Generation device and generation method

Abstract

This generation device comprises: a reception unit that receives information related to a user's illness and information related to the determination of the user's medical level; a determination unit that determines the user's medical level on the basis of the information related to the determination of the user's medical level; a generation unit that, on the basis of the user's medical level, generates a prompt for instructing generation of user browsing information according to the information related to the user's illness; and a control unit that controls a generative AI model for generating the user browsing information on the basis of the prompt generated by the generation unit.

Description

Generation device and generation method

[0001] One aspect of the present disclosure relates to a generating device and a generating method.

[0002] Patent document 1 discloses calculating the importance of comment transmission, which indicates the degree to which a doctor should respond to a patient, based on patient information transmitted from a patient terminal; transmitting the patient information and the importance of comment transmission to a doctor terminal in response to a request to view the patient information; and transmitting comments entered from the doctor terminal to a patient terminal via the Internet.

[0003] JP 2008-47035 A

[0004] While the technology described above allows patients to view doctor comments on their own devices, it is difficult to provide information that is appropriate for the patient's level of understanding. This can result in one-way communication from the doctor. This is one of the reasons why health literacy on the patient side has not been sufficiently improved.

[0005] One aspect of the present disclosure has been made in consideration of the above-mentioned situation, and aims to provide a generation device and a generation method that can contribute to improving patients' health literacy.

[0006] A generation device according to one aspect of the present disclosure includes a reception unit that receives information regarding a user's illness and information regarding the user's medical level assessment, a determination unit that determines the user's medical level based on the information regarding the user's medical level assessment, a generation unit that generates a prompt to instruct the generation of user viewing information corresponding to the information regarding the user's illness based on the user's medical level, and a control unit that controls a generation AI model that generates user viewing information based on the prompt generated by the generation unit.

[0007] A generating device according to one aspect of the present disclosure determines a user's medical level based on information related to the user's medical level determination, and generates a prompt that instructs the user to generate user browsing information corresponding to information about the user's illness based on the determined level. With this configuration, the user's medical level is determined, and a prompt that generates user browsing information corresponding to information about the user's illness is generated taking the determined level into consideration. Therefore, a generating AI model is controlled based on the prompt, and user browsing information corresponding to information about the user's illness is generated while taking the user's medical level into consideration. In this way, generating user browsing information taking into consideration the user's medical level allows information disclosure appropriate to the user's level. This allows information disclosure that is understandable to the user, and allows information from doctors and others to be appropriately conveyed to the user. By disclosing information in this manner on a daily basis, the user's (patient's) health literacy can be improved. As described above, the generating device according to one aspect of the present disclosure can contribute to improving patients' health literacy.

[0008] According to one aspect of the present disclosure, it is possible to contribute to improving the health literacy of patients.

[0009] FIG. 1 is a diagram showing the device configuration of a browsing information output system according to this embodiment. FIG. 2 is a diagram showing an example of a prompt generated by the RAG system. FIG. 3 is a table showing an example of a rewrite table stored in a storage unit. FIG. 4 is a diagram explaining user browsing information output from a generative AI model. FIG. 5 is a flowchart showing processing executed by the RAG system. FIG. 6 is a diagram showing an example of the hardware configuration of the RAG system.

[0010] The present disclosure will be described with reference to the accompanying drawings. Whenever possible, the same parts are designated by the same reference numerals and redundant description will be omitted.

[0011] FIG. 1 is a diagram illustrating the device configuration of a browsing information output system according to this embodiment. The browsing information output system illustrated in FIG. 1 outputs browsing information related to a user's illness in response to an output request from the user. Specifically, the browsing information output system outputs browsing information (text information, illustrations, etc.) appropriate for the user's level based on information about the user's illness and information related to the user's medical level assessment. In the browsing information output system, prompts generated by the RAG system 20 are input into the generation AI model 31, which then outputs the browsing information described above. By presenting browsing information appropriate for the user's level to the user, information disclosure that is understandable to the user can be provided, enabling information from doctors and other professionals to be appropriately conveyed to the user. Such information disclosure on a daily basis can ultimately improve the health literacy of users (patients). In other words, providing information that is understandable to users improves their ability to "obtain," "understand," "evaluate," and "utilize" correct health and medical information (improving health literacy), contributing to the maintenance and promotion of their health and disease prevention.

[0012] 1, the browsing information output system includes a terminal 10, a storage device 15, a Retrieval-Augmented Generation (RAG) system 20, and a server device 30, which are configured to be able 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 generates a prompt based on information received from the terminal 10. A prompt is information indicating an instruction or question input to an AI model in an interactive system such as a dialogue with an AI model or a command line interface (CLI).

[0013] The terminal 10 is a device used by a user (programmer) who is performing programming. The terminal 10 is, for example, a personal computer, a smartphone, a tablet terminal, a feature phone, a server device, a game console, or the like. Note that while only two terminals 10 are illustrated in FIG. 1 , the browsing information output system may include any number of terminals 10, two or more.

[0014] The storage device 15 is a server device that stores questionnaire information for multiple users. The questionnaire information is information indicating the results of a questionnaire regarding the medical level assessment of the user. The details of the questionnaire information will be described later.

[0015] The server device 30 is a device that stores a generative AI model 31 and enables the provision of questions or answers to a user using the generative AI model 31. The generative AI model is a model that, in response to the input of a prompt including input information, generates content according to any one or a combination of the instructions, context, question, and output format indicated by the prompt, and returns the content as response information. The prompt may also include input information, in which case the generative AI model 31 generates response information targeted at the input information. The generative AI model 31 may be, for example, an interactive AI that includes a large language model (LLM) and a user interface (UI) for interacting with the user, enabling text or voice chat with the user. Examples of such generative AI models include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, PaLM2, etc. In this embodiment, an example is described in which the server device 30 provides questions and the like using one generative AI model 31, but the server device 30 may provide questions and the like using multiple generative AI models. Also, while only one server device 30 is illustrated in FIG. 1 , the browsing information output system may include multiple server devices 30. Also, while the above describes an example of a large-scale language model, other AI models may also be used. The generative AI model 31 generates browsing information (user browsing information) to be viewed by the user based on the prompt.

[0016] The RAG system 20 includes, as functional components, a reception unit 21, a determination unit 22, a generation unit 23, an input unit 24 (control unit), and a storage unit 25. The RAG system 20 inputs a prompt corresponding to input information from the terminal 10 to the server device 30, and relays response information from the server device 30 to the prompt to the terminal 10. The RAG system 20 also has a function to generate a prompt based on input information from the terminal 10. The functions of each functional unit of the RAG system 20 will be described in detail below.

[0017] The reception unit 21 receives a request from a user to generate browsing information including information about the user's illness. The reception unit 21 receives the generation request from the user, for example, via the terminal 10. The information about the user's illness may be any information related to the user's illness or health, and may include, for example, at least one of the name of the illness, information indicating the user's health-related desires (e.g., a desire to maintain one's figure), and information about the user's attributes. The information about the user's attributes may be, for example, the user's age, weight, treatment status (information indicating whether the user is undergoing treatment), etc.

[0018] The reception unit 21 receives information regarding the user's medical level assessment from the storage device 15. The medical level can be, for example, rephrased as the health literacy level. The information regarding the user's medical level assessment may be, for example, information based on the results of a questionnaire administered to the user in advance. The questionnaire may be, for example, a questionnaire based on the Health Locus of Control (HLC) scale. HLC is a concept based on the Locus of Control, which classifies whether the cause of an evaluation of health behavior is attributed to oneself or others. The questionnaire may also be based on, for example, the questions in the HLS-EU-Q47. The HLS-EU-Q47 measures the four health literacy abilities of "acquisition," "understanding," "evaluation," and "utilization" across three areas: "healthcare," "disease prevention," and "health promotion." The questionnaire may contain any information that enables a medical level assessment (health literacy level assessment).

[0019] The reception unit 21 may receive, as information related to the user's medical level assessment, information about the user's personality from, for example, the terminal 10. Such information about personality may be information obtained by, for example, a personality estimation AI provided by a telecommunications carrier.

[0020] The reception unit 21 may receive (acquire) each of the above-mentioned information from either the terminal 10 or the storage device 15, or may receive the information from a source other than the terminal 10 or the storage device 15. The reception unit 21 outputs the received information to the determination unit 22.

[0021] The determination unit 22 determines the user's medical level based on the information regarding the user's medical level determination received by the reception unit 21. The determination unit 22 may, for example, determine which of several levels the user falls into. The several levels may be, for example, Level 1: insufficient health literacy, Level 2: slightly insufficient health literacy, Level 3: sufficient health literacy, Level 4: good health literacy, etc. The determination unit 22 may, for example, calculate a standardized index of 0 to 50 points from the responses to 47 items based on the results of the HLS-EU-Q47, and classify a standardized index of 0-25 as Level 1, 25-33 as Level 2, 33-42 as Level 3, and 43-50 as Level 5, etc. Note that the above four levels are merely examples, and three additional levels or five or more levels may be used.

[0022] The determination unit 22 may determine the user's level of medical literacy as a score. The determination unit 22 may calculate a score of 0 to 50 points from the answers to 47 items based on the results of the HLS-EU-Q47. Furthermore, when using the results of the HLS-EU-Q47, the determination unit 22 may calculate scores for the four health literacy abilities of "acquisition," "understanding," "evaluation," and "utilization," and for the three areas of "healthcare," "disease prevention," and "health promotion."

[0023] The determination unit 22 may determine whether the individual is Type 1 (internal control type) or Type 2 (external control type) based on the results of a questionnaire based on the HLC (Health Locus of Control) scale, and perform a level determination. The internal control type is a type in which the individual attributes the cause of their insurance behavior evaluation to themselves. The external control type is a type in which others attribute the cause of their insurance behavior evaluation to external factors. The determination unit 22 may, for example, determine the individual as Type 1 if seven or more of the 14 HLC items are marked with a "yes" and as Type 2 if six or fewer of the 14 HLC items are marked with a "yes" and perform a level determination using the internal control items and the external control items. The determination unit 22 may also perform a score based on the number of "yes" in the HLC (the score is determined so that the greater the number of "yes," the closer the individual is to Type 1). The determination unit 22 may perform a type determination using the internal control items and the external control items, or may perform weighting based on whether the item is internal control or external control, or may perform separate scores for the internal control items and the external control items.

[0024] The generation unit 23 generates a prompt to instruct the generation of browsing information (user browsing information) corresponding to information about the user's illness based on the user's level of medical care. The prompt expresses, in text, for example, commands to be executed by the generation AI model 31 (interactive AI model), tasks to be executed by the generation AI model 31, background / context (e.g., roles, conditions) to be considered by the generation AI model 31, questions to be answered by the generation AI model 31, and the output format of response information from the generation AI model 31. The prompt may also include input information to be used as the target of commands / tasks to be executed by the generation AI model 31. Examples of such input information include data files with file names including a predetermined extension, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data is data such as document data, table data, and graph data that can be processed by a default application program.

[0025] Fig. 2 is a diagram showing an example of a prompt generated by the RAG system 20. The prompt shown in Fig. 2 specifies a task, input information, an example, an output format, and an output image.

[0026] The task is information that indicates an outline of the command content for the generation AI model 31, and in this case, it is specified as "Please create a leaflet based on the input text." A leaflet is an example of viewing information.

[0027] The input information is input information used in creating the leaflet (viewing information). Here, "disease details," "attribute information," and "papers / official documents" are defined. Of these pieces of information, the disease details (disease name) and attribute information are information accepted by the accepting unit 21 as information about the user's illness. Furthermore, the papers / official documents may be information accepted by the accepting unit 21 on a case-by-case basis, or may be predetermined information.

[0028] The examples are example data of output content (information included in the browsing information) for each medical level. In the example shown in FIG. 2, the level, technical terms, and general terms are linked to each other in the examples. This shows how to rewrite (replace) specific technical terms with general terms depending on the level. In this way, the generation unit 23 may generate a prompt that specifies examples of user browsing information for each medical level of the user.

[0029] To realize the example shown in FIG. 2 , for example, the storage unit 25 stores predetermined rewriting information. FIG. 3 is a table illustrating an example of a rewriting table stored in the storage unit 25. In the example shown in FIG. 3 , the rewriting table associates disease, level, technical term, and general term. In the example shown in FIG. 3 , disease: common, level: 1, technical term: KT, and general term (rewritten term): body temperature are defined. In this way, the storage unit 25 stores a rewriting table (rewriting information) that associates technical terms with general terms that generalize the technical terms for easy understanding, for each medical level of the user. The rewriting table defines rewriting to easier (more general) terms for lower levels. In this case, the generation unit 23 generates a prompt that defines examples of rewriting technical terms to general terms for each medical level of the user based on the rewriting information stored in the storage unit 25. Note that the examples defined in the prompt are not limited to those described above. It is sufficient that the medical level is linked to some output content (information included in the browsing information).

[0030] The output format is information indicating the display format of the leaflet (viewed information). In the example shown in Figure 2, illustrations, quizzes, and checklists are specified. Other output formats may also be specified, such as Q&A and medical questionnaires. The illustrations are, for example, graphs related to text information included in the viewed information, or images that complement the text information. The quiz is, for example, a quiz to deepen the user's understanding of illness. The checklist is, for example, a section with checkboxes so that the user can check points that they should pay attention to regarding the illness. The checklist may also be a checklist for determining whether or not the user is prone to illness. The Q&A is, for example, a section with questions that the user can answer and the answers to those questions. The medical questionnaire is, for example, a section equivalent to a medical questionnaire regarding the user's illness.

[0031] The output image is an image file showing an image of the leaflet (viewing information) output from the generative AI model 31. An actual image file may be exemplified as the output image.

[0032] The generation unit 23 determines whether illustrations are necessary based on the user's level of medical care, and if illustrations are necessary, generates a prompt that instructs the generation of viewing information including illustrations related to information about the user's illness. The generation unit 23 may generate the prompt by determining, for example, that if the user is at level 3 or higher, the health literacy level is high and therefore illustrations are not necessary, and that if the user is at level 2 or lower, the health literacy level is low and therefore illustrations are necessary.

[0033] The generation unit 23 may generate a prompt so that the output format changes based on the treatment status of the user accepted by the acceptance unit 21. Specifically, the generation unit 23 may generate a prompt that instructs the user to generate viewing information including a checklist that lists points to note during treatment when the user is undergoing treatment. Furthermore, the generation unit 23 may generate a prompt that instructs the user to generate viewing information including a medical questionnaire when the user is not undergoing treatment.

[0034] The generation unit 23 may generate a prompt that instructs the user to generate viewing information including information introducing health-related services or programs, based on the information on the user's attributes received by the reception unit 21. Specifically, for example, for a user who can use employee benefits provided by the company where the user works, the generation unit 23 may generate a prompt to describe the available employee benefit programs. The generation unit 23 may also use the medical level to change the granularity of the information to be introduced. For example, the generation unit 23 may generate a prompt to describe only the name of the program when the user's medical level is high, and to describe the benefits of the program and how to use it when the user's level is average or below.

[0035] The generation unit 23 may generate a prompt that instructs the user to generate viewing information including information introducing exercise, diet, lifestyle habits, etc. for promoting health that may be of interest to the user, based on the information related to the user's attributes received by the reception unit 21. The generation unit 23 may change the granularity of the information to be introduced based on the level of medical care. The generation unit 23 may generate a prompt that instructs the user to generate viewing information including information introducing consultation or receiving destinations.

[0036] When information about the user's personality (e.g., a personality assessment result) is received by the receiving unit 21, the generating unit 23 may generate a prompt instructing the user to generate browsing information including information about people of the same generation or other surrounding people, in accordance with the personality assessment result. The personality assessment result here may be, for example, high or low harmony.

[0037] The generating unit 23 may generate a prompt for instructing the generation of viewing information so that the display mode changes depending on the results of the questionnaire based on the HLC scale received by the receiving unit 21. The display mode may, for example, include the presence or absence of illustrations and comments. The comments may, for example, be comments from a doctor or family members. As an example, for a user of type 1 (internal control type), a comment that motivates the individual, such as "Let's do our best to live a healthy and fulfilling life!" may be generated, and for a user of type 2 (external control type), a comment, such as "Let's work hard to live a healthy and fulfilling life together," may be generated along with an illustration that shows that the doctor is making the comment.

[0038] The input unit 24 controls the generation AI model 31 that generates browsing information based on the prompt generated by the generation unit 23. In particular, the input unit 24 controls the generation AI model 31 by inputting a prompt to the generation AI model 31. The generation AI model 31 generates and outputs user browsing information in accordance with the input prompt.

[0039] 4A and 4B are diagrams illustrating user viewing information output from the generative AI model 31. Fig. 4A shows an example of a prompt input to the generative AI model 31. Fig. 4B shows user viewing information output from the generative AI model 31 based on the prompt.

[0040] As shown in Figure 4(a), the prompt specifies information about the user's illness, such as: illness type: hypertension; user attribute information: elderly, male, currently undergoing treatment (diagnosed with hypertension); literature related to hypertension is specified as papers and official documents; the prompt also specifies that the health literacy level is Level 1, the type corresponding to the questionnaire results based on the HLC scale is Type 2 (external control); output format: illustration, Q&A, checklist, healthcare services and systems; and output image: image file.

[0041] As shown in Figure 4(b), the user's browsing information, based on the information shown in Figure 4(a), displays information about high blood pressure. Specifically, first, the papers and official documents cited in the prompt are clearly displayed in the upper right corner. Furthermore, since this information is intended for a user with a low level of medical literacy (health literacy level), the information explains high blood pressure using illustrations and tables. Furthermore, since the user is currently undergoing treatment, the phrase "For improvement..." is used (if the user is not currently undergoing treatment, the phrase "For prevention..." could also be used). Furthermore, a Q&A is displayed to deepen understanding. Furthermore, since the user is currently undergoing treatment, a checklist of points to note during treatment is displayed (if the user is not currently undergoing treatment, a medical questionnaire or similar could also be used). Furthermore, since the user is a Type 2 (external control) user, an illustration is displayed showing a doctor making the comment, "Let's work together to achieve a healthy and fulfilling life."

[0042] Next, the processing executed by the RAG system 20 will be described with reference to Fig. 5. Fig. 5 is a flowchart showing the processing executed by the RAG system.

[0043] As shown in FIG. 5, first, the RAG system 20 receives information about the user's illness and information about the user's medical level assessment (step S1).

[0044] Next, the RAG system 20 determines the user's medical level based on the information relating to the user's medical level determination (step S2).

[0045] Next, the RAG system 20 generates a prompt for instructing the user to generate information to be viewed by the user based on the medical level of the user (step S3).

[0046] Finally, in the RAG system 20, the generated prompt is input to the generative AI model 31 (step S4).

[0047] Next, the effects of the RAG system 20 according to this embodiment will be described.

[0048] The RAG system 20 of this embodiment includes a reception unit 21 that receives information regarding the user's illness and information regarding the user's medical level assessment, a judgment unit 22 that judges the user's medical level based on the information regarding the user's medical level assessment, a generation unit 23 that generates a prompt to instruct the generation of user viewing information corresponding to the information regarding the user's illness based on the user's medical level, and an input unit 24 (control unit) that controls a generation AI model 31 that generates user viewing information based on the prompt generated by the generation unit 23.

[0049] In the RAG system 20 according to the present embodiment, the user's medical level is determined based on information regarding the user's medical level assessment, and a prompt is generated based on the determined level, instructing the generation of user-browsed information corresponding to information about the user's illness. According to this configuration, the user's medical level is determined, and a prompt is generated that generates user-browsed information corresponding to information about the user's illness, taking the determined level into consideration. The AI ​​model is controlled based on the prompt, and user-browsed information corresponding to the user's illness is generated while taking the user's medical level into consideration. In this way, the user-browsed information is generated while taking the user's medical level into consideration, enabling information disclosure appropriate to the user's level. This allows for information disclosure that is understandable to the user, and allows information from doctors and others to be appropriately conveyed to the user. By disclosing information on a daily basis, the user's (patient's) health literacy can be improved. As described above, the RAG system 20 according to the present embodiment can contribute to improving patients' health literacy.

[0050] The information about the user's illness may include at least one of the name of the illness, information indicating the user's health needs, and information about the user's attributes. By using such information to generate the user browsing information, the user browsing information can appropriately include information about the illness that the user wants to know.

[0051] The information regarding the medical level assessment of the user may be information based on the results of a questionnaire administered to the user in advance, thereby enabling the level assessment to be performed with high accuracy based on the results of the questionnaire administered to the user.

[0052] The questionnaire is based on the HLC (Health Locus of Control) scale, and the generation unit 23 may generate a prompt for instructing the generation of user browsing information so that the display mode changes depending on the results of the questionnaire based on the HLC scale. The questionnaire based on the HLC scale can distinguish between an internal control type and an external control type, and by changing the display mode depending on such type, browsing information that is likely to interest the user can be displayed.

[0053] The generation unit 23 may determine whether illustrations are necessary based on the user's level of medical care, and if illustrations are necessary, may generate a prompt to instruct the user to generate viewing information including illustrations related to information about the user's illness. In this way, by using illustrations depending on the user's level of medical care (for example, using illustrations when the level is low), viewing information that is likely to interest the user can be displayed.

[0054] The information on the user's attributes includes information indicating whether the user is undergoing treatment, and the generation unit 23 may generate a prompt that instructs the user to generate user viewing information including a checklist containing points to note during treatment if the user is undergoing treatment, or may generate a prompt that instructs the user to generate user viewing information including a medical questionnaire if the user is not undergoing treatment. In this way, a checklist containing points to note during treatment is displayed to a user undergoing treatment, and a medical questionnaire is displayed to a user not undergoing treatment (a user who may start treatment in the future or is in the prevention stage), thereby making it possible to display viewing information that is highly useful to the user.

[0055] The generation unit 23 may generate a prompt that instructs the user to generate information to be viewed by the user, including information introducing health-related services or programs, based on information about the user's attributes. This allows the appropriate display of information that is useful to the user, such as introducing a company's employee benefit program to a user who can use the program.

[0056] The generation unit 23 may generate a prompt that specifies examples of user-browsed information for each level related to the user's medical care. By specifying examples of user-browsed information for each level in this manner, it is possible to improve the accuracy of displaying user-browsed information for each level.

[0057] The RAG system 20 further includes a storage unit 25 that stores rewriting information that associates technical terms with easy-to-understand general terms that generalize the technical terms for each user's medical level. The generation unit 23 may generate prompts that specify examples of how to rewrite technical terms into general terms for each user's medical level based on the rewriting information stored in the storage unit 25. By rewriting (replacing) terms in accordance with the user's level in this manner, it is possible to display viewing information that is easy for the user to understand. Furthermore, by storing the term rewriting information in advance and using this rewriting information, it is possible to easily and appropriately rewrite technical terms into general terms.

[0058] The generating device and generating method of the present disclosure have the following configuration.

[0059] [1] A generation device comprising: a reception unit that receives information about a user's illness and information about a medical level assessment of the user; a determination unit that determines the user's medical level based on the information about the user's medical level assessment; a generation unit that generates a prompt to instruct the generation of user browsing information corresponding to the information about the user's illness based on the user's medical level; and a control unit that controls a generation AI model that generates the user browsing information based on the prompt generated by the generation unit.

[0060] [2] The generating device according to [1], wherein the information relating to the user's illness includes at least one of the name of the illness, information indicating the user's health needs, and information relating to the user's attributes.

[0061] [3] The generating device according to [1] or [2], wherein the information regarding the assessment of the user's medical level is information based on the results of a questionnaire conducted in advance on the user.

[0062] [4] The generation device according to [3], wherein the questionnaire is based on a Health Locus of Control (HLC) scale, and the generation unit generates a prompt to instruct the generation of the user viewing information so that the display mode changes depending on the results of the questionnaire based on the HLC scale.

[0063] [5] The generating device according to any one of [1] to [4], wherein the generating unit determines whether an illustration is necessary based on the medical level of the user, and if the illustration is necessary, generates a prompt to instruct the user to generate the user viewing information including an illustration related to information about the user's illness.

[0064] [6] The information regarding the user's attributes includes information indicating whether the user is undergoing treatment, and the generation unit generates a prompt that instructs the user to generate the user viewing information including a checklist containing points to note during treatment if the user is undergoing treatment, and generates a prompt that instructs the user to generate the user viewing information including a medical questionnaire if the user is not undergoing treatment.

[0065] [7] The generating device according to [2] or [6], wherein the generating unit generates a prompt that instructs the user to generate the user browsing information including information introducing health-related services or systems based on information about the user's attributes.

[0066] [8] The generating device according to any one of [1] to [7], wherein the generating unit generates a prompt that defines examples of the user browsing information for each level related to the user's medical care.

[0067] [9] The generation device described in [8] further comprises a memory unit that stores rewriting information that associates technical terms with general terms that generalize the technical terms in an easy-to-understand manner for each medical level of the user, and the generation unit generates prompts that specify examples of rewriting technical terms to general terms for each medical level of the user based on the rewriting information in the memory unit.

[0068]

[10] A method for generating a prompt using a generation device, the method including: receiving information about a user's illness and information about a medical level assessment of the user; assessing the user's medical level based on the information about the medical level assessment of the user; generating a prompt for instructing the generation of user browsing information corresponding to the information about the user's illness based on the user's medical level; and inputting the generated prompt into a generation AI model that generates the user browsing information based on the prompt.

[0069] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are connected directly or indirectly (e.g., via wire, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or multiple devices with software.

[0070] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0071] For example, the RAG system 20 constituting the browsing information output system according to an embodiment of the present disclosure may function as a computer that performs processing of the control method of the present disclosure. FIG. 6 is a diagram illustrating an example of the hardware configuration of the RAG system 20 according to this embodiment. The above-described RAG system 20 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage device 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like. The RAG system 20 may be configured as a computer device including at least one processor, such as a CPU or GPU, or may be configured as a computer device including multiple processors or may include multiple computer devices. The terminal 10 and the server device 30 may also have a similar hardware configuration.

[0072] In the following description, the term "apparatus" may be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the RAG system 20 may be configured to include one or more of the apparatuses shown in the figure, or may be configured to exclude some of the apparatuses.

[0073] Each function in the RAG system 20 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0074] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the above-mentioned reception unit 21, determination unit 22, generation unit 23, input unit 24, etc. may be realized by the processor 1001.

[0075] The processor 1001 also reads programs (program codes), 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 in accordance with these programs. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the reception unit 21, the determination unit 22, the generation unit 23, and the input unit 24 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be used for other functional blocks. While the above-described various processes have been described as being executed by a single processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0076] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a control method according to an embodiment of the present disclosure.

[0077] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0078] The communication device 1004 is hardware (transmission / reception 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 a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the above-mentioned reception unit 21, input unit 24, etc. may be realized by the communication device 1004.

[0079] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0080] 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 may be configured using different buses between each device.

[0081] Furthermore, the RAG system 20 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0082] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0083] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0084] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0085] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0086] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0087] Although the present disclosure has been described in detail above, it is 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 spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is for illustrative purposes only and does not limit the present disclosure in any way. For example, while the terminal 10, storage device 15, RAG system 20, and server device 30 (device that stores the generative AI model 31) have been described, these configurations (functions) may all be implemented in the terminal 10, all in a cloud device, or in one or more other terminals and devices. Furthermore, the functions of the RAG system 20 and the functions of the generative AI model 31 may be implemented in the same device or in different devices.

[0088] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0089] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0090] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0091] Note that terms described 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 a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0092] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information. For example, a radio resource may be indicated by an index.

[0093] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0094] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," and the like may be used interchangeably.

[0095] 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 suitable terminology.

[0096] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0097] The terms "connected," "coupled," or any variation thereof, refer to 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" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0098] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0099] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0100] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0101] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0102] In the present 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 "coupled" may also be interpreted in the same way as "different."

[0103] 20...RAG system (generation device), 21...reception unit, 22...determination unit, 23...generation unit, 24...input unit, 31...generated AI model.

Claims

1. A generation device comprising: a reception unit that receives information regarding a user's illness and information regarding the user's medical level assessment; a determination unit that determines the user's medical level based on the information regarding the user's medical level assessment; a generation unit that generates a prompt to instruct the generation of user browsing information corresponding to the user's illness information based on the user's medical level; and a control unit that controls a generation AI model that generates the user browsing information based on the prompt generated by the generation unit.

2. The generating device according to claim 1, wherein the information about the user's illness includes at least one of the name of the illness, information indicating the user's health needs, and information about the user's attributes.

3. The generating device according to claim 1, wherein the information regarding the user's medical level assessment is based on the results of a questionnaire administered to the user in advance.

4. The generation device of claim 3, wherein the questionnaire is based on the HLC (Health Locus of Control) scale, and the generation unit generates a prompt to instruct the generation of the user viewing information so that the display mode changes depending on the results of the questionnaire based on the HLC scale.

5. The generating device of claim 1, wherein the generating unit determines whether an illustration is necessary based on the user's level of medical care, and if the illustration is necessary, generates a prompt instructing the user to generate the viewing information including an illustration related to information about the user's illness.

6. The generating device of claim 2, wherein the information regarding the user's attributes includes information indicating whether the user is undergoing treatment, and the generating unit generates a prompt that instructs the user to generate the user viewing information including a checklist containing points to note during treatment if the user is undergoing treatment, and generates a prompt that instructs the user to generate the user viewing information including a medical questionnaire if the user is not undergoing treatment.

7. The generating device according to claim 2, wherein the generating unit generates a prompt that instructs the user to generate the user viewing information including information introducing health-related services or systems based on information regarding the user's attributes.

8. The generating device of claim 1, wherein the generating unit generates a prompt that defines examples of the user's browsing information for each level of the user's medical care.

9. A generating device as described in claim 8, further comprising a memory unit that stores rewriting information that associates technical terms with easy-to-understand general terms that generalize the technical terms for each medical level of the user, and the generating unit generates prompts that specify examples of rewriting technical terms to general terms for each medical level of the user based on the rewriting information in the memory unit.

10. A method for generating a prompt using a generation device, comprising: accepting information regarding a user's illness and information regarding a medical level assessment of the user; assessing the user's medical level based on the information regarding the user's medical level assessment; generating a prompt for instructing the generation of user viewing information corresponding to the information regarding the user's illness based on the user's medical level; and inputting the generated prompt into a generation AI model that generates the user viewing information based on the prompt.

Images