System

Abstract

To provide a system allowing a user to take a meal with well-balanced nutrition without taking time and effort, and to improve and maintain a health condition.SOLUTION: An input unit configured to input contents of a meal ingested by a user, a transmission unit configured to transmit input meal data to a server, a recording unit configured to record the transmitted meal data, an analysis unit configured to analyze the recorded meal data and evaluate a nutrition balance, a proposal unit configured to propose a recipe for supplementing the nutrition balance on the basis of an analysis result, a feedback unit configured for the user to input feedback on the recipe, a re-proposal unit configured to propose the recipe again on the basis of the feedback of the user, and a notification unit configured to notify the user of a final recipe and record the recipe.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

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

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

[0004] Planning daily meal plans is a hassle, and people tend to eat only their favorite foods, which can lead to an unbalanced nutritional intake. This can make it difficult to maintain or improve one's health. Furthermore, achieving an appropriate nutritional balance requires specialized knowledge, which is a high hurdle for average users. Another issue is that it is difficult to respond to users' food preferences and fluctuations in market prices. [Means for solving the problem]

[0005] The present invention provides a system that includes an input means for inputting the details of a user's dietary intake, a transmission means for transmitting the input dietary data to a server, a recording means for recording the transmitted dietary data, an analysis means for analyzing the recorded dietary data and evaluating nutritional balance, a proposal means for proposing recipes to compensate for nutritional imbalance based on the analysis results, a feedback means for the user to input feedback on the recipes, a re-proposal means for re-proposing recipes based on the user's feedback, and a notification means for notifying the user of and recording the final recipe. This allows the user to easily achieve a nutritionally balanced diet and improve and maintain their health. Furthermore, by adding additional input means for the user to input additional information such as sale information and allergy information, and a long-term analysis means for performing long-term nutritional balance analysis, more flexible and accurate health management becomes possible.

[0006] "User" refers to an individual or organization that uses the system and provides meal information using an input means.

[0007] "Input means" refers to hardware and software components that allow a user to input the details of the food they have consumed.

[0008] "Transmission means" refers to hardware and software that has the function of transmitting data input by the input means to the server.

[0009] "Recording means" refers to hardware and software that has the function of storing data received via transmission means in a storage device such as a database.

[0010] "Server" refers to a computer system that receives data sent from an input means and records, analyzes, and notifies the user.

[0011] "Analysis means" refers to algorithms such as AI generation that process data stored in the recording means and evaluate nutritional balance, and their execution devices.

[0012] "Proposal means" refers to hardware and software that has the function of automatically generating and proposing meal menus to improve nutritional balance based on the results of the analysis means.

[0013] "Feedback means" refers to hardware and software that allows a user to input comments or additional information about a suggested recipe.

[0014] The "re-proposal means" refers to a generation AI and its execution device that has the function of proposing new recipes based on user opinions and additional information received through the feedback means.

[0015] The "notification means" refers to hardware and software that has the function of transmitting the finalized recipe to the user and displaying it on the user's terminal.

[0016] "Additional input means" refers to hardware and software that allows the user to input data other than basic dietary information, such as sale information or allergy information.

[0017] "Long-term analysis means" refers to a generation AI and its execution device that has the function of accumulating past dietary data over a long period of time and continuously evaluating nutritional balance and making suggestions for improvement. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention relates to a system that allows users to easily plan and manage their daily meal menus and supports a balanced and healthy diet. This system sends the meal information entered by the user to a server, which analyzes the data, evaluates the nutritional balance, and suggests suitable recipes.

[0040] Overview of program processing

[0041] 1. User input:

[0042] The user enters meal information, including the name of the dish eaten, the ingredients used, and the amount consumed. For example, "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[0043] 2. Data transmission and storage:

[0044] The device sends the entered meal information to the server, which receives the data and records it in a database.

[0045] 3. Nutritional Balance Analysis:

[0046] The server uses the dietary information stored in the database to calculate the nutritional value of each ingredient, and the AI ​​generator then references the nutrient data for each ingredient to evaluate the overall nutritional balance.

[0047] 4. Recipe Suggestions:

[0048] Based on the analysis results, the server's AI will suggest recipes to the user to supplement the nutrients they are lacking. For example, if they are lacking in calcium, it will suggest a spinach and cheese omelet.

[0049] 5. User Feedback:

[0050] Users can review the suggested recipes and enter any changes they need, special offers, or additional information about allergies, such as "Salmon was on sale today" or "I'm allergic to spinach."

[0051] 6. Re-proposal:

[0052] The generative AI will then suggest new recipes based on user feedback, such as grilled salmon and broccoli.

[0053] 7. Notify and save the final recipe:

[0054] The server notifies the user of the finalized recipe and stores the data, allowing the user to prepare a meal according to the recipe.

[0055] Specific examples

[0056] As a specific example, consider the case where the user is "Mr. Tanaka."

[0057] 1. Enter your meal information:

[0058] Tanaka enters that she had "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner.

[0059] 2. Data transmission and storage:

[0060] The device sends the entered information to the server, which records it in a database along with "Tanaka-san's" ID.

[0061] 3. Nutritional Balance Analysis:

[0062] The server-generated AI analyzes the data and identifies calcium deficiency.

[0063] 4. Recipe Suggestions:

[0064] The generative AI suggests a "spinach and cheese omelet" to supplement calcium.

[0065] 5. User Feedback:

[0066] Tanaka gives feedback to the generating AI, saying, "Salmon was on sale."

[0067] 6. Re-proposal:

[0068] The generative AI now suggests "grilled salmon and broccoli."

[0069] 7. Notify and save the final recipe:

[0070] The server sends the recipe for "grilled salmon and broccoli" to Tanaka's device and saves the data. Tanaka then prepares a healthy dinner according to the recipe.

[0071] In this way, the system efficiently manages the user's dietary information and suggests nutritionally balanced meals, thereby contributing to the maintenance and improvement of health.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] The user uses the device to input the details of the meal they ate, including the name of the dish, the ingredients used, the amount consumed, and the cooking method. For example, they might input "Breakfast: yogurt, banana, toast," "Lunch: chicken salad," and "Dinner: grilled salmon, salad, miso soup."

[0075] Step 2:

[0076] The device sends the entered meal information to the server. The sent content includes the user ID and detailed meal information. The data is sent in an appropriate format, such as JSON.

[0077] Step 3:

[0078] The server stores the received data in a database. In addition to the meal information, the date and time of sending and the user ID are also recorded. For example, "User: Tanaka", "Date and time: 2023-10-01", "Breakfast: Yogurt, banana, toast", "Lunch: Chicken salad", "Dinner: Grilled salmon, salad, miso soup" might be recorded.

[0079] Step 4:

[0080] The server calculates the nutritional value of each ingredient based on the dietary information stored in the database. The generative AI retrieves the nutritional value of each ingredient from the database and evaluates the nutritional balance of the entire meal. For example, the nutrients of yogurt (calcium, protein), banana (potassium, vitamin C), and toast (carbohydrates, fiber) are calculated.

[0081] Step 5:

[0082] The generative AI also references past dietary data to analyze long-term nutritional intake, determining whether calcium is insufficient, vitamin D is sufficient, or salt is excessive. For example, the analysis results may include "calcium deficiency," "sufficient vitamin D," or "excess salt."

[0083] Step 6:

[0084] Based on the analysis results, the generative AI will suggest recipes suitable for the user. It will suggest balanced meals, such as recipes to supplement missing nutrients or to reduce excess intake of nutrients. For example, it will suggest a "spinach and cheese omelet" to supplement calcium.

[0085] Step 7:

[0086] The user checks the recipe suggestions from the AI ​​via their device. If the suggestions need to be changed due to reasons such as not being able to obtain certain ingredients or allergies, the user can communicate this information to the AI. For example, they can say, "Salmon was on sale today, so it was cheap."

[0087] Step 8:

[0088] The generative AI reflects user feedback and proposes new recipes, allowing for flexible responses to suit the user's preferences and circumstances. For example, it suggests "grilled salmon and broccoli."

[0089] Step 9:

[0090] The user reviews and selects the final recipe, the server sends the finalized recipe to the user's device, and the user prepares the meal according to the recipe.

[0091] Step 10:

[0092] The server saves the final recipe data in a database. This allows data to be accumulated for future analysis and recommendations. For example, "Recipe: Grilled Salmon and Broccoli," "Date and Time: 2023-10-01," and "User ID: tanaka123" are recorded.

[0093] Through these steps, the system efficiently manages the user's dietary information and suggests nutritionally balanced meals, allowing the user to maintain a healthy diet without any effort.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] In modern society, many users find it difficult to maintain a balanced diet, and dietary management is often neglected, especially in busy daily lives. In addition, each user has different nutritional needs, making it difficult to provide appropriate nutritional advice and recipes tailored to individual conditions. Traditional manual dietary management methods are inefficient and lack appropriate support measures for continuous health maintenance and improvement.

[0097] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0098] In this invention, the server includes an input means for inputting the details of the meals a user has eaten, a transmission means for transmitting the input meal data to the server, and a recording means for recording the transmitted meal data. This allows users to accurately and efficiently manage their own meal data. The server also includes an analysis means for analyzing the recorded meal data using a generative AI model to evaluate nutritional balance, a suggestion means for sending prompts to the generative AI model to suggest recipes to compensate for nutritional imbalance, a re-suggestion means for re-suggesting recipes using the generative AI model based on user feedback, and a notification means for notifying the user of the final recipe and recording it. This allows for appropriate meal suggestions based on each user's nutritional needs, enabling continuous improvement and maintenance of the user's health.

[0099] The "input means" refers to a device or interface that allows the user to input the details of the meal they have eaten.

[0100] "Transmission means" refers to a function or device for transmitting the meal data entered by the user to the server.

[0101] The "recording means" refers to a database or storage system for saving and managing the transmitted meal data.

[0102] "Analysis means using generative AI models" refers to devices or systems that use AI technology to analyze recorded dietary data and evaluate nutritional balance.

[0103] A "prompt sentence" is an input sentence that gives specific instructions to a generative AI model.

[0104] "Proposal means" refers to a function or device that uses a generative AI model to provide users with recipes to compensate for nutritional balance based on the analysis results.

[0105] A "feedback means" is a function or device that allows a user to input opinions or additional information about a recipe.

[0106] A "re-proposal means" is a function or device that uses a generative AI model to re-propose a recipe based on user feedback.

[0107] The "notification means" is a function or device for notifying the user of the final recipe and recording the data.

[0108] This invention relates to a system that allows users to easily plan and manage their daily meal menus and supports a balanced and healthy diet. This system sends the meal information entered by the user to a server, which analyzes the data, evaluates the nutritional balance, and suggests suitable recipes.

[0109] System configuration

[0110] Input Method

[0111] Users enter their meal details using a smartphone app or web interface. The information entered includes the name of the dish, the ingredients used, and the amount consumed. For example, breakfast might include "yogurt and banana," lunch might include "chicken salad," and dinner might include "grilled salmon."

[0112] Transmission method

[0113] The device sends the meal information entered by the user to the server using an HTTP POST request.

[0114] Recording means

[0115] The server records the received meal data in a database, which is used to store each user's meal history and nutritional information. For example, meal details are stored along with the user ID.

[0116] Analytical tools using generative AI models

[0117] The server uses a generative AI model to calculate the nutritional value of each ingredient based on the recorded dietary data. The generative AI model then refers to the nutrient data of the ingredients and evaluates the overall nutritional balance. This evaluation is performed by sending prompt sentences to the generative AI model.

[0118] Proposal means

[0119] The generative AI model then suggests recipes to improve nutritional balance based on the analysis results. For example, if a person is lacking in calcium, it suggests a spinach and cheese omelette.

[0120] Feedback Methods

[0121] Users review the suggested recipes and enter any missing information or specific requirements (such as special offers or allergies), for example, "Salmon was on sale today" or "I'm allergic to spinach."

[0122] Re-proposal means

[0123] The generative AI model re-suggests new recipes based on user feedback, for example, suggesting "grilled salmon and broccoli."

[0124] Notification means

[0125] The server notifies the user of the final recipe and records the data. The user can prepare a meal according to the recipe. Notifications are sent to the device using push notifications or email notifications.

[0126] Specific examples

[0127] For example, if the user is "Tanaka-san":

[0128] 1. Enter your meal information

[0129] Tanaka enters "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner.

[0130] 2. Data transmission and storage

[0131] The terminal sends the entered information to the server, which records it in a database along with Tanaka's ID.

[0132] 3. Analysis of nutritional balance

[0133] The server's generated AI model analyzes Tanaka's data and identifies that he is deficient in calcium.

[0134] 4. Recipe suggestions

[0135] The generative AI model suggests a "spinach and cheese omelet" to supplement calcium.

[0136] 5. User Feedback

[0137] Tanaka provides feedback to the generative AI model that "salmon was on sale."

[0138] 6. Re-proposal

[0139] The generative AI model now suggests "grilled salmon and broccoli."

[0140] 7. Notification and saving of final recipe

[0141] The server sends the recipe for "grilled salmon and broccoli" to Tanaka's device and saves the data. Tanaka then prepares a healthy dinner according to the recipe.

[0142] This system suggests specific, nutritionally balanced recipes by sending the prompt text "User ID: Tanaka, Meal information: Breakfast - yogurt and banana, Lunch - chicken salad, Dinner - grilled salmon. Analyze nutritional balance and check for missing nutrients. Then suggest suitable recipes to supplement those nutrients" to the generative AI model.

[0143] In this way, users can efficiently manage their own dietary data and use it to maintain and improve their health.

[0144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0145] Step 1:

[0146] The user inputs the details of the food they have eaten.

[0147] Input: The user enters the names of the dishes for breakfast, lunch, and dinner, the ingredients used, and the amount consumed into an input form on the terminal.

[0148] How it works: Users use a smartphone app or web interface to enter meal information using a keyboard or touch panel.

[0149] Output: The entered meal information is saved in the device.

[0150] Step 2:

[0151] The terminal transmits the meal information to the server.

[0152] Input: Meal information stored on your device.

[0153] How it works: The device sends the entered meal information to the server using an HTTP POST request.

[0154] Output: Meal information is sent to the server.

[0155] Step 3:

[0156] The server records the received meal information in a database.

[0157] Input: Meal information sent to the server.

[0158] How it works: The server stores the received data in a database using INSERT statements, for example, "Tanaka's ID, Breakfast - yogurt and banana, Lunch - chicken salad, Dinner - grilled salmon".

[0159] Output: The recorded meal information is stored in a database.

[0160] Step 4:

[0161] The server-generated AI model analyzes the dietary information and evaluates nutritional balance.

[0162] Input: Meal information stored in a database.

[0163] How it works: The server extracts the user's dietary information from the database using a SELECT statement and sends a prompt to the generative AI model. The prompt reads, "User ID: Tanaka, Breakfast - Yogurt and banana, Lunch - Chicken salad, Dinner - Grilled salmon. Analyze the nutritional balance and check for any missing nutrients." The generative AI model then analyzes and evaluates the nutritional balance.

[0164] Output: The nutritional balance evaluation results are returned from the generative AI model.

[0165] Step 5:

[0166] Based on the analysis results, the server suggests recipes to improve nutritional balance.

[0167] Input: Nutritional balance assessment results returned by the generative AI model.

[0168] How it works: Based on the evaluation results, the server sends a new prompt to the generative AI model to generate a suitable recipe. For example, "I'm lacking calcium, so please suggest a recipe to supplement my calcium."

[0169] Output: The generative AI model returns a suitable recipe suggestion, for example, "Spinach and Cheese Omelette."

[0170] Step 6:

[0171] The user provides feedback on the suggested recipe.

[0172] Input: A recipe provided by the server.

[0173] How it works: The user reviews the proposed recipe and enters any specials, allergies, or other specific requirements into a feedback form. For example, "Salmon was on sale today" or "I'm allergic to spinach."

[0174] Output: Feedback information is saved to the device.

[0175] Step 7:

[0176] The terminal transmits the feedback information to the server.

[0177] Input: Feedback information stored on the device.

[0178] How it works: The device sends feedback information to the server using an HTTP POST request.

[0179] Output: The feedback information is sent to the server.

[0180] Step 8:

[0181] The server's generative AI model re-proposes new recipes based on the feedback information.

[0182] Input: The feedback information sent to the server.

[0183] How it works: The server sends a new prompt to the generative AI model, suggesting a new recipe that takes the feedback into account. For example, "User ID: Tanaka, salmon is on sale and I'm allergic to spinach. Please suggest a new recipe."

[0184] Output: The generative AI model returns a new recipe suggestion, for example, "Grilled Salmon and Broccoli."

[0185] Step 9:

[0186] The server notifies the user of the final recipe and records the data.

[0187] Input: The final recipe returned from the generative AI model.

[0188] Operation: The server saves the final recipe information in the database and notifies the device via an HTTP response. The device displays the notification to the user and allows them to view the recipe.

[0189] Output: The final recipe information is saved in the database and on the device, and is notified to the user.

[0190] In this way, the system manages the user's dietary information through each step and supports the user's health by suggesting recipes that take nutritional balance into consideration.

[0191] (Application example 1)

[0192] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0193] Conventional food delivery services have had the problem of making it difficult for users to select meals that take into account healthy nutritional balance. In particular, there has been a lack of specific suggestions for supplementing nutrients lacking in daily meals, and meal delivery services based on such suggestions. As a result, users have had to go through the trouble of researching nutritional balance and choosing meals themselves.

[0194] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0195] In this invention, the server includes an input means for inputting the contents of the meal consumed by the user, a transmission means for transmitting the input meal data to the server, a recording means for recording the transmitted meal data, an analysis means for analyzing the recorded meal data and evaluating the nutritional balance, a proposal means for proposing recipes to compensate for the nutritional balance based on the analysis results, a feedback means for the user to input feedback on the recipe, a re-proposal means for re-proposing a recipe based on the user's feedback, a notification means for notifying the user of the final recipe and recording it, and a delivery order means for ordering a meal based on the proposed recipe.

[0196] This allows users to easily manage the nutritional balance of their daily meals and order delivery meals based on suggested healthy recipes, thereby improving the quality of their diet and helping them maintain and improve their health.

[0197] The "input means" refers to a device or interface that allows the user to input the details of the meal they have eaten.

[0198] The "transmission means" is a communication function for transmitting the input meal data to the server.

[0199] "Recording means" refers to devices or software for storing and recording the transmitted dietary data in a database or the like.

[0200] "Analysis means" refers to algorithms or programs that evaluate nutritional balance based on recorded dietary data and identify necessary nutrients.

[0201] The "suggestion method" is a function that uses a generative AI model to suggest recipes to supplement the user's missing nutrients based on the analysis results.

[0202] The "feedback means" is an interface that allows the user to input feedback such as opinions and improvements regarding the proposed recipe.

[0203] A "re-proposal method" is an algorithm or program that regenerates and proposes new recipes based on user feedback.

[0204] The "notification means" is a notification function for notifying the user of the finalized recipe.

[0205] The "delivery ordering means" is a function for ordering food based on the suggested recipe from a delivery service.

[0206] The "additional input means" is an interface that allows the user to input additional information such as sale item information and allergy information.

[0207] The "long-term analysis means" refers to an algorithm or program that analyzes data on long-term nutritional balance with the aim of continuously improving and maintaining the user's health.

[0208] MODE FOR CARRYING OUT THE INVENTION

[0209] The present invention relates to a system that allows users to easily plan and manage their daily meal menus and supports a balanced and healthy diet. This system includes an "input means," "transmission means," "recording means," "analysis means," "suggestion means," "feedback means," "re-suggestion means," "notification means," and "delivery ordering means."

[0210] System configuration

[0211] Hardware

[0212] Device: The smartphone used by the user (Android, iOS)

[0213] Server: Cloud server for processing and storing data

[0214] software

[0215] Database: PostgreSQL is used to store and manage user meal information.

[0216] Backend framework: Python and Flask will be used to build an API to input food information, analyze nutritional balance, suggest recipes, and process orders.

[0217] Generative AI model: Uses OpenAI's GPT to generate nutritionally balanced recipes.

[0218] Front-end framework: React Native is used to build the user interface.

[0219] System processing flow

[0220] 1. Enter your meal information

[0221] An "input method" is provided for users to input the name of the dish they ate, the ingredients used, and the intake amount. For example, they can input "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[0222] 2. Data transmission and storage

[0223] The user's device has a "transmission means" for transmitting the input meal information to the server, and the server stores the received data in a database as a "recording means."

[0224] 3. Analysis of nutritional balance

[0225] The server evaluates the nutritional balance of the recorded dietary data using an "analysis tool." The generative AI model (OpenAI GPT) references the nutrients in each ingredient and calculates the overall nutritional balance.

[0226] 4. Recipe suggestions

[0227] Based on the analysis results, the system will suggest recipes to the user to make up for any missing nutrients. For example, if a user is lacking in calcium, the system will suggest a "spinach and cheese omelet."

[0228] 5. User Feedback

[0229] Users can enter feedback on the suggested recipes using the "Feedback Tool." For example, they can add information such as "Salmon was on sale today" or "I'm allergic to spinach."

[0230] 6. Re-proposal

[0231] The server re-proposes new recipes based on the user's feedback using the "re-proposition method." For example, it suggests "grilled salmon and broccoli."

[0232] 7. Notification and saving of final recipe

[0233] The server notifies the user of the finalized recipe via a "notification means" and stores the data, allowing the user to prepare a meal according to the recipe.

[0234] 8. Delivery Orders

[0235] Healthy meals are provided through a delivery service using a "delivery ordering means" that allows users to order meals based on suggested recipes.

[0236] Specific examples

[0237] An example of a prompt that the user might enter:

[0238] "Suggest calcium-rich recipes based on the user's dietary information. Breakfast: Yogurt and banana, Lunch: Chicken salad, Dinner: Grilled salmon."

[0239] As described above, by utilizing the system of the present invention, users can easily manage the nutritional balance of their daily meals and maintain a healthy diet. In addition, by ordering food delivery based on the suggested recipes, users can reduce their time and effort and instantly consume healthy meals.

[0240] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0241] Step 1:

[0242] The user inputs meal information.

[0243] Input: Meal name, ingredients used, and amount consumed (e.g., Breakfast: Yogurt and banana, Lunch: Chicken salad, Dinner: Grilled salmon)

[0244] Output: Input meal information

[0245] Specific operations: The user uses the smartphone application to input meal information into the input means.

[0246] Step 2:

[0247] The terminal transmits the input meal data to the server.

[0248] Input: Meal information entered by the user

[0249] Output: Meal data sent to the server

[0250] Specific operation: The smartphone application sends this data to the server via the Internet using its internal transmission means.

[0251] Step 3:

[0252] The server stores the transmitted meal data in a recording means.

[0253] Input: Submitted meal data

[0254] Output: Meal data stored in a database

[0255] Specific operation: The server connects to the database (PostgreSQL) and saves the data along with the user ID.

[0256] Step 4:

[0257] The server uses analytical means to evaluate the nutritional balance of the recorded dietary data.

[0258] Input: Saved meal data

[0259] Output: Nutritional balance evaluation results

[0260] Specific operation: The server's generative AI model (OpenAI GPT) calculates the nutritional value of each ingredient contained in the dietary data and evaluates the overall nutritional balance.

[0261] Step 5:

[0262] Based on the analysis results, the server uses the suggestion method to suggest recipes to supplement the missing nutrients.

[0263] Input: Nutritional balance evaluation results

[0264] Output: Suggested recipe

[0265] Specific operation: The server's generative AI model uses prompt text to generate recipes that supplement missing nutrients.

[0266] Example prompt: "Suggest calcium-enriched recipes based on the user's dietary information."

[0267] Step 6:

[0268] The user inputs feedback on the proposed recipe using the input means.

[0269] Input: User feedback on the suggested recipe (e.g., salmon was on sale today, I'm allergic to spinach)

[0270] Output: Input feedback

[0271] What it does: A user uses a smartphone application to provide feedback on a suggested recipe.

[0272] Step 7:

[0273] The server again suggests recipes using the suggestion means based on the user's feedback.

[0274] Input: User feedback

[0275] Output: Re-proposed recipe

[0276] How it works: The server's generative AI model generates new recipes that incorporate user feedback.

[0277] Step 8:

[0278] The server notifies the user of the final recipe using a notification means and stores it in a database.

[0279] Input: Confirmed recipe

[0280] Output: Final recipe notified and final recipe data saved

[0281] Specific operation: The server notifies the smartphone application of the confirmed recipe and saves it in the database.

[0282] Step 9:

[0283] The user orders food based on the confirmed recipe using a delivery ordering means.

[0284] Input: Confirmed recipe

[0285] Output: Delivery order

[0286] Specific operation: The user orders food based on the final recipe from a delivery service via a smartphone application.

[0287] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0288] This invention relates to a system that plans and manages a user's daily meal menu and supports a balanced and healthy diet. This system transmits meal information entered by the user to a server, analyzes the data, evaluates nutritional balance, and suggests suitable recipes. Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions, enabling it to flexibly suggest recipes according to the emotional state of each individual user.

[0289] Overview of program processing

[0290] 1. User input:

[0291] The user enters meal information into the device, including the name of the dish eaten, the ingredients used, and the amount consumed, for example, "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[0292] 2. Data transmission and storage:

[0293] The device sends the entered meal information to the server, which receives the data and records it in a database.

[0294] 3. Nutritional Balance Analysis:

[0295] The server uses the dietary information stored in the database to calculate the nutritional value of each ingredient, and the AI ​​generator then references the nutrient data for each ingredient to evaluate the overall nutritional balance.

[0296] 4. Recipe Suggestions:

[0297] Based on the analysis results, the server's AI will suggest recipes to the user to supplement the nutrients they are lacking. For example, if they are lacking in calcium, it will suggest a spinach and cheese omelet.

[0298] 5. User Feedback:

[0299] The user reviews the suggested recipe and enters any changes needed, special offers, or additional information about allergies, such as "Salmon was on sale today" or "I'm allergic to spinach."

[0300] 6. Re-proposal:

[0301] The generative AI will then suggest new recipes based on user feedback, such as grilled salmon and broccoli.

[0302] 7. Acquiring Emotion Data:

[0303] The device acquires the user's emotional data. The emotion engine uses sensor devices such as cameras and microphones to analyze the user's facial expressions and tone of voice. For example, if the user is tired or stressed, that data is acquired.

[0304] 8. Transmission and storage of emotional data:

[0305] The device transmits the acquired emotion data to the server, which receives the data and records it in a database.

[0306] 9. Sentiment Data Analysis:

[0307] The server analyzes the emotion data, and the generation AI refers to the emotion engine data and evaluates the user's current emotional state, thereby understanding the user's mental state.

[0308] 10. Emotional recipe suggestions:

[0309] The generative AI and emotion engine work together to suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, the system will suggest recipes using ingredients that have a relaxing effect.

[0310] 11. Final Recipe Notification and Saving:

[0311] The server notifies the user of the finalized recipe and saves the data, allowing the user to prepare meals according to the recipe.

[0312] Specific examples

[0313] As a specific example, consider the case where the user is "Mr. Tanaka."

[0314] 1. Enter your meal information:

[0315] Tanaka enters that she had "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner.

[0316] 2. Data transmission and storage:

[0317] The device sends the entered information to the server, which records it in a database along with "Tanaka-san's" ID.

[0318] 3. Nutritional Balance Analysis:

[0319] The server-generated AI analyzes the data and identifies calcium deficiency.

[0320] 4. Recipe Suggestions:

[0321] The generative AI suggests a "spinach and cheese omelet" to supplement calcium.

[0322] 5. User Feedback:

[0323] Tanaka gives feedback to the generating AI, saying, "Salmon was on sale."

[0324] 6. Re-proposal:

[0325] The generative AI now suggests "grilled salmon and broccoli."

[0326] 7. Acquiring Emotion Data:

[0327] When Tanaka is using the device, the emotion engine analyzes her facial expressions and tone of voice to detect when she is feeling stressed.

[0328] 8. Transmission and storage of emotional data:

[0329] The device transmits emotion data to a server, which receives the data and stores it in a long-term database.

[0330] 9. Sentiment Data Analysis:

[0331] The server's generated AI analyzes the emotional data and assesses that Tanaka is currently experiencing stress.

[0332] 10. Emotional recipe suggestions:

[0333] The generative AI suggests "chamomile tea and aloe salad," which uses ingredients with a relaxing effect.

[0334] 11. Final Recipe Notification and Saving:

[0335] The server sends the recipe for "chamomile tea and aloe salad" to Tanaka's device and records the data in the database. Tanaka prepares dinner according to the recipe.

[0336] In this way, the system efficiently manages the user's dietary information and emotional data, and contributes to improving and maintaining overall health by suggesting not only nutritionally balanced meals but also meals that are tailored to the user's mental state.

[0337] The processing flow will be explained below.

[0338] Step 1:

[0339] The user uses the device to input the details of the meals they have eaten. For example, Mr. Tanaka inputs "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[0340] Step 2:

[0341] The device sends the entered meal information to the server. The sent content includes the user ID and detailed information about the entered meal. This data is sent in JSON format.

[0342] Step 3:

[0343] The server stores the received data in a database. The stored information includes the user ID, meal details, and the date and time of sending. Specifically, it records the information as "User ID: tanaka123", "Date and time: 2023-10-01", "Breakfast: yogurt, banana", "Lunch: chicken salad", and "Dinner: grilled salmon".

[0344] Step 4:

[0345] The server calculates nutritional values ​​based on the dietary information stored in the database. The AI ​​then references the nutritional value data of each ingredient and evaluates the total nutritional value of the user. It calculates nutrients such as calcium from yogurt, potassium and vitamin C from bananas, and protein from chicken salad.

[0346] Step 5:

[0347] The AI ​​analyzes nutritional balance, including past dietary data. The server identifies nutrients that are lacking or over-consumption. For example, results such as "lack of calcium," "sufficient vitamin D," and "too much salt" can be obtained.

[0348] Step 6:

[0349] Based on the analysis results, the server's generative AI will suggest recipes to improve nutritional balance, such as a spinach and cheese omelet to supplement calcium.

[0350] Step 7:

[0351] The user can check the recipe suggestions from the AI ​​via their device and provide feedback if changes are needed due to the unavailability of certain ingredients or allergies, for example, by entering information such as "Salmon was on sale today" or "I'm allergic to spinach."

[0352] Step 8:

[0353] The generative AI takes user feedback into account and re-suggests new recipes, such as "grilled salmon and broccoli," depending on the user's preferences and the situation.

[0354] Step 9:

[0355] The device acquires the user's emotional data. The emotion engine analyzes the user's facial expressions and tone of voice via the camera and microphone to detect the user's emotional state. For example, it can detect that Mr. Tanaka is feeling stressed.

[0356] Step 10:

[0357] The device sends the acquired emotion data to the server, which receives the data and records it in a database. The emotion data includes the user ID, emotional state, and acquisition date and time.

[0358] Step 11:

[0359] The server analyzes the emotion data. The generative AI evaluates the user's current emotional state based on the data from the emotion engine. For example, it determines that the user is feeling stressed.

[0360] Step 12:

[0361] The generative AI suggests recipes based on the user's emotional state, using ingredients that reduce stress and fatigue. For example, it suggests a relaxing "chamomile tea and aloe salad."

[0362] Step 13:

[0363] The user reviews and selects the final recipe, the server sends the finalized recipe to the user's device, and the user prepares the meal according to the recipe.

[0364] Step 14:

[0365] The server saves the final recipe data in a database. This accumulates data for future analysis and recommendations. The saved information includes recipe details, submission date and time, and user ID. For example, "Recipe: Chamomile Tea and Aloe Salad," "Date and Time: 2023-10-01," and "User ID: tanaka123" might be recorded.

[0366] Through these steps, the system efficiently manages the user's dietary information and emotional data, ensuring nutritional balance while providing flexible dietary suggestions tailored to the user's emotional state, thereby helping to improve and maintain health.

[0367] Example 2

[0368] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0369] In today's modern dietary habits, many people find it difficult to maintain a balanced, healthy diet. It is also known that emotional states have a significant impact on food choices, and stress and fatigue can lead to poor dietary quality. However, conventional dietary management systems only focus on analyzing nutritional balance, and few of them provide recommendations that take the user's emotional state into account. The present invention aims to solve these problems.

[0370] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0371] In this invention, the server includes an input means for inputting the details of the meals the user has eaten, a transmission means for transmitting the input meal data to the server, and a recording means for recording the transmitted meal data. This allows for the collection and storage of meal information. The server also includes an analysis means for analyzing the recorded meal data and evaluating nutritional balance, a proposal means for proposing recipes to compensate for the nutritional balance based on the analysis results, an emotion analysis means for acquiring and analyzing the user's emotional state, an emotion-based proposal means for proposing recipes based on the user's emotional state, and a notification means for notifying the user of the final recipe and recording it. This allows the user to receive not only nutritionally balanced meal suggestions but also appropriate meal suggestions based on the user's emotional state.

[0372] The "input means" refers to a means for the user to input the details of the food they have eaten, such as an application on a smartphone or computer.

[0373] The "transmission means" is a means for transmitting the input meal data to the server, and uses a communication protocol such as an HTTP request.

[0374] The "recording means" is a means for recording the transmitted meal data in a database or the like, and may utilize a cloud service or a local server.

[0375] The "analysis means" is a means for analyzing the recorded dietary data and evaluating nutritional balance, and involves calculations using a generative AI model and a food database.

[0376] The "suggestion method" is a method for suggesting recipes to users to compensate for nutritional balance based on the analysis results, and uses a generative AI model.

[0377] The "feedback means" is a means for the user to input feedback about the proposed recipe, and is performed via a terminal.

[0378] The "re-suggestion means" is a means for re-suggesting recipes based on user feedback, and uses a generative AI model.

[0379] The "emotion analysis means" is a means for acquiring and analyzing the user's emotional state, and performs analysis using an emotion engine that utilizes sensors such as a camera and microphone.

[0380] The "emotion-responsive suggestion means" is a means for suggesting appropriate recipes based on the user's emotional state, and works in cooperation with a generative AI model and an emotion engine.

[0381] The "notification means" is a means for notifying and recording the final recipe to the user, and has a function for notifying the terminal and storing the data in the server.

[0382] The "sensor means" is a means for acquiring an emotional state, and includes hardware sensors such as a camera and a microphone.

[0383] The "additional input means" is a means for the user to input additional information such as sale information or allergy information, and is implemented using an input form or voice input.

[0384] The "long-term analysis means" is a means for analyzing the long-term nutritional balance with the aim of continuously improving and maintaining the user's health, and involves the long-term accumulation and analysis of data.

[0385] This invention relates to a system that plans and manages a user's daily meal menu and supports a balanced and healthy diet. This system sends the meal information entered by the user to a server, analyzes the data, evaluates the nutritional balance, and suggests suitable recipes. It can also analyze the user's emotional state and make flexible recipe suggestions based on that.

[0386] Specific Examples

[0387] Hardware and Software Configuration

[0388] 1. Device:

[0389] The device used by the user to input meal information and feedback is a smartphone, tablet, or PC. This device is equipped with sensors such as a camera and microphone, and can capture the user's emotional state.

[0390] 2. Server:

[0391] The server that receives, records, and analyzes the data sent by users can use a cloud service (e.g., Amazon Web Services, Google Cloud).The server is equipped with a database (e.g., MySQL, PostgreSQL) for storing and managing data.

[0392] 3. Generative AI Model:

[0393] A generative AI model (e.g., GPT-4) running on the server analyzes dietary and emotional data to generate and suggest appropriate recipes. This model works in conjunction with a food database (e.g., the USDA Nutrient Database) and a sentiment analysis engine.

[0394] System Operation

[0395] 1. User input:

[0396] Users input information about the meals they have eaten through the device's application, such as "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[0397] 2. Data transmission and storage:

[0398] The device sends the entered meal information to the server using the HTTPS protocol, which receives the data and records it in a database.

[0399] 3. Nutritional Balance Analysis:

[0400] Based on the dietary data stored on the server, the generative AI model calculates the nutritional value of each dish, and then refers to a food database to evaluate the overall nutritional balance.

[0401] 4. Recipe Suggestions:

[0402] Based on the analysis results, the generative AI model suggests recipes to supplement missing nutrients. For example, if you are lacking in calcium, it will suggest a "spinach and cheese omelet." The suggestions are displayed on the device screen.

[0403] 5. User Feedback:

[0404] The user reviews the suggested recipes and, if necessary, enters additional information about specials or allergies. For example, they might enter, "Salmon is on sale today" or "I'm allergic to spinach."

[0405] 6. Re-proposal:

[0406] The server receives user feedback, and the generative AI model suggests new recipes, for example, re-proposing "grilled salmon and broccoli."

[0407] 7. Acquiring Emotion Data:

[0408] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and tone of voice to obtain emotional data. This is automatically executed when the user is operating the smartphone.

[0409] 8. Transmission and storage of emotional data:

[0410] The acquired emotion data is sent to the server via HTTPS protocol and recorded in a database.

[0411] 9. Sentiment Data Analysis:

[0412] A generative AI model analyzes the emotional data and assesses the user's current emotional state, determining whether they are stressed or relaxed.

[0413] 10. Emotional recipe suggestions:

[0414] The generative AI model and emotion engine work together to suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, the system will suggest a "chamomile tea and aloe salad" using ingredients that have a relaxing effect.

[0415] 11. Final Recipe Notification and Saving:

[0416] The server notifies the user of the confirmed recipe and stores the data in a database, allowing the user to prepare meals based on the recipe.

[0417] Specific examples

[0418] Examples of prompts include:

[0419] "Enter Ana's meal information. Example: 'Breakfast: Yogurt and banana. Lunch: Chicken salad. Dinner: Grilled salmon'"

[0420] This allows the system to efficiently manage the user's dietary information and emotional data, and contribute to improving and maintaining overall health by suggesting not only nutritionally balanced meals but also meals that correspond to the user's emotional state.

[0421] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0422] Step 1:

[0423] User Input

[0424] The user uses a device (smartphone, tablet, or PC) to enter meal information. For example, they might enter "Breakfast: yogurt and banana," "Lunch: chicken salad," and "Dinner: grilled salmon."

[0425] Input: Dietary information such as what was eaten, ingredients used, and intake amounts.

[0426] Output: Meal information data that can be sent and displayed on the device.

[0427] Step 2:

[0428] Data transmission and storage

[0429] The device sends the meal information to the server. When the user presses the send button, the data is sent to the server via HTTPS. The server stores the received data in a database (e.g., MySQL or PostgreSQL).

[0430] Input: Submitted meal information data.

[0431] Output: Meal information stored in a database.

[0432] Step 3:

[0433] Nutritional balance analysis

[0434] The server uses the dietary data stored in the database to calculate the nutritional value of each dish, and the generative AI model then references a food database (e.g., USDA Nutrient Database) to evaluate the overall nutritional balance.

[0435] Input: Meal information data, food database.

[0436] Output: Nutritional balance assessment results.

[0437] Step 4:

[0438] Recipe Suggestions

[0439] Based on the analysis results, the generative AI model suggests recipes to supplement missing nutrients. For example, if you are lacking in calcium, it will suggest a "spinach and cheese omelet." This suggestion is displayed on the device screen.

[0440] Input: Nutritional balance assessment results.

[0441] Output: Suggested recipe information.

[0442] Step 5:

[0443] User Feedback

[0444] The user uses the device to review the suggested recipes and optionally enter feedback, such as special offers or allergy information. For example, "Salmon is on sale today" or "I'm allergic to spinach."

[0445] Input: Additional information such as special offers, allergy information, etc.

[0446] Output: Feedback data on the device.

[0447] Step 6:

[0448] re-proposal

[0449] The server receives the user's feedback, and the generative AI model re-proposes a new recipe, for example, "grilled salmon and broccoli." This suggestion is also displayed on the device screen.

[0450] Input: Feedback data.

[0451] Output: Re-suggested recipe information.

[0452] Step 7:

[0453] Acquiring emotion data

[0454] The emotion engine uses sensors such as the device's camera and microphone to analyze the user's facial expressions and tone of voice, and acquires emotional data. This is automatically executed when the user is operating the smartphone.

[0455] Input: User's facial expression data, voice data.

[0456] Output: The obtained emotion data.

[0457] Step 8:

[0458] Sending and storing emotional data

[0459] The device transmits the acquired emotion data to the server, which receives the data and records it in a database.

[0460] Input: The acquired emotion data.

[0461] Output: Emotion data stored in a database.

[0462] Step 9:

[0463] Sentiment Data Analysis

[0464] The server's generative AI model analyzes the emotion data and assesses the user's current emotional state, for example, determining whether they are stressed or relaxed.

[0465] Input: Stored emotion data.

[0466] Output: User's emotional state assessment result.

[0467] Step 10:

[0468] Emotion-based recipe suggestions

[0469] The generative AI model and emotion engine work together to suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, the system will suggest a relaxing dish called "chamomile tea and aloe salad."

[0470] Input: User's emotional state assessment results.

[0471] Output: Suggested recipe information based on emotional state.

[0472] Step 11:

[0473] Notification and saving of final recipe

[0474] The server notifies the user of the confirmed recipe and stores the data in a database, allowing the user to prepare meals based on the recipe.

[0475] Input: Final recipe information.

[0476] Output: Recipe information notified to the user's device, recipe information saved in the database.

[0477] (Application example 2)

[0478] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0479] Conventional nutrition management systems evaluate nutritional balance based solely on the user's dietary information and suggest appropriate recipes, but do not consider the mental state or emotions of each individual user. As a result, it is difficult to provide comprehensive support that also takes into account the user's mental health. Furthermore, there was no mechanism for reflecting the suggested recipes in actual food delivery, which meant it took time and effort for users to reflect the suggested recipes in their actual meals.

[0480] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for inputting the contents of the meals the user has eaten, a transmission means for transmitting the input meal data to the server, a recording means for recording the transmitted meal data, an analysis means for analyzing the recorded meal data and evaluating nutritional balance, a suggestion means for suggesting recipes to compensate for the nutritional balance based on the analysis results, a feedback means for the user to input feedback on the recipes, a sentiment analysis means for acquiring and analyzing the user's emotional data, a re-suggestion means for re-suggesting recipes based on the sentiment analysis means, an ordering means for ordering the suggested recipe from a food delivery service, and a notification means for notifying the user of the final recipe and recording it. This makes it possible to suggest flexible and healthy eating habits according to the user's emotional state and to arrange food delivery that actually reflects the suggestions in real time.

[0481] The "input means for inputting the details of the meal taken by the user" is an interface that allows the user to input the details, ingredients, and intake amount of the meal into the terminal.

[0482] The "transmission means for transmitting input meal data to the server" is a communication function for transmitting meal data from the terminal to the server.

[0483] The "recording means for recording transmitted meal data" is a function for storing transmitted meal data in a database.

[0484] The "analysis means for analyzing recorded dietary data and evaluating nutritional balance" is a system for calculating the nutrients of each ingredient based on the recorded data and evaluating the overall nutritional balance.

[0485] The "means for proposing recipes to compensate for nutritional imbalance based on the analysis results" is a function that generates a menu to compensate for missing nutrients based on the analysis results.

[0486] The "feedback means for users to input feedback about recipes" is an interface for users to input opinions and information about suggested recipes.

[0487] The "emotion analysis means for acquiring and analyzing user emotion data" refers to a sensor and analysis engine for analyzing the user's facial expressions and tone of voice to understand their emotional state.

[0488] The "re-suggestion means for re-suggesting recipes based on emotion analysis means" is a function for re-suggesting appropriate recipes by taking into account emotion data.

[0489] "Means for arranging to order the suggested recipe from a food delivery service" is a function for ordering ingredients and dishes from a food delivery service based on the suggested recipe.

[0490] The "notification means for notifying the user of the final recipe and recording it" is a function for notifying the user of the final recipe and recording that information in a database.

[0491] This invention is a system that plans and manages a user's daily meal menu and supports a balanced diet. Users can input information about the meals they have eaten, and the system analyzes that information to evaluate the nutritional balance. The system also grasps the user's emotional state and makes flexible recipe suggestions based on that. Furthermore, it provides a mechanism for reflecting the suggested recipes in a food delivery service.

[0492] User Interface and Input Methods

[0493] First, the user inputs meal information using a device such as a smartphone. The input interface is used to input the meal contents, ingredients used, and intake amount. For example, a specific menu item such as "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon" can be input. The information entered by the user is sent to the server in real time and recorded in a database.

[0494] Server and Data Analysis

[0495] The server receives the input data and records it in a database. The recorded data is then analyzed to assess nutritional balance. The nutrition database is referenced, the nutrients for each ingredient are calculated, and the overall nutritional balance is assessed. This process is carried out using Python and the relevant nutrition database APIs.

[0496] Recipe suggestions

[0497] Based on the analysis results, the server uses a generative AI model to suggest recipes to compensate for missing nutrients. For example, if a user is lacking in calcium, it will suggest a "spinach and cheese omelet." The suggested recipe is then notified to the user.

[0498] Feedback and sentiment data

[0499] Users can provide feedback on the suggested recipes. For example, they can provide information such as "Salmon was on sale today" or "I'm allergic to spinach." The system also collects user emotional data. The emotion analysis engine uses a camera and microphone to analyze the user's facial expressions and tone of voice to assess their stress and fatigue levels.

[0500] Re-proposal and food delivery arrangements

[0501] Based on the acquired emotional data, the server uses the generative AI and emotion analysis engine to re-suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, it will suggest "chamomile tea and aloe salad." The final recipe is then ordered from a food delivery service, and the user is notified of the decision.

[0502] Specific examples

[0503] For example, if the user is "Mr. Tanaka," he inputs that he had "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner. The server receives this and analyzes that he is lacking in calcium. It then suggests "spinach and cheese omelette," but Mr. Tanaka gives feedback that "salmon was on sale." The server then re-suggests "grilled salmon and broccoli."

[0504] Prompt Sentence Examples

[0505] "The user entered today's diet information: yogurt and banana for breakfast, chicken salad for lunch, and grilled salmon for dinner. The user is currently feeling stressed. Please suggest a dinner recipe that takes into consideration nutritional balance and uses ingredients that have a relaxing effect."

[0506] In this way, this invention efficiently manages the user's dietary information and emotional data, and not only proposes nutritionally balanced meals but also flexibly suggests meals that correspond to the user's emotional state. Furthermore, by reflecting the suggested recipes in the actual food delivery service, it contributes to improving and maintaining the user's health.

[0507] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0508] Step 1:

[0509] Users use a device such as a smartphone to input the details of the meal they ate. Specifically, they enter the name of the meal, the ingredients used, the amount consumed, etc. into an input form. Once this information is entered, the device immediately sends the data to the server.

[0510] Input: User's dietary information (e.g., yogurt and banana for breakfast, chicken salad for lunch, grilled salmon for dinner)

[0511] Output: Meal data sent to the server

[0512] Step 2:

[0513] The device sends the entered meal data to a server, which receives the data and records it in a database.

[0514] Input: Meal data sent from the device

[0515] Output: Meal data stored in a database

[0516] Step 3:

[0517] The server uses the dietary data stored in the database to calculate the value of each nutrient and evaluate the overall nutritional balance. The generative AI model references the nutrition database to identify the necessary nutrients. This step uses Python and related nutrition database APIs.

[0518] Input: Dietary data recorded in the database

[0519] Output: Nutritional balance evaluation results

[0520] Step 4:

[0521] The server uses a generative AI model to evaluate nutritional balance and suggests recipes to supplement missing nutrients.

[0522] Input: Nutritional balance evaluation results

[0523] Output: Suggested recipe (e.g. spinach and cheese omelette)

[0524] Step 5:

[0525] The user can then enter feedback on the suggested recipe, such as allergies or special offers, which is then sent back to the server.

[0526] Input: User feedback information (e.g., salmon was on sale, I'm allergic to spinach)

[0527] Output: Feedback information sent to the server

[0528] Step 6:

[0529] The server receives the user's feedback and proposes new recipes, and the generative AI model generates new recipes based on the feedback.

[0530] Input: Feedback information

[0531] Output: Recipe suggestions (e.g., grilled salmon and broccoli)

[0532] Step 7:

[0533] To obtain the user's emotional data, the device uses sensor devices such as a camera and microphone to analyze the user's facial expressions and tone of voice and evaluate their emotional state.

[0534] Input: User facial and voice data

[0535] Output: Emotion data

[0536] Step 8:

[0537] The device transmits the acquired emotion data to the server, which receives the data and records it in a database.

[0538] Input: Emotion data sent from the device

[0539] Output: Emotion data stored in a database

[0540] Step 9:

[0541] The server analyzes the emotional data and evaluates the user's current emotional state. The generative AI model then refers to the emotional data and evaluates the emotional state.

[0542] Input: Emotion data stored in a database

[0543] Output: Emotional state assessment result

[0544] Step 10:

[0545] A generative AI model and an emotion analysis engine work together to suggest recipes based on the user's emotional state.

[0546] Input: Emotional state assessment result

[0547] Output: Suggested recipes based on emotions (e.g., chamomile tea and aloe salad)

[0548] Step 11:

[0549] The server notifies the user of the confirmed recipe and records the data in a database. The user then places an order with the food delivery service based on the proposed recipe.

[0550] Input: Final recipe

[0551] Output: Recipe notification and food delivery order to the user

[0552] Through the above steps, the present invention efficiently manages the user's dietary information and emotional data, and realizes flexible meal suggestions and food delivery arrangements that take into account both nutritional balance and emotional state.

[0553] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0554] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0555] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0556] [Second embodiment]

[0557] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0558] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0559] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0560] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0561] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0562] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0563] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0564] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0565] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0566] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0567] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0568] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0569] This invention relates to a system that allows users to easily plan and manage their daily meal menus and supports a balanced and healthy diet. This system sends the meal information entered by the user to a server, which analyzes the data, evaluates the nutritional balance, and suggests suitable recipes.

[0570] Overview of program processing

[0571] 1. User input:

[0572] The user enters meal information, including the name of the dish eaten, the ingredients used, and the amount consumed. For example, "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[0573] 2. Data transmission and storage:

[0574] The device sends the entered meal information to the server, which receives the data and records it in a database.

[0575] 3. Nutritional Balance Analysis:

[0576] The server uses the dietary information stored in the database to calculate the nutritional value of each ingredient, and the AI ​​generator then references the nutrient data for each ingredient to evaluate the overall nutritional balance.

[0577] 4. Recipe Suggestions:

[0578] Based on the analysis results, the server's AI will suggest recipes to the user to supplement the nutrients they are lacking. For example, if they are lacking in calcium, it will suggest a spinach and cheese omelet.

[0579] 5. User Feedback:

[0580] Users can review the suggested recipes and enter any changes they need, special offers, or additional information about allergies, such as "Salmon was on sale today" or "I'm allergic to spinach."

[0581] 6. Re-proposal:

[0582] The generative AI will then suggest new recipes based on user feedback, such as grilled salmon and broccoli.

[0583] 7. Notify and save the final recipe:

[0584] The server notifies the user of the finalized recipe and stores the data, allowing the user to prepare a meal according to the recipe.

[0585] Specific examples

[0586] As a specific example, consider the case where the user is "Mr. Tanaka."

[0587] 1. Enter your meal information:

[0588] Tanaka enters that she had "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner.

[0589] 2. Data transmission and storage:

[0590] The device sends the entered information to the server, which records it in a database along with "Tanaka-san's" ID.

[0591] 3. Nutritional Balance Analysis:

[0592] The server-generated AI analyzes the data and identifies calcium deficiency.

[0593] 4. Recipe Suggestions:

[0594] The generative AI suggests a "spinach and cheese omelet" to supplement calcium.

[0595] 5. User Feedback:

[0596] Tanaka gives feedback to the generating AI, saying, "Salmon was on sale."

[0597] 6. Re-proposal:

[0598] The generative AI now suggests "grilled salmon and broccoli."

[0599] 7. Notify and save the final recipe:

[0600] The server sends the recipe for "grilled salmon and broccoli" to Tanaka's device and saves the data. Tanaka then prepares a healthy dinner according to the recipe.

[0601] In this way, the system efficiently manages the user's dietary information and suggests nutritionally balanced meals, thereby contributing to the maintenance and improvement of health.

[0602] The processing flow will be explained below.

[0603] Step 1:

[0604] The user uses the device to input the details of the meal they ate, including the name of the dish, the ingredients used, the amount consumed, and the cooking method. For example, they might input "Breakfast: yogurt, banana, toast," "Lunch: chicken salad," and "Dinner: grilled salmon, salad, miso soup."

[0605] Step 2:

[0606] The device sends the entered meal information to the server. The sent content includes the user ID and detailed meal information. The data is sent in an appropriate format, such as JSON.

[0607] Step 3:

[0608] The server stores the received data in a database. In addition to the meal information, the date and time of sending and the user ID are also recorded. For example, "User: Tanaka", "Date and time: 2023-10-01", "Breakfast: Yogurt, banana, toast", "Lunch: Chicken salad", "Dinner: Grilled salmon, salad, miso soup" might be recorded.

[0609] Step 4:

[0610] The server calculates the nutritional value of each ingredient based on the dietary information stored in the database. The generative AI retrieves the nutritional value of each ingredient from the database and evaluates the nutritional balance of the entire meal. For example, the nutrients of yogurt (calcium, protein), banana (potassium, vitamin C), and toast (carbohydrates, fiber) are calculated.

[0611] Step 5:

[0612] The generative AI also references past dietary data to analyze long-term nutritional intake, determining whether calcium is insufficient, vitamin D is sufficient, or salt is excessive. For example, the analysis results may include "calcium deficiency," "sufficient vitamin D," or "excess salt."

[0613] Step 6:

[0614] Based on the analysis results, the generative AI will suggest recipes suitable for the user. It will suggest balanced meals, such as recipes to supplement missing nutrients or to reduce excess intake of nutrients. For example, it will suggest a "spinach and cheese omelet" to supplement calcium.

[0615] Step 7:

[0616] The user checks the recipe suggestions from the AI ​​via their device. If the suggestions need to be changed due to reasons such as not being able to obtain certain ingredients or allergies, the user can communicate this information to the AI. For example, they can say, "Salmon was on sale today, so it was cheap."

[0617] Step 8:

[0618] The generative AI reflects user feedback and proposes new recipes, allowing for flexible responses to suit the user's preferences and circumstances. For example, it suggests "grilled salmon and broccoli."

[0619] Step 9:

[0620] The user reviews and selects the final recipe, the server sends the finalized recipe to the user's device, and the user prepares the meal according to the recipe.

[0621] Step 10:

[0622] The server saves the final recipe data in a database. This allows data to be accumulated for future analysis and recommendations. For example, "Recipe: Grilled Salmon and Broccoli," "Date and Time: 2023-10-01," and "User ID: tanaka123" are recorded.

[0623] Through these steps, the system efficiently manages the user's dietary information and suggests nutritionally balanced meals, allowing the user to maintain a healthy diet without any effort.

[0624] Example 1

[0625] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0626] In modern society, many users find it difficult to maintain a balanced diet, and dietary management is often neglected, especially in busy daily lives. In addition, each user has different nutritional needs, making it difficult to provide appropriate nutritional advice and recipes tailored to individual conditions. Traditional manual dietary management methods are inefficient and lack appropriate support measures for continuous health maintenance and improvement.

[0627] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0628] In this invention, the server includes an input means for inputting the details of the meals a user has eaten, a transmission means for transmitting the input meal data to the server, and a recording means for recording the transmitted meal data. This allows users to accurately and efficiently manage their own meal data. The server also includes an analysis means for analyzing the recorded meal data using a generative AI model to evaluate nutritional balance, a suggestion means for sending prompts to the generative AI model to suggest recipes to compensate for nutritional imbalance, a re-suggestion means for re-suggesting recipes using the generative AI model based on user feedback, and a notification means for notifying the user of the final recipe and recording it. This allows for appropriate meal suggestions based on each user's nutritional needs, enabling continuous improvement and maintenance of the user's health.

[0629] The "input means" refers to a device or interface that allows the user to input the details of the meal they have eaten.

[0630] "Transmission means" refers to a function or device for transmitting the meal data entered by the user to the server.

[0631] The "recording means" refers to a database or storage system for saving and managing the transmitted meal data.

[0632] "Analysis means using generative AI models" refers to devices or systems that use AI technology to analyze recorded dietary data and evaluate nutritional balance.

[0633] A "prompt sentence" is an input sentence that gives specific instructions to a generative AI model.

[0634] "Proposal means" refers to a function or device that uses a generative AI model to provide users with recipes to compensate for nutritional balance based on the analysis results.

[0635] A "feedback means" is a function or device that allows a user to input opinions or additional information about a recipe.

[0636] A "re-proposal means" is a function or device that uses a generative AI model to re-propose a recipe based on user feedback.

[0637] The "notification means" is a function or device for notifying the user of the final recipe and recording the data.

[0638] This invention relates to a system that allows users to easily plan and manage their daily meal menus and supports a balanced and healthy diet. This system sends the meal information entered by the user to a server, which analyzes the data, evaluates the nutritional balance, and suggests suitable recipes.

[0639] System configuration

[0640] Input Method

[0641] Users enter their meal details using a smartphone app or web interface. The information entered includes the name of the dish, the ingredients used, and the amount consumed. For example, breakfast might include "yogurt and banana," lunch might include "chicken salad," and dinner might include "grilled salmon."

[0642] Transmission method

[0643] The device sends the meal information entered by the user to the server using an HTTP POST request.

[0644] Recording means

[0645] The server records the received meal data in a database, which is used to store each user's meal history and nutritional information. For example, meal details are stored along with the user ID.

[0646] Analytical tools using generative AI models

[0647] The server uses a generative AI model to calculate the nutritional value of each ingredient based on the recorded dietary data. The generative AI model then refers to the nutrient data of the ingredients and evaluates the overall nutritional balance. This evaluation is performed by sending prompt sentences to the generative AI model.

[0648] Proposal means

[0649] The generative AI model then suggests recipes to improve nutritional balance based on the analysis results. For example, if a person is lacking in calcium, it suggests a spinach and cheese omelette.

[0650] Feedback Methods

[0651] Users review the suggested recipes and enter any missing information or specific requirements (such as special offers or allergies), for example, "Salmon was on sale today" or "I'm allergic to spinach."

[0652] Re-proposal means

[0653] The generative AI model re-suggests new recipes based on user feedback, for example, suggesting "grilled salmon and broccoli."

[0654] Notification means

[0655] The server notifies the user of the final recipe and records the data. The user can prepare a meal according to the recipe. Notifications are sent to the device using push notifications or email notifications.

[0656] Specific examples

[0657] For example, if the user is "Tanaka-san":

[0658] 1. Enter your meal information

[0659] Tanaka enters "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner.

[0660] 2. Data transmission and storage

[0661] The terminal sends the entered information to the server, which records it in a database along with Tanaka's ID.

[0662] 3. Analysis of nutritional balance

[0663] The server's generated AI model analyzes Tanaka's data and identifies that he is deficient in calcium.

[0664] 4. Recipe suggestions

[0665] The generative AI model suggests a "spinach and cheese omelet" to supplement calcium.

[0666] 5. User Feedback

[0667] Tanaka provides feedback to the generative AI model that "salmon was on sale."

[0668] 6. Re-proposal

[0669] The generative AI model now suggests "grilled salmon and broccoli."

[0670] 7. Notification and saving of final recipe

[0671] The server sends the recipe for "grilled salmon and broccoli" to Tanaka's device and saves the data. Tanaka then prepares a healthy dinner according to the recipe.

[0672] This system suggests specific, nutritionally balanced recipes by sending the prompt text "User ID: Tanaka, Meal information: Breakfast - yogurt and banana, Lunch - chicken salad, Dinner - grilled salmon. Analyze nutritional balance and check for missing nutrients. Then suggest suitable recipes to supplement those nutrients" to the generative AI model.

[0673] In this way, users can efficiently manage their own dietary data and use it to maintain and improve their health.

[0674] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0675] Step 1:

[0676] The user inputs the details of the food they have eaten.

[0677] Input: The user enters the names of the dishes for breakfast, lunch, and dinner, the ingredients used, and the amount consumed into an input form on the terminal.

[0678] How it works: Users use a smartphone app or web interface to enter meal information using a keyboard or touch panel.

[0679] Output: The entered meal information is saved in the device.

[0680] Step 2:

[0681] The terminal transmits the meal information to the server.

[0682] Input: Meal information stored on your device.

[0683] How it works: The device sends the entered meal information to the server using an HTTP POST request.

[0684] Output: Meal information is sent to the server.

[0685] Step 3:

[0686] The server records the received meal information in a database.

[0687] Input: Meal information sent to the server.

[0688] How it works: The server stores the received data in a database using INSERT statements, for example, "Tanaka's ID, Breakfast - yogurt and banana, Lunch - chicken salad, Dinner - grilled salmon".

[0689] Output: The recorded meal information is stored in a database.

[0690] Step 4:

[0691] The server-generated AI model analyzes the dietary information and evaluates nutritional balance.

[0692] Input: Meal information stored in a database.

[0693] How it works: The server extracts the user's dietary information from the database using a SELECT statement and sends a prompt to the generative AI model. The prompt reads, "User ID: Tanaka, Breakfast - Yogurt and banana, Lunch - Chicken salad, Dinner - Grilled salmon. Analyze the nutritional balance and check for any missing nutrients." The generative AI model then analyzes and evaluates the nutritional balance.

[0694] Output: The nutritional balance evaluation results are returned from the generative AI model.

[0695] Step 5:

[0696] Based on the analysis results, the server suggests recipes to improve nutritional balance.

[0697] Input: Nutritional balance assessment results returned by the generative AI model.

[0698] How it works: Based on the evaluation results, the server sends a new prompt to the generative AI model to generate a suitable recipe. For example, "I'm lacking calcium, so please suggest a recipe to supplement my calcium."

[0699] Output: The generative AI model returns a suitable recipe suggestion, for example, "Spinach and Cheese Omelette."

[0700] Step 6:

[0701] The user provides feedback on the suggested recipe.

[0702] Input: A recipe provided by the server.

[0703] How it works: The user reviews the proposed recipe and enters any specials, allergies, or other specific requirements into a feedback form. For example, "Salmon was on sale today" or "I'm allergic to spinach."

[0704] Output: Feedback information is saved to the device.

[0705] Step 7:

[0706] The terminal transmits the feedback information to the server.

[0707] Input: Feedback information stored on the device.

[0708] How it works: The device sends feedback information to the server using an HTTP POST request.

[0709] Output: The feedback information is sent to the server.

[0710] Step 8:

[0711] The server's generative AI model re-proposes new recipes based on the feedback information.

[0712] Input: The feedback information sent to the server.

[0713] How it works: The server sends a new prompt to the generative AI model, suggesting a new recipe that takes the feedback into account. For example, "User ID: Tanaka, salmon is on sale and I'm allergic to spinach. Please suggest a new recipe."

[0714] Output: The generative AI model returns a new recipe suggestion, for example, "Grilled Salmon and Broccoli."

[0715] Step 9:

[0716] The server notifies the user of the final recipe and records the data.

[0717] Input: The final recipe returned from the generative AI model.

[0718] Operation: The server saves the final recipe information in the database and notifies the device via an HTTP response. The device displays the notification to the user and allows them to view the recipe.

[0719] Output: The final recipe information is saved in the database and on the device, and is notified to the user.

[0720] In this way, the system manages the user's dietary information through each step and supports the user's health by suggesting recipes that take nutritional balance into consideration.

[0721] (Application example 1)

[0722] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0723] Conventional food delivery services have had the problem of making it difficult for users to select meals that take into account healthy nutritional balance. In particular, there has been a lack of specific suggestions for supplementing nutrients lacking in daily meals, and meal delivery services based on such suggestions. As a result, users have had to go through the trouble of researching nutritional balance and choosing meals themselves.

[0724] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0725] In this invention, the server includes an input means for inputting the contents of the meal consumed by the user, a transmission means for transmitting the input meal data to the server, a recording means for recording the transmitted meal data, an analysis means for analyzing the recorded meal data and evaluating the nutritional balance, a proposal means for proposing recipes to compensate for the nutritional balance based on the analysis results, a feedback means for the user to input feedback on the recipe, a re-proposal means for re-proposing a recipe based on the user's feedback, a notification means for notifying the user of the final recipe and recording it, and a delivery order means for ordering a meal based on the proposed recipe.

[0726] This allows users to easily manage the nutritional balance of their daily meals and order delivery meals based on suggested healthy recipes, thereby improving the quality of their diet and helping them maintain and improve their health.

[0727] The "input means" refers to a device or interface that allows the user to input the details of the meal they have eaten.

[0728] The "transmission means" is a communication function for transmitting the input meal data to the server.

[0729] "Recording means" refers to devices or software for storing and recording the transmitted dietary data in a database or the like.

[0730] "Analysis means" refers to algorithms or programs that evaluate nutritional balance based on recorded dietary data and identify necessary nutrients.

[0731] The "suggestion method" is a function that uses a generative AI model to suggest recipes to supplement the user's missing nutrients based on the analysis results.

[0732] The "feedback means" is an interface that allows the user to input feedback such as opinions and improvements regarding the proposed recipe.

[0733] A "re-proposal method" is an algorithm or program that regenerates and proposes new recipes based on user feedback.

[0734] The "notification means" is a notification function for notifying the user of the finalized recipe.

[0735] The "delivery ordering means" is a function for ordering food based on the suggested recipe from a delivery service.

[0736] The "additional input means" is an interface that allows the user to input additional information such as sale item information and allergy information.

[0737] The "long-term analysis means" refers to an algorithm or program that analyzes data on long-term nutritional balance with the aim of continuously improving and maintaining the user's health.

[0738] MODE FOR CARRYING OUT THE INVENTION

[0739] The present invention relates to a system that allows users to easily plan and manage their daily meal menus and supports a balanced and healthy diet. This system includes an "input means," "transmission means," "recording means," "analysis means," "suggestion means," "feedback means," "re-suggestion means," "notification means," and "delivery ordering means."

[0740] System configuration

[0741] Hardware

[0742] Device: The smartphone used by the user (Android, iOS)

[0743] Server: Cloud server for processing and storing data

[0744] software

[0745] Database: PostgreSQL is used to store and manage user meal information.

[0746] Backend framework: Python and Flask will be used to build an API to input food information, analyze nutritional balance, suggest recipes, and process orders.

[0747] Generative AI model: Uses OpenAI's GPT to generate nutritionally balanced recipes.

[0748] Front-end framework: React Native is used to build the user interface.

[0749] System processing flow

[0750] 1. Enter your meal information

[0751] An "input method" is provided for users to input the name of the dish they ate, the ingredients used, and the intake amount. For example, they can input "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[0752] 2. Data transmission and storage

[0753] The user's device has a "transmission means" for transmitting the input meal information to the server, and the server stores the received data in a database as a "recording means."

[0754] 3. Analysis of nutritional balance

[0755] The server evaluates the nutritional balance of the recorded dietary data using an "analysis tool." The generative AI model (OpenAI GPT) references the nutrients in each ingredient and calculates the overall nutritional balance.

[0756] 4. Recipe suggestions

[0757] Based on the analysis results, the system will suggest recipes to the user to make up for any missing nutrients. For example, if a user is lacking in calcium, the system will suggest a "spinach and cheese omelet."

[0758] 5. User Feedback

[0759] Users can enter feedback on the suggested recipes using the "Feedback Tool." For example, they can add information such as "Salmon was on sale today" or "I'm allergic to spinach."

[0760] 6. Re-proposal

[0761] The server re-proposes new recipes based on the user's feedback using the "re-proposition method." For example, it suggests "grilled salmon and broccoli."

[0762] 7. Notification and saving of final recipe

[0763] The server notifies the user of the finalized recipe via a "notification means" and stores the data, allowing the user to prepare a meal according to the recipe.

[0764] 8. Delivery Orders

[0765] Healthy meals are provided through a delivery service using a "delivery ordering means" that allows users to order meals based on suggested recipes.

[0766] Specific examples

[0767] An example of a prompt that the user might enter:

[0768] "Suggest calcium-rich recipes based on the user's dietary information. Breakfast: Yogurt and banana, Lunch: Chicken salad, Dinner: Grilled salmon."

[0769] As described above, by utilizing the system of the present invention, users can easily manage the nutritional balance of their daily meals and maintain a healthy diet. In addition, by ordering food delivery based on the suggested recipes, users can reduce their time and effort and instantly consume healthy meals.

[0770] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0771] Step 1:

[0772] The user inputs meal information.

[0773] Input: Meal name, ingredients used, and amount consumed (e.g., Breakfast: Yogurt and banana, Lunch: Chicken salad, Dinner: Grilled salmon)

[0774] Output: Input meal information

[0775] Specific operations: The user uses the smartphone application to input meal information into the input means.

[0776] Step 2:

[0777] The terminal transmits the input meal data to the server.

[0778] Input: Meal information entered by the user

[0779] Output: Meal data sent to the server

[0780] Specific operation: The smartphone application sends this data to the server via the Internet using its internal transmission means.

[0781] Step 3:

[0782] The server stores the transmitted meal data in a recording means.

[0783] Input: Submitted meal data

[0784] Output: Meal data stored in a database

[0785] Specific operation: The server connects to the database (PostgreSQL) and saves the data along with the user ID.

[0786] Step 4:

[0787] The server uses analytical means to evaluate the nutritional balance of the recorded dietary data.

[0788] Input: Saved meal data

[0789] Output: Nutritional balance evaluation results

[0790] Specific operation: The server's generative AI model (OpenAI GPT) calculates the nutritional value of each ingredient contained in the dietary data and evaluates the overall nutritional balance.

[0791] Step 5:

[0792] Based on the analysis results, the server uses the suggestion method to suggest recipes to supplement the missing nutrients.

[0793] Input: Nutritional balance evaluation results

[0794] Output: Suggested recipe

[0795] Specific operation: The server's generative AI model uses prompt text to generate recipes that supplement missing nutrients.

[0796] Example prompt: "Suggest calcium-enriched recipes based on the user's dietary information."

[0797] Step 6:

[0798] The user inputs feedback on the proposed recipe using the input means.

[0799] Input: User feedback on the suggested recipe (e.g., salmon was on sale today, I'm allergic to spinach)

[0800] Output: Input feedback

[0801] What it does: A user uses a smartphone application to provide feedback on a suggested recipe.

[0802] Step 7:

[0803] The server again suggests recipes using the suggestion means based on the user's feedback.

[0804] Input: User feedback

[0805] Output: Re-proposed recipe

[0806] How it works: The server's generative AI model generates new recipes that incorporate user feedback.

[0807] Step 8:

[0808] The server notifies the user of the final recipe using a notification means and stores it in a database.

[0809] Input: Confirmed recipe

[0810] Output: Final recipe notified and final recipe data saved

[0811] Specific operation: The server notifies the smartphone application of the confirmed recipe and saves it in the database.

[0812] Step 9:

[0813] The user orders food based on the confirmed recipe using a delivery ordering means.

[0814] Input: Confirmed recipe

[0815] Output: Delivery order

[0816] Specific operation: The user orders food based on the final recipe from a delivery service via a smartphone application.

[0817] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0818] This invention relates to a system that plans and manages a user's daily meal menu and supports a balanced and healthy diet. This system transmits meal information entered by the user to a server, analyzes the data, evaluates nutritional balance, and suggests suitable recipes. Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions, enabling it to flexibly suggest recipes according to the emotional state of each individual user.

[0819] Overview of program processing

[0820] 1. User input:

[0821] The user enters meal information into the device, including the name of the dish eaten, the ingredients used, and the amount consumed, for example, "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[0822] 2. Data transmission and storage:

[0823] The device sends the entered meal information to the server, which receives the data and records it in a database.

[0824] 3. Nutritional Balance Analysis:

[0825] The server uses the dietary information stored in the database to calculate the nutritional value of each ingredient, and the AI ​​generator then references the nutrient data for each ingredient to evaluate the overall nutritional balance.

[0826] 4. Recipe Suggestions:

[0827] Based on the analysis results, the server's AI will suggest recipes to the user to supplement the nutrients they are lacking. For example, if they are lacking in calcium, it will suggest a spinach and cheese omelet.

[0828] 5. User Feedback:

[0829] The user reviews the suggested recipe and enters any changes needed, special offers, or additional information about allergies, such as "Salmon was on sale today" or "I'm allergic to spinach."

[0830] 6. Re-proposal:

[0831] The generative AI will then suggest new recipes based on user feedback, such as grilled salmon and broccoli.

[0832] 7. Acquiring Emotion Data:

[0833] The device acquires the user's emotional data. The emotion engine uses sensor devices such as cameras and microphones to analyze the user's facial expressions and tone of voice. For example, if the user is tired or stressed, that data is acquired.

[0834] 8. Transmission and storage of emotional data:

[0835] The device transmits the acquired emotion data to the server, which receives the data and records it in a database.

[0836] 9. Sentiment Data Analysis:

[0837] The server analyzes the emotion data, and the generation AI refers to the emotion engine data and evaluates the user's current emotional state, thereby understanding the user's mental state.

[0838] 10. Emotional recipe suggestions:

[0839] The generative AI and emotion engine work together to suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, the system will suggest recipes using ingredients that have a relaxing effect.

[0840] 11. Final Recipe Notification and Saving:

[0841] The server notifies the user of the finalized recipe and saves the data, allowing the user to prepare meals according to the recipe.

[0842] Specific examples

[0843] As a specific example, consider the case where the user is "Mr. Tanaka."

[0844] 1. Enter your meal information:

[0845] Tanaka enters that she had "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner.

[0846] 2. Data transmission and storage:

[0847] The device sends the entered information to the server, which records it in a database along with "Tanaka-san's" ID.

[0848] 3. Nutritional Balance Analysis:

[0849] The server-generated AI analyzes the data and identifies calcium deficiency.

[0850] 4. Recipe Suggestions:

[0851] The generative AI suggests a "spinach and cheese omelet" to supplement calcium.

[0852] 5. User Feedback:

[0853] Tanaka gives feedback to the generating AI, saying, "Salmon was on sale."

[0854] 6. Re-proposal:

[0855] The generative AI now suggests "grilled salmon and broccoli."

[0856] 7. Acquiring Emotion Data:

[0857] When Tanaka is using the device, the emotion engine analyzes her facial expressions and tone of voice to detect when she is feeling stressed.

[0858] 8. Transmission and storage of emotional data:

[0859] The device transmits emotion data to a server, which receives the data and stores it in a long-term database.

[0860] 9. Sentiment Data Analysis:

[0861] The server's generated AI analyzes the emotional data and assesses that Tanaka is currently experiencing stress.

[0862] 10. Emotional recipe suggestions:

[0863] The generative AI suggests "chamomile tea and aloe salad," which uses ingredients with a relaxing effect.

[0864] 11. Final Recipe Notification and Saving:

[0865] The server sends the recipe for "chamomile tea and aloe salad" to Tanaka's device and records the data in the database. Tanaka prepares dinner according to the recipe.

[0866] In this way, the system efficiently manages the user's dietary information and emotional data, and contributes to improving and maintaining overall health by suggesting not only nutritionally balanced meals but also meals that are tailored to the user's mental state.

[0867] The processing flow will be explained below.

[0868] Step 1:

[0869] The user uses the device to input the details of the meals they have eaten. For example, Mr. Tanaka inputs "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[0870] Step 2:

[0871] The device sends the entered meal information to the server. The sent content includes the user ID and detailed information about the entered meal. This data is sent in JSON format.

[0872] Step 3:

[0873] The server stores the received data in a database. The stored information includes the user ID, meal details, and the date and time of sending. Specifically, it records the information as "User ID: tanaka123", "Date and time: 2023-10-01", "Breakfast: yogurt, banana", "Lunch: chicken salad", and "Dinner: grilled salmon".

[0874] Step 4:

[0875] The server calculates nutritional values ​​based on the dietary information stored in the database. The AI ​​then references the nutritional value data of each ingredient and evaluates the total nutritional value of the user. It calculates nutrients such as calcium from yogurt, potassium and vitamin C from bananas, and protein from chicken salad.

[0876] Step 5:

[0877] The AI ​​analyzes nutritional balance, including past dietary data. The server identifies nutrients that are lacking or over-consumption. For example, results such as "lack of calcium," "sufficient vitamin D," and "too much salt" can be obtained.

[0878] Step 6:

[0879] Based on the analysis results, the server's generative AI will suggest recipes to improve nutritional balance, such as a spinach and cheese omelet to supplement calcium.

[0880] Step 7:

[0881] The user can check the recipe suggestions from the AI ​​via their device and provide feedback if changes are needed due to the unavailability of certain ingredients or allergies, for example, by entering information such as "Salmon was on sale today" or "I'm allergic to spinach."

[0882] Step 8:

[0883] The generative AI takes user feedback into account and re-suggests new recipes, such as "grilled salmon and broccoli," depending on the user's preferences and the situation.

[0884] Step 9:

[0885] The device acquires the user's emotional data. The emotion engine analyzes the user's facial expressions and tone of voice via the camera and microphone to detect the user's emotional state. For example, it can detect that Mr. Tanaka is feeling stressed.

[0886] Step 10:

[0887] The device sends the acquired emotion data to the server, which receives the data and records it in a database. The emotion data includes the user ID, emotional state, and acquisition date and time.

[0888] Step 11:

[0889] The server analyzes the emotion data. The generative AI evaluates the user's current emotional state based on the data from the emotion engine. For example, it determines that the user is feeling stressed.

[0890] Step 12:

[0891] The generative AI suggests recipes based on the user's emotional state, using ingredients that reduce stress and fatigue. For example, it suggests a relaxing "chamomile tea and aloe salad."

[0892] Step 13:

[0893] The user reviews and selects the final recipe, the server sends the finalized recipe to the user's device, and the user prepares the meal according to the recipe.

[0894] Step 14:

[0895] The server saves the final recipe data in a database. This accumulates data for future analysis and recommendations. The saved information includes recipe details, submission date and time, and user ID. For example, "Recipe: Chamomile Tea and Aloe Salad," "Date and Time: 2023-10-01," and "User ID: tanaka123" might be recorded.

[0896] Through these steps, the system efficiently manages the user's dietary information and emotional data, ensuring nutritional balance while providing flexible dietary suggestions tailored to the user's emotional state, thereby helping to improve and maintain health.

[0897] Example 2

[0898] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0899] In today's modern dietary habits, many people find it difficult to maintain a balanced, healthy diet. It is also known that emotional states have a significant impact on food choices, and stress and fatigue can lead to poor dietary quality. However, conventional dietary management systems only focus on analyzing nutritional balance, and few of them provide recommendations that take the user's emotional state into account. The present invention aims to solve these problems.

[0900] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0901] In this invention, the server includes an input means for inputting the details of the meals the user has eaten, a transmission means for transmitting the input meal data to the server, and a recording means for recording the transmitted meal data. This allows for the collection and storage of meal information. The server also includes an analysis means for analyzing the recorded meal data and evaluating nutritional balance, a proposal means for proposing recipes to compensate for the nutritional balance based on the analysis results, an emotion analysis means for acquiring and analyzing the user's emotional state, an emotion-based proposal means for proposing recipes based on the user's emotional state, and a notification means for notifying the user of the final recipe and recording it. This allows the user to receive not only nutritionally balanced meal suggestions but also appropriate meal suggestions based on the user's emotional state.

[0902] The "input means" refers to a means for the user to input the details of the food they have eaten, such as an application on a smartphone or computer.

[0903] The "transmission means" is a means for transmitting the input meal data to the server, and uses a communication protocol such as an HTTP request.

[0904] The "recording means" is a means for recording the transmitted meal data in a database or the like, and may utilize a cloud service or a local server.

[0905] The "analysis means" is a means for analyzing the recorded dietary data and evaluating nutritional balance, and involves calculations using a generative AI model and a food database.

[0906] The "suggestion method" is a method for suggesting recipes to users to compensate for nutritional balance based on the analysis results, and uses a generative AI model.

[0907] The "feedback means" is a means for the user to input feedback about the proposed recipe, and is performed via a terminal.

[0908] The "re-suggestion means" is a means for re-suggesting recipes based on user feedback, and uses a generative AI model.

[0909] The "emotion analysis means" is a means for acquiring and analyzing the user's emotional state, and performs analysis using an emotion engine that utilizes sensors such as a camera and microphone.

[0910] The "emotion-responsive suggestion means" is a means for suggesting appropriate recipes based on the user's emotional state, and works in cooperation with a generative AI model and an emotion engine.

[0911] The "notification means" is a means for notifying and recording the final recipe to the user, and has a function for notifying the terminal and storing the data in the server.

[0912] The "sensor means" is a means for acquiring an emotional state, and includes hardware sensors such as a camera and a microphone.

[0913] The "additional input means" is a means for the user to input additional information such as sale information or allergy information, and is implemented using an input form or voice input.

[0914] The "long-term analysis means" is a means for analyzing the long-term nutritional balance with the aim of continuously improving and maintaining the user's health, and involves the long-term accumulation and analysis of data.

[0915] This invention relates to a system that plans and manages a user's daily meal menu and supports a balanced and healthy diet. This system sends the meal information entered by the user to a server, analyzes the data, evaluates the nutritional balance, and suggests suitable recipes. It can also analyze the user's emotional state and make flexible recipe suggestions based on that.

[0916] Specific Examples

[0917] Hardware and Software Configuration

[0918] 1. Device:

[0919] The device used by the user to input meal information and feedback is a smartphone, tablet, or PC. This device is equipped with sensors such as a camera and microphone, and can capture the user's emotional state.

[0920] 2. Server:

[0921] The server that receives, records, and analyzes the data sent by users can use a cloud service (e.g., Amazon Web Services, Google Cloud).The server is equipped with a database (e.g., MySQL, PostgreSQL) for storing and managing data.

[0922] 3. Generative AI Model:

[0923] A generative AI model (e.g., GPT-4) running on the server analyzes dietary and emotional data to generate and suggest appropriate recipes. This model works in conjunction with a food database (e.g., the USDA Nutrient Database) and a sentiment analysis engine.

[0924] System Operation

[0925] 1. User input:

[0926] Users input information about the meals they have eaten through the device's application, such as "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[0927] 2. Data transmission and storage:

[0928] The device sends the entered meal information to the server using the HTTPS protocol, which receives the data and records it in a database.

[0929] 3. Nutritional Balance Analysis:

[0930] Based on the dietary data stored on the server, the generative AI model calculates the nutritional value of each dish, and then refers to a food database to evaluate the overall nutritional balance.

[0931] 4. Recipe Suggestions:

[0932] Based on the analysis results, the generative AI model suggests recipes to supplement missing nutrients. For example, if you are lacking in calcium, it will suggest a "spinach and cheese omelet." The suggestions are displayed on the device screen.

[0933] 5. User Feedback:

[0934] The user reviews the suggested recipes and, if necessary, enters additional information about specials or allergies. For example, they might enter, "Salmon is on sale today" or "I'm allergic to spinach."

[0935] 6. Re-proposal:

[0936] The server receives user feedback, and the generative AI model suggests new recipes, for example, re-proposing "grilled salmon and broccoli."

[0937] 7. Acquiring Emotion Data:

[0938] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and tone of voice to obtain emotional data. This is automatically executed when the user is operating the smartphone.

[0939] 8. Transmission and storage of emotional data:

[0940] The acquired emotion data is sent to the server via HTTPS protocol and recorded in a database.

[0941] 9. Sentiment Data Analysis:

[0942] A generative AI model analyzes the emotional data and assesses the user's current emotional state, determining whether they are stressed or relaxed.

[0943] 10. Emotional recipe suggestions:

[0944] The generative AI model and emotion engine work together to suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, the system will suggest a "chamomile tea and aloe salad" using ingredients that have a relaxing effect.

[0945] 11. Final Recipe Notification and Saving:

[0946] The server notifies the user of the confirmed recipe and stores the data in a database, allowing the user to prepare meals based on the recipe.

[0947] Specific examples

[0948] Examples of prompts include:

[0949] "Enter Ana's meal information. Example: 'Breakfast: Yogurt and banana. Lunch: Chicken salad. Dinner: Grilled salmon'"

[0950] This allows the system to efficiently manage the user's dietary information and emotional data, and contribute to improving and maintaining overall health by suggesting not only nutritionally balanced meals but also meals that correspond to the user's emotional state.

[0951] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0952] Step 1:

[0953] User Input

[0954] The user uses a device (smartphone, tablet, or PC) to enter meal information. For example, they might enter "Breakfast: yogurt and banana," "Lunch: chicken salad," and "Dinner: grilled salmon."

[0955] Input: Dietary information such as what was eaten, ingredients used, and intake amounts.

[0956] Output: Meal information data that can be sent and displayed on the device.

[0957] Step 2:

[0958] Data transmission and storage

[0959] The device sends the meal information to the server. When the user presses the send button, the data is sent to the server via HTTPS. The server stores the received data in a database (e.g., MySQL or PostgreSQL).

[0960] Input: Submitted meal information data.

[0961] Output: Meal information stored in a database.

[0962] Step 3:

[0963] Nutritional balance analysis

[0964] The server uses the dietary data stored in the database to calculate the nutritional value of each dish, and the generative AI model then references a food database (e.g., USDA Nutrient Database) to evaluate the overall nutritional balance.

[0965] Input: Meal information data, food database.

[0966] Output: Nutritional balance assessment results.

[0967] Step 4:

[0968] Recipe Suggestions

[0969] Based on the analysis results, the generative AI model suggests recipes to supplement missing nutrients. For example, if you are lacking in calcium, it will suggest a "spinach and cheese omelet." This suggestion is displayed on the device screen.

[0970] Input: Nutritional balance assessment results.

[0971] Output: Suggested recipe information.

[0972] Step 5:

[0973] User Feedback

[0974] The user uses the device to review the suggested recipes and optionally enter feedback, such as special offers or allergy information. For example, "Salmon is on sale today" or "I'm allergic to spinach."

[0975] Input: Additional information such as special offers, allergy information, etc.

[0976] Output: Feedback data on the device.

[0977] Step 6:

[0978] re-proposal

[0979] The server receives the user's feedback, and the generative AI model re-proposes a new recipe, for example, "grilled salmon and broccoli." This suggestion is also displayed on the device screen.

[0980] Input: Feedback data.

[0981] Output: Re-suggested recipe information.

[0982] Step 7:

[0983] Acquiring emotion data

[0984] The emotion engine uses sensors such as the device's camera and microphone to analyze the user's facial expressions and tone of voice, and acquires emotional data. This is automatically executed when the user is operating the smartphone.

[0985] Input: User's facial expression data, voice data.

[0986] Output: The obtained emotion data.

[0987] Step 8:

[0988] Sending and storing emotional data

[0989] The device transmits the acquired emotion data to the server, which receives the data and records it in a database.

[0990] Input: The acquired emotion data.

[0991] Output: Emotion data stored in a database.

[0992] Step 9:

[0993] Sentiment Data Analysis

[0994] The server's generative AI model analyzes the emotion data and assesses the user's current emotional state, for example, determining whether they are stressed or relaxed.

[0995] Input: Stored emotion data.

[0996] Output: User's emotional state assessment result.

[0997] Step 10:

[0998] Emotion-based recipe suggestions

[0999] The generative AI model and emotion engine work together to suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, the system will suggest a relaxing dish called "chamomile tea and aloe salad."

[1000] Input: User's emotional state assessment results.

[1001] Output: Suggested recipe information based on emotional state.

[1002] Step 11:

[1003] Notification and saving of final recipe

[1004] The server notifies the user of the confirmed recipe and stores the data in a database, allowing the user to prepare meals based on the recipe.

[1005] Input: Final recipe information.

[1006] Output: Recipe information notified to the user's device, recipe information saved in the database.

[1007] (Application example 2)

[1008] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1009] Conventional nutrition management systems evaluate nutritional balance based solely on the user's dietary information and suggest appropriate recipes, but do not consider the mental state or emotions of each individual user. As a result, it is difficult to provide comprehensive support that also takes into account the user's mental health. Furthermore, there was no mechanism for reflecting the suggested recipes in actual food delivery, which meant it took time and effort for users to reflect the suggested recipes in their actual meals.

[1010] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for inputting the contents of the meals the user has eaten, a transmission means for transmitting the input meal data to the server, a recording means for recording the transmitted meal data, an analysis means for analyzing the recorded meal data and evaluating nutritional balance, a suggestion means for suggesting recipes to compensate for the nutritional balance based on the analysis results, a feedback means for the user to input feedback on the recipes, a sentiment analysis means for acquiring and analyzing the user's emotional data, a re-suggestion means for re-suggesting recipes based on the sentiment analysis means, an ordering means for ordering the suggested recipe from a food delivery service, and a notification means for notifying the user of the final recipe and recording it. This makes it possible to suggest flexible and healthy eating habits according to the user's emotional state and to arrange food delivery that actually reflects the suggestions in real time.

[1011] The "input means for inputting the details of the meal taken by the user" is an interface that allows the user to input the details, ingredients, and intake amount of the meal into the terminal.

[1012] The "transmission means for transmitting input meal data to the server" is a communication function for transmitting meal data from the terminal to the server.

[1013] The "recording means for recording transmitted meal data" is a function for storing transmitted meal data in a database.

[1014] The "analysis means for analyzing recorded dietary data and evaluating nutritional balance" is a system for calculating the nutrients of each ingredient based on the recorded data and evaluating the overall nutritional balance.

[1015] The "means for proposing recipes to compensate for nutritional imbalance based on the analysis results" is a function that generates a menu to compensate for missing nutrients based on the analysis results.

[1016] The "feedback means for users to input feedback about recipes" is an interface for users to input opinions and information about suggested recipes.

[1017] The "emotion analysis means for acquiring and analyzing user emotion data" refers to a sensor and analysis engine for analyzing the user's facial expressions and tone of voice to understand their emotional state.

[1018] The "re-suggestion means for re-suggesting recipes based on emotion analysis means" is a function for re-suggesting appropriate recipes by taking into account emotion data.

[1019] "Means for arranging to order the suggested recipe from a food delivery service" is a function for ordering ingredients and dishes from a food delivery service based on the suggested recipe.

[1020] The "notification means for notifying the user of the final recipe and recording it" is a function for notifying the user of the final recipe and recording that information in a database.

[1021] This invention is a system that plans and manages a user's daily meal menu and supports a balanced diet. Users can input information about the meals they have eaten, and the system analyzes that information to evaluate the nutritional balance. The system also grasps the user's emotional state and makes flexible recipe suggestions based on that. Furthermore, it provides a mechanism for reflecting the suggested recipes in a food delivery service.

[1022] User Interface and Input Methods

[1023] First, the user inputs meal information using a device such as a smartphone. The input interface is used to input the meal contents, ingredients used, and intake amount. For example, a specific menu item such as "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon" can be input. The information entered by the user is sent to the server in real time and recorded in a database.

[1024] Server and Data Analysis

[1025] The server receives the input data and records it in a database. The recorded data is then analyzed to assess nutritional balance. The nutrition database is referenced, the nutrients for each ingredient are calculated, and the overall nutritional balance is assessed. This process is carried out using Python and the relevant nutrition database APIs.

[1026] Recipe suggestions

[1027] Based on the analysis results, the server uses a generative AI model to suggest recipes to compensate for missing nutrients. For example, if a user is lacking in calcium, it will suggest a "spinach and cheese omelet." The suggested recipe is then notified to the user.

[1028] Feedback and sentiment data

[1029] Users can provide feedback on the suggested recipes. For example, they can provide information such as "Salmon was on sale today" or "I'm allergic to spinach." The system also collects user emotional data. The emotion analysis engine uses a camera and microphone to analyze the user's facial expressions and tone of voice to assess their stress and fatigue levels.

[1030] Re-proposal and food delivery arrangements

[1031] Based on the acquired emotional data, the server uses the generative AI and emotion analysis engine to re-suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, it will suggest "chamomile tea and aloe salad." The final recipe is then ordered from a food delivery service, and the user is notified of the decision.

[1032] Specific examples

[1033] For example, if the user is "Mr. Tanaka," he inputs that he had "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner. The server receives this and analyzes that he is lacking in calcium. It then suggests "spinach and cheese omelette," but Mr. Tanaka gives feedback that "salmon was on sale." The server then re-suggests "grilled salmon and broccoli."

[1034] Prompt Sentence Examples

[1035] "The user entered today's diet information: yogurt and banana for breakfast, chicken salad for lunch, and grilled salmon for dinner. The user is currently feeling stressed. Please suggest a dinner recipe that takes into consideration nutritional balance and uses ingredients that have a relaxing effect."

[1036] In this way, this invention efficiently manages the user's dietary information and emotional data, and not only proposes nutritionally balanced meals but also flexibly suggests meals that correspond to the user's emotional state. Furthermore, by reflecting the suggested recipes in the actual food delivery service, it contributes to improving and maintaining the user's health.

[1037] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1038] Step 1:

[1039] Users use a device such as a smartphone to input the details of the meal they ate. Specifically, they enter the name of the meal, the ingredients used, the amount consumed, etc. into an input form. Once this information is entered, the device immediately sends the data to the server.

[1040] Input: User's dietary information (e.g., yogurt and banana for breakfast, chicken salad for lunch, grilled salmon for dinner)

[1041] Output: Meal data sent to the server

[1042] Step 2:

[1043] The device sends the entered meal data to a server, which receives the data and records it in a database.

[1044] Input: Meal data sent from the device

[1045] Output: Meal data stored in a database

[1046] Step 3:

[1047] The server uses the dietary data stored in the database to calculate the value of each nutrient and evaluate the overall nutritional balance. The generative AI model references the nutrition database to identify the necessary nutrients. This step uses Python and related nutrition database APIs.

[1048] Input: Dietary data recorded in the database

[1049] Output: Nutritional balance evaluation results

[1050] Step 4:

[1051] The server uses a generative AI model to evaluate nutritional balance and suggests recipes to supplement missing nutrients.

[1052] Input: Nutritional balance evaluation results

[1053] Output: Suggested recipe (e.g. spinach and cheese omelette)

[1054] Step 5:

[1055] The user can then enter feedback on the suggested recipe, such as allergies or special offers, which is then sent back to the server.

[1056] Input: User feedback information (e.g., salmon was on sale, I'm allergic to spinach)

[1057] Output: Feedback information sent to the server

[1058] Step 6:

[1059] The server receives the user's feedback and proposes new recipes, and the generative AI model generates new recipes based on the feedback.

[1060] Input: Feedback information

[1061] Output: Recipe suggestions (e.g., grilled salmon and broccoli)

[1062] Step 7:

[1063] To obtain the user's emotional data, the device uses sensor devices such as a camera and microphone to analyze the user's facial expressions and tone of voice and evaluate their emotional state.

[1064] Input: User facial and voice data

[1065] Output: Emotion data

[1066] Step 8:

[1067] The device transmits the acquired emotion data to the server, which receives the data and records it in a database.

[1068] Input: Emotion data sent from the device

[1069] Output: Emotion data stored in a database

[1070] Step 9:

[1071] The server analyzes the emotional data and evaluates the user's current emotional state. The generative AI model then refers to the emotional data and evaluates the emotional state.

[1072] Input: Emotion data stored in a database

[1073] Output: Emotional state assessment result

[1074] Step 10:

[1075] A generative AI model and an emotion analysis engine work together to suggest recipes based on the user's emotional state.

[1076] Input: Emotional state assessment result

[1077] Output: Suggested recipes based on emotions (e.g., chamomile tea and aloe salad)

[1078] Step 11:

[1079] The server notifies the user of the confirmed recipe and records the data in a database. The user then places an order with the food delivery service based on the proposed recipe.

[1080] Input: Final recipe

[1081] Output: Recipe notification and food delivery order to the user

[1082] Through the above steps, the present invention efficiently manages the user's dietary information and emotional data, and realizes flexible meal suggestions and food delivery arrangements that take into account both nutritional balance and emotional state.

[1083] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1084] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1085] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1086] [Third embodiment]

[1087] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1088] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1089] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1090] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1091] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1092] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1093] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1094] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1095] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1096] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1097] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1098] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1099] This invention relates to a system that allows users to easily plan and manage their daily meal menus and supports a balanced and healthy diet. This system sends the meal information entered by the user to a server, which analyzes the data, evaluates the nutritional balance, and suggests suitable recipes.

[1100] Overview of program processing

[1101] 1. User input:

[1102] The user enters meal information, including the name of the dish eaten, the ingredients used, and the amount consumed. For example, "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[1103] 2. Data transmission and storage:

[1104] The device sends the entered meal information to the server, which receives the data and records it in a database.

[1105] 3. Nutritional Balance Analysis:

[1106] The server uses the dietary information stored in the database to calculate the nutritional value of each ingredient, and the AI ​​generator then references the nutrient data for each ingredient to evaluate the overall nutritional balance.

[1107] 4. Recipe Suggestions:

[1108] Based on the analysis results, the server's AI will suggest recipes to the user to supplement the nutrients they are lacking. For example, if they are lacking in calcium, it will suggest a spinach and cheese omelet.

[1109] 5. User Feedback:

[1110] Users can review the suggested recipes and enter any changes they need, special offers, or additional information about allergies, such as "Salmon was on sale today" or "I'm allergic to spinach."

[1111] 6. Re-proposal:

[1112] The generative AI will then suggest new recipes based on user feedback, such as grilled salmon and broccoli.

[1113] 7. Notify and save the final recipe:

[1114] The server notifies the user of the finalized recipe and stores the data, allowing the user to prepare a meal according to the recipe.

[1115] Specific examples

[1116] As a specific example, consider the case where the user is "Mr. Tanaka."

[1117] 1. Enter your meal information:

[1118] Tanaka enters that she had "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner.

[1119] 2. Data transmission and storage:

[1120] The device sends the entered information to the server, which records it in a database along with "Tanaka-san's" ID.

[1121] 3. Nutritional Balance Analysis:

[1122] The server-generated AI analyzes the data and identifies calcium deficiency.

[1123] 4. Recipe Suggestions:

[1124] The generative AI suggests a "spinach and cheese omelet" to supplement calcium.

[1125] 5. User Feedback:

[1126] Tanaka gives feedback to the generating AI, saying, "Salmon was on sale."

[1127] 6. Re-proposal:

[1128] The generative AI now suggests "grilled salmon and broccoli."

[1129] 7. Notify and save the final recipe:

[1130] The server sends the recipe for "grilled salmon and broccoli" to Tanaka's device and saves the data. Tanaka then prepares a healthy dinner according to the recipe.

[1131] In this way, the system efficiently manages the user's dietary information and suggests nutritionally balanced meals, thereby contributing to the maintenance and improvement of health.

[1132] The processing flow will be explained below.

[1133] Step 1:

[1134] The user uses the device to input the details of the meal they ate, including the name of the dish, the ingredients used, the amount consumed, and the cooking method. For example, they might input "Breakfast: yogurt, banana, toast," "Lunch: chicken salad," and "Dinner: grilled salmon, salad, miso soup."

[1135] Step 2:

[1136] The device sends the entered meal information to the server. The sent content includes the user ID and detailed meal information. The data is sent in an appropriate format, such as JSON.

[1137] Step 3:

[1138] The server stores the received data in a database. In addition to the meal information, the date and time of sending and the user ID are also recorded. For example, "User: Tanaka", "Date and time: 2023-10-01", "Breakfast: Yogurt, banana, toast", "Lunch: Chicken salad", "Dinner: Grilled salmon, salad, miso soup" might be recorded.

[1139] Step 4:

[1140] The server calculates the nutritional value of each ingredient based on the dietary information stored in the database. The generative AI retrieves the nutritional value of each ingredient from the database and evaluates the nutritional balance of the entire meal. For example, the nutrients of yogurt (calcium, protein), banana (potassium, vitamin C), and toast (carbohydrates, fiber) are calculated.

[1141] Step 5:

[1142] The generative AI also references past dietary data to analyze long-term nutritional intake, determining whether calcium is insufficient, vitamin D is sufficient, or salt is excessive. For example, the analysis results may include "calcium deficiency," "sufficient vitamin D," or "excess salt."

[1143] Step 6:

[1144] Based on the analysis results, the generative AI will suggest recipes suitable for the user. It will suggest balanced meals, such as recipes to supplement missing nutrients or to reduce excess intake of nutrients. For example, it will suggest a "spinach and cheese omelet" to supplement calcium.

[1145] Step 7:

[1146] The user checks the recipe suggestions from the AI ​​via their device. If the suggestions need to be changed due to reasons such as not being able to obtain certain ingredients or allergies, the user can communicate this information to the AI. For example, they can say, "Salmon was on sale today, so it was cheap."

[1147] Step 8:

[1148] The generative AI reflects user feedback and proposes new recipes, allowing for flexible responses to suit the user's preferences and circumstances. For example, it suggests "grilled salmon and broccoli."

[1149] Step 9:

[1150] The user reviews and selects the final recipe, the server sends the finalized recipe to the user's device, and the user prepares the meal according to the recipe.

[1151] Step 10:

[1152] The server saves the final recipe data in a database. This allows data to be accumulated for future analysis and recommendations. For example, "Recipe: Grilled Salmon and Broccoli," "Date and Time: 2023-10-01," and "User ID: tanaka123" are recorded.

[1153] Through these steps, the system efficiently manages the user's dietary information and suggests nutritionally balanced meals, allowing the user to maintain a healthy diet without any effort.

[1154] Example 1

[1155] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1156] In modern society, many users find it difficult to maintain a balanced diet, and dietary management is often neglected, especially in busy daily lives. In addition, each user has different nutritional needs, making it difficult to provide appropriate nutritional advice and recipes tailored to individual conditions. Traditional manual dietary management methods are inefficient and lack appropriate support measures for continuous health maintenance and improvement.

[1157] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1158] In this invention, the server includes an input means for inputting the details of the meals a user has eaten, a transmission means for transmitting the input meal data to the server, and a recording means for recording the transmitted meal data. This allows users to accurately and efficiently manage their own meal data. The server also includes an analysis means for analyzing the recorded meal data using a generative AI model to evaluate nutritional balance, a suggestion means for sending prompts to the generative AI model to suggest recipes to compensate for nutritional imbalance, a re-suggestion means for re-suggesting recipes using the generative AI model based on user feedback, and a notification means for notifying the user of the final recipe and recording it. This allows for appropriate meal suggestions based on each user's nutritional needs, enabling continuous improvement and maintenance of the user's health.

[1159] The "input means" refers to a device or interface that allows the user to input the details of the meal they have eaten.

[1160] "Transmission means" refers to a function or device for transmitting the meal data entered by the user to the server.

[1161] The "recording means" refers to a database or storage system for saving and managing the transmitted meal data.

[1162] "Analysis means using generative AI models" refers to devices or systems that use AI technology to analyze recorded dietary data and evaluate nutritional balance.

[1163] A "prompt sentence" is an input sentence that gives specific instructions to a generative AI model.

[1164] "Proposal means" refers to a function or device that uses a generative AI model to provide users with recipes to compensate for nutritional balance based on the analysis results.

[1165] A "feedback means" is a function or device that allows a user to input opinions or additional information about a recipe.

[1166] A "re-proposal means" is a function or device that uses a generative AI model to re-propose a recipe based on user feedback.

[1167] The "notification means" is a function or device for notifying the user of the final recipe and recording the data.

[1168] This invention relates to a system that allows users to easily plan and manage their daily meal menus and supports a balanced and healthy diet. This system sends the meal information entered by the user to a server, which analyzes the data, evaluates the nutritional balance, and suggests suitable recipes.

[1169] System configuration

[1170] Input Method

[1171] Users enter their meal details using a smartphone app or web interface. The information entered includes the name of the dish, the ingredients used, and the amount consumed. For example, breakfast might include "yogurt and banana," lunch might include "chicken salad," and dinner might include "grilled salmon."

[1172] Transmission method

[1173] The device sends the meal information entered by the user to the server using an HTTP POST request.

[1174] Recording means

[1175] The server records the received meal data in a database, which is used to store each user's meal history and nutritional information. For example, meal details are stored along with the user ID.

[1176] Analytical tools using generative AI models

[1177] The server uses a generative AI model to calculate the nutritional value of each ingredient based on the recorded dietary data. The generative AI model then refers to the nutrient data of the ingredients and evaluates the overall nutritional balance. This evaluation is performed by sending prompt sentences to the generative AI model.

[1178] Proposal means

[1179] The generative AI model then suggests recipes to improve nutritional balance based on the analysis results. For example, if a person is lacking in calcium, it suggests a spinach and cheese omelette.

[1180] Feedback Methods

[1181] Users review the suggested recipes and enter any missing information or specific requirements (such as special offers or allergies), for example, "Salmon was on sale today" or "I'm allergic to spinach."

[1182] Re-proposal means

[1183] The generative AI model re-suggests new recipes based on user feedback, for example, suggesting "grilled salmon and broccoli."

[1184] Notification means

[1185] The server notifies the user of the final recipe and records the data. The user can prepare a meal according to the recipe. Notifications are sent to the device using push notifications or email notifications.

[1186] Specific examples

[1187] For example, if the user is "Tanaka-san":

[1188] 1. Enter your meal information

[1189] Tanaka enters "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner.

[1190] 2. Data transmission and storage

[1191] The terminal sends the entered information to the server, which records it in a database along with Tanaka's ID.

[1192] 3. Analysis of nutritional balance

[1193] The server's generated AI model analyzes Tanaka's data and identifies that he is deficient in calcium.

[1194] 4. Recipe suggestions

[1195] The generative AI model suggests a "spinach and cheese omelet" to supplement calcium.

[1196] 5. User Feedback

[1197] Tanaka provides feedback to the generative AI model that "salmon was on sale."

[1198] 6. Re-proposal

[1199] The generative AI model now suggests "grilled salmon and broccoli."

[1200] 7. Notification and saving of final recipe

[1201] The server sends the recipe for "grilled salmon and broccoli" to Tanaka's device and saves the data. Tanaka then prepares a healthy dinner according to the recipe.

[1202] This system suggests specific, nutritionally balanced recipes by sending the prompt text "User ID: Tanaka, Meal information: Breakfast - yogurt and banana, Lunch - chicken salad, Dinner - grilled salmon. Analyze nutritional balance and check for missing nutrients. Then suggest suitable recipes to supplement those nutrients" to the generative AI model.

[1203] In this way, users can efficiently manage their own dietary data and use it to maintain and improve their health.

[1204] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1205] Step 1:

[1206] The user inputs the details of the food they have eaten.

[1207] Input: The user enters the names of the dishes for breakfast, lunch, and dinner, the ingredients used, and the amount consumed into an input form on the terminal.

[1208] How it works: Users use a smartphone app or web interface to enter meal information using a keyboard or touch panel.

[1209] Output: The entered meal information is saved in the device.

[1210] Step 2:

[1211] The terminal transmits the meal information to the server.

[1212] Input: Meal information stored on your device.

[1213] How it works: The device sends the entered meal information to the server using an HTTP POST request.

[1214] Output: Meal information is sent to the server.

[1215] Step 3:

[1216] The server records the received meal information in a database.

[1217] Input: Meal information sent to the server.

[1218] How it works: The server stores the received data in a database using INSERT statements, for example, "Tanaka's ID, Breakfast - yogurt and banana, Lunch - chicken salad, Dinner - grilled salmon".

[1219] Output: The recorded meal information is stored in a database.

[1220] Step 4:

[1221] The server-generated AI model analyzes the dietary information and evaluates nutritional balance.

[1222] Input: Meal information stored in a database.

[1223] How it works: The server extracts the user's dietary information from the database using a SELECT statement and sends a prompt to the generative AI model. The prompt reads, "User ID: Tanaka, Breakfast - Yogurt and banana, Lunch - Chicken salad, Dinner - Grilled salmon. Analyze the nutritional balance and check for any missing nutrients." The generative AI model then analyzes and evaluates the nutritional balance.

[1224] Output: The nutritional balance evaluation results are returned from the generative AI model.

[1225] Step 5:

[1226] Based on the analysis results, the server suggests recipes to improve nutritional balance.

[1227] Input: Nutritional balance assessment results returned by the generative AI model.

[1228] How it works: Based on the evaluation results, the server sends a new prompt to the generative AI model to generate a suitable recipe. For example, "I'm lacking calcium, so please suggest a recipe to supplement my calcium."

[1229] Output: The generative AI model returns a suitable recipe suggestion, for example, "Spinach and Cheese Omelette."

[1230] Step 6:

[1231] The user provides feedback on the suggested recipe.

[1232] Input: A recipe provided by the server.

[1233] How it works: The user reviews the proposed recipe and enters any specials, allergies, or other specific requirements into a feedback form. For example, "Salmon was on sale today" or "I'm allergic to spinach."

[1234] Output: Feedback information is saved to the device.

[1235] Step 7:

[1236] The terminal transmits the feedback information to the server.

[1237] Input: Feedback information stored on the device.

[1238] How it works: The device sends feedback information to the server using an HTTP POST request.

[1239] Output: The feedback information is sent to the server.

[1240] Step 8:

[1241] The server's generative AI model re-proposes new recipes based on the feedback information.

[1242] Input: The feedback information sent to the server.

[1243] How it works: The server sends a new prompt to the generative AI model, suggesting a new recipe that takes the feedback into account. For example, "User ID: Tanaka, salmon is on sale and I'm allergic to spinach. Please suggest a new recipe."

[1244] Output: The generative AI model returns a new recipe suggestion, for example, "Grilled Salmon and Broccoli."

[1245] Step 9:

[1246] The server notifies the user of the final recipe and records the data.

[1247] Input: The final recipe returned from the generative AI model.

[1248] Operation: The server saves the final recipe information in the database and notifies the device via an HTTP response. The device displays the notification to the user and allows them to view the recipe.

[1249] Output: The final recipe information is saved in the database and on the device, and is notified to the user.

[1250] In this way, the system manages the user's dietary information through each step and supports the user's health by suggesting recipes that take nutritional balance into consideration.

[1251] (Application example 1)

[1252] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1253] Conventional food delivery services have had the problem of making it difficult for users to select meals that take into account healthy nutritional balance. In particular, there has been a lack of specific suggestions for supplementing nutrients lacking in daily meals, and meal delivery services based on such suggestions. As a result, users have had to go through the trouble of researching nutritional balance and choosing meals themselves.

[1254] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1255] In this invention, the server includes an input means for inputting the contents of the meal consumed by the user, a transmission means for transmitting the input meal data to the server, a recording means for recording the transmitted meal data, an analysis means for analyzing the recorded meal data and evaluating the nutritional balance, a proposal means for proposing recipes to compensate for the nutritional balance based on the analysis results, a feedback means for the user to input feedback on the recipe, a re-proposal means for re-proposing a recipe based on the user's feedback, a notification means for notifying the user of the final recipe and recording it, and a delivery order means for ordering a meal based on the proposed recipe.

[1256] This allows users to easily manage the nutritional balance of their daily meals and order delivery meals based on suggested healthy recipes, thereby improving the quality of their diet and helping them maintain and improve their health.

[1257] The "input means" refers to a device or interface that allows the user to input the details of the meal they have eaten.

[1258] The "transmission means" is a communication function for transmitting the input meal data to the server.

[1259] "Recording means" refers to devices or software for storing and recording the transmitted dietary data in a database or the like.

[1260] "Analysis means" refers to algorithms or programs that evaluate nutritional balance based on recorded dietary data and identify necessary nutrients.

[1261] The "suggestion method" is a function that uses a generative AI model to suggest recipes to supplement the user's missing nutrients based on the analysis results.

[1262] The "feedback means" is an interface that allows the user to input feedback such as opinions and improvements regarding the proposed recipe.

[1263] A "re-proposal method" is an algorithm or program that regenerates and proposes new recipes based on user feedback.

[1264] The "notification means" is a notification function for notifying the user of the finalized recipe.

[1265] The "delivery ordering means" is a function for ordering food based on the suggested recipe from a delivery service.

[1266] The "additional input means" is an interface that allows the user to input additional information such as sale item information and allergy information.

[1267] The "long-term analysis means" refers to an algorithm or program that analyzes data on long-term nutritional balance with the aim of continuously improving and maintaining the user's health.

[1268] MODE FOR CARRYING OUT THE INVENTION

[1269] The present invention relates to a system that allows users to easily plan and manage their daily meal menus and supports a balanced and healthy diet. This system includes an "input means," "transmission means," "recording means," "analysis means," "suggestion means," "feedback means," "re-suggestion means," "notification means," and "delivery ordering means."

[1270] System configuration

[1271] Hardware

[1272] Device: The smartphone used by the user (Android, iOS)

[1273] Server: Cloud server for processing and storing data

[1274] software

[1275] Database: PostgreSQL is used to store and manage user meal information.

[1276] Backend framework: Python and Flask will be used to build an API to input food information, analyze nutritional balance, suggest recipes, and process orders.

[1277] Generative AI model: Uses OpenAI's GPT to generate nutritionally balanced recipes.

[1278] Front-end framework: React Native is used to build the user interface.

[1279] System processing flow

[1280] 1. Enter your meal information

[1281] An "input method" is provided for users to input the name of the dish they ate, the ingredients used, and the intake amount. For example, they can input "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[1282] 2. Data transmission and storage

[1283] The user's device has a "transmission means" for transmitting the input meal information to the server, and the server stores the received data in a database as a "recording means."

[1284] 3. Analysis of nutritional balance

[1285] The server evaluates the nutritional balance of the recorded dietary data using an "analysis tool." The generative AI model (OpenAI GPT) references the nutrients in each ingredient and calculates the overall nutritional balance.

[1286] 4. Recipe suggestions

[1287] Based on the analysis results, the system will suggest recipes to the user to make up for any missing nutrients. For example, if a user is lacking in calcium, the system will suggest a "spinach and cheese omelet."

[1288] 5. User Feedback

[1289] Users can enter feedback on the suggested recipes using the "Feedback Tool." For example, they can add information such as "Salmon was on sale today" or "I'm allergic to spinach."

[1290] 6. Re-proposal

[1291] The server re-proposes new recipes based on the user's feedback using the "re-proposition method." For example, it suggests "grilled salmon and broccoli."

[1292] 7. Notification and saving of final recipe

[1293] The server notifies the user of the finalized recipe via a "notification means" and stores the data, allowing the user to prepare a meal according to the recipe.

[1294] 8. Delivery Orders

[1295] Healthy meals are provided through a delivery service using a "delivery ordering means" that allows users to order meals based on suggested recipes.

[1296] Specific examples

[1297] An example of a prompt that the user might enter:

[1298] "Suggest calcium-rich recipes based on the user's dietary information. Breakfast: Yogurt and banana, Lunch: Chicken salad, Dinner: Grilled salmon."

[1299] As described above, by utilizing the system of the present invention, users can easily manage the nutritional balance of their daily meals and maintain a healthy diet. In addition, by ordering food delivery based on the suggested recipes, users can reduce their time and effort and instantly consume healthy meals.

[1300] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1301] Step 1:

[1302] The user inputs meal information.

[1303] Input: Meal name, ingredients used, and amount consumed (e.g., Breakfast: Yogurt and banana, Lunch: Chicken salad, Dinner: Grilled salmon)

[1304] Output: Input meal information

[1305] Specific operations: The user uses the smartphone application to input meal information into the input means.

[1306] Step 2:

[1307] The terminal transmits the input meal data to the server.

[1308] Input: Meal information entered by the user

[1309] Output: Meal data sent to the server

[1310] Specific operation: The smartphone application sends this data to the server via the Internet using its internal transmission means.

[1311] Step 3:

[1312] The server stores the transmitted meal data in a recording means.

[1313] Input: Submitted meal data

[1314] Output: Meal data stored in a database

[1315] Specific operation: The server connects to the database (PostgreSQL) and saves the data along with the user ID.

[1316] Step 4:

[1317] The server uses analytical means to evaluate the nutritional balance of the recorded dietary data.

[1318] Input: Saved meal data

[1319] Output: Nutritional balance evaluation results

[1320] Specific operation: The server's generative AI model (OpenAI GPT) calculates the nutritional value of each ingredient contained in the dietary data and evaluates the overall nutritional balance.

[1321] Step 5:

[1322] Based on the analysis results, the server uses the suggestion method to suggest recipes to supplement the missing nutrients.

[1323] Input: Nutritional balance evaluation results

[1324] Output: Suggested recipe

[1325] Specific operation: The server's generative AI model uses prompt text to generate recipes that supplement missing nutrients.

[1326] Example prompt: "Suggest calcium-enriched recipes based on the user's dietary information."

[1327] Step 6:

[1328] The user inputs feedback on the proposed recipe using the input means.

[1329] Input: User feedback on the suggested recipe (e.g., salmon was on sale today, I'm allergic to spinach)

[1330] Output: Input feedback

[1331] What it does: A user uses a smartphone application to provide feedback on a suggested recipe.

[1332] Step 7:

[1333] The server again suggests recipes using the suggestion means based on the user's feedback.

[1334] Input: User feedback

[1335] Output: Re-proposed recipe

[1336] How it works: The server's generative AI model generates new recipes that incorporate user feedback.

[1337] Step 8:

[1338] The server notifies the user of the final recipe using a notification means and stores it in a database.

[1339] Input: Confirmed recipe

[1340] Output: Final recipe notified and final recipe data saved

[1341] Specific operation: The server notifies the smartphone application of the confirmed recipe and saves it in the database.

[1342] Step 9:

[1343] The user orders food based on the confirmed recipe using a delivery ordering means.

[1344] Input: Confirmed recipe

[1345] Output: Delivery order

[1346] Specific operation: The user orders food based on the final recipe from a delivery service via a smartphone application.

[1347] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1348] This invention relates to a system that plans and manages a user's daily meal menu and supports a balanced and healthy diet. This system transmits meal information entered by the user to a server, analyzes the data, evaluates nutritional balance, and suggests suitable recipes. Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions, enabling it to flexibly suggest recipes according to the emotional state of each individual user.

[1349] Overview of program processing

[1350] 1. User input:

[1351] The user enters meal information into the device, including the name of the dish eaten, the ingredients used, and the amount consumed, for example, "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[1352] 2. Data transmission and storage:

[1353] The device sends the entered meal information to the server, which receives the data and records it in a database.

[1354] 3. Nutritional Balance Analysis:

[1355] The server uses the dietary information stored in the database to calculate the nutritional value of each ingredient, and the AI ​​generator then references the nutrient data for each ingredient to evaluate the overall nutritional balance.

[1356] 4. Recipe Suggestions:

[1357] Based on the analysis results, the server's AI will suggest recipes to the user to supplement the nutrients they are lacking. For example, if they are lacking in calcium, it will suggest a spinach and cheese omelet.

[1358] 5. User Feedback:

[1359] The user reviews the suggested recipe and enters any changes needed, special offers, or additional information about allergies, such as "Salmon was on sale today" or "I'm allergic to spinach."

[1360] 6. Re-proposal:

[1361] The generative AI will then suggest new recipes based on user feedback, such as grilled salmon and broccoli.

[1362] 7. Acquiring Emotion Data:

[1363] The device acquires the user's emotional data. The emotion engine uses sensor devices such as cameras and microphones to analyze the user's facial expressions and tone of voice. For example, if the user is tired or stressed, that data is acquired.

[1364] 8. Transmission and storage of emotional data:

[1365] The device transmits the acquired emotion data to the server, which receives the data and records it in a database.

[1366] 9. Sentiment Data Analysis:

[1367] The server analyzes the emotion data, and the generation AI refers to the emotion engine data and evaluates the user's current emotional state, thereby understanding the user's mental state.

[1368] 10. Emotional recipe suggestions:

[1369] The generative AI and emotion engine work together to suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, the system will suggest recipes using ingredients that have a relaxing effect.

[1370] 11. Final Recipe Notification and Saving:

[1371] The server notifies the user of the finalized recipe and saves the data, allowing the user to prepare meals according to the recipe.

[1372] Specific examples

[1373] As a specific example, consider the case where the user is "Mr. Tanaka."

[1374] 1. Enter your meal information:

[1375] Tanaka enters that she had "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner.

[1376] 2. Data transmission and storage:

[1377] The device sends the entered information to the server, which records it in a database along with "Tanaka-san's" ID.

[1378] 3. Nutritional Balance Analysis:

[1379] The server-generated AI analyzes the data and identifies calcium deficiency.

[1380] 4. Recipe Suggestions:

[1381] The generative AI suggests a "spinach and cheese omelet" to supplement calcium.

[1382] 5. User Feedback:

[1383] Tanaka gives feedback to the generating AI, saying, "Salmon was on sale."

[1384] 6. Re-proposal:

[1385] The generative AI now suggests "grilled salmon and broccoli."

[1386] 7. Acquiring Emotion Data:

[1387] When Tanaka is using the device, the emotion engine analyzes her facial expressions and tone of voice to detect when she is feeling stressed.

[1388] 8. Transmission and storage of emotional data:

[1389] The device transmits emotion data to a server, which receives the data and stores it in a long-term database.

[1390] 9. Sentiment Data Analysis:

[1391] The server's generated AI analyzes the emotional data and assesses that Tanaka is currently experiencing stress.

[1392] 10. Emotional recipe suggestions:

[1393] The generative AI suggests "chamomile tea and aloe salad," which uses ingredients with a relaxing effect.

[1394] 11. Final Recipe Notification and Saving:

[1395] The server sends the recipe for "chamomile tea and aloe salad" to Tanaka's device and records the data in the database. Tanaka prepares dinner according to the recipe.

[1396] In this way, the system efficiently manages the user's dietary information and emotional data, and contributes to improving and maintaining overall health by suggesting not only nutritionally balanced meals but also meals that are tailored to the user's mental state.

[1397] The processing flow will be explained below.

[1398] Step 1:

[1399] The user uses the device to input the details of the meals they have eaten. For example, Mr. Tanaka inputs "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[1400] Step 2:

[1401] The device sends the entered meal information to the server. The sent content includes the user ID and detailed information about the entered meal. This data is sent in JSON format.

[1402] Step 3:

[1403] The server stores the received data in a database. The stored information includes the user ID, meal details, and the date and time of sending. Specifically, it records the information as "User ID: tanaka123", "Date and time: 2023-10-01", "Breakfast: yogurt, banana", "Lunch: chicken salad", and "Dinner: grilled salmon".

[1404] Step 4:

[1405] The server calculates nutritional values ​​based on the dietary information stored in the database. The AI ​​then references the nutritional value data of each ingredient and evaluates the total nutritional value of the user. It calculates nutrients such as calcium from yogurt, potassium and vitamin C from bananas, and protein from chicken salad.

[1406] Step 5:

[1407] The AI ​​analyzes nutritional balance, including past dietary data. The server identifies nutrients that are lacking or over-consumption. For example, results such as "lack of calcium," "sufficient vitamin D," and "too much salt" can be obtained.

[1408] Step 6:

[1409] Based on the analysis results, the server's generative AI will suggest recipes to improve nutritional balance, such as a spinach and cheese omelet to supplement calcium.

[1410] Step 7:

[1411] The user can check the recipe suggestions from the AI ​​via their device and provide feedback if changes are needed due to the unavailability of certain ingredients or allergies, for example, by entering information such as "Salmon was on sale today" or "I'm allergic to spinach."

[1412] Step 8:

[1413] The generative AI takes user feedback into account and re-suggests new recipes, such as "grilled salmon and broccoli," depending on the user's preferences and the situation.

[1414] Step 9:

[1415] The device acquires the user's emotional data. The emotion engine analyzes the user's facial expressions and tone of voice via the camera and microphone to detect the user's emotional state. For example, it can detect that Mr. Tanaka is feeling stressed.

[1416] Step 10:

[1417] The device sends the acquired emotion data to the server, which receives the data and records it in a database. The emotion data includes the user ID, emotional state, and acquisition date and time.

[1418] Step 11:

[1419] The server analyzes the emotion data. The generative AI evaluates the user's current emotional state based on the data from the emotion engine. For example, it determines that the user is feeling stressed.

[1420] Step 12:

[1421] The generative AI suggests recipes based on the user's emotional state, using ingredients that reduce stress and fatigue. For example, it suggests a relaxing "chamomile tea and aloe salad."

[1422] Step 13:

[1423] The user reviews and selects the final recipe, the server sends the finalized recipe to the user's device, and the user prepares the meal according to the recipe.

[1424] Step 14:

[1425] The server saves the final recipe data in a database. This accumulates data for future analysis and recommendations. The saved information includes recipe details, submission date and time, and user ID. For example, "Recipe: Chamomile Tea and Aloe Salad," "Date and Time: 2023-10-01," and "User ID: tanaka123" might be recorded.

[1426] Through these steps, the system efficiently manages the user's dietary information and emotional data, ensuring nutritional balance while providing flexible dietary suggestions tailored to the user's emotional state, thereby helping to improve and maintain health.

[1427] Example 2

[1428] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1429] In today's modern dietary habits, many people find it difficult to maintain a balanced, healthy diet. It is also known that emotional states have a significant impact on food choices, and stress and fatigue can lead to poor dietary quality. However, conventional dietary management systems only focus on analyzing nutritional balance, and few of them provide recommendations that take the user's emotional state into account. The present invention aims to solve these problems.

[1430] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1431] In this invention, the server includes an input means for inputting the details of the meals the user has eaten, a transmission means for transmitting the input meal data to the server, and a recording means for recording the transmitted meal data. This allows for the collection and storage of meal information. The server also includes an analysis means for analyzing the recorded meal data and evaluating nutritional balance, a proposal means for proposing recipes to compensate for the nutritional balance based on the analysis results, an emotion analysis means for acquiring and analyzing the user's emotional state, an emotion-based proposal means for proposing recipes based on the user's emotional state, and a notification means for notifying the user of the final recipe and recording it. This allows the user to receive not only nutritionally balanced meal suggestions but also appropriate meal suggestions based on the user's emotional state.

[1432] The "input means" refers to a means for the user to input the details of the food they have eaten, such as an application on a smartphone or computer.

[1433] The "transmission means" is a means for transmitting the input meal data to the server, and uses a communication protocol such as an HTTP request.

[1434] The "recording means" is a means for recording the transmitted meal data in a database or the like, and may utilize a cloud service or a local server.

[1435] The "analysis means" is a means for analyzing the recorded dietary data and evaluating nutritional balance, and involves calculations using a generative AI model and a food database.

[1436] The "suggestion method" is a method for suggesting recipes to users to compensate for nutritional balance based on the analysis results, and uses a generative AI model.

[1437] The "feedback means" is a means for the user to input feedback about the proposed recipe, and is performed via a terminal.

[1438] The "re-suggestion means" is a means for re-suggesting recipes based on user feedback, and uses a generative AI model.

[1439] The "emotion analysis means" is a means for acquiring and analyzing the user's emotional state, and performs analysis using an emotion engine that utilizes sensors such as a camera and microphone.

[1440] The "emotion-responsive suggestion means" is a means for suggesting appropriate recipes based on the user's emotional state, and works in cooperation with a generative AI model and an emotion engine.

[1441] The "notification means" is a means for notifying and recording the final recipe to the user, and has a function for notifying the terminal and storing the data in the server.

[1442] The "sensor means" is a means for acquiring an emotional state, and includes hardware sensors such as a camera and a microphone.

[1443] The "additional input means" is a means for the user to input additional information such as sale information or allergy information, and is implemented using an input form or voice input.

[1444] The "long-term analysis means" is a means for analyzing the long-term nutritional balance with the aim of continuously improving and maintaining the user's health, and involves the long-term accumulation and analysis of data.

[1445] This invention relates to a system that plans and manages a user's daily meal menu and supports a balanced and healthy diet. This system sends the meal information entered by the user to a server, analyzes the data, evaluates the nutritional balance, and suggests suitable recipes. It can also analyze the user's emotional state and make flexible recipe suggestions based on that.

[1446] Specific Examples

[1447] Hardware and Software Configuration

[1448] 1. Device:

[1449] The device used by the user to input meal information and feedback is a smartphone, tablet, or PC. This device is equipped with sensors such as a camera and microphone, and can capture the user's emotional state.

[1450] 2. Server:

[1451] The server that receives, records, and analyzes the data sent by users can use a cloud service (e.g., Amazon Web Services, Google Cloud).The server is equipped with a database (e.g., MySQL, PostgreSQL) for storing and managing data.

[1452] 3. Generative AI Model:

[1453] A generative AI model (e.g., GPT-4) running on the server analyzes dietary and emotional data to generate and suggest appropriate recipes. This model works in conjunction with a food database (e.g., the USDA Nutrient Database) and a sentiment analysis engine.

[1454] System Operation

[1455] 1. User input:

[1456] Users input information about the meals they have eaten through the device's application, such as "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[1457] 2. Data transmission and storage:

[1458] The device sends the entered meal information to the server using the HTTPS protocol, which receives the data and records it in a database.

[1459] 3. Nutritional Balance Analysis:

[1460] Based on the dietary data stored on the server, the generative AI model calculates the nutritional value of each dish, and then refers to a food database to evaluate the overall nutritional balance.

[1461] 4. Recipe Suggestions:

[1462] Based on the analysis results, the generative AI model suggests recipes to supplement missing nutrients. For example, if you are lacking in calcium, it will suggest a "spinach and cheese omelet." The suggestions are displayed on the device screen.

[1463] 5. User Feedback:

[1464] The user reviews the suggested recipes and, if necessary, enters additional information about specials or allergies. For example, they might enter, "Salmon is on sale today" or "I'm allergic to spinach."

[1465] 6. Re-proposal:

[1466] The server receives user feedback, and the generative AI model suggests new recipes, for example, re-proposing "grilled salmon and broccoli."

[1467] 7. Acquiring Emotion Data:

[1468] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and tone of voice to obtain emotional data. This is automatically executed when the user is operating the smartphone.

[1469] 8. Transmission and storage of emotional data:

[1470] The acquired emotion data is sent to the server via HTTPS protocol and recorded in a database.

[1471] 9. Sentiment Data Analysis:

[1472] A generative AI model analyzes the emotional data and assesses the user's current emotional state, determining whether they are stressed or relaxed.

[1473] 10. Emotional recipe suggestions:

[1474] The generative AI model and emotion engine work together to suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, the system will suggest a "chamomile tea and aloe salad" using ingredients that have a relaxing effect.

[1475] 11. Final Recipe Notification and Saving:

[1476] The server notifies the user of the confirmed recipe and stores the data in a database, allowing the user to prepare meals based on the recipe.

[1477] Specific examples

[1478] Examples of prompts include:

[1479] "Enter Ana's meal information. Example: 'Breakfast: Yogurt and banana. Lunch: Chicken salad. Dinner: Grilled salmon'"

[1480] This allows the system to efficiently manage the user's dietary information and emotional data, and contribute to improving and maintaining overall health by suggesting not only nutritionally balanced meals but also meals that correspond to the user's emotional state.

[1481] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1482] Step 1:

[1483] User Input

[1484] The user uses a device (smartphone, tablet, or PC) to enter meal information. For example, they might enter "Breakfast: yogurt and banana," "Lunch: chicken salad," and "Dinner: grilled salmon."

[1485] Input: Dietary information such as what was eaten, ingredients used, and intake amounts.

[1486] Output: Meal information data that can be sent and displayed on the device.

[1487] Step 2:

[1488] Data transmission and storage

[1489] The device sends the meal information to the server. When the user presses the send button, the data is sent to the server via HTTPS. The server stores the received data in a database (e.g., MySQL or PostgreSQL).

[1490] Input: Submitted meal information data.

[1491] Output: Meal information stored in a database.

[1492] Step 3:

[1493] Nutritional balance analysis

[1494] The server uses the dietary data stored in the database to calculate the nutritional value of each dish, and the generative AI model then references a food database (e.g., USDA Nutrient Database) to evaluate the overall nutritional balance.

[1495] Input: Meal information data, food database.

[1496] Output: Nutritional balance assessment results.

[1497] Step 4:

[1498] Recipe Suggestions

[1499] Based on the analysis results, the generative AI model suggests recipes to supplement missing nutrients. For example, if you are lacking in calcium, it will suggest a "spinach and cheese omelet." This suggestion is displayed on the device screen.

[1500] Input: Nutritional balance assessment results.

[1501] Output: Suggested recipe information.

[1502] Step 5:

[1503] User Feedback

[1504] The user uses the device to review the suggested recipes and optionally enter feedback, such as special offers or allergy information. For example, "Salmon is on sale today" or "I'm allergic to spinach."

[1505] Input: Additional information such as special offers, allergy information, etc.

[1506] Output: Feedback data on the device.

[1507] Step 6:

[1508] re-proposal

[1509] The server receives the user's feedback, and the generative AI model re-proposes a new recipe, for example, "grilled salmon and broccoli." This suggestion is also displayed on the device screen.

[1510] Input: Feedback data.

[1511] Output: Re-suggested recipe information.

[1512] Step 7:

[1513] Acquiring emotion data

[1514] The emotion engine uses sensors such as the device's camera and microphone to analyze the user's facial expressions and tone of voice, and acquires emotional data. This is automatically executed when the user is operating the smartphone.

[1515] Input: User's facial expression data, voice data.

[1516] Output: The obtained emotion data.

[1517] Step 8:

[1518] Sending and storing emotional data

[1519] The device transmits the acquired emotion data to the server, which receives the data and records it in a database.

[1520] Input: The acquired emotion data.

[1521] Output: Emotion data stored in a database.

[1522] Step 9:

[1523] Sentiment Data Analysis

[1524] The server's generative AI model analyzes the emotion data and assesses the user's current emotional state, for example, determining whether they are stressed or relaxed.

[1525] Input: Stored emotion data.

[1526] Output: User's emotional state assessment result.

[1527] Step 10:

[1528] Emotion-based recipe suggestions

[1529] The generative AI model and emotion engine work together to suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, the system will suggest a relaxing dish called "chamomile tea and aloe salad."

[1530] Input: User's emotional state assessment results.

[1531] Output: Suggested recipe information based on emotional state.

[1532] Step 11:

[1533] Notification and saving of final recipe

[1534] The server notifies the user of the confirmed recipe and stores the data in a database, allowing the user to prepare meals based on the recipe.

[1535] Input: Final recipe information.

[1536] Output: Recipe information notified to the user's device, recipe information saved in the database.

[1537] (Application example 2)

[1538] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1539] Conventional nutrition management systems evaluate nutritional balance based solely on the user's dietary information and suggest appropriate recipes, but do not consider the mental state or emotions of each individual user. As a result, it is difficult to provide comprehensive support that also takes into account the user's mental health. Furthermore, there was no mechanism for reflecting the suggested recipes in actual food delivery, which meant it took time and effort for users to reflect the suggested recipes in their actual meals.

[1540] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for inputting the contents of the meals the user has eaten, a transmission means for transmitting the input meal data to the server, a recording means for recording the transmitted meal data, an analysis means for analyzing the recorded meal data and evaluating nutritional balance, a suggestion means for suggesting recipes to compensate for the nutritional balance based on the analysis results, a feedback means for the user to input feedback on the recipes, a sentiment analysis means for acquiring and analyzing the user's emotional data, a re-suggestion means for re-suggesting recipes based on the sentiment analysis means, an ordering means for ordering the suggested recipe from a food delivery service, and a notification means for notifying the user of the final recipe and recording it. This makes it possible to suggest flexible and healthy eating habits according to the user's emotional state and to arrange food delivery that actually reflects the suggestions in real time.

[1541] The "input means for inputting the details of the meal taken by the user" is an interface that allows the user to input the details, ingredients, and intake amount of the meal into the terminal.

[1542] The "transmission means for transmitting input meal data to the server" is a communication function for transmitting meal data from the terminal to the server.

[1543] The "recording means for recording transmitted meal data" is a function for storing transmitted meal data in a database.

[1544] The "analysis means for analyzing recorded dietary data and evaluating nutritional balance" is a system for calculating the nutrients of each ingredient based on the recorded data and evaluating the overall nutritional balance.

[1545] The "means for proposing recipes to compensate for nutritional imbalance based on the analysis results" is a function that generates a menu to compensate for missing nutrients based on the analysis results.

[1546] The "feedback means for users to input feedback about recipes" is an interface for users to input opinions and information about suggested recipes.

[1547] The "emotion analysis means for acquiring and analyzing user emotion data" refers to a sensor and analysis engine for analyzing the user's facial expressions and tone of voice to understand their emotional state.

[1548] The "re-suggestion means for re-suggesting recipes based on emotion analysis means" is a function for re-suggesting appropriate recipes by taking into account emotion data.

[1549] "Means for arranging to order the suggested recipe from a food delivery service" is a function for ordering ingredients and dishes from a food delivery service based on the suggested recipe.

[1550] The "notification means for notifying the user of the final recipe and recording it" is a function for notifying the user of the final recipe and recording that information in a database.

[1551] This invention is a system that plans and manages a user's daily meal menu and supports a balanced diet. Users can input information about the meals they have eaten, and the system analyzes that information to evaluate the nutritional balance. The system also grasps the user's emotional state and makes flexible recipe suggestions based on that. Furthermore, it provides a mechanism for reflecting the suggested recipes in a food delivery service.

[1552] User Interface and Input Methods

[1553] First, the user inputs meal information using a device such as a smartphone. The input interface is used to input the meal contents, ingredients used, and intake amount. For example, a specific menu item such as "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon" can be input. The information entered by the user is sent to the server in real time and recorded in a database.

[1554] Server and Data Analysis

[1555] The server receives the input data and records it in a database. The recorded data is then analyzed to assess nutritional balance. The nutrition database is referenced, the nutrients for each ingredient are calculated, and the overall nutritional balance is assessed. This process is carried out using Python and the relevant nutrition database APIs.

[1556] Recipe suggestions

[1557] Based on the analysis results, the server uses a generative AI model to suggest recipes to compensate for missing nutrients. For example, if a user is lacking in calcium, it will suggest a "spinach and cheese omelet." The suggested recipe is then notified to the user.

[1558] Feedback and sentiment data

[1559] Users can provide feedback on the suggested recipes. For example, they can provide information such as "Salmon was on sale today" or "I'm allergic to spinach." The system also collects user emotional data. The emotion analysis engine uses a camera and microphone to analyze the user's facial expressions and tone of voice to assess their stress and fatigue levels.

[1560] Re-proposal and food delivery arrangements

[1561] Based on the acquired emotional data, the server uses the generative AI and emotion analysis engine to re-suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, it will suggest "chamomile tea and aloe salad." The final recipe is then ordered from a food delivery service, and the user is notified of the decision.

[1562] Specific examples

[1563] For example, if the user is "Mr. Tanaka," he inputs that he had "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner. The server receives this and analyzes that he is lacking in calcium. It then suggests "spinach and cheese omelette," but Mr. Tanaka gives feedback that "salmon was on sale." The server then re-suggests "grilled salmon and broccoli."

[1564] Prompt Sentence Examples

[1565] "The user entered today's diet information: yogurt and banana for breakfast, chicken salad for lunch, and grilled salmon for dinner. The user is currently feeling stressed. Please suggest a dinner recipe that takes into consideration nutritional balance and uses ingredients that have a relaxing effect."

[1566] In this way, this invention efficiently manages the user's dietary information and emotional data, and not only proposes nutritionally balanced meals but also flexibly suggests meals that correspond to the user's emotional state. Furthermore, by reflecting the suggested recipes in the actual food delivery service, it contributes to improving and maintaining the user's health.

[1567] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1568] Step 1:

[1569] Users use a device such as a smartphone to input the details of the meal they ate. Specifically, they enter the name of the meal, the ingredients used, the amount consumed, etc. into an input form. Once this information is entered, the device immediately sends the data to the server.

[1570] Input: User's dietary information (e.g., yogurt and banana for breakfast, chicken salad for lunch, grilled salmon for dinner)

[1571] Output: Meal data sent to the server

[1572] Step 2:

[1573] The device sends the entered meal data to a server, which receives the data and records it in a database.

[1574] Input: Meal data sent from the device

[1575] Output: Meal data stored in a database

[1576] Step 3:

[1577] The server uses the dietary data stored in the database to calculate the value of each nutrient and evaluate the overall nutritional balance. The generative AI model references the nutrition database to identify the necessary nutrients. This step uses Python and related nutrition database APIs.

[1578] Input: Dietary data recorded in the database

[1579] Output: Nutritional balance evaluation results

[1580] Step 4:

[1581] The server uses a generative AI model to evaluate nutritional balance and suggests recipes to supplement missing nutrients.

[1582] Input: Nutritional balance evaluation results

[1583] Output: Suggested recipe (e.g. spinach and cheese omelette)

[1584] Step 5:

[1585] The user can then enter feedback on the suggested recipe, such as allergies or special offers, which is then sent back to the server.

[1586] Input: User feedback information (e.g., salmon was on sale, I'm allergic to spinach)

[1587] Output: Feedback information sent to the server

[1588] Step 6:

[1589] The server receives the user's feedback and proposes new recipes, and the generative AI model generates new recipes based on the feedback.

[1590] Input: Feedback information

[1591] Output: Recipe suggestions (e.g., grilled salmon and broccoli)

[1592] Step 7:

[1593] To obtain the user's emotional data, the device uses sensor devices such as a camera and microphone to analyze the user's facial expressions and tone of voice and evaluate their emotional state.

[1594] Input: User facial and voice data

[1595] Output: Emotion data

[1596] Step 8:

[1597] The device transmits the acquired emotion data to the server, which receives the data and records it in a database.

[1598] Input: Emotion data sent from the device

[1599] Output: Emotion data stored in a database

[1600] Step 9:

[1601] The server analyzes the emotional data and evaluates the user's current emotional state. The generative AI model then refers to the emotional data and evaluates the emotional state.

[1602] Input: Emotion data stored in a database

[1603] Output: Emotional state assessment result

[1604] Step 10:

[1605] A generative AI model and an emotion analysis engine work together to suggest recipes based on the user's emotional state.

[1606] Input: Emotional state assessment result

[1607] Output: Suggested recipes based on emotions (e.g., chamomile tea and aloe salad)

[1608] Step 11:

[1609] The server notifies the user of the confirmed recipe and records the data in a database. The user then places an order with the food delivery service based on the proposed recipe.

[1610] Input: Final recipe

[1611] Output: Recipe notification and food delivery order to the user

[1612] Through the above steps, the present invention efficiently manages the user's dietary information and emotional data, and realizes flexible meal suggestions and food delivery arrangements that take into account both nutritional balance and emotional state.

[1613] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1614] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1615] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1616] [Fourth embodiment]

[1617] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1618] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1619] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1620] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1621] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1622] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1623] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1624] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1625] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1626] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1627] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1628] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1629] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1630] This invention relates to a system that allows users to easily plan and manage their daily meal menus and supports a balanced and healthy diet. This system sends the meal information entered by the user to a server, which analyzes the data, evaluates the nutritional balance, and suggests suitable recipes.

[1631] Overview of program processing

[1632] 1. User input:

[1633] The user enters meal information, including the name of the dish eaten, the ingredients used, and the amount consumed. For example, "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[1634] 2. Data transmission and storage:

[1635] The device sends the entered meal information to the server, which receives the data and records it in a database.

[1636] 3. Nutritional Balance Analysis:

[1637] The server uses the dietary information stored in the database to calculate the nutritional value of each ingredient, and the AI ​​generator then references the nutrient data for each ingredient to evaluate the overall nutritional balance.

[1638] 4. Recipe Suggestions:

[1639] Based on the analysis results, the server's AI will suggest recipes to the user to supplement the nutrients they are lacking. For example, if they are lacking in calcium, it will suggest a spinach and cheese omelet.

[1640] 5. User Feedback:

[1641] Users can review the suggested recipes and enter any changes they need, special offers, or additional information about allergies, such as "Salmon was on sale today" or "I'm allergic to spinach."

[1642] 6. Re-proposal:

[1643] The generative AI will then suggest new recipes based on user feedback, such as grilled salmon and broccoli.

[1644] 7. Notify and save the final recipe:

[1645] The server notifies the user of the finalized recipe and stores the data, allowing the user to prepare a meal according to the recipe.

[1646] Specific examples

[1647] As a specific example, consider the case where the user is "Mr. Tanaka."

[1648] 1. Enter your meal information:

[1649] Tanaka enters that she had "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner.

[1650] 2. Data transmission and storage:

[1651] The device sends the entered information to the server, which records it in a database along with "Tanaka-san's" ID.

[1652] 3. Nutritional Balance Analysis:

[1653] The server-generated AI analyzes the data and identifies calcium deficiency.

[1654] 4. Recipe Suggestions:

[1655] The generative AI suggests a "spinach and cheese omelet" to supplement calcium.

[1656] 5. User Feedback:

[1657] Tanaka gives feedback to the generating AI, saying, "Salmon was on sale."

[1658] 6. Re-proposal:

[1659] The generative AI now suggests "grilled salmon and broccoli."

[1660] 7. Notify and save the final recipe:

[1661] The server sends the recipe for "grilled salmon and broccoli" to Tanaka's device and saves the data. Tanaka then prepares a healthy dinner according to the recipe.

[1662] In this way, the system efficiently manages the user's dietary information and suggests nutritionally balanced meals, thereby contributing to the maintenance and improvement of health.

[1663] The processing flow will be explained below.

[1664] Step 1:

[1665] The user uses the device to input the details of the meal they ate, including the name of the dish, the ingredients used, the amount consumed, and the cooking method. For example, they might input "Breakfast: yogurt, banana, toast," "Lunch: chicken salad," and "Dinner: grilled salmon, salad, miso soup."

[1666] Step 2:

[1667] The device sends the entered meal information to the server. The sent content includes the user ID and detailed meal information. The data is sent in an appropriate format, such as JSON.

[1668] Step 3:

[1669] The server stores the received data in a database. In addition to the meal information, the date and time of sending and the user ID are also recorded. For example, "User: Tanaka", "Date and time: 2023-10-01", "Breakfast: Yogurt, banana, toast", "Lunch: Chicken salad", "Dinner: Grilled salmon, salad, miso soup" might be recorded.

[1670] Step 4:

[1671] The server calculates the nutritional value of each ingredient based on the dietary information stored in the database. The generative AI retrieves the nutritional value of each ingredient from the database and evaluates the nutritional balance of the entire meal. For example, the nutrients of yogurt (calcium, protein), banana (potassium, vitamin C), and toast (carbohydrates, fiber) are calculated.

[1672] Step 5:

[1673] The generative AI also references past dietary data to analyze long-term nutritional intake, determining whether calcium is insufficient, vitamin D is sufficient, or salt is excessive. For example, the analysis results may include "calcium deficiency," "sufficient vitamin D," or "excess salt."

[1674] Step 6:

[1675] Based on the analysis results, the generative AI will suggest recipes suitable for the user. It will suggest balanced meals, such as recipes to supplement missing nutrients or to reduce excess intake of nutrients. For example, it will suggest a "spinach and cheese omelet" to supplement calcium.

[1676] Step 7:

[1677] The user checks the recipe suggestions from the AI ​​via their device. If the suggestions need to be changed due to reasons such as not being able to obtain certain ingredients or allergies, the user can communicate this information to the AI. For example, they can say, "Salmon was on sale today, so it was cheap."

[1678] Step 8:

[1679] The generative AI reflects user feedback and proposes new recipes, allowing for flexible responses to suit the user's preferences and circumstances. For example, it suggests "grilled salmon and broccoli."

[1680] Step 9:

[1681] The user reviews and selects the final recipe, the server sends the finalized recipe to the user's device, and the user prepares the meal according to the recipe.

[1682] Step 10:

[1683] The server saves the final recipe data in a database. This allows data to be accumulated for future analysis and recommendations. For example, "Recipe: Grilled Salmon and Broccoli," "Date and Time: 2023-10-01," and "User ID: tanaka123" are recorded.

[1684] Through these steps, the system efficiently manages the user's dietary information and suggests nutritionally balanced meals, allowing the user to maintain a healthy diet without any effort.

[1685] Example 1

[1686] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1687] In modern society, many users find it difficult to maintain a balanced diet, and dietary management is often neglected, especially in busy daily lives. In addition, each user has different nutritional needs, making it difficult to provide appropriate nutritional advice and recipes tailored to individual conditions. Traditional manual dietary management methods are inefficient and lack appropriate support measures for continuous health maintenance and improvement.

[1688] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1689] In this invention, the server includes an input means for inputting the details of the meals a user has eaten, a transmission means for transmitting the input meal data to the server, and a recording means for recording the transmitted meal data. This allows users to accurately and efficiently manage their own meal data. The server also includes an analysis means for analyzing the recorded meal data using a generative AI model to evaluate nutritional balance, a suggestion means for sending prompts to the generative AI model to suggest recipes to compensate for nutritional imbalance, a re-suggestion means for re-suggesting recipes using the generative AI model based on user feedback, and a notification means for notifying the user of the final recipe and recording it. This allows for appropriate meal suggestions based on each user's nutritional needs, enabling continuous improvement and maintenance of the user's health.

[1690] The "input means" refers to a device or interface that allows the user to input the details of the meal they have eaten.

[1691] "Transmission means" refers to a function or device for transmitting the meal data entered by the user to the server.

[1692] The "recording means" refers to a database or storage system for saving and managing the transmitted meal data.

[1693] "Analysis means using generative AI models" refers to devices or systems that use AI technology to analyze recorded dietary data and evaluate nutritional balance.

[1694] A "prompt sentence" is an input sentence that gives specific instructions to a generative AI model.

[1695] "Proposal means" refers to a function or device that uses a generative AI model to provide users with recipes to compensate for nutritional balance based on the analysis results.

[1696] A "feedback means" is a function or device that allows a user to input opinions or additional information about a recipe.

[1697] A "re-proposal means" is a function or device that uses a generative AI model to re-propose a recipe based on user feedback.

[1698] The "notification means" is a function or device for notifying the user of the final recipe and recording the data.

[1699] This invention relates to a system that allows users to easily plan and manage their daily meal menus and supports a balanced and healthy diet. This system sends the meal information entered by the user to a server, which analyzes the data, evaluates the nutritional balance, and suggests suitable recipes.

[1700] System configuration

[1701] Input Method

[1702] Users enter their meal details using a smartphone app or web interface. The information entered includes the name of the dish, the ingredients used, and the amount consumed. For example, breakfast might include "yogurt and banana," lunch might include "chicken salad," and dinner might include "grilled salmon."

[1703] Transmission method

[1704] The device sends the meal information entered by the user to the server using an HTTP POST request.

[1705] Recording means

[1706] The server records the received meal data in a database, which is used to store each user's meal history and nutritional information. For example, meal details are stored along with the user ID.

[1707] Analytical tools using generative AI models

[1708] The server uses a generative AI model to calculate the nutritional value of each ingredient based on the recorded dietary data. The generative AI model then refers to the nutrient data of the ingredients and evaluates the overall nutritional balance. This evaluation is performed by sending prompt sentences to the generative AI model.

[1709] Proposal means

[1710] The generative AI model then suggests recipes to improve nutritional balance based on the analysis results. For example, if a person is lacking in calcium, it suggests a spinach and cheese omelette.

[1711] Feedback Methods

[1712] Users review the suggested recipes and enter any missing information or specific requirements (such as special offers or allergies), for example, "Salmon was on sale today" or "I'm allergic to spinach."

[1713] Re-proposal means

[1714] The generative AI model re-suggests new recipes based on user feedback, for example, suggesting "grilled salmon and broccoli."

[1715] Notification means

[1716] The server notifies the user of the final recipe and records the data. The user can prepare a meal according to the recipe. Notifications are sent to the device using push notifications or email notifications.

[1717] Specific examples

[1718] For example, if the user is "Tanaka-san":

[1719] 1. Enter your meal information

[1720] Tanaka enters "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner.

[1721] 2. Data transmission and storage

[1722] The terminal sends the entered information to the server, which records it in a database along with Tanaka's ID.

[1723] 3. Analysis of nutritional balance

[1724] The server's generated AI model analyzes Tanaka's data and identifies that he is deficient in calcium.

[1725] 4. Recipe suggestions

[1726] The generative AI model suggests a "spinach and cheese omelet" to supplement calcium.

[1727] 5. User Feedback

[1728] Tanaka provides feedback to the generative AI model that "salmon was on sale."

[1729] 6. Re-proposal

[1730] The generative AI model now suggests "grilled salmon and broccoli."

[1731] 7. Notification and saving of final recipe

[1732] The server sends the recipe for "grilled salmon and broccoli" to Tanaka's device and saves the data. Tanaka then prepares a healthy dinner according to the recipe.

[1733] This system suggests specific, nutritionally balanced recipes by sending the prompt text "User ID: Tanaka, Meal information: Breakfast - yogurt and banana, Lunch - chicken salad, Dinner - grilled salmon. Analyze nutritional balance and check for missing nutrients. Then suggest suitable recipes to supplement those nutrients" to the generative AI model.

[1734] In this way, users can efficiently manage their own dietary data and use it to maintain and improve their health.

[1735] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1736] Step 1:

[1737] The user inputs the details of the food they have eaten.

[1738] Input: The user enters the names of the dishes for breakfast, lunch, and dinner, the ingredients used, and the amount consumed into an input form on the terminal.

[1739] How it works: Users use a smartphone app or web interface to enter meal information using a keyboard or touch panel.

[1740] Output: The entered meal information is saved in the device.

[1741] Step 2:

[1742] The terminal transmits the meal information to the server.

[1743] Input: Meal information stored on your device.

[1744] How it works: The device sends the entered meal information to the server using an HTTP POST request.

[1745] Output: Meal information is sent to the server.

[1746] Step 3:

[1747] The server records the received meal information in a database.

[1748] Input: Meal information sent to the server.

[1749] How it works: The server stores the received data in a database using INSERT statements, for example, "Tanaka's ID, Breakfast - yogurt and banana, Lunch - chicken salad, Dinner - grilled salmon".

[1750] Output: The recorded meal information is stored in a database.

[1751] Step 4:

[1752] The server-generated AI model analyzes the dietary information and evaluates nutritional balance.

[1753] Input: Meal information stored in a database.

[1754] How it works: The server extracts the user's dietary information from the database using a SELECT statement and sends a prompt to the generative AI model. The prompt reads, "User ID: Tanaka, Breakfast - Yogurt and banana, Lunch - Chicken salad, Dinner - Grilled salmon. Analyze the nutritional balance and check for any missing nutrients." The generative AI model then analyzes and evaluates the nutritional balance.

[1755] Output: The nutritional balance evaluation results are returned from the generative AI model.

[1756] Step 5:

[1757] Based on the analysis results, the server suggests recipes to improve nutritional balance.

[1758] Input: Nutritional balance assessment results returned by the generative AI model.

[1759] How it works: Based on the evaluation results, the server sends a new prompt to the generative AI model to generate a suitable recipe. For example, "I'm lacking calcium, so please suggest a recipe to supplement my calcium."

[1760] Output: The generative AI model returns a suitable recipe suggestion, for example, "Spinach and Cheese Omelette."

[1761] Step 6:

[1762] The user provides feedback on the suggested recipe.

[1763] Input: A recipe provided by the server.

[1764] How it works: The user reviews the proposed recipe and enters any specials, allergies, or other specific requirements into a feedback form. For example, "Salmon was on sale today" or "I'm allergic to spinach."

[1765] Output: Feedback information is saved to the device.

[1766] Step 7:

[1767] The terminal transmits the feedback information to the server.

[1768] Input: Feedback information stored on the device.

[1769] How it works: The device sends feedback information to the server using an HTTP POST request.

[1770] Output: The feedback information is sent to the server.

[1771] Step 8:

[1772] The server's generative AI model re-proposes new recipes based on the feedback information.

[1773] Input: The feedback information sent to the server.

[1774] How it works: The server sends a new prompt to the generative AI model, suggesting a new recipe that takes the feedback into account. For example, "User ID: Tanaka, salmon is on sale and I'm allergic to spinach. Please suggest a new recipe."

[1775] Output: The generative AI model returns a new recipe suggestion, for example, "Grilled Salmon and Broccoli."

[1776] Step 9:

[1777] The server notifies the user of the final recipe and records the data.

[1778] Input: The final recipe returned from the generative AI model.

[1779] Operation: The server saves the final recipe information in the database and notifies the device via an HTTP response. The device displays the notification to the user and allows them to view the recipe.

[1780] Output: The final recipe information is saved in the database and on the device, and is notified to the user.

[1781] In this way, the system manages the user's dietary information through each step and supports the user's health by suggesting recipes that take nutritional balance into consideration.

[1782] (Application example 1)

[1783] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1784] Conventional food delivery services have had the problem of making it difficult for users to select meals that take into account healthy nutritional balance. In particular, there has been a lack of specific suggestions for supplementing nutrients lacking in daily meals, and meal delivery services based on such suggestions. As a result, users have had to go through the trouble of researching nutritional balance and choosing meals themselves.

[1785] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1786] In this invention, the server includes an input means for inputting the contents of the meal consumed by the user, a transmission means for transmitting the input meal data to the server, a recording means for recording the transmitted meal data, an analysis means for analyzing the recorded meal data and evaluating the nutritional balance, a proposal means for proposing recipes to compensate for the nutritional balance based on the analysis results, a feedback means for the user to input feedback on the recipe, a re-proposal means for re-proposing a recipe based on the user's feedback, a notification means for notifying the user of the final recipe and recording it, and a delivery order means for ordering a meal based on the proposed recipe.

[1787] This allows users to easily manage the nutritional balance of their daily meals and order delivery meals based on suggested healthy recipes, thereby improving the quality of their diet and helping them maintain and improve their health.

[1788] The "input means" refers to a device or interface that allows the user to input the details of the meal they have eaten.

[1789] The "transmission means" is a communication function for transmitting the input meal data to the server.

[1790] "Recording means" refers to devices or software for storing and recording the transmitted dietary data in a database or the like.

[1791] "Analysis means" refers to algorithms or programs that evaluate nutritional balance based on recorded dietary data and identify necessary nutrients.

[1792] The "suggestion method" is a function that uses a generative AI model to suggest recipes to supplement the user's missing nutrients based on the analysis results.

[1793] The "feedback means" is an interface that allows the user to input feedback such as opinions and improvements regarding the proposed recipe.

[1794] A "re-proposal method" is an algorithm or program that regenerates and proposes new recipes based on user feedback.

[1795] The "notification means" is a notification function for notifying the user of the finalized recipe.

[1796] The "delivery ordering means" is a function for ordering food based on the suggested recipe from a delivery service.

[1797] The "additional input means" is an interface that allows the user to input additional information such as sale item information and allergy information.

[1798] The "long-term analysis means" refers to an algorithm or program that analyzes data on long-term nutritional balance with the aim of continuously improving and maintaining the user's health.

[1799] MODE FOR CARRYING OUT THE INVENTION

[1800] The present invention relates to a system that allows users to easily plan and manage their daily meal menus and supports a balanced and healthy diet. This system includes an "input means," "transmission means," "recording means," "analysis means," "suggestion means," "feedback means," "re-suggestion means," "notification means," and "delivery ordering means."

[1801] System configuration

[1802] Hardware

[1803] Device: The smartphone used by the user (Android, iOS)

[1804] Server: Cloud server for processing and storing data

[1805] software

[1806] Database: PostgreSQL is used to store and manage user meal information.

[1807] Backend framework: Python and Flask will be used to build an API to input food information, analyze nutritional balance, suggest recipes, and process orders.

[1808] Generative AI model: Uses OpenAI's GPT to generate nutritionally balanced recipes.

[1809] Front-end framework: React Native is used to build the user interface.

[1810] System processing flow

[1811] 1. Enter your meal information

[1812] An "input method" is provided for users to input the name of the dish they ate, the ingredients used, and the intake amount. For example, they can input "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[1813] 2. Data transmission and storage

[1814] The user's device has a "transmission means" for transmitting the input meal information to the server, and the server stores the received data in a database as a "recording means."

[1815] 3. Analysis of nutritional balance

[1816] The server evaluates the nutritional balance of the recorded dietary data using an "analysis tool." The generative AI model (OpenAI GPT) references the nutrients in each ingredient and calculates the overall nutritional balance.

[1817] 4. Recipe suggestions

[1818] Based on the analysis results, the system will suggest recipes to the user to make up for any missing nutrients. For example, if a user is lacking in calcium, the system will suggest a "spinach and cheese omelet."

[1819] 5. User Feedback

[1820] Users can enter feedback on the suggested recipes using the "Feedback Tool." For example, they can add information such as "Salmon was on sale today" or "I'm allergic to spinach."

[1821] 6. Re-proposal

[1822] The server re-proposes new recipes based on the user's feedback using the "re-proposition method." For example, it suggests "grilled salmon and broccoli."

[1823] 7. Notification and saving of final recipe

[1824] The server notifies the user of the finalized recipe via a "notification means" and stores the data, allowing the user to prepare a meal according to the recipe.

[1825] 8. Delivery Orders

[1826] Healthy meals are provided through a delivery service using a "delivery ordering means" that allows users to order meals based on suggested recipes.

[1827] Specific examples

[1828] An example of a prompt that the user might enter:

[1829] "Suggest calcium-rich recipes based on the user's dietary information. Breakfast: Yogurt and banana, Lunch: Chicken salad, Dinner: Grilled salmon."

[1830] As described above, by utilizing the system of the present invention, users can easily manage the nutritional balance of their daily meals and maintain a healthy diet. In addition, by ordering food delivery based on the suggested recipes, users can reduce their time and effort and instantly consume healthy meals.

[1831] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1832] Step 1:

[1833] The user inputs meal information.

[1834] Input: Meal name, ingredients used, and amount consumed (e.g., Breakfast: Yogurt and banana, Lunch: Chicken salad, Dinner: Grilled salmon)

[1835] Output: Input meal information

[1836] Specific operations: The user uses the smartphone application to input meal information into the input means.

[1837] Step 2:

[1838] The terminal transmits the input meal data to the server.

[1839] Input: Meal information entered by the user

[1840] Output: Meal data sent to the server

[1841] Specific operation: The smartphone application sends this data to the server via the Internet using its internal transmission means.

[1842] Step 3:

[1843] The server stores the transmitted meal data in a recording means.

[1844] Input: Submitted meal data

[1845] Output: Meal data stored in a database

[1846] Specific operation: The server connects to the database (PostgreSQL) and saves the data along with the user ID.

[1847] Step 4:

[1848] The server uses analytical means to evaluate the nutritional balance of the recorded dietary data.

[1849] Input: Saved meal data

[1850] Output: Nutritional balance evaluation results

[1851] Specific operation: The server's generative AI model (OpenAI GPT) calculates the nutritional value of each ingredient contained in the dietary data and evaluates the overall nutritional balance.

[1852] Step 5:

[1853] Based on the analysis results, the server uses the suggestion method to suggest recipes to supplement the missing nutrients.

[1854] Input: Nutritional balance evaluation results

[1855] Output: Suggested recipe

[1856] Specific operation: The server's generative AI model uses prompt text to generate recipes that supplement missing nutrients.

[1857] Example prompt: "Suggest calcium-enriched recipes based on the user's dietary information."

[1858] Step 6:

[1859] The user inputs feedback on the proposed recipe using the input means.

[1860] Input: User feedback on the suggested recipe (e.g., salmon was on sale today, I'm allergic to spinach)

[1861] Output: Input feedback

[1862] What it does: A user uses a smartphone application to provide feedback on a suggested recipe.

[1863] Step 7:

[1864] The server again suggests recipes using the suggestion means based on the user's feedback.

[1865] Input: User feedback

[1866] Output: Re-proposed recipe

[1867] How it works: The server's generative AI model generates new recipes that incorporate user feedback.

[1868] Step 8:

[1869] The server notifies the user of the final recipe using a notification means and stores it in a database.

[1870] Input: Confirmed recipe

[1871] Output: Final recipe notified and final recipe data saved

[1872] Specific operation: The server notifies the smartphone application of the confirmed recipe and saves it in the database.

[1873] Step 9:

[1874] The user orders food based on the confirmed recipe using a delivery ordering means.

[1875] Input: Confirmed recipe

[1876] Output: Delivery order

[1877] Specific operation: The user orders food based on the final recipe from a delivery service via a smartphone application.

[1878] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1879] This invention relates to a system that plans and manages a user's daily meal menu and supports a balanced and healthy diet. This system transmits meal information entered by the user to a server, analyzes the data, evaluates nutritional balance, and suggests suitable recipes. Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions, enabling it to flexibly suggest recipes according to the emotional state of each individual user.

[1880] Overview of program processing

[1881] 1. User input:

[1882] The user enters meal information into the device, including the name of the dish eaten, the ingredients used, and the amount consumed, for example, "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[1883] 2. Data transmission and storage:

[1884] The device sends the entered meal information to the server, which receives the data and records it in a database.

[1885] 3. Nutritional Balance Analysis:

[1886] The server uses the dietary information stored in the database to calculate the nutritional value of each ingredient, and the AI ​​generator then references the nutrient data for each ingredient to evaluate the overall nutritional balance.

[1887] 4. Recipe Suggestions:

[1888] Based on the analysis results, the server's AI will suggest recipes to the user to supplement the nutrients they are lacking. For example, if they are lacking in calcium, it will suggest a spinach and cheese omelet.

[1889] 5. User Feedback:

[1890] The user reviews the suggested recipe and enters any changes needed, special offers, or additional information about allergies, such as "Salmon was on sale today" or "I'm allergic to spinach."

[1891] 6. Re-proposal:

[1892] The generative AI will then suggest new recipes based on user feedback, such as grilled salmon and broccoli.

[1893] 7. Acquiring Emotion Data:

[1894] The device acquires the user's emotional data. The emotion engine uses sensor devices such as cameras and microphones to analyze the user's facial expressions and tone of voice. For example, if the user is tired or stressed, that data is acquired.

[1895] 8. Transmission and storage of emotional data:

[1896] The device transmits the acquired emotion data to the server, which receives the data and records it in a database.

[1897] 9. Sentiment Data Analysis:

[1898] The server analyzes the emotion data, and the generation AI refers to the emotion engine data and evaluates the user's current emotional state, thereby understanding the user's mental state.

[1899] 10. Emotional recipe suggestions:

[1900] The generative AI and emotion engine work together to suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, the system will suggest recipes using ingredients that have a relaxing effect.

[1901] 11. Final Recipe Notification and Saving:

[1902] The server notifies the user of the finalized recipe and saves the data, allowing the user to prepare meals according to the recipe.

[1903] Specific examples

[1904] As a specific example, consider the case where the user is "Mr. Tanaka."

[1905] 1. Enter your meal information:

[1906] Tanaka enters that she had "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner.

[1907] 2. Data transmission and storage:

[1908] The device sends the entered information to the server, which records it in a database along with "Tanaka-san's" ID.

[1909] 3. Nutritional Balance Analysis:

[1910] The server-generated AI analyzes the data and identifies calcium deficiency.

[1911] 4. Recipe Suggestions:

[1912] The generative AI suggests a "spinach and cheese omelet" to supplement calcium.

[1913] 5. User Feedback:

[1914] Tanaka gives feedback to the generating AI, saying, "Salmon was on sale."

[1915] 6. Re-proposal:

[1916] The generative AI now suggests "grilled salmon and broccoli."

[1917] 7. Acquiring Emotion Data:

[1918] When Tanaka is using the device, the emotion engine analyzes her facial expressions and tone of voice to detect when she is feeling stressed.

[1919] 8. Transmission and storage of emotional data:

[1920] The device transmits emotion data to a server, which receives the data and stores it in a long-term database.

[1921] 9. Sentiment Data Analysis:

[1922] The server's generated AI analyzes the emotional data and assesses that Tanaka is currently experiencing stress.

[1923] 10. Emotional recipe suggestions:

[1924] The generative AI suggests "chamomile tea and aloe salad," which uses ingredients with a relaxing effect.

[1925] 11. Final Recipe Notification and Saving:

[1926] The server sends the recipe for "chamomile tea and aloe salad" to Tanaka's device and records the data in the database. Tanaka prepares dinner according to the recipe.

[1927] In this way, the system efficiently manages the user's dietary information and emotional data, and contributes to improving and maintaining overall health by suggesting not only nutritionally balanced meals but also meals that are tailored to the user's mental state.

[1928] The processing flow will be explained below.

[1929] Step 1:

[1930] The user uses the device to input the details of the meals they have eaten. For example, Mr. Tanaka inputs "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[1931] Step 2:

[1932] The device sends the entered meal information to the server. The sent content includes the user ID and detailed information about the entered meal. This data is sent in JSON format.

[1933] Step 3:

[1934] The server stores the received data in a database. The stored information includes the user ID, meal details, and the date and time of sending. Specifically, it records the information as "User ID: tanaka123", "Date and time: 2023-10-01", "Breakfast: yogurt, banana", "Lunch: chicken salad", and "Dinner: grilled salmon".

[1935] Step 4:

[1936] The server calculates nutritional values ​​based on the dietary information stored in the database. The AI ​​then references the nutritional value data of each ingredient and evaluates the total nutritional value of the user. It calculates nutrients such as calcium from yogurt, potassium and vitamin C from bananas, and protein from chicken salad.

[1937] Step 5:

[1938] The AI ​​analyzes nutritional balance, including past dietary data. The server identifies nutrients that are lacking or over-consumption. For example, results such as "lack of calcium," "sufficient vitamin D," and "too much salt" can be obtained.

[1939] Step 6:

[1940] Based on the analysis results, the server's generative AI will suggest recipes to improve nutritional balance, such as a spinach and cheese omelet to supplement calcium.

[1941] Step 7:

[1942] The user can check the recipe suggestions from the AI ​​via their device and provide feedback if changes are needed due to the unavailability of certain ingredients or allergies, for example, by entering information such as "Salmon was on sale today" or "I'm allergic to spinach."

[1943] Step 8:

[1944] The generative AI takes user feedback into account and re-suggests new recipes, such as "grilled salmon and broccoli," depending on the user's preferences and the situation.

[1945] Step 9:

[1946] The device acquires the user's emotional data. The emotion engine analyzes the user's facial expressions and tone of voice via the camera and microphone to detect the user's emotional state. For example, it can detect that Mr. Tanaka is feeling stressed.

[1947] Step 10:

[1948] The device sends the acquired emotion data to the server, which receives the data and records it in a database. The emotion data includes the user ID, emotional state, and acquisition date and time.

[1949] Step 11:

[1950] The server analyzes the emotion data. The generative AI evaluates the user's current emotional state based on the data from the emotion engine. For example, it determines that the user is feeling stressed.

[1951] Step 12:

[1952] The generative AI suggests recipes based on the user's emotional state, using ingredients that reduce stress and fatigue. For example, it suggests a relaxing "chamomile tea and aloe salad."

[1953] Step 13:

[1954] The user reviews and selects the final recipe, the server sends the finalized recipe to the user's device, and the user prepares the meal according to the recipe.

[1955] Step 14:

[1956] The server saves the final recipe data in a database. This accumulates data for future analysis and recommendations. The saved information includes recipe details, submission date and time, and user ID. For example, "Recipe: Chamomile Tea and Aloe Salad," "Date and Time: 2023-10-01," and "User ID: tanaka123" might be recorded.

[1957] Through these steps, the system efficiently manages the user's dietary information and emotional data, ensuring nutritional balance while providing flexible dietary suggestions tailored to the user's emotional state, thereby helping to improve and maintain health.

[1958] Example 2

[1959] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1960] In today's modern dietary habits, many people find it difficult to maintain a balanced, healthy diet. It is also known that emotional states have a significant impact on food choices, and stress and fatigue can lead to poor dietary quality. However, conventional dietary management systems only focus on analyzing nutritional balance, and few of them provide recommendations that take the user's emotional state into account. The present invention aims to solve these problems.

[1961] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1962] In this invention, the server includes an input means for inputting the details of the meals the user has eaten, a transmission means for transmitting the input meal data to the server, and a recording means for recording the transmitted meal data. This allows for the collection and storage of meal information. The server also includes an analysis means for analyzing the recorded meal data and evaluating nutritional balance, a proposal means for proposing recipes to compensate for the nutritional balance based on the analysis results, an emotion analysis means for acquiring and analyzing the user's emotional state, an emotion-based proposal means for proposing recipes based on the user's emotional state, and a notification means for notifying the user of the final recipe and recording it. This allows the user to receive not only nutritionally balanced meal suggestions but also appropriate meal suggestions based on the user's emotional state.

[1963] The "input means" refers to a means for the user to input the details of the food they have eaten, such as an application on a smartphone or computer.

[1964] The "transmission means" is a means for transmitting the input meal data to the server, and uses a communication protocol such as an HTTP request.

[1965] The "recording means" is a means for recording the transmitted meal data in a database or the like, and may utilize a cloud service or a local server.

[1966] The "analysis means" is a means for analyzing the recorded dietary data and evaluating nutritional balance, and involves calculations using a generative AI model and a food database.

[1967] The "suggestion method" is a method for suggesting recipes to users to compensate for nutritional balance based on the analysis results, and uses a generative AI model.

[1968] The "feedback means" is a means for the user to input feedback about the proposed recipe, and is performed via a terminal.

[1969] The "re-suggestion means" is a means for re-suggesting recipes based on user feedback, and uses a generative AI model.

[1970] The "emotion analysis means" is a means for acquiring and analyzing the user's emotional state, and performs analysis using an emotion engine that utilizes sensors such as a camera and microphone.

[1971] The "emotion-responsive suggestion means" is a means for suggesting appropriate recipes based on the user's emotional state, and works in cooperation with a generative AI model and an emotion engine.

[1972] The "notification means" is a means for notifying and recording the final recipe to the user, and has a function for notifying the terminal and storing the data in the server.

[1973] The "sensor means" is a means for acquiring an emotional state, and includes hardware sensors such as a camera and a microphone.

[1974] The "additional input means" is a means for the user to input additional information such as sale information or allergy information, and is implemented using an input form or voice input.

[1975] The "long-term analysis means" is a means for analyzing the long-term nutritional balance with the aim of continuously improving and maintaining the user's health, and involves the long-term accumulation and analysis of data.

[1976] This invention relates to a system that plans and manages a user's daily meal menu and supports a balanced and healthy diet. This system sends the meal information entered by the user to a server, analyzes the data, evaluates the nutritional balance, and suggests suitable recipes. It can also analyze the user's emotional state and make flexible recipe suggestions based on that.

[1977] Specific Examples

[1978] Hardware and Software Configuration

[1979] 1. Device:

[1980] The device used by the user to input meal information and feedback is a smartphone, tablet, or PC. This device is equipped with sensors such as a camera and microphone, and can capture the user's emotional state.

[1981] 2. Server:

[1982] The server that receives, records, and analyzes the data sent by users can use a cloud service (e.g., Amazon Web Services, Google Cloud).The server is equipped with a database (e.g., MySQL, PostgreSQL) for storing and managing data.

[1983] 3. Generative AI Model:

[1984] A generative AI model (e.g., GPT-4) running on the server analyzes dietary and emotional data to generate and suggest appropriate recipes. This model works in conjunction with a food database (e.g., the USDA Nutrient Database) and a sentiment analysis engine.

[1985] System Operation

[1986] 1. User input:

[1987] Users input information about the meals they have eaten through the device's application, such as "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon."

[1988] 2. Data transmission and storage:

[1989] The device sends the entered meal information to the server using the HTTPS protocol, which receives the data and records it in a database.

[1990] 3. Nutritional Balance Analysis:

[1991] Based on the dietary data stored on the server, the generative AI model calculates the nutritional value of each dish, and then refers to a food database to evaluate the overall nutritional balance.

[1992] 4. Recipe Suggestions:

[1993] Based on the analysis results, the generative AI model suggests recipes to supplement missing nutrients. For example, if you are lacking in calcium, it will suggest a "spinach and cheese omelet." The suggestions are displayed on the device screen.

[1994] 5. User Feedback:

[1995] The user reviews the suggested recipes and, if necessary, enters additional information about specials or allergies. For example, they might enter, "Salmon is on sale today" or "I'm allergic to spinach."

[1996] 6. Re-proposal:

[1997] The server receives user feedback, and the generative AI model suggests new recipes, for example, re-proposing "grilled salmon and broccoli."

[1998] 7. Acquiring Emotion Data:

[1999] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and tone of voice to obtain emotional data. This is automatically executed when the user is operating the smartphone.

[2000] 8. Transmission and storage of emotional data:

[2001] The acquired emotion data is sent to the server via HTTPS protocol and recorded in a database.

[2002] 9. Sentiment Data Analysis:

[2003] A generative AI model analyzes the emotional data and assesses the user's current emotional state, determining whether they are stressed or relaxed.

[2004] 10. Emotional recipe suggestions:

[2005] The generative AI model and emotion engine work together to suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, the system will suggest a "chamomile tea and aloe salad" using ingredients that have a relaxing effect.

[2006] 11. Final Recipe Notification and Saving:

[2007] The server notifies the user of the confirmed recipe and stores the data in a database, allowing the user to prepare meals based on the recipe.

[2008] Specific examples

[2009] Examples of prompts include:

[2010] "Enter Ana's meal information. Example: 'Breakfast: Yogurt and banana. Lunch: Chicken salad. Dinner: Grilled salmon'"

[2011] This allows the system to efficiently manage the user's dietary information and emotional data, and contribute to improving and maintaining overall health by suggesting not only nutritionally balanced meals but also meals that correspond to the user's emotional state.

[2012] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2013] Step 1:

[2014] User Input

[2015] The user uses a device (smartphone, tablet, or PC) to enter meal information. For example, they might enter "Breakfast: yogurt and banana," "Lunch: chicken salad," and "Dinner: grilled salmon."

[2016] Input: Dietary information such as what was eaten, ingredients used, and intake amounts.

[2017] Output: Meal information data that can be sent and displayed on the device.

[2018] Step 2:

[2019] Data transmission and storage

[2020] The device sends the meal information to the server. When the user presses the send button, the data is sent to the server via HTTPS. The server stores the received data in a database (e.g., MySQL or PostgreSQL).

[2021] Input: Submitted meal information data.

[2022] Output: Meal information stored in a database.

[2023] Step 3:

[2024] Nutritional balance analysis

[2025] The server uses the dietary data stored in the database to calculate the nutritional value of each dish, and the generative AI model then references a food database (e.g., USDA Nutrient Database) to evaluate the overall nutritional balance.

[2026] Input: Meal information data, food database.

[2027] Output: Nutritional balance assessment results.

[2028] Step 4:

[2029] Recipe Suggestions

[2030] Based on the analysis results, the generative AI model suggests recipes to supplement missing nutrients. For example, if you are lacking in calcium, it will suggest a "spinach and cheese omelet." This suggestion is displayed on the device screen.

[2031] Input: Nutritional balance assessment results.

[2032] Output: Suggested recipe information.

[2033] Step 5:

[2034] User Feedback

[2035] The user uses the device to review the suggested recipes and optionally enter feedback, such as special offers or allergy information. For example, "Salmon is on sale today" or "I'm allergic to spinach."

[2036] Input: Additional information such as special offers, allergy information, etc.

[2037] Output: Feedback data on the device.

[2038] Step 6:

[2039] re-proposal

[2040] The server receives the user's feedback, and the generative AI model re-proposes a new recipe, for example, "grilled salmon and broccoli." This suggestion is also displayed on the device screen.

[2041] Input: Feedback data.

[2042] Output: Re-suggested recipe information.

[2043] Step 7:

[2044] Acquiring emotion data

[2045] The emotion engine uses sensors such as the device's camera and microphone to analyze the user's facial expressions and tone of voice, and acquires emotional data. This is automatically executed when the user is operating the smartphone.

[2046] Input: User's facial expression data, voice data.

[2047] Output: The obtained emotion data.

[2048] Step 8:

[2049] Sending and storing emotional data

[2050] The device transmits the acquired emotion data to the server, which receives the data and records it in a database.

[2051] Input: The acquired emotion data.

[2052] Output: Emotion data stored in a database.

[2053] Step 9:

[2054] Sentiment Data Analysis

[2055] The server's generative AI model analyzes the emotion data and assesses the user's current emotional state, for example, determining whether they are stressed or relaxed.

[2056] Input: Stored emotion data.

[2057] Output: User's emotional state assessment result.

[2058] Step 10:

[2059] Emotion-based recipe suggestions

[2060] The generative AI model and emotion engine work together to suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, the system will suggest a relaxing dish called "chamomile tea and aloe salad."

[2061] Input: User's emotional state assessment results.

[2062] Output: Suggested recipe information based on emotional state.

[2063] Step 11:

[2064] Notification and saving of final recipe

[2065] The server notifies the user of the confirmed recipe and stores the data in a database, allowing the user to prepare meals based on the recipe.

[2066] Input: Final recipe information.

[2067] Output: Recipe information notified to the user's device, recipe information saved in the database.

[2068] (Application example 2)

[2069] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2070] Conventional nutrition management systems evaluate nutritional balance based solely on the user's dietary information and suggest appropriate recipes, but do not consider the mental state or emotions of each individual user. As a result, it is difficult to provide comprehensive support that also takes into account the user's mental health. Furthermore, there was no mechanism for reflecting the suggested recipes in actual food delivery, which meant it took time and effort for users to reflect the suggested recipes in their actual meals.

[2071] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for inputting the contents of the meals the user has eaten, a transmission means for transmitting the input meal data to the server, a recording means for recording the transmitted meal data, an analysis means for analyzing the recorded meal data and evaluating nutritional balance, a suggestion means for suggesting recipes to compensate for the nutritional balance based on the analysis results, a feedback means for the user to input feedback on the recipes, a sentiment analysis means for acquiring and analyzing the user's emotional data, a re-suggestion means for re-suggesting recipes based on the sentiment analysis means, an ordering means for ordering the suggested recipe from a food delivery service, and a notification means for notifying the user of the final recipe and recording it. This makes it possible to suggest flexible and healthy eating habits according to the user's emotional state and to arrange food delivery that actually reflects the suggestions in real time.

[2072] The "input means for inputting the details of the meal taken by the user" is an interface that allows the user to input the details, ingredients, and intake amount of the meal into the terminal.

[2073] The "transmission means for transmitting input meal data to the server" is a communication function for transmitting meal data from the terminal to the server.

[2074] The "recording means for recording transmitted meal data" is a function for storing transmitted meal data in a database.

[2075] The "analysis means for analyzing recorded dietary data and evaluating nutritional balance" is a system for calculating the nutrients of each ingredient based on the recorded data and evaluating the overall nutritional balance.

[2076] The "means for proposing recipes to compensate for nutritional imbalance based on the analysis results" is a function that generates a menu to compensate for missing nutrients based on the analysis results.

[2077] The "feedback means for users to input feedback about recipes" is an interface for users to input opinions and information about suggested recipes.

[2078] The "emotion analysis means for acquiring and analyzing user emotion data" refers to a sensor and analysis engine for analyzing the user's facial expressions and tone of voice to understand their emotional state.

[2079] The "re-suggestion means for re-suggesting recipes based on emotion analysis means" is a function for re-suggesting appropriate recipes by taking into account emotion data.

[2080] "Means for arranging to order the suggested recipe from a food delivery service" is a function for ordering ingredients and dishes from a food delivery service based on the suggested recipe.

[2081] The "notification means for notifying the user of the final recipe and recording it" is a function for notifying the user of the final recipe and recording that information in a database.

[2082] This invention is a system that plans and manages a user's daily meal menu and supports a balanced diet. Users can input information about the meals they have eaten, and the system analyzes that information to evaluate the nutritional balance. The system also grasps the user's emotional state and makes flexible recipe suggestions based on that. Furthermore, it provides a mechanism for reflecting the suggested recipes in a food delivery service.

[2083] User Interface and Input Methods

[2084] First, the user inputs meal information using a device such as a smartphone. The input interface is used to input the meal contents, ingredients used, and intake amount. For example, a specific menu item such as "Breakfast: Yogurt and banana," "Lunch: Chicken salad," and "Dinner: Grilled salmon" can be input. The information entered by the user is sent to the server in real time and recorded in a database.

[2085] Server and Data Analysis

[2086] The server receives the input data and records it in a database. The recorded data is then analyzed to assess nutritional balance. The nutrition database is referenced, the nutrients for each ingredient are calculated, and the overall nutritional balance is assessed. This process is carried out using Python and the relevant nutrition database APIs.

[2087] Recipe suggestions

[2088] Based on the analysis results, the server uses a generative AI model to suggest recipes to compensate for missing nutrients. For example, if a user is lacking in calcium, it will suggest a "spinach and cheese omelet." The suggested recipe is then notified to the user.

[2089] Feedback and sentiment data

[2090] Users can provide feedback on the suggested recipes. For example, they can provide information such as "Salmon was on sale today" or "I'm allergic to spinach." The system also collects user emotional data. The emotion analysis engine uses a camera and microphone to analyze the user's facial expressions and tone of voice to assess their stress and fatigue levels.

[2091] Re-proposal and food delivery arrangements

[2092] Based on the acquired emotional data, the server uses the generative AI and emotion analysis engine to re-suggest recipes based on the user's emotional state. For example, if the user is feeling stressed, it will suggest "chamomile tea and aloe salad." The final recipe is then ordered from a food delivery service, and the user is notified of the decision.

[2093] Specific examples

[2094] For example, if the user is "Mr. Tanaka," he inputs that he had "yogurt and banana" for breakfast, "chicken salad" for lunch, and "grilled salmon" for dinner. The server receives this and analyzes that he is lacking in calcium. It then suggests "spinach and cheese omelette," but Mr. Tanaka gives feedback that "salmon was on sale." The server then re-suggests "grilled salmon and broccoli."

[2095] Prompt Sentence Examples

[2096] "The user entered today's diet information: yogurt and banana for breakfast, chicken salad for lunch, and grilled salmon for dinner. The user is currently feeling stressed. Please suggest a dinner recipe that takes into consideration nutritional balance and uses ingredients that have a relaxing effect."

[2097] In this way, this invention efficiently manages the user's dietary information and emotional data, and not only proposes nutritionally balanced meals but also flexibly suggests meals that correspond to the user's emotional state. Furthermore, by reflecting the suggested recipes in the actual food delivery service, it contributes to improving and maintaining the user's health.

[2098] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2099] Step 1:

[2100] Users use a device such as a smartphone to input the details of the meal they ate. Specifically, they enter the name of the meal, the ingredients used, the amount consumed, etc. into an input form. Once this information is entered, the device immediately sends the data to the server.

[2101] Input: User's dietary information (e.g., yogurt and banana for breakfast, chicken salad for lunch, grilled salmon for dinner)

[2102] Output: Meal data sent to the server

[2103] Step 2:

[2104] The device sends the entered meal data to a server, which receives the data and records it in a database.

[2105] Input: Meal data sent from the device

[2106] Output: Meal data stored in a database

[2107] Step 3:

[2108] The server uses the dietary data stored in the database to calculate the value of each nutrient and evaluate the overall nutritional balance. The generative AI model references the nutrition database to identify the necessary nutrients. This step uses Python and related nutrition database APIs.

[2109] Input: Dietary data recorded in the database

[2110] Output: Nutritional balance evaluation results

[2111] Step 4:

[2112] The server uses a generative AI model to evaluate nutritional balance and suggests recipes to supplement missing nutrients.

[2113] Input: Nutritional balance evaluation results

[2114] Output: Suggested recipe (e.g. spinach and cheese omelette)

[2115] Step 5:

[2116] The user can then enter feedback on the suggested recipe, such as allergies or special offers, which is then sent back to the server.

[2117] Input: User feedback information (e.g., salmon was on sale, I'm allergic to spinach)

[2118] Output: Feedback information sent to the server

[2119] Step 6:

[2120] The server receives the user's feedback and proposes new recipes, and the generative AI model generates new recipes based on the feedback.

[2121] Input: Feedback information

[2122] Output: Recipe suggestions (e.g., grilled salmon and broccoli)

[2123] Step 7:

[2124] To obtain the user's emotional data, the device uses sensor devices such as a camera and microphone to analyze the user's facial expressions and tone of voice and evaluate their emotional state.

[2125] Input: User facial and voice data

[2126] Output: Emotion data

[2127] Step 8:

[2128] The device transmits the acquired emotion data to the server, which receives the data and records it in a database.

[2129] Input: Emotion data sent from the device

[2130] Output: Emotion data stored in a database

[2131] Step 9:

[2132] The server analyzes the emotional data and evaluates the user's current emotional state. The generative AI model then refers to the emotional data and evaluates the emotional state.

[2133] Input: Emotion data stored in a database

[2134] Output: Emotional state assessment result

[2135] Step 10:

[2136] A generative AI model and an emotion analysis engine work together to suggest recipes based on the user's emotional state.

[2137] Input: Emotional state assessment result

[2138] Output: Suggested recipes based on emotions (e.g., chamomile tea and aloe salad)

[2139] Step 11:

[2140] The server notifies the user of the confirmed recipe and records the data in a database. The user then places an order with the food delivery service based on the proposed recipe.

[2141] Input: Final recipe

[2142] Output: Recipe notification and food delivery order to the user

[2143] Through the above steps, the present invention efficiently manages the user's dietary information and emotional data, and realizes flexible meal suggestions and food delivery arrangements that take into account both nutritional balance and emotional state.

[2144] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2145] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2146] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2147] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2148] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2149] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2150] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2151] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2152] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2153] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2154] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2155] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2156] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2157] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2158] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2159] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2160] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2161] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2162] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, i...

Claims

1. an input means for inputting the details of meals taken by the user; a transmitting means for transmitting the input meal data to a server; a recording means for recording the transmitted meal data; an analytical means for analyzing the recorded dietary data and evaluating nutritional balance; A suggestion means for suggesting recipes to supplement nutritional balance based on the analysis results; a feedback means for a user to input feedback regarding the recipe; a re-recommendation means for re-recommending a recipe based on user feedback; a notification means for notifying and recording the final recipe to the user; A system including:

2. 10. The system of claim 1, further comprising additional input means for a user to input additional information such as special offer information and allergy information.

3. The system according to claim 1 , further comprising a long-term analysis means for performing a long-term nutritional balance analysis for the purpose of continuously improving and maintaining the user's health condition.

Images