System

Abstract

An object of a system according to an embodiment is to realize the proposal of a menu, the ordering of food materials, and the automation of cooking that meet individual needs.SOLUTION: A system according to an embodiment includes a generation AI, a menu suggestion unit, a food ingredient ordering unit, a cooking automatization unit, and a check acceptance unit. The generating AI proposes menus based on constraints such as user preferences and family allergies. A menu proposing part automatically orders necessary food materials on the basis of the menu proposed by the generated AI. The foodstuff ordering unit puts the ordered foodstuff into the fully automatic cooker and automates cooking. The cooking automation unit confirms a menu and accepts an order through an application used on a daily basis. The confirmation acceptance unit performs confirmation of a menu and acceptance of an order through an application that is routinely used.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] Conventional technology does not adequately automate the process of suggesting menus that meet individual needs, ordering ingredients, and cooking, and there is room for improvement.

[0005] The system according to the embodiment aims to realize the automation of menu suggestions, ingredient ordering, and cooking that meet individual needs. [Means for solving the problem]

[0006] The system according to the embodiment comprises a generation AI, a menu suggestion unit, an ingredient ordering unit, a cooking automation unit, and a confirmation and acceptance unit. The generation AI suggests a menu based on the user's preferences and constraints such as family allergies. The menu suggestion unit automatically orders the necessary ingredients based on the menu suggested by the generation AI. The ingredient ordering unit automates cooking by putting the ordered ingredients into a fully automatic cooker. The cooking automation unit confirms the menu and accepts the order through an app that is used daily. The confirmation and acceptance unit confirms the menu and accepts the order through an app that is used daily. [Effects of the Invention]

[0007] The system according to the embodiment can propose menus that meet individual needs, order ingredients, and automate cooking. [Brief explanation of the drawings]

[0008] [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. DETAILED DESCRIPTION OF THE INVENTION

[0009] 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.

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

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

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

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

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

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

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

[0017] 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.

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

[0019] The 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.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. 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 (see FIG. 2) acquires the data indicating the user input.

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

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

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

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

[0025] The storage 32 stores a 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The automatic menu suggestion system according to an embodiment of the present invention utilizes a generative AI to automatically suggest menus based on user preferences and family allergies, automatically order the necessary ingredients, and automate the cooking process. This significantly reduces the user's workload and enables the provision of healthy meals tailored to individual needs.

[0029] An automatic menu suggestion system according to an embodiment includes a generation AI, a menu suggestion unit, an ingredient ordering unit, a cooking automation unit, and a confirmation and acceptance unit. The generation AI includes a menu suggestion unit that suggests a menu based on constraints such as a user's preferences and family allergies. For example, the generation AI suggests an optimal menu based on the user's past selection history and survey results. The generation AI can also suggest a menu that excludes ingredients that cause allergies by taking into account family members' allergy information. The ingredient ordering unit automatically orders the necessary ingredients based on the menu suggested by the menu suggestion unit. For example, the generation AI automatically orders the necessary ingredients from an online store, and the user simply confirms and accepts the order via LINE (registered trademark). The cooking automation unit automates cooking by adding the ingredients ordered by the ingredient ordering unit to a fully automatic cooker. For example, when ingredients are added to the fully automatic cooker, the cooker automatically cooks the food and provides the completed dish. The confirmation and acceptance unit confirms the menu and accepts the order through a commonly used app. For example, a user may receive a message on LINE (registered trademark) saying, "Today's menu is a grilled fish set meal. Do you accept the order?" and simply reply "Yes" to complete the order. This allows the automatic menu suggestion system according to the embodiment to significantly reduce the user's workload and provide healthy meals that meet individual needs.

[0030] The menu suggestion unit can analyze the user's past meal history and suggest menus that correspond to the season and weather. For example, the menu suggestion unit uses a generation AI to store the user's past meal history in a database and analyze seasonal trends in ingredients and cooking. For example, it suggests cold and refreshing dishes in the summer, and hot and stewed dishes in the winter. The menu suggestion unit also obtains weather data in real time and suggests menus that correspond to the weather. For example, it suggests hot soups and stews on rainy days, and barbecues and salads on sunny days. The menu suggestion unit also takes into account the seasons of ingredients according to the season and weather to suggest optimal menus. For example, it suggests dishes using fresh vegetables in the spring, and dishes using mushrooms and root vegetables in the fall. In this way, the system can improve user satisfaction by suggesting optimal menus that correspond to the season and weather.

[0031] The menu suggestion unit can acquire the user's health data in real time and suggest healthy menus based on that data. For example, the generation AI in the menu suggestion unit acquires the user's health data (e.g., blood sugar level and weight) from a wearable device or smartphone app and suggests healthy menus based on that data. For example, if the blood sugar level is high, it suggests low-carbohydrate dishes. The menu suggestion unit also regularly monitors the user's weight and BMI and suggests menus suitable for dieting and weight management based on that data. For example, it suggests dishes that take calorie restriction and nutritional balance into consideration. The menu suggestion unit also suggests menus according to the user's health goals (e.g., muscle building or weight loss). For example, it suggests high-protein dishes for a user aiming to build muscle, and low-calorie dishes for a user aiming to lose weight. In this way, health management is supported by suggesting menus according to the user's health condition.

[0032] The menu suggestion unit can suggest menus that take into account the user's cultural background and religious restrictions. For example, the menu suggestion unit registers the user's cultural background and religious restrictions in a database, and the generation AI suggests an appropriate menu based on that information. For example, it suggests dishes that are halal or kosher. The menu suggestion unit also suggests menus that match cultural holidays and events. For example, it suggests a traditional Christmas dinner for Christmas and traditional Hanukkah dishes for Hanukkah. The menu suggestion unit also suggests menus that avoid specific ingredients or cooking methods based on the user's cultural background. For example, it suggests dishes that do not contain animal products for vegetarian and vegan users. In this way, user satisfaction is improved by suggesting menus that take into account the user's cultural background and religious restrictions.

[0033] The menu suggestion unit can also consider the preferences of the user's friends and family to propose a shared meal plan. For example, the menu suggestion unit registers the food preferences and allergy information of the user's friends and family in a database, and the generation AI uses that information to propose a menu that will satisfy everyone. For example, it may propose dishes that the whole family will like. The menu suggestion unit also takes into account the schedules of friends and family when proposing a shared meal plan. For example, it may propose a special dinner on a day when everyone can get together. The menu suggestion unit also analyzes past meal history and feedback to propose a menu that reflects the preferences of friends and family. For example, it may re-suggest dishes that were popular in the past. In this way, meal plans that take the preferences of the user's friends and family into consideration can be proposed, providing a meal that will satisfy everyone.

[0034] The ingredient ordering unit can analyze a user's past purchase history and automatically order ingredients at the optimal timing. For example, the generation AI stores the user's past purchase history in a database, and the ingredient ordering unit automatically orders ingredients at the optimal timing based on that data. For example, it automatically reorders ingredients before they run out. The ingredient ordering unit also analyzes the purchase history and understands the user's consumption patterns. For example, for a user who consumes a lot of ingredients on weekends, it automatically orders ingredients before the weekend. The ingredient ordering unit also predicts the consumption frequency of specific ingredients based on the user's purchase history and automatically orders them at the necessary timing. For example, it periodically orders ingredients that are frequently consumed, such as milk and bread. In this way, by automatically ordering ingredients at the optimal timing based on the user's past purchase history, ingredient waste is reduced and efficient ingredient management is achieved.

[0035] The ingredient ordering unit can evaluate the freshness and quality of ingredients and order from the optimal supplier. For example, the ingredient ordering unit uses a generation AI to collect ingredient freshness and quality data from online stores and local markets, and then orders from the optimal supplier based on that data. For example, it prioritizes ordering highly fresh vegetables and fruits. The ingredient ordering unit also analyzes user reviews and rating scores to evaluate ingredient quality. For example, it orders ingredients from highly rated suppliers. The ingredient ordering unit also monitors the freshness and quality of ingredients in real time and builds a system to select the optimal supplier. For example, it prioritizes suppliers that provide ingredients with guaranteed freshness. This allows the system to evaluate the freshness and quality of ingredients and order from the optimal supplier, thereby providing high-quality ingredients to users.

[0036] The food ordering department can order ingredients directly from local farmers and markets, supporting the local economy. For example, the food ordering department could build a system in which the generation AI orders ingredients directly from local farmers and markets, supporting the local economy. For example, it could prioritize ordering fresh local vegetables and fruits. The food ordering department could also register information about local farmers and markets in a database, and the generation AI could use that information to select the optimal supplier. For example, it could order ingredients from local organic farmers. The food ordering department could also strengthen collaboration with local farmers and markets and develop a platform to support the local economy. For example, it could provide an online marketplace that introduces local ingredients. This would support the local economy and provide fresh local ingredients by ordering ingredients directly from local farmers and markets.

[0037] The food ordering unit can prioritize ordering environmentally friendly ingredients to minimize the user's eco-footprint. For example, the food ordering unit builds a system in which the generation AI prioritizes ordering environmentally friendly ingredients, thereby minimizing the user's eco-footprint. For example, organic produce and locally produced ingredients are prioritized for ordering. The food ordering unit also registers information about environmentally friendly ingredients in a database, and the generation AI selects the optimal supplier based on that information. For example, ingredients with a low carbon footprint are ordered. The food ordering unit also monitors the user's eco-footprint and develops a system that suggests environmentally friendly ingredients. For example, seafood from sustainable fisheries is suggested. In this way, by prioritizing ordering environmentally friendly ingredients, the user's eco-footprint is minimized and a sustainable diet is supported.

[0038] The cooking automation unit can automatically select a cooking method that maximizes the nutritional value of ingredients. For example, the cooking automation unit creates a system in which a fully automatic cooker automatically selects the optimal cooking method to maximize the nutritional value of ingredients. For example, it selects low-temperature cooking or steaming to preserve vitamins and minerals. The cooking automation unit also takes into account the different nutritional values ​​of each ingredient and suggests a cooking method that maximizes that nutritional value. For example, it steams vegetables for a short time to preserve their vitamin C. The cooking automation unit also monitors the nutritional value of ingredients in real time and adjusts the optimal cooking method during cooking. For example, it fine-tunes the temperature and time during cooking to preserve nutritional value. This allows the fully automatic cooker to automatically select a cooking method that maximizes the nutritional value of ingredients, providing healthy meals.

[0039] The cooking automation unit can fine-tune cooking time and temperature according to the user's preferences. For example, a fully automatic cooker stores user preferences in a database and fine-tunes cooking time and temperature based on that information. For example, it reflects the user's preferred doneness of doneness or simmering. The cooking automation unit also creates a system in which the fully automatic cooker adjusts cooking time and temperature in real time based on user feedback. For example, if the user requests food be "a little softer," the cooking automation unit extends the cooking time. The cooking automation unit also analyzes the user's past cooking history and suggests optimal cooking times and temperatures based on that data. For example, it recreates cooking methods that were popular in the past. In this way, fine-tuning cooking times and temperatures according to the user's preferences improves user satisfaction.

[0040] The cooking automation unit can have the function of automatically recreating dishes from different countries. For example, the fully automatic cooker stores recipes for dishes from different countries in a database and automatically recreates them based on that information. For example, the cooking automation unit automatically cooks Italian or Chinese dishes. The cooking automation unit also analyzes the cooking methods and ingredients of dishes from different countries, and the fully automatic cooker selects the optimal cooking method based on that information. For example, it adjusts the boiling time for pasta or the heat level for stir-fries. The cooking automation unit also suggests and automatically cooks dishes from different countries in response to user requests. For example, it cooks tacos in response to a request such as "I want to eat Mexican food today." In this way, the automatic recreation of dishes from different countries provides users with a diverse dining experience.

[0041] The cooking automation unit can continuously improve cooking methods based on user feedback. For example, the cooking automation unit stores user feedback in a database, and the fully automatic cooker continuously improves the cooking method based on that information. For example, the cooking time is adjusted in response to a request such as "a little softer." The cooking automation unit also collects feedback in real time, and builds a system in which the fully automatic cooker immediately improves the cooking method based on that data. For example, if a user requests "a little more salt," the amount of seasoning is adjusted. The cooking automation unit also analyzes the user's past feedback, and the fully automatic cooker suggests the optimal cooking method based on that data. For example, it recreates a cooking method that was popular in the past. In this way, user satisfaction is increased by continuously improving cooking methods based on user feedback.

[0042] The confirmation and acceptance unit enables the generation AI to make optimal suggestions based on the user's past selection history when confirming a menu on LINE (registered trademark). The confirmation and acceptance unit, for example, stores the user's past selection history in a database, and the generation AI proposes optimal menus based on that information. For example, it proposes dishes that were popular in the past. The confirmation and acceptance unit also builds a system in which, when confirming a menu on LINE (registered trademark), the generation AI analyzes the user's selection history in real time and makes optimal suggestions. For example, if a user requests, "I want to eat Japanese food today," the generation AI proposes a Japanese menu. The confirmation and acceptance unit also allows the generation AI to propose optimal menus according to the season and weather based on the user's selection history. For example, in summer, it proposes cold or refreshing dishes, and in winter, it proposes warm or stewed dishes. In this way, optimal suggestions based on the user's past selection history improve user satisfaction.

[0043] The confirmation and acceptance unit allows the generation AI to consider the user's schedule and propose the optimal delivery time when accepting an order on LINE (registered trademark). The confirmation and acceptance unit, for example, obtains the user's schedule from a calendar app or schedule management app, and the generation AI proposes the optimal delivery time based on that information. For example, it sets delivery for a time period when the user is at home. The confirmation and acceptance unit also builds a system in which the generation AI analyzes the user's schedule in real time when accepting an order on LINE (registered trademark) and proposes the optimal delivery time. For example, if a user requests delivery after 3:00 p.m., it sets delivery for that time period. The confirmation and acceptance unit also develops an algorithm that allows the generation AI to propose the optimal delivery time based on the user's schedule. For example, it analyzes the user's past delivery history and predicts the optimal time period. This improves user convenience by proposing the optimal delivery time based on the user's schedule.

[0044] The confirmation and acceptance unit can provide similar functions in messaging apps other than LINE (registered trademark). The confirmation and acceptance unit builds a system that provides similar menu confirmation and order acceptance functions in messaging apps other than LINE (registered trademark) (e.g., WhatsApp and WeChat). For example, a message such as "Today's menu is a grilled fish set meal. Do you accept the order?" is received on WhatsApp. The confirmation and acceptance unit also uses the API of each messaging app to provide the menu confirmation and order acceptance functions with a generation AI. For example, a message such as "Today's menu is a grilled fish set meal. Do you accept the order?" is received on WeChat. The confirmation and acceptance unit also provides the optimal menu confirmation and order acceptance functions with a generation AI depending on the messaging app used by the user. For example, the confirmation and acceptance unit allows the user to check the menu and accept the order using the app they normally use. This improves user convenience by providing similar functions in messaging apps other than LINE (registered trademark).

[0045] The confirmation and acceptance unit can provide a function that allows the generation AI to share with the user's friends and family when confirming a menu on LINE (registered trademark). The confirmation and acceptance unit builds a system that provides a function that allows the generation AI to share with the user's friends and family when confirming a menu on LINE (registered trademark). For example, all family members receive a message saying, "Today's menu is a grilled fish set meal. Do you accept the order?" The confirmation and acceptance unit also generates a link for sharing with friends and family, making it easy to share on LINE (registered trademark). For example, when a "Share today's menu with friends" button is pressed, a menu link is sent to friends. The confirmation and acceptance unit also provides a group function for sharing with friends and family, so that all group members receive a message on LINE (registered trademark) confirming the menu and accepting the order. For example, a family group receives a message saying, "Today's menu is a grilled fish set meal. Do you accept the order?" This provides a function that allows the user to share menus with their friends and family, promoting communication and sharing the enjoyment of meals.

[0046] Generative AI can analyze user feedback in real time and instantly improve its suggestions. For example, generative AI can collect user feedback in real time and build a system that instantly improves suggestions based on that data. For example, it can adjust the next suggestion based on a request such as "a little more salt." Generative AI can also analyze feedback in real time and instantly improve its suggestions based on that data. For example, if a user provides feedback that "this dish is too spicy," it can adjust the spiciness in the next suggestion. Generative AI can also develop a system that continuously improves suggestions based on user feedback. For example, it can analyze past feedback and make suggestions that match the user's preferences. In this way, user satisfaction can be improved by analyzing user feedback in real time and instantly improving suggestions.

[0047] Generative AI can propose long-term meal plans based on user feedback. For example, generative AI stores user feedback in a database and proposes long-term meal plans based on that information. For example, it proposes meal plans that match the user's health goals. Generative AI can also learn the user's tastes and preferences based on the feedback and build a system that proposes long-term meal plans. For example, if a user gives feedback that they want to eat more vegetables, it will propose a vegetable-centered meal plan. Generative AI can also analyze user feedback and propose long-term meal plans based on that data. For example, it can propose meal plans that take into account the user's health condition and nutritional balance. In this way, it can support the user's health management by proposing long-term meal plans based on user feedback.

[0048] Generative AI can generate general suggestions that are also useful to other users based on user feedback. For example, generative AI stores user feedback in a database and generates general suggestions that are also useful to other users based on that information. For example, if a particular dish is well received, it will be suggested to other users as well. Generative AI can also build a system that generates general suggestions based on feedback. For example, it can analyze users' tastes and preferences, find commonalities, and make general suggestions. Generative AI can also analyze user feedback and generate suggestions that are also useful to other users based on that data. For example, if a particular ingredient or cooking method is well received, it will be suggested to other users as well. In this way, by generating general suggestions that are also useful to other users based on user feedback, the value of the entire system is improved.

[0049] Generative AI can suggest new recipes and ingredients based on user feedback. For example, generative AI stores user feedback in a database and suggests new recipes and ingredients based on that information. For example, if a user gives feedback saying, "I want to eat healthier food," it will suggest new healthy recipes. Generative AI can also build a system that suggests new recipes and ingredients based on feedback. For example, it can analyze a user's tastes and preferences and generate new recipes. Generative AI can also analyze user feedback and suggest new recipes and ingredients based on that data. For example, if a user gives feedback saying, "I want more variety," it will suggest new dishes. In this way, suggesting new recipes and ingredients based on user feedback improves the user's dining experience.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The automatic menu suggestion system can also obtain the user's exercise data and suggest menus based on the amount of exercise. For example, on days when the user has consumed a lot of calories, it can suggest high-calorie dishes that are suitable for replenishing energy. It can also suggest protein-rich dishes to support post-exercise recovery. Furthermore, it can suggest menus that include ingredients that help repair muscles depending on the type of exercise. This makes it possible to provide optimal meals based on the user's exercise habits.

[0052] The automatic menu suggestion system can also take into account the user's travel plans and suggest menus that incorporate local specialties and dishes from the region the user is traveling to. For example, if the user is planning a trip to Italy, the system can suggest menus that incorporate Italian cuisine. It can also suggest dishes that suit the climate and culture of the destination. It can also suggest balanced meals that take into account the nutrients needed during the trip. This allows the system to provide the optimal meals according to the user's travel plans.

[0053] The automatic menu suggestion system can also acquire the user's sleep data and suggest menus based on the user's sleep quality. For example, if the user is not getting enough sleep, it can suggest dishes that use ingredients with a relaxing effect. It can also suggest ingredients that contain specific vitamins and minerals to improve sleep quality. Furthermore, it can suggest dishes that are easy to digest even if eaten late at night based on the user's sleep patterns. This makes it possible to provide the optimal meals to improve the user's sleep quality.

[0054] The automatic menu suggestion system can also consider the user's hobbies and interests and suggest dishes related to them. For example, if the user's hobby is watching movies, the system can suggest dishes that match the theme of the movie. Also, if the user is interested in a particular country or culture, the system can suggest dishes related to that country or culture. It can also suggest events or special meals related to the user's hobbies. This makes it possible to provide the optimal meal according to the user's hobbies and interests.

[0055] The automatic menu suggestion system can also take into account the diet of the user's pet and suggest menus that can be enjoyed together with the pet. For example, if the user has a dog, it will suggest dishes that the dog can eat. It can also suggest dishes that use ingredients suitable for pets, taking into account the pet's health condition and allergy information. It can also suggest special meals for pets' birthdays and special events. This makes it possible to provide the optimal meals that the user and pet can enjoy together.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The menu suggestion unit proposes a menu based on the user's preferences and constraints such as family allergies. For example, the generation AI proposes the optimal menu based on the user's past selection history and survey results. It can also consider family allergy information and propose a menu that excludes ingredients that cause allergies. Step 2: The ingredient ordering unit automatically orders the necessary ingredients based on the menu proposed by the menu suggestion unit. For example, the generation AI automatically orders the necessary ingredients from an online store, and the user only needs to confirm and accept the order details via LINE (registered trademark). Step 3: The cooking automation unit automates cooking by putting the ingredients ordered by the ingredient ordering unit into the automatic cooker. For example, when ingredients are put into the automatic cooker, the cooker automatically cooks the food and serves the finished dish. Step 4: The confirmation and acceptance unit confirms the menu and accepts the order through the app that the user uses on a daily basis. For example, the user receives a message on LINE (registered trademark) saying, "Today's menu is a grilled fish set meal. Do you accept the order?" and simply replies "Yes" to complete the order.

[0058] (Example 2) The automatic menu suggestion system according to an embodiment of the present invention utilizes a generative AI to automatically suggest menus based on user preferences and family allergies, automatically order the necessary ingredients, and automate the cooking process. This significantly reduces the user's workload and enables the provision of healthy meals tailored to individual needs.

[0059] An automatic menu suggestion system according to an embodiment includes a generation AI, a menu suggestion unit, an ingredient ordering unit, a cooking automation unit, and a confirmation and acceptance unit. The generation AI includes a menu suggestion unit that suggests a menu based on constraints such as a user's preferences and family allergies. For example, the generation AI suggests an optimal menu based on the user's past selection history and survey results. The generation AI can also suggest a menu that excludes ingredients that cause allergies by taking into account family members' allergy information. The ingredient ordering unit automatically orders the necessary ingredients based on the menu suggested by the menu suggestion unit. For example, the generation AI automatically orders the necessary ingredients from an online store, and the user simply confirms and accepts the order via LINE (registered trademark). The cooking automation unit automates cooking by adding the ingredients ordered by the ingredient ordering unit to a fully automatic cooker. For example, when ingredients are added to the fully automatic cooker, the cooker automatically cooks the food and provides the completed dish. The confirmation and acceptance unit confirms the menu and accepts the order through a commonly used app. For example, a user may receive a message on LINE (registered trademark) saying, "Today's menu is a grilled fish set meal. Do you accept the order?" and simply reply "Yes" to complete the order. This allows the automatic menu suggestion system according to the embodiment to significantly reduce the user's workload and provide healthy meals that meet individual needs.

[0060] The menu suggestion unit can analyze the user's past meal history and suggest menus that correspond to the season and weather. For example, the menu suggestion unit uses a generation AI to store the user's past meal history in a database and analyze seasonal trends in ingredients and cooking. For example, it suggests cold and refreshing dishes in the summer, and hot and stewed dishes in the winter. The menu suggestion unit also obtains weather data in real time and suggests menus that correspond to the weather. For example, it suggests hot soups and stews on rainy days, and barbecues and salads on sunny days. The menu suggestion unit also takes into account the seasons of ingredients according to the season and weather to suggest optimal menus. For example, it suggests dishes using fresh vegetables in the spring, and dishes using mushrooms and root vegetables in the fall. In this way, the system can improve user satisfaction by suggesting optimal menus that correspond to the season and weather.

[0061] The menu suggestion unit can acquire the user's health data in real time and suggest healthy menus based on that data. For example, the generation AI in the menu suggestion unit acquires the user's health data (e.g., blood sugar level and weight) from a wearable device or smartphone app and suggests healthy menus based on that data. For example, if the blood sugar level is high, it suggests low-carbohydrate dishes. The menu suggestion unit also regularly monitors the user's weight and BMI and suggests menus suitable for dieting and weight management based on that data. For example, it suggests dishes that take calorie restriction and nutritional balance into consideration. The menu suggestion unit also suggests menus according to the user's health goals (e.g., muscle building or weight loss). For example, it suggests high-protein dishes for a user aiming to build muscle, and low-calorie dishes for a user aiming to lose weight. In this way, health management is supported by suggesting menus according to the user's health condition.

[0062] The menu suggestion unit can use the emotion estimation function to analyze the user's current emotional state and suggest a menu that matches their mood. For example, the menu suggestion unit analyzes the user's emotional state in real time using the smartphone's camera and microphone, and the generation AI uses that data to suggest a menu that matches their mood. For example, if the user is feeling stressed, the unit suggests dishes that have a relaxing effect. The menu suggestion unit also uses the emotion estimation function to calculate the user's emotional score and suggest a menu based on that score. For example, if the user is feeling strongly positive, the unit suggests dishes that will further enhance their joyful mood. The menu suggestion unit also analyzes the user's emotional state and suggests a menu that is suitable for a change of mood or to refresh themselves. For example, if the user is tired, the unit suggests dishes that will replenish their energy, and if the user is feeling down, the unit suggests dishes that will brighten their mood. In this way, by suggesting menus that match the user's emotional state, user satisfaction is improved.

[0063] The menu suggestion unit can suggest menus that take into account the user's cultural background and religious restrictions. For example, the menu suggestion unit registers the user's cultural background and religious restrictions in a database, and the generation AI suggests an appropriate menu based on that information. For example, it suggests dishes that are halal or kosher. The menu suggestion unit also suggests menus that match cultural holidays and events. For example, it suggests a traditional Christmas dinner for Christmas and traditional Hanukkah dishes for Hanukkah. The menu suggestion unit also suggests menus that avoid specific ingredients or cooking methods based on the user's cultural background. For example, it suggests dishes that do not contain animal products for vegetarian and vegan users. In this way, user satisfaction is improved by suggesting menus that take into account the user's cultural background and religious restrictions.

[0064] The menu suggestion unit can also consider the preferences of the user's friends and family to propose a shared meal plan. For example, the menu suggestion unit registers the food preferences and allergy information of the user's friends and family in a database, and the generation AI uses that information to propose a menu that will satisfy everyone. For example, it may propose dishes that the whole family will like. The menu suggestion unit also takes into account the schedules of friends and family when proposing a shared meal plan. For example, it may propose a special dinner on a day when everyone can get together. The menu suggestion unit also analyzes past meal history and feedback to propose a menu that reflects the preferences of friends and family. For example, it may re-suggest dishes that were popular in the past. In this way, meal plans that take the preferences of the user's friends and family into consideration can be proposed, providing a meal that will satisfy everyone.

[0065] The menu suggestion unit uses the emotion estimation function to analyze the emotional state of each family member and suggest a menu that will satisfy everyone. For example, the menu suggestion unit analyzes the emotional state of each family member in real time using a smartphone or tablet camera, and the generation AI uses that data to suggest a menu that will satisfy everyone. For example, it suggests dishes that will relax everyone. The menu suggestion unit also uses the emotion estimation function to calculate the emotional scores of each family member and suggest a menu based on that score. For example, it suggests dishes that will make everyone feel positive. The menu suggestion unit also analyzes the emotional state of each family member and suggests events or special meals that everyone can enjoy. For example, it suggests barbecues and picnics that everyone can enjoy. In this way, by suggesting menus that correspond to the emotional state of each family member, it is possible to provide a meal that will satisfy everyone.

[0066] The ingredient ordering unit can analyze a user's past purchase history and automatically order ingredients at the optimal timing. For example, the generation AI stores the user's past purchase history in a database, and the ingredient ordering unit automatically orders ingredients at the optimal timing based on that data. For example, it automatically reorders ingredients before they run out. The ingredient ordering unit also analyzes the purchase history and understands the user's consumption patterns. For example, for a user who consumes a lot of ingredients on weekends, it automatically orders ingredients before the weekend. The ingredient ordering unit also predicts the consumption frequency of specific ingredients based on the user's purchase history and automatically orders them at the necessary timing. For example, it periodically orders ingredients that are frequently consumed, such as milk and bread. In this way, by automatically ordering ingredients at the optimal timing based on the user's past purchase history, ingredient waste is reduced and efficient ingredient management is achieved.

[0067] The ingredient ordering unit can evaluate the freshness and quality of ingredients and order from the optimal supplier. For example, the ingredient ordering unit uses a generation AI to collect ingredient freshness and quality data from online stores and local markets, and then orders from the optimal supplier based on that data. For example, it prioritizes ordering highly fresh vegetables and fruits. The ingredient ordering unit also analyzes user reviews and rating scores to evaluate ingredient quality. For example, it orders ingredients from highly rated suppliers. The ingredient ordering unit also monitors the freshness and quality of ingredients in real time and builds a system to select the optimal supplier. For example, it prioritizes suppliers that provide ingredients with guaranteed freshness. This allows the system to evaluate the freshness and quality of ingredients and order from the optimal supplier, thereby providing high-quality ingredients to users.

[0068] The ingredient ordering unit can use the emotion estimation function to suggest special ingredients according to the user's emotional state. For example, the ingredient ordering unit analyzes the user's emotional state in real time, and the generation AI suggests special ingredients according to the emotional state based on that data. For example, if the user is feeling stressed, the ingredient ordering unit suggests herbal tea with a relaxing effect. The ingredient ordering unit also uses the emotion estimation function to calculate the user's emotion score and suggests special ingredients based on that score. For example, it suggests chocolate to bring out positive emotions. The ingredient ordering unit also analyzes the user's emotional state and suggests ingredients suitable for a change of mood or to refresh the user. For example, if the user is tired, it suggests nuts or fruit to replenish energy. In this way, suggesting special ingredients according to the user's emotional state improves user satisfaction.

[0069] The food ordering department can order ingredients directly from local farmers and markets, supporting the local economy. For example, the food ordering department could build a system in which the generation AI orders ingredients directly from local farmers and markets, supporting the local economy. For example, it could prioritize ordering fresh local vegetables and fruits. The food ordering department could also register information about local farmers and markets in a database, and the generation AI could use that information to select the optimal supplier. For example, it could order ingredients from local organic farmers. The food ordering department could also strengthen collaboration with local farmers and markets and develop a platform to support the local economy. For example, it could provide an online marketplace that introduces local ingredients. This would support the local economy and provide fresh local ingredients by ordering ingredients directly from local farmers and markets.

[0070] The food ordering unit can prioritize ordering environmentally friendly ingredients to minimize the user's eco-footprint. For example, the food ordering unit builds a system in which the generation AI prioritizes ordering environmentally friendly ingredients, thereby minimizing the user's eco-footprint. For example, organic produce and locally produced ingredients are prioritized for ordering. The food ordering unit also registers information about environmentally friendly ingredients in a database, and the generation AI selects the optimal supplier based on that information. For example, ingredients with a low carbon footprint are ordered. The food ordering unit also monitors the user's eco-footprint and develops a system that suggests environmentally friendly ingredients. For example, seafood from sustainable fisheries is suggested. In this way, by prioritizing ordering environmentally friendly ingredients, the user's eco-footprint is minimized and a sustainable diet is supported.

[0071] The ingredient ordering unit can use the emotion estimation function to analyze the user's emotions toward specific ingredients and select ingredients based on those emotions. For example, the ingredient ordering unit analyzes the user's emotional state in real time, and the generation AI analyzes the user's emotions toward specific ingredients based on that data. For example, if the user has positive emotions toward a specific ingredient, the ingredient is prioritized for ordering. The ingredient ordering unit also uses the emotion estimation function to calculate the user's emotion score and select ingredients based on that score. For example, it suggests ingredients that will elicit positive emotions. The ingredient ordering unit also analyzes the user's emotional state and selects ingredients that are suitable for a change of mood or to refresh the user. For example, if the user is tired, it suggests ingredients that will replenish energy. In this way, analyzing the user's emotions toward specific ingredients and selecting ingredients based on those emotions improves user satisfaction.

[0072] The cooking automation unit can automatically select a cooking method that maximizes the nutritional value of ingredients. For example, the cooking automation unit creates a system in which a fully automatic cooker automatically selects the optimal cooking method to maximize the nutritional value of ingredients. For example, it selects low-temperature cooking or steaming to preserve vitamins and minerals. The cooking automation unit also takes into account the different nutritional values ​​of each ingredient and suggests a cooking method that maximizes that nutritional value. For example, it steams vegetables for a short time to preserve their vitamin C. The cooking automation unit also monitors the nutritional value of ingredients in real time and adjusts the optimal cooking method during cooking. For example, it fine-tunes the temperature and time during cooking to preserve nutritional value. This allows the fully automatic cooker to automatically select a cooking method that maximizes the nutritional value of ingredients, providing healthy meals.

[0073] The cooking automation unit can fine-tune cooking time and temperature according to the user's preferences. For example, a fully automatic cooker stores user preferences in a database and fine-tunes cooking time and temperature based on that information. For example, it reflects the user's preferred doneness of doneness or simmering. The cooking automation unit also creates a system in which the fully automatic cooker adjusts cooking time and temperature in real time based on user feedback. For example, if the user requests food be "a little softer," the cooking automation unit extends the cooking time. The cooking automation unit also analyzes the user's past cooking history and suggests optimal cooking times and temperatures based on that data. For example, it recreates cooking methods that were popular in the past. In this way, fine-tuning cooking times and temperatures according to the user's preferences improves user satisfaction.

[0074] The cooking automation unit can use the emotion estimation function to select a cooking method that corresponds to the user's emotional state. For example, the cooking automation unit analyzes the user's emotional state in real time, and the fully automatic cooker selects a cooking method that corresponds to the emotional state based on that data. For example, a cooking method using herbs with a relaxing effect is selected. The cooking automation unit also uses the emotion estimation function to calculate the user's emotion score and suggests a cooking method based on that score. For example, if the user is feeling stressed, a soup with a relaxing effect is suggested. The cooking automation unit also analyzes the user's emotional state and selects a cooking method that is suitable for changing mood or refreshing. For example, if the user is tired, a dish that replenishes energy is suggested. In this way, selecting a cooking method that corresponds to the user's emotional state improves user satisfaction.

[0075] The cooking automation unit can have the function of automatically recreating dishes from different countries. For example, the fully automatic cooker stores recipes for dishes from different countries in a database and automatically recreates them based on that information. For example, the cooking automation unit automatically cooks Italian or Chinese dishes. The cooking automation unit also analyzes the cooking methods and ingredients of dishes from different countries, and the fully automatic cooker selects the optimal cooking method based on that information. For example, it adjusts the boiling time for pasta or the heat level for stir-fries. The cooking automation unit also suggests and automatically cooks dishes from different countries in response to user requests. For example, it cooks tacos in response to a request such as "I want to eat Mexican food today." In this way, the automatic recreation of dishes from different countries provides users with a diverse dining experience.

[0076] The cooking automation unit can continuously improve cooking methods based on user feedback. For example, the cooking automation unit stores user feedback in a database, and the fully automatic cooker continuously improves the cooking method based on that information. For example, the cooking time is adjusted in response to a request such as "a little softer." The cooking automation unit also collects feedback in real time, and builds a system in which the fully automatic cooker immediately improves the cooking method based on that data. For example, if a user requests "a little more salt," the amount of seasoning is adjusted. The cooking automation unit also analyzes the user's past feedback, and the fully automatic cooker suggests the optimal cooking method based on that data. For example, it recreates a cooking method that was popular in the past. In this way, user satisfaction is increased by continuously improving cooking methods based on user feedback.

[0077] The cooking automation unit can use the emotion estimation function to analyze the emotional states of all family members and select a cooking method that will satisfy everyone. For example, the cooking automation unit analyzes the emotional states of all family members in real time using a smartphone or tablet camera, and the fully automatic cooker selects a cooking method that will satisfy everyone based on that data. For example, it can suggest dishes that will relax everyone. The cooking automation unit can also use the emotion estimation function to calculate the emotional scores of all family members and suggest cooking methods based on those scores. For example, it can suggest dishes that will make everyone feel positive. The cooking automation unit can also analyze the emotional states of all family members and suggest events or special meals that everyone can enjoy. For example, it can suggest barbecues or picnics that everyone can enjoy. In this way, a cooking method that suits the emotional states of all family members can be selected, making it possible to provide meals that satisfy everyone.

[0078] The confirmation and acceptance unit enables the generation AI to make optimal suggestions based on the user's past selection history when confirming a menu on LINE (registered trademark). The confirmation and acceptance unit, for example, stores the user's past selection history in a database, and the generation AI proposes optimal menus based on that information. For example, it proposes dishes that were popular in the past. The confirmation and acceptance unit also builds a system in which, when confirming a menu on LINE (registered trademark), the generation AI analyzes the user's selection history in real time and makes optimal suggestions. For example, if a user requests, "I want to eat Japanese food today," the generation AI proposes a Japanese menu. The confirmation and acceptance unit also allows the generation AI to propose optimal menus according to the season and weather based on the user's selection history. For example, in summer, it proposes cold or refreshing dishes, and in winter, it proposes warm or stewed dishes. In this way, optimal suggestions based on the user's past selection history improve user satisfaction.

[0079] The confirmation and acceptance unit allows the generation AI to consider the user's schedule and propose the optimal delivery time when accepting an order on LINE (registered trademark). The confirmation and acceptance unit, for example, obtains the user's schedule from a calendar app or schedule management app, and the generation AI proposes the optimal delivery time based on that information. For example, it sets delivery for a time period when the user is at home. The confirmation and acceptance unit also builds a system in which the generation AI analyzes the user's schedule in real time when accepting an order on LINE (registered trademark) and proposes the optimal delivery time. For example, if a user requests delivery after 3:00 p.m., it sets delivery for that time period. The confirmation and acceptance unit also develops an algorithm that allows the generation AI to propose the optimal delivery time based on the user's schedule. For example, it analyzes the user's past delivery history and predicts the optimal time period. This improves user convenience by proposing the optimal delivery time based on the user's schedule.

[0080] The confirmation and acceptance unit uses the emotion estimation function to suggest a menu that corresponds to the user's emotional state, thereby eliciting positive emotions. The confirmation and acceptance unit, for example, analyzes the user's emotional state in real time, and the generation AI uses that data to suggest a menu that corresponds to the emotional state. For example, if the user is feeling stressed, the confirmation and acceptance unit suggests dishes that have a relaxing effect. The confirmation and acceptance unit also uses the emotion estimation function to calculate the user's emotion score and suggests a menu based on that score. For example, if the user is feeling strongly positive, the confirmation and acceptance unit suggests dishes that will further enhance a happy mood. The confirmation and acceptance unit also analyzes the user's emotional state and suggests a menu that is suitable for a change of mood or refreshing the user. For example, if the user is tired, the confirmation and acceptance unit suggests dishes that will replenish energy, and if the user is feeling depressed, the confirmation and acceptance unit suggests dishes that will brighten the mood. In this way, by suggesting a menu that corresponds to the user's emotional state, positive emotions are elicited from the user and satisfaction is improved.

[0081] The confirmation and acceptance unit can provide similar functions in messaging apps other than LINE (registered trademark). The confirmation and acceptance unit builds a system that provides similar menu confirmation and order acceptance functions in messaging apps other than LINE (registered trademark) (e.g., WhatsApp and WeChat). For example, a message such as "Today's menu is a grilled fish set meal. Do you accept the order?" is received on WhatsApp. The confirmation and acceptance unit also uses the API of each messaging app to provide the menu confirmation and order acceptance functions with a generation AI. For example, a message such as "Today's menu is a grilled fish set meal. Do you accept the order?" is received on WeChat. The confirmation and acceptance unit also provides the optimal menu confirmation and order acceptance functions with a generation AI depending on the messaging app used by the user. For example, the confirmation and acceptance unit allows the user to check the menu and accept the order using the app they normally use. This improves user convenience by providing similar functions in messaging apps other than LINE (registered trademark).

[0082] The confirmation and acceptance unit can provide a function that allows the generation AI to share with the user's friends and family when confirming a menu on LINE (registered trademark). The confirmation and acceptance unit builds a system that provides a function that allows the generation AI to share with the user's friends and family when confirming a menu on LINE (registered trademark). For example, all family members receive a message saying, "Today's menu is a grilled fish set meal. Do you accept the order?" The confirmation and acceptance unit also generates a link for sharing with friends and family, making it easy to share on LINE (registered trademark). For example, when a "Share today's menu with friends" button is pressed, a menu link is sent to friends. The confirmation and acceptance unit also provides a group function for sharing with friends and family, so that all group members receive a message on LINE (registered trademark) confirming the menu and accepting the order. For example, a family group receives a message saying, "Today's menu is a grilled fish set meal. Do you accept the order?" This provides a function that allows the user to share menus with their friends and family, promoting communication and sharing the enjoyment of meals.

[0083] The confirmation and acceptance unit uses the emotion estimation function to analyze the emotional states of all family members and can propose a menu that will satisfy everyone. For example, the confirmation and acceptance unit analyzes the emotional states of all family members in real time using a smartphone or tablet camera, and the generation AI uses that data to propose a menu that will satisfy everyone. For example, it proposes dishes that will relax everyone. The confirmation and acceptance unit also uses the emotion estimation function to calculate the emotional scores of all family members and propose a menu based on those scores. For example, it proposes dishes that everyone feels positive about. The confirmation and acceptance unit also analyzes the emotional states of all family members and suggests events or special meals that everyone can enjoy. For example, it suggests a barbecue or picnic that everyone can enjoy. In this way, a menu that satisfies everyone can be provided by proposing a menu that suits the emotional states of all family members.

[0084] Generative AI can analyze user feedback in real time and instantly improve its suggestions. For example, generative AI can collect user feedback in real time and build a system that instantly improves suggestions based on that data. For example, it can adjust the next suggestion based on a request such as "a little more salt." Generative AI can also analyze feedback in real time and instantly improve its suggestions based on that data. For example, if a user provides feedback that "this dish is too spicy," it can adjust the spiciness in the next suggestion. Generative AI can also develop a system that continuously improves suggestions based on user feedback. For example, it can analyze past feedback and make suggestions that match the user's preferences. In this way, user satisfaction can be improved by analyzing user feedback in real time and instantly improving suggestions.

[0085] Generative AI can propose long-term meal plans based on user feedback. For example, generative AI stores user feedback in a database and proposes long-term meal plans based on that information. For example, it proposes meal plans that match the user's health goals. Generative AI can also learn the user's tastes and preferences based on the feedback and build a system that proposes long-term meal plans. For example, if a user gives feedback that they want to eat more vegetables, it will propose a vegetable-centered meal plan. Generative AI can also analyze user feedback and propose long-term meal plans based on that data. For example, it can propose meal plans that take into account the user's health condition and nutritional balance. In this way, it can support the user's health management by proposing long-term meal plans based on user feedback.

[0086] The generative AI can use its emotion estimation function to analyze the emotions contained in user feedback and make suggestions based on those emotions. For example, the generative AI can analyze the emotions contained in user feedback in real time and make suggestions based on those emotions based on that data. For example, it can adjust the next suggestion based on feedback with a strong positive emotion. The generative AI can also use its emotion estimation function to calculate an emotion score contained in the user feedback and make suggestions based on that score. For example, it can identify areas for improvement based on feedback with a strong negative emotion. The generative AI can also build a system that analyzes user feedback and makes suggestions based on emotions. For example, if a user gives feedback that "this dish was delicious," it will suggest a similar dish next time. In this way, by analyzing the emotions contained in user feedback and making suggestions based on emotions, user satisfaction can be improved.

[0087] Generative AI can generate general suggestions that are also useful to other users based on user feedback. For example, generative AI stores user feedback in a database and generates general suggestions that are also useful to other users based on that information. For example, if a particular dish is well received, it will be suggested to other users as well. Generative AI can also build a system that generates general suggestions based on feedback. For example, it can analyze users' tastes and preferences, find commonalities, and make general suggestions. Generative AI can also analyze user feedback and generate suggestions that are also useful to other users based on that data. For example, if a particular ingredient or cooking method is well received, it will be suggested to other users as well. In this way, by generating general suggestions that are also useful to other users based on user feedback, the value of the entire system is improved.

[0088] Generative AI can suggest new recipes and ingredients based on user feedback. For example, generative AI stores user feedback in a database and suggests new recipes and ingredients based on that information. For example, if a user gives feedback saying, "I want to eat healthier food," it will suggest new healthy recipes. Generative AI can also build a system that suggests new recipes and ingredients based on feedback. For example, it can analyze a user's tastes and preferences and generate new recipes. Generative AI can also analyze user feedback and suggest new recipes and ingredients based on that data. For example, if a user gives feedback saying, "I want more variety," it will suggest new dishes. In this way, suggesting new recipes and ingredients based on user feedback improves the user's dining experience.

[0089] The generative AI can use its emotion estimation function to analyze the feedback of all family members and make suggestions that will satisfy everyone. For example, the generative AI can analyze the emotions contained in the feedback of all family members in real time and make suggestions that will satisfy everyone based on that data. For example, it can suggest dishes that all family members feel positive about. The generative AI can also use its emotion estimation function to calculate an emotional score contained in the feedback of all family members and make suggestions based on that score. For example, it can suggest dishes that will make everyone relax. The generative AI can also analyze the feedback of all family members and build a system that makes suggestions based on emotions. For example, it can suggest events or special meals that everyone can enjoy. In this way, by analyzing the feedback of all family members and making suggestions that will satisfy everyone, the satisfaction of the entire family is improved.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The automatic menu suggestion system can also obtain the user's exercise data and suggest menus based on the amount of exercise. For example, on days when the user has consumed a lot of calories, it can suggest high-calorie dishes that are suitable for replenishing energy. It can also suggest protein-rich dishes to support post-exercise recovery. Furthermore, it can suggest menus that include ingredients that help repair muscles depending on the type of exercise. This makes it possible to provide optimal meals based on the user's exercise habits.

[0092] The automatic menu suggestion system can also take into account the user's travel plans and suggest menus that incorporate local specialties and dishes from the region the user is traveling to. For example, if the user is planning a trip to Italy, the system can suggest menus that incorporate Italian cuisine. It can also suggest dishes that suit the climate and culture of the destination. It can also suggest balanced meals that take into account the nutrients needed during the trip. This allows the system to provide the optimal meals according to the user's travel plans.

[0093] The automatic menu suggestion system can also acquire the user's sleep data and suggest menus based on the user's sleep quality. For example, if the user is not getting enough sleep, it can suggest dishes that use ingredients with a relaxing effect. It can also suggest ingredients that contain specific vitamins and minerals to improve sleep quality. Furthermore, it can suggest dishes that are easy to digest even if eaten late at night based on the user's sleep patterns. This makes it possible to provide the optimal meals to improve the user's sleep quality.

[0094] The automatic menu suggestion system can also consider the user's hobbies and interests and suggest dishes related to them. For example, if the user's hobby is watching movies, the system can suggest dishes that match the theme of the movie. Also, if the user is interested in a particular country or culture, the system can suggest dishes related to that country or culture. It can also suggest events or special meals related to the user's hobbies. This makes it possible to provide the optimal meal according to the user's hobbies and interests.

[0095] The automatic menu suggestion system can also take into account the diet of the user's pet and suggest menus that can be enjoyed together with the pet. For example, if the user has a dog, it will suggest dishes that the dog can eat. It can also suggest dishes that use ingredients suitable for pets, taking into account the pet's health condition and allergy information. It can also suggest special meals for pets' birthdays and special events. This makes it possible to provide the optimal meals that the user and pet can enjoy together.

[0096] The automatic menu suggestion system can use its emotion estimation function to suggest music that matches the user's emotional state and improve the meal atmosphere. For example, if the user wants to relax, music with a relaxing effect can be suggested. Alternatively, if the user wants to cheer up, energetic music can be suggested. Furthermore, it is also possible to suggest music that will enhance the meal atmosphere according to the user's emotional state. This can improve meal satisfaction by providing optimal music that matches the user's emotional state.

[0097] The automatic menu suggestion system can use its emotion estimation function to suggest desserts that correspond to the user's emotional state. For example, if the user is feeling stressed, it can suggest desserts that have a relaxing effect. Also, if the user is feeling positive, it can suggest desserts that will further enhance that mood. Furthermore, it can also suggest desserts that are suitable for a change of mood or for refreshing the user, depending on the user's emotional state. This can improve meal satisfaction by providing the optimal dessert that corresponds to the user's emotional state.

[0098] The automatic menu suggestion system can use its emotion estimation function to suggest drinks that correspond to the user's emotional state. For example, if the user wants to relax, it can suggest relaxing herbal tea. If the user wants to feel energized, it can also suggest energetic drinks. Furthermore, it can suggest drinks that are suitable for a change of mood or for refreshing yourself, depending on the user's emotional state. This can improve meal satisfaction by providing the optimal drink that corresponds to the user's emotional state.

[0099] The automatic menu suggestion system can use its emotion estimation function to suggest meal presentations that correspond to the user's emotional state. For example, if the user wants to relax, it can suggest meal presentations and table settings that have a relaxing effect. If the user wants to cheer up, it can also suggest an energetic presentation. It can also suggest presentations that enhance the atmosphere of the meal according to the user's emotional state. This can improve meal satisfaction by providing the optimal meal presentation that corresponds to the user's emotional state.

[0100] The automatic menu suggestion system can use its emotion estimation function to suggest meal timings according to the user's emotional state. For example, if the user is feeling stressed, it can suggest meals at times that are relaxing. If the user wants to feel energized, it can also suggest meals at times that are energizing. Furthermore, it can also suggest meals at times that are suitable for a change of mood or for refreshing, depending on the user's emotional state. This can improve meal satisfaction by providing optimal meal timings according to the user's emotional state.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The menu suggestion unit proposes a menu based on the user's preferences and constraints such as family allergies. For example, the generation AI proposes the optimal menu based on the user's past selection history and survey results. It can also consider family allergy information and propose a menu that excludes ingredients that cause allergies. Step 2: The ingredient ordering unit automatically orders the necessary ingredients based on the menu proposed by the menu suggestion unit. For example, the generation AI automatically orders the necessary ingredients from an online store, and the user only needs to confirm and accept the order details via LINE (registered trademark). Step 3: The cooking automation unit automates cooking by putting the ingredients ordered by the ingredient ordering unit into the automatic cooker. For example, when ingredients are put into the automatic cooker, the cooker automatically cooks the food and serves the finished dish. Step 4: The confirmation and acceptance unit confirms the menu and accepts the order through the app that the user uses on a daily basis. For example, the user receives a message on LINE (registered trademark) saying, "Today's menu is a grilled fish set meal. Do you accept the order?" and simply replies "Yes" to complete the order.

[0103] 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.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0109] 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.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] 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.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0124] 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.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] 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.

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0129] 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.

[0130] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0131] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0139] 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.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] 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 image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] 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.

[0143] The control object 443 includes a display device, LEDs in the eyes, and motors that drive 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.

[0144] 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.

[0145] 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.

[0146] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] 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.

[0153] FIG. 9 illustrates 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 behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions 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.

[0154] 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.

[0155] 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).

[0156] 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 expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, 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 expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] 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."

[0158] 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.

[0159] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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. A processor also includes 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.

[0164] The hardware resource that executes the specific process 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 process may be a single processor.

[0165] 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.

[0166] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. Equipped with generative AI, The generated AI is a menu suggestion unit that suggests menus based on user preferences and restrictions such as family allergies; an ingredient ordering unit that automatically orders ingredients based on the menu proposed by the menu proposal unit; a cooking automation unit that puts the ingredients ordered by the ingredient ordering unit into a fully automatic cooker to automate cooking; A confirmation and approval unit that confirms menus and approves orders through an application that is used daily. A system characterized by:

2. The menu suggestion unit Analyze the user's past meal history and suggest menus according to the season and weather The system of claim 1 .

3. The menu suggestion unit Obtaining the user's health data in real time and suggesting healthy meals based on that data The system of claim 1 .

4. The menu suggestion unit Analyze the user's current emotional state and suggest a menu that matches their mood The system of claim 1 .

5. The menu suggestion unit Suggesting menus that take into account the user's cultural background and religious restrictions The system of claim 1 .

6. The menu suggestion unit It also takes into account the preferences of the user's friends and family to suggest shared meal plans. The system of claim 1 .

7. The menu suggestion unit Analyze the emotional state of each family member and suggest a menu that will satisfy everyone The system of claim 1 .

8. The ingredient ordering unit Analyze the user's past purchase history and automatically order ingredients at the optimal time. The system of claim 1 .

Images