Generation device and generation method

Abstract

To provide a generation device and a generation method capable of contributing to health promotion of a user.SOLUTION: The RAG system 20 includes a reception section 21 that receives information relating to users who are to receive provision of a menu and information relating to positions of the users, a determination section 22 that determines a concept relating to creation of a menu for a predetermined period based on the information relating to the users and the information relating to the positions, a generation section 23 that generates a prompt for issuing an instruction to create the menu based on the concept, and an inputting section 24 that controls a generation AI model 31 that creates the menu based on the prompt generated by the generation section 23.SELECTED DRAWING: Figure 2

Description

[Technical Field]

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

[0002] Patent Document 1 discloses a technology for creating a menu based on user information and information set by the user. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2000-67029 Summary of the Invention [Problem to be solved by the invention]

[0004] There is a demand for technology that can encourage users to change their eating habits by suggesting meals that are reasonable for them, thereby contributing to promoting their health.

[0005] One aspect of the present disclosure has been made in consideration of the above-described circumstances, and aims to provide a generation device and a generation method that can contribute to promoting the health of users. [Means for solving the problem]

[0006] A generation device according to one aspect of the present disclosure includes a reception unit that receives information about a user receiving a menu and information about the user's location, a determination unit that determines a concept for creating a menu for a specified period based on the information about the user and the information about the location, a generation unit that generates a prompt to instruct the creation of the menu based on the concept, and a control unit that controls a generation AI model that creates the menu based on the prompt generated by the generation unit.

[0007] A generation device according to one aspect of the present disclosure determines a concept for creating a menu based on information about the user and information about the user's location. This configuration allows for appropriate determination of a concept for creating a menu suited to the user, based on, for example, information about the user's physical condition and lifestyle (information about the user) and information about the user's place of residence and frequently visited places (information about the user's location). In other words, by taking into account not only information about the user but also information about the user's location (such as where the user lives and frequently visits), a concept for creating a menu that takes into account, for example, information about supermarkets and restaurants that are easy for the user to visit can be determined. A generative AI model that creates the menu is controlled by prompts generated based on the concept thus determined, allowing for menu suggestions that are easy for the user to adopt (reasonable) and appropriately encouraging the user to change their eating habits in line with the menu. As described above, the generation device according to one aspect of the present disclosure can contribute to promoting the user's health by suggesting menus that are easy for the user to adopt. [Effects of the Invention]

[0008] According to one aspect of the present disclosure, it is possible to contribute to promoting the health of a user. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an overview of a menu creation system according to this embodiment. [Figure 2] FIG. 2 is a diagram showing the device configuration of the menu creation system. [Figure 3] FIG. 3 is a diagram illustrating an example of a prompt generated by the RAG system. [Figure 4] FIG. 4 is a flowchart showing the processing executed by the RAG system. [Figure 5] FIG. 5 is a diagram illustrating an example of a hardware configuration of the RAG system. DETAILED DESCRIPTION OF THE INVENTION

[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or equivalent elements are designated by the same reference numerals, and redundant description will be omitted.

[0011] FIG. 1 is a diagram illustrating an overview of a menu creation system according to this embodiment. The menu creation system uses a generation AI to make reasonable and continuous meal suggestions based on an individual's physical condition and dietary habits. In the example shown in FIG. 1, information about physical condition, existing eating habits, and suggestion level is input to the generation AI, and the generation AI suggests meals for a certain period of time. The information about physical condition may be, for example, health checkup result data, healthcare AI estimation results (e.g., frailty, immunity), smartphone logs (e.g., exercise amount), etc. The information about existing eating habits may be, for example, information about home cooking frequency (including information about not cooking at home), information about food procurement sources (e.g., convenience stores, delivery), information about eating habits (e.g., food preferences, meal frequency, number of items in meals), etc. The information about suggestion level may be information about the frequency with which suggestions are accepted or the type of suggestion (e.g., main dish, side dish). Meals for a certain period of time may be proposed, for example, to a user who cooks at home as recipes containing necessary nutrients (recipes to be prepared by cooking at home), and to a user who does not cook at home as products containing necessary nutrients (meals to be purchased at a convenience store, etc.). In this way, meals for a certain period of time proposed by the menu creation system may include both recipes for cooking at home and products to be purchased. The menu creation system may propose meals for a certain period of time as a menu table. The menu table may include menus for meals for the certain period of time.

[0012] Figure 2 is a diagram showing the device configuration of the menu creation system. The menu creation system includes a terminal 10, a RAG (Retrieval-Augmented Generation) system 20, and a server device 30, which are configured to be able to communicate with each other via networks including wireless communication networks and fixed communication networks. 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 dialogue with an AI model or a command line interface (CLI).

[0013] The terminal 10 is a device used by a user who receives a menu. 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. Although only two terminals 10 are illustrated in FIG. 2, the menu creation system may include any number of terminals 10, two or more. A user who receives a menu refers to the menu and prepares a meal based on the menu.

[0014] The server device 30 stores a generative AI model 31 and is capable of providing a menu using the generative AI model 31. The generative AI model is a model that, in response to a prompt containing input information, generates content based on 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-scale 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, and PaLM2. While this embodiment describes an example in which the server device 30 provides a menu using one generative AI model 31, the server device 30 may also provide menus using multiple generative AI models. 2 shows only one server device 30, the menu creation system may include multiple server devices 30. The generative AI model 31 creates and outputs a menu based on the prompts.

[0015] The RAG system 20 is configured to include, 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 the input information from the terminal 10. The function of each functional unit of the RAG system 20 will be described in detail below.

[0016] The reception unit 21 receives information about the user who will receive the menu table and information about the location of the user from the terminal 10. The reception unit 21 outputs the received information to the determination unit 22.

[0017] The reception unit 21 may receive information about the user including at least one of information about the user's physical condition, information about eating habits, information about past menus provided, information about cooking skills, and information about the purpose of creating the menu.

[0018] Information regarding the user's physical condition is information that indicates the user's physical condition, and may be, for example, health checkup result data, healthcare AI estimation results (frailty, immunity, etc.), smartphone logs (amount of exercise, etc.), etc.

[0019] Information regarding a user's eating habits may be, for example, information such as frequency of cooking at home (including information that the user does not cook at home), information indicating where food is obtained (convenience stores, delivery, etc.), and information indicating eating habits (food preferences, frequency of eating, number of items in meals).

[0020] Information regarding a user's past menu offerings is information regarding menu offerings (offered menu offerings) that the user has received in the past using the menu creation system, and may be, for example, information indicating the acceptance status of menu offering suggestions, information indicating the frequency of acceptance, information indicating the type of suggestion, etc.

[0021] The information about the user's cooking skills is information that directly or indirectly indicates the user's cooking ability, and may be, for example, information indicating whether the user cooks at home or not.

[0022] Information regarding the user's purpose for creating a menu is information indicating why the user is using the menu creation system, and may be information indicating purposes such as increasing muscle mass, beauty, health, etc.

[0023] The reception unit 21 may receive information about a location including at least one of the user's residential location and a frequently visited location. A frequently visited location is, for example, a location that the user visits daily, such as a place where the user goes to work or school. A frequently visited location may be, for example, five days or more per week. The reception unit 21 may receive information indicating the "user's residential location" or the "frequently visited location" (meaningful location information) from the terminal 10, or may simply receive information indicating a location from the terminal 10 and identify it as the "user's residential location" or the "frequently visited location" based on the time period, frequency, etc., thereby receiving information about a location including at least one of the user's residential location and the frequently visited location.

[0024] The determination unit 22 determines a concept for creating a menu for a predetermined period based on the information about the user and the information about the location received by the reception unit 21. The predetermined period may be, for example, about 1 day to 30 days. The determination unit 22 may determine, as the concept, at least one of information about target values ​​of nutrients, information about ingredients to be excluded, preference information about ingredients, and information about the purpose of creating the menu.

[0025] The information on nutrient target values ​​is information on the target values ​​of nutrients set in the menu, and is information indicating target values ​​for nutrients such as energy (calories), protein, fat, carbohydrates, salt equivalents, etc. Specifically, target values ​​are indicated such as lower and upper limits for energy (calories) and lower and upper limits for protein for each of the day / breakfast / lunch / dinner.

[0026] The determination unit 22 may determine information regarding the target value of a nutrient corresponding to the information about the user (specifically, information indicating an illness indicated by the physical condition) received by the reception unit 21, by referring to nutrient target value calculation information in which the physical condition (specifically, information indicating an illness) is associated with the target value of a nutrient. In this case, the nutrient target value calculation information may be stored in the storage unit 25. With this configuration, when the physical condition indicates a specific illness, the target value of the nutrient corresponding to the illness can be easily and quickly determined.

[0027] The determination unit 22 may determine information regarding the target values ​​of nutrients corresponding to the information about the user (specifically, the purpose of creating a menu) received by the reception unit 21 by referencing nutrient target value calculation information that associates the purpose of creating a menu with the target values ​​of nutrients. In this case, the nutrient target value calculation information may be stored in the storage unit 25. With this configuration, the target values ​​of nutrients can be easily and quickly determined according to the purpose of creating a menu for each user.

[0028] The information on ingredients to be excluded is information on ingredients and menus that should not be added to the menu, such as information on irritants (e.g., mapo tofu containing chili peppers) when the user is a patient with chronic pancreatitis.

[0029] The determination unit 22 may determine information about ingredients to be excluded that corresponds to the information about the user received by the reception unit 21 (more specifically, information indicating an illness indicated by the physical condition, or information indicating an illness indicated in the information about the purpose of creating the menu) by referring to excluded ingredient information that associates physical conditions (more specifically, information indicating an illness) with ingredients (ingredients and menu items) to be excluded. In this case, the excluded ingredient information may be stored in the storage unit 25. With this configuration, when the physical condition indicates a specific illness, ingredients that should never be included in a menu can be appropriately excluded.

[0030] When the receiving unit 21 receives information about the dietary habits (more specifically, information indicating disliked ingredients, etc.), the determining unit 22 may determine information about ingredients to be excluded based on the information about the dietary habits.

[0031] The preference information regarding ingredients is, for example, information about the user's favorite menu items and ingredients. When the information regarding dietary habits (more specifically, information indicating favorite ingredients, etc.) is received by the receiving unit 21, the determining unit 22 may determine the preference information regarding ingredients (information indicating which ingredients and menu items the user prefers) based on the information regarding the dietary habits.

[0032] The determination unit 22 may determine the preference information regarding ingredients so that the more frequently an ingredient is included in the information about the user's eating habits received by the reception unit 21, the more the ingredient is preferred by the user. In this case, the determination unit 22 may analyze the usage history of ingredients (or menu items) over a predetermined period, and determine the preference information regarding ingredients for ingredients (or menu items) that exceed a predetermined frequency.

[0033] The information regarding the purpose of creating a menu is information indicating the purpose for which the user is using the menu creation system, such as information indicating the purpose of increasing muscle mass, beauty, maintaining health, etc. The determination unit 22 may use the information regarding the purpose for which the user is using the menu creation system, which is received by the reception unit 21, to determine the information regarding the purpose for which the user is using the menu creation system.

[0034] The determination unit 22 may determine information regarding the purpose of creating a menu for the user based on the information regarding the user's physical condition received by the reception unit 21. For example, when the information regarding the physical condition indicates a medical checkup result indicating that the muscle mass is less than a predetermined threshold, the determination unit 22 may determine that the purpose of creating a menu for the user is to increase muscle mass.

[0035] The determination unit 22 may determine multiple purposes as information regarding the purpose for creating a menu for the user. For example, if the results of a health check indicate that the user's muscle mass is lower than a predetermined threshold and that the user has chronic pancreatitis, the determination unit 22 may determine that the purpose for creating a menu for the user is to increase muscle mass and maintain health. Also, for example, if the user's muscle mass is insufficient, the priority of increasing muscle mass may be determined according to the level of insufficient muscle mass. For example, if multiple purposes have been determined, the determination unit 22 may prioritize the multiple purposes according to the priority as described above.

[0036] The determination unit 22 takes into consideration the information about the location received by the reception unit 21 when determining the above-mentioned concept. That is, the determination unit 22 may take into consideration the information about the location when determining information about nutrient target values, information about ingredients to be excluded, information about ingredient preference, or information about the purpose of creating a menu. The determination unit 22 may, for example, take into consideration the user's residential location, etc., determine information about nutrient target values ​​(e.g., increasing the calorie allowance because the location is a long walking distance), information about ingredients to be excluded (e.g., specific menu names sold at a nearby supermarket), information about ingredient preference (e.g., specific menu names sold at a nearby supermarket), and the purpose of creating a menu (e.g., increasing the muscle mass increase target because the location is a long walking distance). The determination unit 22 outputs the determined concept to the generation unit 23.

[0037] The generation unit 23 generates a prompt for instructing the creation of a menu based on the concept determined by the determination unit 22. The prompt expresses, in text, for example, the command to be executed by the generation AI model 31 (interactive AI model), the task to be executed by the generation AI model 31, the background and context (e.g., role, condition) to be considered by the generation AI model 31, the question to be answered by the generation AI model 31, and the output format of the response information from the generation AI model 31. The prompt may also include input information that is the target of the command and task to be executed by the generation AI model 31. Examples of such input information include data files with file names that include 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.

[0038] FIG. 3 is a diagram showing an example of a prompt generated by the RAG system 20. The prompt shown in FIG. 3 specifies a role, a task, a condition, and an output format. The role is information that specifies the role that the generative AI model 31 will play in outputting, and in this case, it is specified as a "nutritionist" involved in creating a menu. The task is information that outlines the instructions to the generative AI model 31, and in this case, it is specified as "Please generate a menu."

[0039] The conditions are information that indicate detailed conditions for a task. The conditions may specify information about each of the concepts described above. In the example shown in FIG. 3, the conditions specify the concepts of "target nutrient information" (information about target values ​​of nutrients), "NG menu information" (information about ingredients to be excluded), "favorite ingredients" (information about food preferences), and "purpose" (information about the purpose of creating a menu). In addition, a restriction on location information is specified, such as "Please create using ingredients that can be obtained near the location information below." Another condition is specified: "Create four meals a day for one week. Please change the menu every day so that you don't get bored."

[0040] The output format is information that indicates the content of the menu to be output. In the example shown in Figure 3, it is specified that the menu should be output to include information such as "date, menu, nutritional information, ingredients, etc."

[0041] The generation unit 23 may generate a prompt in which a concept is defined and an example of a menu corresponding to the concept is defined. In this case, the generation unit 23 may acquire an example of an ingredient (or menu) corresponding to the concept by referring to example information in which the concept is associated with an example of an ingredient (or menu), and generate a prompt in which the example is defined. Nutritional information may be further associated with the example information, and the generation unit 23 may generate a prompt in which an example of the nutritional information is defined. The example information may be stored in the storage unit 25, for example.

[0042] When an ingredient to be excluded is specified in the determined concept, the generation unit 23 may generate a prompt that specifies a replacement ingredient to be substituted for the ingredient to be excluded.

[0043] The generation unit 23 may determine menu candidates based on the information about the user's cooking skills received by the reception unit 21, and generate a prompt that defines the menu candidates.

[0044] The generation unit 23 may generate a prompt that specifies an explanation of the concept or an explanation related to dietary education (knowledge about diet, such as the effects of nutrients and their relevance to goals such as health and muscle mass increase).

[0045] The input unit 24 controls the generative AI model 31 based on the prompt generated by the generation unit 23. The input unit 24 inputs the prompt to the generative AI model 31. The generative AI model 31 creates and outputs a menu in response to the input prompt.

[0046] Next, the processing executed by the RAG system 20 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the processing executed by the RAG system.

[0047] As shown in FIG. 4, first, the RAG system 20 receives information about the user and information about the user's location from the terminal 10 (step S1).

[0048] Next, in the RAG system 20, a concept for creating a menu for a predetermined period is determined based on the information about the user and the information about the location (step S2).

[0049] Next, the RAG system 20 generates a prompt for instructing the creation of a menu based on the concept (step S3).

[0050] Finally, in the RAG system 20, the generated prompt is input to the generative AI model 31 (step S4).

[0051] Next, the effects of the RAG system 20 according to this embodiment will be described.

[0052] The RAG system 20 of this embodiment includes a reception unit 21 that receives information about the user receiving the menu and information about the user's location, a determination unit 22 that determines a concept for creating a menu for a specified period based on the information about the user and the information about the location, a generation unit 23 that generates a prompt to instruct the creation of the menu based on the concept, and an input unit 24 that controls a generation AI model 31 that creates the menu based on the prompt generated by the generation unit 23.

[0053] In the RAG system 20 according to this embodiment, a concept for creating a menu is determined based on information about the user and their location. This configuration allows for appropriate determination of a concept for creating a menu suited to the user, based on, for example, information about the user's physical condition and lifestyle (user information) and information about the user's place of residence and frequently visited places (user location information). In other words, by taking into account not only user information but also information about the user's location (such as where the user lives and frequently visits), a concept for creating a menu that takes into account, for example, information about supermarkets and restaurants that are convenient for the user can be determined. The prompts generated based on the concept thus determined control the AI ​​model 31 that creates the menu, thereby suggesting a menu that is easy for the user to adopt (reasonable) and appropriately encouraging the user to change their eating habits in line with the menu. As described above, the RAG system 20 according to this embodiment contributes to promoting the user's health by suggesting a menu that is easy for the user to adopt.

[0054] The reception unit 21 may receive information about the user, including at least one of information about the user's physical condition, information about the user's eating habits, information about past menus provided, information about cooking skills, and information about the purpose of creating the menu. By determining the concept based on such user information, a menu that is more suitable for the user can be created.

[0055] The reception unit 21 may receive information about locations including at least one of the user's residence location and a location frequently visited by the user. With this configuration, it is possible to propose a menu that is easy for the user to adopt (reasonable) by taking into consideration information about locations where the user stays for a long time.

[0056] The determination unit 22 may determine, as a concept, at least one of information on target nutrient values, information on ingredients to be excluded, information on ingredient preferences, and information on the purpose of creating the menu. By generating prompts based on such concepts, a menu that is more suitable for the user can be created.

[0057] The determination unit 22 may determine information regarding the target values ​​of nutrients corresponding to the information regarding the user received by the reception unit 21, by referring to nutrient target value calculation information in which the physical condition or the purpose of creating a menu is associated with the target values ​​of nutrients. With this configuration, information regarding the target values ​​of nutrients can be determined easily, quickly, and appropriately based on the associated information in advance.

[0058] The determination unit 22 may refer to the excluded ingredient information in which the physical condition and the ingredients to be excluded are associated with each other, and determine the information on the ingredients to be excluded that corresponds to the information on the user received by the reception unit 21. With this configuration, the information on the ingredients to be excluded can be determined easily, quickly, and appropriately based on the previously associated information.

[0059] The determination unit 22 may determine the preference information regarding ingredients such that the more frequently an ingredient is included in the information about the user's eating habits received by the reception unit 21, the more preferred the ingredient is by the user. With this configuration, the preference information regarding ingredients can be determined with high accuracy, taking into account the information about the eating habits.

[0060] The determination unit 22 may determine information regarding the purpose of creating a menu for the user based on information regarding the user's physical condition received by the reception unit 21. With this configuration, it is possible to appropriately generate a menu that can contribute to promoting the user's health based on, for example, information indicating the user's illness.

[0061] The generation unit 23 may generate a prompt in which a concept is defined and an example of a menu corresponding to the concept is defined. By defining the example in the prompt, a menu that is more in line with the concept can be generated.

[0062] The generating device and generating method of the present disclosure have the following configuration.

[0063] [1] A reception unit that receives information about a user who receives a menu and information about the location of the user; A determination unit that determines a concept for creating a menu for a predetermined period based on the information about the user and the information about the location; A generation unit that generates a prompt for instructing the creation of a menu based on the concept; A generation device comprising: a control unit that controls a generative AI model that creates a menu based on the prompt generated by the generation unit.

[0064] [2] The generation device described in [1], wherein the reception unit receives information about the user including at least one of information about the user's physical condition, information about eating habits, information about past menus provided, information about cooking skills, and information about the purpose of creating the menu.

[0065] [3] The generating device according to [1] or [2], wherein the reception unit receives information about the location including at least one of the user's residential location and a frequently visited location.

[0066] [4] The determination unit determines, as the concept, at least one of information regarding target nutrient values, information regarding ingredients to be excluded, preference information regarding ingredients, and information regarding the purpose of creating the menu. A generation device described in any one of [1] to [3].

[0067] [5] The receiving unit receives information about the user including at least one of information about the user's physical condition and information about the user's purpose for creating a menu chart, The determination unit determines information regarding the target values ​​of nutrients corresponding to the information about the user accepted by the acceptance unit by referring to nutrient target value calculation information in which the physical condition or purpose of creating a menu is associated with the target values ​​of nutrients. [4] A generation device as described in

[0068] [6] the receiving unit receives information about the user including information about the user's physical condition; The generation device described in [4] or [5], wherein the determination unit determines the information on the ingredients to be excluded that corresponds to the information on the user received by the reception unit by referring to excluded ingredient information in which the physical condition and the ingredients to be excluded are associated.

[0069] [7] the receiving unit receives information about the user including information about the user's eating habits; The generation device described in any one of [4] to [6], wherein the determination unit determines the preference information regarding the ingredients so that the more frequently an ingredient is included in the information regarding the user's eating habits received by the reception unit, the more preferred the ingredient is by the user.

[0070] [8] the receiving unit receives information about the user including information about the user's physical condition; The generation device described in any one of [4] to [7], wherein the determination unit determines information regarding the purpose of creating a menu for the user based on information regarding the user's physical condition received by the reception unit.

[0071] [9] The generating device according to any one of [1] to [8], wherein the generating unit generates the prompt in which the concept is defined and an example of a menu corresponding to the concept is defined.

[0072]

[10] A generation method performed by a generation device, Accepting information about a user who will receive the menu and information about the user's location; determining a concept for creating a menu for a predetermined period based on the information about the user and the information about the location; generating a prompt for instructing the creation of a menu based on the concept; and controlling a generative AI model that creates a menu based on the prompt.

[0073] 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 (for example, by wire, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or multiple devices with software.

[0074] Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, election, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocation, 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.

[0075] For example, the RAG system 20 constituting the menu creation 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. 5 illustrates an example of the hardware configuration of the RAG system 20 according to this embodiment. The RAG system 20 may be physically configured as a computer device including a processor 1001, memory 1002, storage 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.

[0076] In the following description, the term "apparatus" can 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.

[0077] 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.

[0078] 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.

[0079] The processor 1001 also loads 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 the 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 made for other functional blocks. While the above-described various processes have been described as being executed by one 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.

[0080] 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.

[0081] Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of 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 disc), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy 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.

[0082] 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, for example, a network device, a network controller, a network card, or a communication module. 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.

[0083] The input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (for example, a touch panel).

[0084] 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.

[0085] Furthermore, 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, processor 1001 may be implemented using at least one of these pieces of hardware.

[0086] 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), 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), 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.

[0087] 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.

[0088] 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.

[0089] 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).

[0090] Each aspect / embodiment described in this disclosure may be used alone, in combination, or switched depending on the implementation. Furthermore, notification of predetermined information (e.g., notification that "X is true") is not limited to being done explicitly, but may be done implicitly (e.g., by not notifying the predetermined information).

[0091] 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 may be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure, as defined by the appended claims. Therefore, the description of the present disclosure is for illustrative purposes only and is not intended to be limiting of the present disclosure. For example, while the terminal 10, the RAG system 20, and the server device 30 (devices that store the generative AI model 31) have been described, these configurations (functions) may be implemented entirely in the terminal 10, entirely 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.

[0092] 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.

[0093] 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), these wired and / or wireless technologies are included within the definition of transmission media.

[0094] 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.

[0095] Note that terms explained 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.

[0096] 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.

[0097] 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.

[0098] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," etc. may be used interchangeably.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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."

[0103] Any reference to an element using a designation such as "first," "second," etc., 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. 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.

[0104] When used in this disclosure, the terms "include," "including," and variations thereof are intended to be inclusive, similar to the term "comprising." Furthermore, when used in this disclosure, the term "or" is not intended to be an exclusive or.

[0105] 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.

[0106] 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." [Explanation of symbols]

[0107] 20...RAG system (generation device), 21...reception unit, 22...decision unit, 23...generation unit, 24...input unit (control unit), 31...generative AI model.

Claims

1. A reception unit that receives information about a user who receives a menu and information about the location of the user; A determination unit that determines a concept for creating a menu for a predetermined period based on the information about the user and the information about the location; A generation unit that generates a prompt for instructing the creation of a menu based on the concept; A generation device comprising: a control unit that controls a generation AI model that creates a menu based on the prompt generated by the generation unit.

2. The generation device according to claim 1, wherein the reception unit receives information about the user including at least one of information about the user's physical condition, information about eating habits, information about past menus provided, information about cooking skills, and information about the purpose of creating the menu.

3. The generating device according to claim 1 , wherein the receiving unit receives information about the location including at least one of a location where the user lives and a location where the user frequently visits.

4. The generation device according to any one of claims 1 to 3, wherein the determination unit determines as the concept at least one of information regarding target nutrient values, information regarding ingredients to be excluded, preference information regarding ingredients, and information regarding the purpose of creating the menu.

5. The receiving unit receives information about the user including at least one of information about the user's physical condition and information about the user's purpose for creating a menu chart, The generation device of claim 4, wherein the determination unit determines information regarding the target values ​​of nutrients corresponding to the information about the user accepted by the acceptance unit by referring to nutrient target value calculation information in which the physical condition or purpose of creating a menu is associated with the target values ​​of nutrients.

6. the receiving unit receives information about the user including information about the user's physical condition; The generation device according to claim 4 , wherein the determination unit determines the information on the ingredients to be excluded that corresponds to the information on the user received by the reception unit by referring to excluded ingredient information in which a physical condition and the ingredients to be excluded are associated with each other.

7. the receiving unit receives information about the user including information about the user's eating habits; The generation device according to claim 4, wherein the determination unit determines the preference information regarding the ingredients so that the more frequently an ingredient is included in the information regarding the user's eating habits received by the reception unit, the more the ingredient is preferred by the user.

8. the receiving unit receives information about the user including information about the user's physical condition; The generating device according to claim 4 , wherein the determining unit determines information regarding the purpose of creating the menu for the user based on information regarding the user's physical condition received by the receiving unit.

9. The generating device according to claim 1 , wherein the generating unit generates the prompt in which the concept is defined and an example of a menu corresponding to the concept is defined.

10. A generation method performed by a generation device, Accepting information about a user who will receive the menu and information about the user's location; determining a concept for creating a menu for a predetermined period based on the information about the user and the information about the location; generating a prompt for instructing the creation of a menu based on the concept; and controlling a generative AI model that creates a menu based on the prompt.

Images