【0038】 The generating apparatus and generating method of this disclosure have the following configuration. 【0039】 [1] A generation device comprising: an attribute acquisition unit that acquires first attribute information which is attribute information of the target patient and which includes at least information regarding the progression of the patient's dementia, and second attribute information which is attribute information of the target caregiver; a guideline storage unit that stores in advance guideline information which indicates guidelines for advice to the caregiver, corresponding to the progression of the patient's dementia and the caregiver's attributes; an information generation unit that reads the guideline information which is corresponding to the information regarding the progression of dementia included in the first attribute information acquired by the attribute acquisition unit and the second attribute information acquired by the attribute acquisition unit from the guideline storage unit, and generates input information which includes the guideline information and requests the generation of advice information regarding the care of the target patient to the target caregiver; and an advice acquisition unit that acquires the advice information by inputting the input information into a generation AI model. 【0040】 [2] The generation apparatus according to [1] above, wherein the attribute acquisition unit acquires information regarding the progression determined based on the response information from the target patient. 【0041】[3] The generation device according to [2] above, further comprising a question generation unit that generates question information for the target patient, wherein the attribute acquisition unit acquires information regarding the degree of progression determined based on the response information responded by the target patient to the question information. 【0042】 [4] The generation device according to [3] above, wherein the question generation unit generates the question information based on the attributes of the target patient. 【0043】 [5] The generation device according to any one of [1] to [4] above, wherein the information generation unit detects a change in the information regarding the current degree of progression from the information regarding the degree of progression of the target patient acquired in the past, and includes an instruction to change the granularity of the information according to the change in the input information. 【0044】 [6] The generation device according to any one of [1] to [5] above, wherein the information generation unit specifies the guideline information included in the input information in the past for a patient and a caregiver having a relationship similar to the relationship between the target patient and the target caregiver, and includes the specified guideline information in the input information. 【0045】 [7] A generation method executed by a generation device, comprising: an attribute acquisition step of acquiring first attribute information which is attribute information of the target patient including at least information regarding the degree of progression of dementia of the target patient, and second attribute information which is attribute information of the target caregiver; a guideline storage step of pre-storing guideline information indicating guidelines for advice to the caregiver in association with the degree of progression of dementia of the patient and the attributes of the caregiver; an information generation step of reading out the guideline information associated with the information regarding the degree of progression of dementia included in the first attribute information acquired by the attribute acquisition step and the second attribute information acquired by the attribute acquisition step from the information stored by the guideline storage step, and generating input information including the guideline information and requesting generation of advice information regarding care of the target patient for the target caregiver; and an advice acquisition step of acquiring the advice information by inputting the input information into a generation AI model. 【0046】The block diagram used in the description of the above embodiment shows functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may be realized by combining the one or more devices with software. 【0047】 Functions include, but are not limited to, judgment, decision, determination, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited. 【0048】For example, the RAG system 20 that constitutes the generation device in one embodiment of the present disclosure may function as a computer that performs the processing of the generation method of the present disclosure. FIG. 5 is a diagram showing an example of the hardware configuration of the RAG system 20 according to one embodiment of the present disclosure. The above-mentioned RAG system 20 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like. Note that the RAG system 20 may be configured as a computer device including at least one processor such as a CPU or a GPU, may be configured as a computer device including a plurality of processors, or may be configured including a plurality of computer devices. The terminal 10A, the terminal 10B, and the server device 30 may also have a similar hardware configuration. 【0049】 In the following description, the term "device" can be read as a circuit, a device, a unit, or the like. The hardware configuration of the RAG system 20 may be configured to include one or more of each device shown in the figure, or may be configured without including some devices. 【0050】 Each function in the RAG system 20 is realized by causing the processor 1001 to read a predetermined software (program) onto hardware such as the processor 1001 and the memory 1002, so that the processor 1001 performs calculations and controls communication by the communication device 1004, or controls at least one of reading and writing data in the memory 1002 and the storage 1003. 【0051】 The processor 1001 controls the entire computer by operating an operating system, for example. The processor 1001 may be constituted by a central processing unit (CPU: Central Processing Unit) including an interface with peripheral devices, a control device, an arithmetic device, a register, and the like. For example, the above-mentioned attribute acquisition unit 21, question generation unit 22, dialogue control unit 23, symptom determination unit 24, pointer identification unit 25, information generation unit 26, advice acquisition unit 27, and the like may be realized by the processor 1001. 【0052】 Furthermore, the processor 1001 reads programs (program code), software modules, data, etc., from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, the attribute acquisition unit 21, the question generation unit 22, the dialogue control unit 23, the symptom determination unit 24, the guideline identification unit 25, the information generation unit 26, and the advice acquisition unit 27 may be implemented by a control program stored in the memory 1002 and operated on the processor 1001, and other functional blocks may be implemented similarly. The above-described various processes have been explained as being executed by one processor 1001, but they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may also be transmitted from a network via a telecommunications line. 【0053】 The memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may also be called a register, cache, main memory, etc. The memory 1002 can store executable programs (program code), software modules, etc., for carrying out the generation method according to one embodiment of the present disclosure. 【0054】The storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital multipurpose disc, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. The storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including at least one of memory 1002 and storage 1003. 【0055】 The communication device 1004 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include, for example, a high-frequency switch, duplexer, filter, frequency synthesizer, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the attribute acquisition unit 21, dialogue control unit 23, advice acquisition unit 27, etc., described above may be implemented by the communication device 1004. 【0056】 The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel). 【0057】Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device. 【0058】 Furthermore, the RAG system 20 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components. 【0059】 Information notification is not limited to the embodiments described herein and may be carried out by other means. For example, information notification may be carried out by physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, broadcast information (MIB (Master Information Block), SIB (System Information Block))), other signals, or combinations thereof. RRC signaling may also be called RRC messages, and may be, for example, RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc. 【0060】The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented. 【0061】 Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be transmitted to other devices. 【0062】 The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value). 【0063】 Each aspect / embodiment described in this disclosure may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification). 【0064】 Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Accordingly, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way. 【0065】 The generation system 1 is not limited to the configuration shown in Figure 1 above. Figure 6 shows the configuration of generation system 1A according to a modified example of the present disclosure. Generation system 1A differs from generation system 1 in that the RAG system 20 is equipped with a history storage unit 29 and the functions of the information generation unit 26A are added. 【0066】In the RAG system 20, the history storage unit 29 stores history information related to the guideline information previously generated by the information generation unit 26A, and the information generation unit 26A refers to the history storage unit 29 and adds the guideline information to the prompt. Figure 7 shows an example of the data structure of the history information stored in the history storage unit 29. In this way, the history storage unit 29 stores example advice sentences that were previously decided for the target caregiver and included in the prompt, in association with information indicating the personality, which is one of the target patient's attribute information; information indicating the personality, which is one of the target caregiver's attribute information; information indicating the relationship with the patient, which is one of the target caregiver's attribute information; and information indicating the number of visits, which is one of the target caregiver's attribute information. For example, the history storage unit 29 stores an example advice sentence, "Please try to respond empathetically without denying what the patient is seeing. Also, please create an environment that is less likely to cause hallucinations, such as increasing the lighting in the patient's room..." in association with the target patient's personality "sensitive", the target caregiver's personality "gentle", relationship "living together", and number of care visits "30 days". 【0067】 The information generation unit 26A extracts combinations of attribute information similar to the attributes of the target patient and target caregiver who are the subject of the information provision processing from the history information stored in the history storage unit 29, and identifies example advice sentences associated with the extracted combinations of attribute information. For example, the information generation unit 26A extracts a specific number of history information entries with high similarity in the combinations of attribute information. Then, the information generation unit 26 adds the identified multiple example advice sentences as policy information to the prompt. As a result, the RAG system 20 can include policy information previously decided for patients and caregivers who have a relationship similar to the relationship between the target patient and target caregiver in the prompt. 【0068】 According to the above modification, consistent advice information can be generated for all users, including patients and caregivers. 【0069】Furthermore, in the generation systems 1 and 1A described above, the RAG system 20 may be implemented in terminal 10A or terminal 10B. This configuration can be achieved by installing an application that performs the functions of the RAG system 20 in terminal 10A or terminal 10B. Also, although Figures 1 and 6 show an example in which the pointer storage unit 28 is implemented within the RAG system 20, the pointer storage unit 28 may be implemented in terminal 10A or terminal 10B. 【0070】 Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name. 【0071】 Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technologies (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium. 【0072】 The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof. 【0073】In addition, terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of the channel and symbol may be a signal (signaling). Also, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, cell, frequency carrier, etc. 【0074】 Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a given value, or other corresponding information. For example, wireless resources may be indicated by an index. 【0075】 The names used for the parameters described above are not restrictive in any way. Furthermore, the formulas and other expressions using these parameters may differ from those expressly disclosed in this disclosure. Various channels (e.g., PUCCH, PDCCH, etc.) and information elements can be identified by any suitable name, and therefore, the various names assigned to these various channels and information elements are not restrictive in any way. 【0076】 In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably. 【0077】 A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other appropriate term. 【0078】As used in this disclosure, the terms “determining” and “determining” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, or inquiring (e.g., searching in a table, database, or other data structure), or ascertaining. “Determining” may also include, for example, receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, or accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having been "judged" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having been "judged" or "decided" after some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering." 【0079】The terms “connected,” “coupled,” or any variation thereof, mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables, and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain. 【0080】 In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on." 【0081】 Any reference to elements using designations such as “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to first and second elements do not imply that only two elements may be employed, or that the first element must precede the second element in any way. 【0082】 Where the terms “include,” “including,” and their variations are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to be exclusive OR. 【0083】In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural. 【0084】 In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different." 【0085】 10A, 10B... Terminals, 20... RAG system, 30... Server device, 31... Interactive AI model, 21... Attribute acquisition unit, 22... Question generation unit, 26, 26A... Information generation unit, 27... Advice acquisition unit, 28... Guideline storage unit.

Claims

1. A generation device comprising: an attribute acquisition unit that acquires first attribute information which is attribute information of the target patient and which includes at least information regarding the progression of the patient's dementia, and second attribute information which is attribute information of the target caregiver; a guideline storage unit that stores guideline information indicating guidelines for advice to the caregiver, corresponding to the progression of the patient's dementia and the caregiver's attributes; an information generation unit that reads the guideline information, which is corresponding to the information regarding the progression of dementia included in the first attribute information acquired by the attribute acquisition unit and the second attribute information acquired by the attribute acquisition unit, from the guideline storage unit and generates input information which includes the guideline information and requests the generation of advice information regarding the care of the target patient to the target caregiver; and an advice acquisition unit that acquires the advice information by inputting the input information into a generation AI model.

2. The generation apparatus according to claim 1, wherein the attribute acquisition unit acquires information regarding the degree of progression determined based on the response information from the target patient.

3. The generation apparatus according to claim 2, further comprising a question generation unit that generates question information for the target patient, wherein the attribute acquisition unit acquires information regarding the progression of the disease determined based on the response information received from the target patient in response to the question information.

4. The generation apparatus according to claim 3, wherein the question generation unit generates the question information based on the attributes of the target patient.

5. The generation apparatus according to claim 1, wherein the information generation unit detects a change in the current information regarding the progression of the patient from information regarding the progression of the patient acquired in the past, and includes an instruction in the input information to change the granularity of the information according to the change.

6. The generation apparatus according to claim 1, wherein the information generation unit identifies the guideline information previously included in the input information with respect to patients and caregivers having a relationship similar to the relationship between the target patient and the target caregiver, and includes the identified guideline information in the input information.

7. A generation method performed by a generation device, comprising: an attribute acquisition step of acquiring first attribute information which is attribute information of a target patient and which includes at least information regarding the progression of dementia of the target patient, and second attribute information which is attribute information of a target caregiver; a guideline storage step of pre-storing guideline information which indicates guidelines for advice to a caregiver, corresponding to the progression of dementia of the patient and the attributes of the caregiver; an information generation step of reading the guideline information which is associated with the information regarding the progression of dementia included in the first attribute information acquired by the attribute acquisition step and the second attribute information acquired by the attribute acquisition step from the information stored by the guideline storage step, and generating input information which includes the guideline information and requests the generation of advice information regarding the care of the target patient to the target caregiver; and an advice acquisition step of acquiring the advice information by inputting the input information into a generation AI model.

Images