system

Abstract

We provide the system. [Solution] A means of obtaining user preferences, dietary restrictions, health data, budget, and location information, Based on the above input data and location information, a means for collecting menu, price, nutritional information, and rating information from nearby restaurants, Based on the above collected data and user input data, a generation means for generating a lunch plan is provided. A means for notifying the user of the generated lunch plan, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, busy people such as businesspersons, students, and housewives have limited time to create their daily lunch plans. As a result, it is often difficult to make healthy food choices. Furthermore, it is even more difficult for people with allergies or dietary restrictions to find appropriate menus. Also, choosing a menu while considering budget and taste preferences is very time-consuming. It is necessary to solve these problems and provide a system that allows users to enjoy a convenient and healthy lunch.

Means for Solving the Problems

[0005] The present invention solves the above-mentioned problems by the following means. First, it provides means for users to input their preferences, dietary restrictions, health data, budget, and location information. Next, it provides means for collecting menu, price, nutritional information, and rating information from nearby restaurants based on the input data and location information. Subsequently, it provides generation means for generating a lunch plan based on the collected data and the user's input data. Furthermore, it constructs a system that includes means for notifying the user of the generated lunch plan. In addition, it improves user convenience by including means for providing coupons and discount benefits to specific restaurants based on the collected data, and means for users to make reservations based on the generated lunch plan. Furthermore, by providing means for collecting rating data from users and reflecting it in the generation of the next lunch plan, and means for periodically updating the collected data from nearby restaurants, it is possible to always provide a lunch plan using the latest information.

[0006] A "user" refers to an individual who uses this system to create a lunch plan.

[0007] "Preferences" refer to the user's preferred ingredients and culinary genres.

[0008] "Dietary restrictions" refer to foods or types of cuisine that should be avoided due to allergies or health reasons.

[0009] "Health data" refers to the user's physical information, such as weight, target weight, and height.

[0010] "Budget" refers to the maximum amount of money a user is willing to spend per meal.

[0011] "Location information" refers to the geographical information of the place where the user eats lunch, such as their workplace or school.

[0012] A "database" refers to an information management system used to store user and restaurant information.

[0013] "Collected data" refers to menus, prices, nutritional information, and ratings obtained from restaurants.

[0014] "Menu" refers to the items and contents of the meals offered by a restaurant.

[0015] "Price" refers to the monetary value set for each item on a restaurant's menu.

[0016] "Nutritional information" refers to information about the nutrients and calories contained in each menu item.

[0017] "Rating information" refers to user reviews of restaurants and menus collected from social media, review sites, and other sources.

[0018] "Generation method" refers to the processes and functions within the system that create lunch plans based on collected data and user input data.

[0019] A "lunch plan" refers to meal suggestions generated based on the user's preferences, dietary restrictions, health data, budget, and rating information.

[0020] A "coupon" refers to a discount voucher or special offer that users can use when paying at a restaurant.

[0021] "Reservation" refers to the act of a user securing a seat at a restaurant in advance based on a lunch plan.

[0022] "Evaluation data" refers to feedback information provided by users about their lunch plans and the restaurants they have visited. [Brief explanation of the drawing]

[0023] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. <0000​​​​​​​​​​​​​​​​​​​​​​​​​In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0027] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0028] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0029] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0030] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0031] [First Embodiment]

[0032] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0033] As shown in Figure 1, the 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.

[0034] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0035] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0036] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0037] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0038] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0039] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0041] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0042] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0043] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0044] A specific embodiment of the present invention will now be described. This system generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information. The user first creates an account using a device (such as a smartphone or personal computer) and completes the initial setup.

[0045] 1. Account creation and initial setup

[0046] The user accesses the system and proceeds to the account creation page. Here, the user enters the following information:

[0047] Basic information: Name, email address, password

[0048] Preferences: Preferred ingredients and cuisine types (e.g., Japanese food, Chinese food, vegetarian)

[0049] Dietary restrictions: Foods and dishes to avoid for allergies or health reasons.

[0050] Health data: weight, target weight, height, etc.

[0051] Budget: Maximum budget per meal

[0052] Location information: Places where you eat lunch, such as your workplace or school.

[0053] This information is sent from the terminal to the server and stored in the database.

[0054] 2. Gathering store information

[0055] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on location data. This includes using external APIs and obtaining data through web scraping. The collected data is stored in a database and updated in real time.

[0056] 3. Creating a lunch plan

[0057] The server retrieves user profile information and store information from the database and uses a generation AI to generate a lunch plan that takes the following factors into consideration:

[0058] Nutritional balance: Calculating necessary nutrients and calories

[0059] User preferences and dietary restrictions

[0060] Budget: The set upper limit per meal.

[0061] Reviews and ratings: Selected based on collected review information.

[0062] The generated lunch plan will be notified to the user via email or in-app notification.

[0063] 4. Offering benefits and monetization

[0064] The generated lunch plans include coupons and discounts for specific restaurants. Users can use these to receive discounts when paying at the restaurants. The server manages these coupons and discounts. Additionally, a monthly fee is charged to the restaurants to generate revenue.

[0065] 5. Booking and Reviews

[0066] Users can make restaurant reservations within the app based on the provided lunch plan. After enjoying their lunch, users can rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. When generating future lunch plans, this rating data is reflected, providing plans that better match the user's preferences.

[0067] Specific example

[0068] For example, suppose Ms. Tanaka creates an account and sets her preferences as Japanese food, dietary restrictions as gluten-free, and budget as under 1000 yen per meal. The server collects information from restaurants around Ms. Tanaka's workplace, including information on Japanese food and gluten-free menus. Based on the collected data, the generating AI suggests the following as a Monday lunch plan, taking into account nutritional balance, budget, and customer reviews:

[0069] Store A: Grilled Chicken Salad (600 yen)

[0070] Store B: Gluten-free salmon sushi (800 yen)

[0071] Ms. Tanaka will also be offered a 10% discount coupon for Restaurant A. Ms. Tanaka will choose this plan, make a reservation at Restaurant A, and enter a review after lunch. This review will be reflected in future lunch plans.

[0072] The above describes specific embodiments of the present invention. This system allows users to easily and efficiently enjoy a healthy lunch.

[0073] The following describes the processing flow.

[0074] Step 1:

[0075] The user accesses the account creation page and enters the required information. This includes basic information, preferences, dietary restrictions, health data, budget, and location information. After completing the input, the device sends the information to the server.

[0076] Step 2:

[0077] The server stores the received user information in a database and creates a custom profile for each user.

[0078] Step 3:

[0079] The server uses the user's location information to collect menu, price, nutritional information, and ratings from nearby restaurants. This data is collected through APIs and web scraping. The collected data is stored in the server's database.

[0080] Step 4:

[0081] The server retrieves user profile information and store information from the database. Based on this, a generating AI creates a lunch plan. The generating AI takes into account nutritional balance, user preferences and dietary restrictions, budget, and rating information.

[0082] Step 5:

[0083] The server generates a lunch plan and notifies the user. The notification is sent via email or in-app notification.

[0084] Step 6:

[0085] When a user reviews the lunch plan and wants to reserve their desired menu item from the options, they make the reservation within the app.

[0086] Step 7:

[0087] The server notifies the restaurant of the user's reservation information, and the reservation is confirmed.

[0088] Step 8:

[0089] Users enjoy the suggested lunch and enter their ratings for the restaurant and menu within the app.

[0090] Step 9:

[0091] The server receives user evaluation data and stores it in the database. This evaluation data will be used to generate the next lunch plan.

[0092] Step 10:

[0093] The server provides coupons and discount offers to specific restaurants, allowing users to receive discounts.

[0094] Step 11:

[0095] The server regularly updates the restaurant data it collects, ensuring that it always maintains the latest menu, prices, and ratings.

[0096] (Example 1)

[0097] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0098] In today's busy lifestyle, easily choosing healthy and nutritionally balanced meals is crucial. However, finding the perfect lunch that suits individual dietary restrictions, preferences, and budgets is not easy. In addition, the time and effort required to gather necessary information from a wide variety of restaurants is a significant burden. Furthermore, there is a lack of systems that incorporate each user's rating into future selections to provide lunch plans that better suit their preferences.

[0099] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0100] In this invention, the server includes means for prompting the user to input their preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and rating information from nearby restaurants based on the input data and location information; means for generating a lunch plan using a generative AI model based on the collected data and the user's input data; means for notifying the user of the generated lunch plan; means for creating prompt sentences to be used in generating the lunch plan; and means for reflecting the previous rating data when generating a possible next lunch plan. This makes it possible to easily and efficiently provide a healthy lunch that matches the user's preferences, restrictions, and budget.

[0101] "User preferences" refer to the types of ingredients and cuisines that users like, and represent their individual tastes in food choices.

[0102] "Dietary restrictions" refer to foods and dishes that users should avoid for allergies or health reasons.

[0103] "Health data" refers to information about a user's health, such as their weight, target weight, and height.

[0104] "Budget" refers to the maximum amount of money a user can spend per meal.

[0105] "Location information" refers to the geographical information of where the user plans to have lunch.

[0106] "Input data" refers to information that users provide to the system, such as preferences, dietary restrictions, health data, budget, and location information.

[0107] "Store information" refers to menu, price, nutritional information, and ratings information collected from nearby restaurants.

[0108] "Collected data" refers to restaurant menus, prices, nutritional information, and ratings collected based on location information.

[0109] A "generative AI model" refers to an artificial intelligence model that generates the optimal lunch plan based on user input data and store information.

[0110] A "prompt" refers to a pre-designed set of questions or commands intended for input into a generative AI model.

[0111] A "lunch plan" refers to meal suggestions generated considering the user's preferences, dietary restrictions, budget, and location.

[0112] "Evaluation data" refers to user ratings and feedback on stores and menus they have used.

[0113] A "coupon" refers to a discount voucher or special offer that can be used at a specific store.

[0114] "Notification method" refers to the means of informing users of the generated lunch plan, and includes email and in-app notifications.

[0115] A specific embodiment of the present invention will now be described. This system generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information. The details are described below.

[0116] Account creation and initial setup

[0117] Users access the system using a device (such as a smartphone or computer) and proceed to the account creation page. Here, users enter their name, email address, password, preferred foods and cuisine types, dietary restrictions, health data such as weight, target weight, and height, a budget limit per meal, and location information such as their workplace or school. This information is sent from the device to the server and stored in the database.

[0118] Gathering store information

[0119] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the user's location. This collection includes data acquisition using external APIs such as the Google Places API and Yelp API, as well as web scraping techniques (using tools such as BeautifulSoup and Scrapy). The collected data is stored in a database and updated in real time.

[0120] Creating a lunch plan

[0121] The server retrieves user profile information and store information from the database and creates prompts for a generative AI model (e.g., OpenAI's GPT-3). These prompts include user preferences, dietary restrictions, nutritional balance, budget, ratings, and customer reviews. Examples of prompt statements include:

[0122] The user prefers Japanese food, has a gluten-free diet, and a budget of under 1000 yen per meal. Please propose the optimal lunch plan.

[0123] The server uses this prompt to run a generation AI model and generate the optimal lunch plan. The generated lunch plan is then notified to the user via email or in-app notification.

[0124] Offering benefits and monetization

[0125] The generated lunch plans include coupons and discounts for specific restaurants. Users can use these to receive discounts when paying at the restaurants. The server manages these coupons and discounts and generates revenue by collecting a monthly fee from the restaurants.

[0126] Reservations and Reviews

[0127] Users can make restaurant reservations within the app based on the provided lunch plan. After enjoying their lunch, users can rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. When generating future lunch plans, this rating data is reflected, providing plans that better suit the user's preferences.

[0128] Specific example

[0129] For example, a user creates an account and sets their preferences as Japanese food, dietary restrictions as gluten-free, and budget as under 1000 yen per meal. The server collects information from restaurants around the user's workplace, including information on Japanese food and gluten-free menus. Based on the collected data, the generating AI proposes a lunch plan like the following, taking into account nutritional balance, budget, and customer reviews:

[0130] Store A: Grilled Chicken Salad (600 yen)

[0131] Store B: Gluten-free salmon sushi (800 yen)

[0132] Along with notifying users of this plan, they will be offered a 10% discount coupon for Restaurant A. Users will choose this plan, make a reservation at Restaurant A, enjoy their lunch, and then enter a review within the app. This review will be reflected in future lunch plans.

[0133] The above describes specific embodiments of the present invention. This system allows users to easily and efficiently enjoy a healthy lunch.

[0134] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0135] Step 1: Account creation and initial setup

[0136] Users access the system using their devices (smartphones or computers) and proceed to the account creation page. They fill out a form with their name, email address, password, preferred foods and cuisine types, dietary restrictions, health data such as weight, target weight, and height, a budget limit per meal, and location information. This entered data is sent from the device to the server and stored in a database.

[0137] Step 2: Gathering store information

[0138] The server uses the user's location information to collect menu, price, nutritional information, and rating information from nearby restaurants. Specifically, it uses external APIs such as the Google Places API and the Yelp API to obtain data. It also uses web scraping techniques to collect necessary information from restaurant websites. The collected restaurant information is stored in a database.

[0139] Input: Location information

[0140] Data processing: Data is obtained using external APIs or web scraping.

[0141] Output: Store Information Database

[0142] Step 3: Generate a lunch plan

[0143] The server retrieves user profile information and store information from the database and creates prompts to input into the generated AI model. These prompts include user preferences, dietary restrictions, nutritional balance, budget, ratings, and customer reviews. Examples of specific prompt statements:

[0144] The user prefers Japanese food, has a gluten-free diet, and a budget of under 1000 yen per meal. Please propose the optimal lunch plan.

[0145] The generation AI model generates the optimal lunch plan based on prompts. The generated lunch plan is saved by the server.

[0146] Input: User profile information, store information

[0147] Data processing: Execution of generative AI models

[0148] Output: Generated lunch plan

[0149] Step 4: Notification of lunch plan

[0150] The server notifies the user of the generated lunch plan. The notification is sent via email or in-app notification, making it easy for the user to check their lunch plan.

[0151] Input: Generated lunch plan

[0152] Data processing: Creating and sending notifications

[0153] Output: Notification to the user

[0154] Step 5: Offering perks and monetization

[0155] The server adds coupons and discounts for specific restaurants to the generated lunch plans. This includes generating and managing coupon codes. When users utilize these discounts, the system collects a monthly fee from the restaurants, generating revenue.

[0156] Input: Lunch plan, store information

[0157] Data processing: Coupon code generation

[0158] Output: Granting of discount benefits

[0159] Step 6: Make a reservation

[0160] Users make restaurant reservations within the app based on the provided lunch plans. The reservation function works in conjunction with the restaurant's reservation system, allowing users to complete reservations smoothly.

[0161] Input: Lunch plan

[0162] Data processing: Integration with the reservation system

[0163] Output: Restaurant reservation confirmation

[0164] Step 7: Enter your evaluation

[0165] After users enjoy their lunch, they can rate the restaurant and menu within the app. A rating form is provided, allowing users to enter rating scores and comments. This rating data is sent to a server and stored in a database.

[0166] Input: User rating data

[0167] Data processing: Evaluation data storage

[0168] Output: Saved evaluation data

[0169] Step 8: Reflect evaluation data

[0170] The server will incorporate the previous evaluation data when generating subsequent lunch plans. This will enable the provision of more accurate lunch plans that better match the user's preferences.

[0171] Input: Evaluation data

[0172] Data processing: Reflection in lunch plan generation

[0173] Output: Highly accurate lunch plan

[0174] The above describes the processing flow of this system's program.

[0175] (Application Example 1)

[0176] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0177] In modern society, it is a challenging task to easily and quickly propose lunch plans that take into account individual user preferences, health conditions, dietary restrictions, and budgets. Furthermore, there is a lack of systems that can reliably deliver satisfactory plans while simultaneously strengthening collaborations with local restaurants. In particular, generating optimal lunch plans for individual users requires sophisticated processing based on vast amounts of data, thus necessitating the provision of an efficient and effective system.

[0178] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0179] In this invention, the server includes means for prompting the user to input preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and rating information from nearby restaurants based on the input data and location information; means for generating a lunch plan using a generative AI model based on the collected data and the user's input data; and means for sending the generated lunch plan as a prompt message to the generative AI model and notifying the user. This makes it possible to quickly generate and notify the user of an optimal lunch plan that is suitable for each user's preferences and conditions.

[0180] A "user" refers to an individual who uses this system and is the entity that provides information such as preferences, dietary restrictions, and health data.

[0181] "Preferences" refer to the user's favorite ingredients and types of cuisine.

[0182] "Dietary restrictions" refer to foods or dishes that should be avoided due to allergies or health reasons.

[0183] "Health data" refers to the user's physical information, such as weight, target weight, and height.

[0184] "Budget" refers to the maximum amount of money a user plans to spend per meal.

[0185] "Location information" refers to the geographical information of the place where the user is eating.

[0186] "Menu information" refers to information that describes the dishes offered by a restaurant.

[0187] "Price information" refers to information that shows the selling price of each menu item at a restaurant.

[0188] "Nutritional information" refers to information that shows the nutritional components and calories contained in each menu item.

[0189] "Rating information" refers to information that shows the ratings and reviews that past users have given to a restaurant or its menu.

[0190] A "generative AI model" refers to an artificial intelligence model used to generate lunch plans based on user preferences, health data, budget, and location information.

[0191] A "prompt statement" refers to an input statement provided to a generative AI model.

[0192] "Means of notification" refers to the means of informing users of the generated lunch plan.

[0193] A "coupon" refers to a discount voucher that can be used at a specific restaurant.

[0194] A "discount offer" refers to a service offered by a restaurant that reduces the price of specific items.

[0195] "Methods for making reservations" refers to the means by which users can secure seats and menu items at restaurants in advance based on a lunch plan that has been generated.

[0196] The system of the present invention is designed to generate and provide customized lunch plans to users based on their individual preferences, health data, budget, and location information.

[0197] 1. Account creation and initial setup

[0198] Users first create an account using their own device (such as a smartphone or computer). The following information is required when creating an account:

[0199] Basic information: Name, email address, password

[0200] Tastes: Favorite ingredients and dishes

[0201] Dietary restrictions: Foods and dishes to avoid for allergies or health reasons.

[0202] Health data: weight, target weight, height, etc.

[0203] Budget: Maximum budget per meal

[0204] Location information: The place where we plan to have lunch

[0205] 2. Information Gathering

[0206] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on user input data and location information. This includes data acquisition through the use of external APIs and web scraping.

[0207] 3. Creating a lunch plan

[0208] The server uses a generative AI model to generate lunch plans based on the user's preferences, dietary restrictions, health data, budget, and information on nearby restaurants. Specific prompts are sent to the generative AI model, and its responses are collected as lunch plans.

[0209] Example of a prompt

[0210] "The user's preference is for Japanese food, their budget is 1000 yen, and their dietary restriction is gluten-free. Their current location is Tokyo. Here is some information on nearby restaurants..."

[0211] 4. Notification of lunch plan

[0212] The generated lunch plan will be notified to the user's device. Specifically, the user will receive an email or an in-app notification.

[0213] 5. Provision of benefits

[0214] The server uses collected data to provide coupons and discount offers to specific restaurants. These offers are included in lunch plans, allowing users to receive discounts when paying at the restaurant.

[0215] 6. Booking and Reviews

[0216] Users can make restaurant reservations within the app based on the generated lunch plan. After enjoying their lunch, users can also rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. When generating future lunch plans, this rating data is reflected, providing plans that better match the user's preferences.

[0217] The above describes a specific embodiment of the present invention. This system enables users to efficiently enjoy lunch that is perfectly suited to their individual preferences and circumstances.

[0218] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0219] Step 1:

[0220] Users create an account using their own device (such as a smartphone or computer). During account creation, users enter their name, email address, password, preferences, dietary restrictions, health data, budget, and location information. This information is sent from the device to the server and stored in the database.

[0221] Input: Name, email address, password, preferences, dietary restrictions, health data, budget, location information

[0222] Output: Saving user information to the database

[0223] Step 2:

[0224] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the user's location. This collection utilizes external APIs and web scraping. The collected information is stored in a database and updated in real time.

[0225] Input: User's location information

[0226] Output: Saving restaurant information to a database

[0227] Step 3:

[0228] The server generates lunch plans using a generative AI model based on the entered user information and collected restaurant information. During this process, the generative AI model receives prompt messages and retrieves the most suitable lunch plan as its response.

[0229] Input: User information, restaurant information

[0230] Output: Generated lunch plan

[0231] Specific operation: The system generates a prompt message such as, "User preference: Japanese food, budget: 1000 yen, dietary restrictions: gluten-free. Current location: Tokyo. Nearby restaurant information:..." and sends it to the AI ​​model. In response, the AI ​​model retrieves the optimal lunch plan (for example, "Grilled Chicken Salad at Restaurant A").

[0232] Step 4:

[0233] Once a lunch plan is generated, the server notifies the user. This notification is sent to the user's device via email or in-app notification.

[0234] Input: Generated lunch plan

[0235] Output: Notification to the user's device

[0236] Step 5:

[0237] The server suggests coupons and discount offers for specific restaurants based on the collected data. These offers are included in the generated lunch plan, which the user can then utilize.

[0238] Input: Collected data, generated lunch plan

[0239] Output: Coupons and discounts included in the lunch plan

[0240] Step 6:

[0241] Users can make restaurant reservations using their devices based on the provided lunch plans. Reservation information is sent to a server for coordination with the restaurants.

[0242] Input: Lunch plan, user reservation information

[0243] Output: Reservation notification to restaurant

[0244] Step 7:

[0245] After users enjoy their lunch, they enter their ratings of the restaurant and menu within the app. This rating data is sent to the server and stored in a database. This rating data is then used to generate future lunch plans.

[0246] Input: User rating information

[0247] Output: Saving evaluation data to a database

[0248] The above outlines the specific processing steps and flow of this system.

[0249] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0250] A specific embodiment of the present invention will now be described. This system generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information, and also recognizes the user's emotions to customize the lunch plan. The user first creates an account using a device (such as a smartphone or personal computer) and completes the initial setup.

[0251] 1. Account creation and initial setup

[0252] Users access the system and enter basic information (name, email address, password), preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (where they will have lunch) on the account creation page. After completing the input, the information is sent from the device to the server and stored in the database.

[0253] 2. Gathering store information

[0254] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on location data. Collection methods include using external APIs and web scraping. The collected data is stored in the server's database and updated in real time.

[0255] 3. Utilizing the Emotional Engine

[0256] When a user accesses the system from their device, the emotion engine uses the built-in camera and microphone to recognize the user's emotions. The emotion engine analyzes the user's facial expressions, tone of voice, and word choice to determine their current emotional state. For example, it can determine whether the user is stressed or relaxed.

[0257] 4. Creating a lunch plan

[0258] The server, taking into account the user's emotional data recognized by the emotion engine, retrieves user profile information and store information from the database. Based on this, the generative AI generates a lunch plan. The generative AI takes the following factors into consideration:

[0259] Nutritional balance: Calculating necessary nutrients and calories

[0260] User preferences and dietary restrictions

[0261] Budget: The set upper limit per meal.

[0262] Reviews and ratings: Collected review information

[0263] Emotional state: Selecting the most suitable menu or store based on the user's current emotional state.

[0264] For example, if the user is tired, a relaxing cafe or a light meal might be suggested. If the user is excited, a meal that will replenish their energy might be suggested.

[0265] 5. Notification of lunch plan and provision of benefits

[0266] The server notifies users of the generated lunch plans. Notifications are sent via email or in-app notifications. In addition, certain restaurants are given coupons and discounts, which users can use to receive discounts. The server manages these coupons and discounts, and generates revenue by collecting a monthly fee from the restaurants.

[0267] 6. Booking and Reviews

[0268] Users can make restaurant reservations within the app based on the provided lunch plan. After enjoying their lunch, users enter their ratings for the restaurant and menu within the app. This rating data is sent to the server and stored in a database. This rating data will be reflected when generating future lunch plans.

[0269] Specific example

[0270] For example, suppose Ms. Tanaka creates an account and sets her preferences as Japanese food, dietary restrictions as gluten-free, and budget as under 1000 yen per meal. One day, when Ms. Tanaka is feeling stressed, she requests a lunch plan. The server's emotion engine recognizes her stress level and suggests a menu from a relaxing restaurant. For example, it might select a restaurant that serves Japanese food and offers a gluten-free "chicken mince and soft-boiled egg salad" (800 yen) and offer a 10% discount coupon as a perk. Ms. Tanaka chooses this plan, makes a reservation at the restaurant, and enters a review after lunch.

[0271] The above describes a specific embodiment of the present invention. This system allows users to enjoy an optimal lunch tailored to their emotional state on any given day, and to maintain a healthy diet.

[0272] The following describes the processing flow.

[0273] Step 1:

[0274] The user accesses the account creation page. Here, they enter basic information (name, email address, password), preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (location of workplace or school).

[0275] Step 2:

[0276] The terminal sends the entered information to the server. The transmitted data is stored in a database by the server, and a custom profile is created for each user.

[0277] Step 3:

[0278] The server collects menu, price, nutritional information, and evaluation information from surrounding restaurants and eateries based on the user's location information. The collection methods include using external APIs and web scraping. The collected data is stored in a database and updated in real-time.

[0279] Step 4:

[0280] (When the user requests the generation of a lunch plan, the terminal uses devices such as cameras and microphones to identify the user's emotional state by the emotion engine. The emotion engine analyzes the user's emotions through facial expression analysis, voice tone analysis, word choice, etc. For example, it identifies whether the user is feeling stressed or relaxed.

[0281] Step 5:

[0282] The server retrieves the user profile information and store information from the database, and also retrieves the data on the emotional state from the emotion engine. Based on these data, the generation AI generates a lunch plan considering the following factors:

[0283] Nutritional balance: Calculation of required nutrients and calories

[0284] User preferences and dietary restrictions

[0285] Budget: Set upper limit per meal

[0286] Evaluations and reviews: Collected evaluation information

[0287] Emotional state: Select a menu and store that suits the user's current emotion

[0288] For example, if the user is tired, suggest a relaxing café or light meal, and if the user is excited, suggest a meal that can replenish energy.

[0289] Step 6:

[0290] The server generates lunch plans and notifies users. Notifications are sent via email or in-app notifications. In addition, coupons and discounts are offered at certain restaurants, which users can use to receive discounts.

[0291] Step 7:

[0292] When a user makes a restaurant reservation based on a provided lunch plan, the reservation process is performed within the app.

[0293] Step 8:

[0294] The server notifies the restaurant of the user's reservation information and confirms the reservation.

[0295] Step 9:

[0296] Users enjoy the suggested lunch and enter their ratings for the restaurant and menu within the app.

[0297] Step 10:

[0298] The server receives user evaluation data and stores it in the database. This evaluation data will be used to generate the next lunch plan.

[0299] Step 11:

[0300] The server regularly updates its database of restaurants, maintaining the latest menus, prices, and ratings, ensuring that information is always up-to-date.

[0301] Through the specific processing steps described above, users are offered a lunch plan best suited to their emotional state on that day. For example, when Ms. Tanaka is feeling stressed, a restaurant offering a gluten-free Japanese-style "chicken mince and soft-boiled egg salad" is suggested, and she can also obtain a discount coupon. Ms. Tanaka chooses this plan, makes a reservation, enjoys her lunch, and then gives a high rating. As a result, the next lunch plan will be even more appropriate.

[0302] (Example 2)

[0303] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0304] Conventional lunch plan generation systems typically provide plans based on static data such as user preferences, dietary restrictions, and budget, and are particularly unable to provide lunch plans that respond to users' dynamic emotional states. Therefore, it was difficult to provide the optimal lunch plan according to the user's mood and emotions at any given time. Furthermore, there was no mechanism in place to incorporate evaluation data into subsequent plans, making continuous improvement to increase user satisfaction difficult.

[0305] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 2 is realized by the following means. In this invention, the server includes means for allowing a user to input their preferences, dietary restrictions, health data, budget, and location information, means for collecting menu, price, nutritional information, and evaluation information from surrounding food-providing facilities based on the input data and location information, means for analyzing emotion data using the camera and microphone of the terminal to recognize the user's emotional state, generation AI means for generating a lunch plan based on the collected data, the user's input data, and the emotion data, means for notifying the user of the generated lunch plan, means for providing coupons and discount benefits for specific facilities, and means for allowing the user to make a reservation based on the lunch plan. As a result, it becomes possible to provide an optimal lunch plan not only according to the user's preferences and dietary restrictions but also according to their emotional state at that time. Furthermore, by reflecting the evaluation data in the generation of plans after the next time, the user's satisfaction can be continuously improved.

[0306] The "user" refers to the target for inputting basic information, preferences, and emotional state for generating a lunch plan using the system.

[0307] "Preferences" refers to the selection information of ingredients and cuisine genres that the user likes.

[0308] "Dietary restrictions" refers to information regarding ingredients and allergies that the user wants to avoid.

[0309] "Health data" refers to physical information such as the user's weight, target weight, and height.

[0310] "Budget" refers to the cost ceiling set by the user per meal.

[0311] "Location information" refers to the geographical information of the place where the user has lunch.

[0312] "Food-providing facility" refers to a facility that provides food such as surrounding restaurants and eateries.

[0313] "Menu" refers to the list of dishes offered at each food service establishment.

[0314] "Price" refers to the cost of each dish listed on the menu.

[0315] "Nutritional information" refers to health-related data such as the nutrients and calories contained in each menu item.

[0316] "Rating information" refers to user ratings and reviews of food service establishments and the menus they offer.

[0317] "Emotional state" refers to the psychological state obtained by analyzing the user's facial expressions, tone of voice, and other factors.

[0318] "Emotional data" refers to information about the user's emotions that has been analyzed by the emotion engine.

[0319] "Generative AI" refers to artificial intelligence technology that generates lunch plans based on data.

[0320] A "lunch plan" refers to meal suggestions provided based on collected data and user input.

[0321] A "coupon" refers to a discount voucher that can be used at a specific restaurant.

[0322] A "discount offer" refers to a discount service that a user can receive under specific conditions.

[0323] "Reservation" refers to the act of a user securing a restaurant in advance based on a suggested lunch plan.

[0324] "Rating data" refers to information about the evaluations that users have given to food service establishments and menus.

[0325] This invention is a system that generates and notifies / provides a lunch plan to the user based on the user's preferences, dietary restrictions, health data, budget, location information, and emotional state. This system is realized by utilizing the elements of a server, terminal, and user.

[0326] Account creation and initial setup

[0327] First, users access the system using a device (such as a smartphone or computer). After entering basic information (name, email address, password) on the account creation page, they enter their preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (where they will eat lunch). The device sends this information to the server, where it is stored in the server's database.

[0328] Gathering store information

[0329] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the location information set by the user. This is done using external APIs such as the Google Maps API and web scraping techniques. The collected data is stored in the server's database and updated in real time.

[0330] Utilizing the Emotion Engine

[0331] When a user requests to generate a lunch plan, the emotion engine uses the device's built-in camera and microphone to recognize the user's emotions. The emotion engine uses, for example, Google Cloud Vision's facial recognition API or Amazon Rekognition's facial analysis API to analyze facial expressions and tone of voice to determine the user's emotional state.

[0332] Creating a lunch plan

[0333] The server retrieves user profile information and collected store information from the database, taking into account the user's emotional data recognized by the emotion engine. It then generates a lunch plan using a generative AI (e.g., OpenAI GPT-4). The generative AI provides the optimal plan by considering factors such as nutritional balance, preferences, dietary restrictions, budget, evaluation information, and emotional state.

[0334] Lunch plan notification and special offer

[0335] The server notifies users of the generated lunch plans. Notifications are sent via email or in-app notifications. In addition, coupons and discounts are provided to certain establishments, which users can use to receive discounts. The server manages these coupons and discounts, and revenue is generated by collecting a monthly fee from the establishments.

[0336] Reservations and Reviews

[0337] Users can make reservations at restaurants within the app based on the provided lunch plan. After enjoying their lunch, users can rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. This rating data will be reflected when future lunch plans are generated.

[0338] As a concrete example, consider a case where a user creates an account by entering the following information using a device.

[0339] Name: Taro Tanaka

[0340] Email address: taro@example.com

[0341] Preferred ingredients and cuisine type: Japanese food

[0342] Dietary restrictions: Gluten-free

[0343] Health data: 70kg, target weight 65kg, height 175cm

[0344] Budget: 1000 yen

[0345] Location information: Around Tokyo Station

[0346] When Ms. Tanaka requests a lunch plan while feeling stressed, the emotional engine recognizes her stress level and suggests a plan that includes a relaxing cafe or a light meal. For example, a restaurant offering a "minced chicken and soft-boiled egg salad" (800 yen) is selected, and a 10% discount coupon is provided.

[0347] Examples of prompt statements are as follows:

[0348] Please create a program for a system that generates the optimal lunch plan based on the user's preferences, dietary restrictions, health data, budget, location, and emotional state.

[0349] This system not only allows users to enjoy the perfect lunch tailored to their emotional state on any given day, but also enables continuous improvement in satisfaction by incorporating evaluation data into future plan generation.

[0350] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0351] Step 1:

[0352] Users access the system using their devices and enter basic information (name, email address, password), preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (where they will have lunch) on the account creation page.

[0353] Input: All information entered by the user.

[0354] Output: Information transmission from the terminal to the server.

[0355] Step 2:

[0356] The terminal sends the information entered by the user to the server, where it is stored in the server's database.

[0357] Input: User input information.

[0358] Output: Sending data to the server and saving it to the database.

[0359] Specific operation: The terminal sends data to the server using a data transmission protocol (e.g., HTTPS), and the server stores the received information in a database.

[0360] Step 3:

[0361] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the location information set by the user. For this purpose, it utilizes the Google Maps API and web scraping techniques.

[0362] Input: User's location information.

[0363] Output: Data collection and database updates for surrounding facilities.

[0364] Specific operation: Use the Google Maps API to retrieve information about nearby restaurants based on location data, and save that information to the server's database.

[0365] Step 4:

[0366] When a user requests a lunch plan to be generated, the emotion engine uses the device's built-in camera and microphone to recognize the user's emotions. The emotion engine uses Google Cloud Vision's facial recognition API and Amazon Rekognition's facial analysis API to analyze facial expressions and tone of voice.

[0367] Input: User's facial image and voice data.

[0368] Output: User emotional state data.

[0369] Specific operation: The camera captures the user's facial expressions, and the emotion engine performs image analysis to generate emotion data.

[0370] Step 5:

[0371] The server uses the emotion data recognized by the emotion engine to retrieve user profile information and store information from the database, and generates a lunch plan using a generative AI (e.g., OpenAI GPT-4). The generative AI takes into account emotion data, nutritional balance, preferences, dietary restrictions, budget, and rating information.

[0372] Input: Sentimental data, user profile information, store information.

[0373] Output: The optimal lunch plan.

[0374] Specific operation: Retrieve necessary information from the database, input it into the generating AI, and generate a lunch plan.

[0375] Step 6:

[0376] The server notifies the user of the generated lunch plan. Notifications are sent via email or in-app notifications.

[0377] Input: Generated lunch plan.

[0378] Output: Notification to the user.

[0379] Specific operation: The server sends notifications to the user via the mail server or push notification server.

[0380] Step 7:

[0381] Users can make reservations at restaurants within the app based on the provided lunch plans.

[0382] Input: Lunch plan, user reservation request.

[0383] Output: Reservation information for the facility.

[0384] Specific operation: The app sends the reservation information to another service (reservation system API) to confirm the reservation.

[0385] Step 8:

[0386] After enjoying their lunch, users can leave a review of the facilities and menu within the app.

[0387] Input: User ratings.

[0388] Output: Evaluation data sent to the server.

[0389] Specific operation: User ratings are saved to a database and reflected in future lunch plan generation.

[0390] (Application Example 2)

[0391] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0392] While systems already exist that provide lunch plans based on user preferences, dietary restrictions, health data, budget, and location, these systems do not consider the user's emotional state. Therefore, they fail to provide meal plans that are optimal for the user's immediate emotional state, making it difficult to increase user satisfaction. There is a need for a system that provides more personalized lunch plans tailored to the user's emotional state on any given day.

[0393] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0394] In this invention, the server includes means for receiving user preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and rating information from nearby restaurants based on the input data and location information; means for generating a lunch plan based on the collected data and user input data; means for recognizing the user's emotions using a built-in camera and microphone and supplying the emotion data to the generation means; and means for notifying the user of the generated lunch plan. This makes it possible to provide the optimal lunch plan in real time according to the user's emotional state.

[0395] "Preferences" refer to the types of ingredients and cuisines that users enjoy.

[0396] "Dietary restrictions" refers to information about foods that users should avoid or foods they are allergic to.

[0397] "Health data" refers to health-related information such as the user's weight, height, and target weight.

[0398] "Budget" refers to the maximum amount a user can spend per meal.

[0399] "Location information" refers to information about the place where the user plans to have lunch.

[0400] A "menu" is a list of dishes offered by a restaurant.

[0401] "Price" refers to the cost of a menu item offered by a restaurant.

[0402] "Nutritional information" refers to information such as calories and nutrients included in the menu.

[0403] "Rating information" refers to user reviews and ratings of nearby restaurants and their menus.

[0404] The "generation method" refers to the means of creating a lunch plan based on user input data and collected data.

[0405] "Emotions" refer to the user's current psychological state.

[0406] "Emotional data" refers to information about a user's emotional state.

[0407] A "built-in camera" is a camera that is built into the user's device.

[0408] A "microphone" is an audio input device built into a user's device.

[0409] "Notification method" refers to the means of informing users of the generated lunch plan.

[0410] The system of this invention generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information. Furthermore, it analyzes the user's emotional state using an emotion engine and uses that data to further personalize the lunch plan.

[0411] Hardware and software to be used

[0412] Smartphones: Collect user input data and use the camera and microphone to acquire emotional data.

[0413] Server: Generates a lunch plan based on input and collected data and notifies the user.

[0414] Emotion Engine: Software for analyzing a user's emotional state. It uses facial expression analysis and voice analysis.

[0415] Generative AI Model: Generates the optimal lunch plan based on the user's profile and sentiment data.

[0416] External APIs and web scraping: Methods for collecting restaurant menus, prices, nutritional information, and ratings.

[0417] Data processing and data calculation

[0418] First, users enter basic information, preferences, dietary restrictions, health data, budget, and location information via their smartphones. This information is sent to a server and stored in a database.

[0419] When a user requests a lunch plan, an emotion engine uses the smartphone's camera and microphone to analyze the user's emotions. The analyzed emotion data is sent to a server and input into a generative AI model along with data about the restaurant.

[0420] The generative AI model generates the optimal lunch plan based on preferences, dietary restrictions, health data, budget, location, and emotional data. This lunch plan takes into account nutritional balance, budget, and current emotional state.

[0421] The generated lunch plan is notified to the user via smartphone. At the same time, coupons and discounts are also offered for specific restaurants.

[0422] Specific example

[0423] For example, suppose a user prefers Japanese food, sets a gluten-free diet as a restriction, and sets a budget of under 1000 yen per meal. When the user requests a lunch plan via smartphone, the emotion engine detects a state of stress. Based on this information, the generative AI model suggests a relaxing Japanese menu, such as a "chicken mince and soft-boiled egg salad" (800 yen). Furthermore, a 10% discount coupon is offered.

[0424] Example of a prompt

[0425] The user's preferences are Japanese food, dietary restrictions are gluten-free, and budget is 1000 yen per meal. Their location is Tokyo, and their emotional state is stressed. Based on this, please propose the optimal lunch plan.

[0426] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0427] Step 1:

[0428] Users enter basic information, preferences, dietary restrictions, health data, budget, and location information via their smartphones.

[0429] Input data: User's basic information, preferences, dietary restrictions, health data, budget, and location information.

[0430] Output data: The input data is sent to the server and stored in the database.

[0431] Step 2:

[0432] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the user's location.

[0433] Input data: User's location information

[0434] Data processing: Collect restaurant information using external APIs and web scraping.

[0435] Output data: The collected restaurant menus, prices, nutritional information, and ratings are stored in a database.

[0436] Step 3:

[0437] When a user requests a lunch plan via their smartphone, the emotion engine uses the built-in camera and microphone to analyze the user's emotions.

[0438] Input data: User's lunch plan request, user's facial image data, audio data

[0439] Data processing: The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[0440] Output data: The analyzed emotion data is sent to the server.

[0441] Step 4:

[0442] The server uses a generative AI model to generate lunch plans based on collected data and sentiment data.

[0443] Input data: User preferences, dietary restrictions, health data, budget, location information, sentiment data, information on nearby restaurants.

[0444] Data Calculation: A generative AI model analyzes the input data and generates the optimal lunch plan.

[0445] Output data: The generated lunch plan is stored on the server.

[0446] Step 5:

[0447] The server notifies the user of the generated lunch plan. The lunch plan is displayed on the smartphone, and coupons and discounts for specific restaurants are also offered.

[0448] Input data: Generated lunch plans, coupons and discount offers for specific stores.

[0449] Output data: Lunch plans, coupons, and discount offers are sent to the user's smartphone.

[0450] Step 6:

[0451] Users make restaurant reservations based on lunch plans. The reservation process is completed through a smartphone application.

[0452] Input data: Lunch plan selected by the user

[0453] Data processing: Generating reservation information, sending reservation requests to stores.

[0454] Output data: A reservation completion notification is displayed on the user's smartphone.

[0455] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0456] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0457] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0458] [Second Embodiment]

[0459] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0460] As shown in Figure 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.

[0461] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0462] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0463] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0464] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0465] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0466] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0467] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0468] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0469] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0470] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0471] A specific embodiment of the present invention will now be described. This system generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information. The user first creates an account using a device (such as a smartphone or personal computer) and completes the initial setup.

[0472] 1. Account creation and initial setup

[0473] The user accesses the system and proceeds to the account creation page. Here, the user enters the following information:

[0474] Basic information: Name, email address, password

[0475] Preferences: Preferred ingredients and cuisine types (e.g., Japanese food, Chinese food, vegetarian)

[0476] Dietary restrictions: Foods and dishes to avoid for allergies or health reasons.

[0477] Health data: weight, target weight, height, etc.

[0478] Budget: Maximum budget per meal

[0479] Location information: Places where you eat lunch, such as your workplace or school.

[0480] This information is sent from the terminal to the server and stored in the database.

[0481] 2. Gathering store information

[0482] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on location data. This includes using external APIs and obtaining data through web scraping. The collected data is stored in a database and updated in real time.

[0483] 3. Creating a lunch plan

[0484] The server retrieves user profile information and store information from the database and uses a generation AI to generate a lunch plan that takes the following factors into consideration:

[0485] Nutritional balance: Calculating necessary nutrients and calories

[0486] User preferences and dietary restrictions

[0487] Budget: The set upper limit per meal.

[0488] Reviews and ratings: Selected based on collected review information.

[0489] The generated lunch plan will be notified to the user via email or in-app notification.

[0490] 4. Offering benefits and monetization

[0491] The generated lunch plans include coupons and discounts for specific restaurants. Users can use these to receive discounts when paying at the restaurants. The server manages these coupons and discounts. Additionally, a monthly fee is charged to the restaurants to generate revenue.

[0492] 5. Booking and Reviews

[0493] Users can make restaurant reservations within the app based on the provided lunch plan. After enjoying their lunch, users can rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. When generating future lunch plans, this rating data is reflected, providing plans that better match the user's preferences.

[0494] Specific example

[0495] For example, suppose Ms. Tanaka creates an account and sets her preferences as Japanese food, dietary restrictions as gluten-free, and budget as under 1000 yen per meal. The server collects information from restaurants around Ms. Tanaka's workplace, including information on Japanese food and gluten-free menus. Based on the collected data, the generating AI suggests the following as a Monday lunch plan, taking into account nutritional balance, budget, and customer reviews:

[0496] Store A: Grilled Chicken Salad (600 yen)

[0497] Store B: Gluten-free salmon sushi (800 yen)

[0498] Ms. Tanaka will also be offered a 10% discount coupon for Restaurant A. Ms. Tanaka will choose this plan, make a reservation at Restaurant A, and enter a review after lunch. This review will be reflected in future lunch plans.

[0499] The above describes specific embodiments of the present invention. This system allows users to easily and efficiently enjoy a healthy lunch.

[0500] The following describes the processing flow.

[0501] Step 1:

[0502] The user accesses the account creation page and enters the required information. This includes basic information, preferences, dietary restrictions, health data, budget, and location information. After completing the input, the device sends the information to the server.

[0503] Step 2:

[0504] The server stores the received user information in a database and creates a custom profile for each user.

[0505] Step 3:

[0506] The server uses the user's location information to collect menu, price, nutritional information, and ratings from nearby restaurants. This data is collected through APIs and web scraping. The collected data is stored in the server's database.

[0507] Step 4:

[0508] The server retrieves user profile information and store information from the database. Based on this, a generating AI creates a lunch plan. The generating AI takes into account nutritional balance, user preferences and dietary restrictions, budget, and rating information.

[0509] Step 5:

[0510] The server generates a lunch plan and notifies the user. The notification is sent via email or in-app notification.

[0511] Step 6:

[0512] When a user reviews the lunch plan and wants to reserve their desired menu item from the options, they make the reservation within the app.

[0513] Step 7:

[0514] The server notifies the restaurant of the user's reservation information, and the reservation is confirmed.

[0515] Step 8:

[0516] Users enjoy the suggested lunch and enter their ratings for the restaurant and menu within the app.

[0517] Step 9:

[0518] The server receives user evaluation data and stores it in the database. This evaluation data will be used to generate the next lunch plan.

[0519] Step 10:

[0520] The server provides coupons and discount offers to specific restaurants, allowing users to receive discounts.

[0521] Step 11:

[0522] The server regularly updates the restaurant data it collects, ensuring that it always maintains the latest menu, prices, and ratings.

[0523] (Example 1)

[0524] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0525] In today's busy lifestyle, easily choosing healthy and nutritionally balanced meals is crucial. However, finding the perfect lunch that suits individual dietary restrictions, preferences, and budgets is not easy. In addition, the time and effort required to gather necessary information from a wide variety of restaurants is a significant burden. Furthermore, there is a lack of systems that incorporate each user's rating into future selections to provide lunch plans that better suit their preferences.

[0526] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0527] In this invention, the server includes means for prompting the user to input their preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and rating information from nearby restaurants based on the input data and location information; means for generating a lunch plan using a generative AI model based on the collected data and the user's input data; means for notifying the user of the generated lunch plan; means for creating prompt sentences to be used in generating the lunch plan; and means for reflecting the previous rating data when generating a possible next lunch plan. This makes it possible to easily and efficiently provide a healthy lunch that matches the user's preferences, restrictions, and budget.

[0528] "User preferences" refer to the types of ingredients and cuisines that users like, and represent their individual tastes in food choices.

[0529] "Dietary restrictions" refer to foods and dishes that users should avoid for allergies or health reasons.

[0530] "Health data" refers to information about a user's health, such as their weight, target weight, and height.

[0531] "Budget" refers to the maximum amount of money a user can spend per meal.

[0532] "Location information" refers to the geographical information of where the user plans to have lunch.

[0533] "Input data" refers to information that users provide to the system, such as preferences, dietary restrictions, health data, budget, and location information.

[0534] "Store information" refers to menu, price, nutritional information, and ratings information collected from nearby restaurants.

[0535] "Collected data" refers to restaurant menus, prices, nutritional information, and ratings collected based on location information.

[0536] A "generative AI model" refers to an artificial intelligence model that generates the optimal lunch plan based on user input data and store information.

[0537] A "prompt" refers to a pre-designed set of questions or commands intended for input into a generative AI model.

[0538] A "lunch plan" refers to meal suggestions generated considering the user's preferences, dietary restrictions, budget, and location.

[0539] "Evaluation data" refers to user ratings and feedback on stores and menus they have used.

[0540] A "coupon" refers to a discount voucher or special offer that can be used at a specific store.

[0541] "Notification method" refers to the means of informing users of the generated lunch plan, and includes email and in-app notifications.

[0542] A specific embodiment of the present invention will now be described. This system generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information. The details are described below.

[0543] Account creation and initial setup

[0544] Users access the system using a device (such as a smartphone or computer) and proceed to the account creation page. Here, users enter their name, email address, password, preferred foods and cuisine types, dietary restrictions, health data such as weight, target weight, and height, a budget limit per meal, and location information such as their workplace or school. This information is sent from the device to the server and stored in the database.

[0545] Gathering store information

[0546] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the user's location. This collection includes data acquisition using external APIs such as the Google Places API and Yelp API, as well as web scraping techniques (using tools such as BeautifulSoup and Scrapy). The collected data is stored in a database and updated in real time.

[0547] Creating a lunch plan

[0548] The server retrieves user profile information and store information from the database and creates prompts for a generative AI model (e.g., OpenAI's GPT-3). These prompts include user preferences, dietary restrictions, nutritional balance, budget, ratings, and customer reviews. Examples of prompt statements include:

[0549] The user prefers Japanese food, has a gluten-free diet, and a budget of under 1000 yen per meal. Please propose the optimal lunch plan.

[0550] The server uses this prompt to run a generation AI model and generate the optimal lunch plan. The generated lunch plan is then notified to the user via email or in-app notification.

[0551] Offering benefits and monetization

[0552] The generated lunch plans include coupons and discounts for specific restaurants. Users can use these to receive discounts when paying at the restaurants. The server manages these coupons and discounts and generates revenue by collecting a monthly fee from the restaurants.

[0553] Reservations and Reviews

[0554] Users can make restaurant reservations within the app based on the provided lunch plan. After enjoying their lunch, users can rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. When generating future lunch plans, this rating data is reflected, providing plans that better suit the user's preferences.

[0555] Specific example

[0556] For example, a user creates an account and sets their preferences as Japanese food, dietary restrictions as gluten-free, and budget as under 1000 yen per meal. The server collects information from restaurants around the user's workplace, including information on Japanese food and gluten-free menus. Based on the collected data, the generating AI proposes a lunch plan like the following, taking into account nutritional balance, budget, and customer reviews:

[0557] Store A: Grilled Chicken Salad (600 yen)

[0558] Store B: Gluten-free salmon sushi (800 yen)

[0559] Along with notifying users of this plan, they will be offered a 10% discount coupon for Restaurant A. Users will choose this plan, make a reservation at Restaurant A, enjoy their lunch, and then enter a review within the app. This review will be reflected in future lunch plans.

[0560] The above describes specific embodiments of the present invention. This system allows users to easily and efficiently enjoy a healthy lunch.

[0561] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0562] Step 1: Account creation and initial setup

[0563] Users access the system using their devices (smartphones or computers) and proceed to the account creation page. They fill out a form with their name, email address, password, preferred foods and cuisine types, dietary restrictions, health data such as weight, target weight, and height, a budget limit per meal, and location information. This entered data is sent from the device to the server and stored in a database.

[0564] Step 2: Gathering store information

[0565] The server uses the user's location information to collect menu, price, nutritional information, and rating information from nearby restaurants. Specifically, it uses external APIs such as the Google Places API and the Yelp API to obtain data. It also uses web scraping techniques to collect necessary information from restaurant websites. The collected restaurant information is stored in a database.

[0566] Input: Location information

[0567] Data processing: Data is obtained using external APIs or web scraping.

[0568] Output: Store Information Database

[0569] Step 3: Generate a lunch plan

[0570] The server retrieves user profile information and store information from the database and creates prompts to input into the generated AI model. These prompts include user preferences, dietary restrictions, nutritional balance, budget, ratings, and customer reviews. Examples of specific prompt statements:

[0571] The user prefers Japanese food, has a gluten-free diet, and a budget of under 1000 yen per meal. Please propose the optimal lunch plan.

[0572] The generation AI model generates the optimal lunch plan based on prompts. The generated lunch plan is saved by the server.

[0573] Input: User profile information, store information

[0574] Data processing: Execution of generative AI models

[0575] Output: Generated lunch plan

[0576] Step 4: Notification of lunch plan

[0577] The server notifies the user of the generated lunch plan. The notification is sent via email or in-app notification, making it easy for the user to check their lunch plan.

[0578] Input: Generated lunch plan

[0579] Data processing: Creating and sending notifications

[0580] Output: Notification to the user

[0581] Step 5: Offering perks and monetization

[0582] The server adds coupons and discounts for specific restaurants to the generated lunch plans. This includes generating and managing coupon codes. When users utilize these discounts, the system collects a monthly fee from the restaurants, generating revenue.

[0583] Input: Lunch plan, store information

[0584] Data processing: Coupon code generation

[0585] Output: Granting of discount benefits

[0586] Step 6: Make a reservation

[0587] Users make restaurant reservations within the app based on the provided lunch plans. The reservation function works in conjunction with the restaurant's reservation system, allowing users to complete reservations smoothly.

[0588] Input: Lunch plan

[0589] Data processing: Integration with the reservation system

[0590] Output: Restaurant reservation confirmation

[0591] Step 7: Enter your evaluation

[0592] After users enjoy their lunch, they can rate the restaurant and menu within the app. A rating form is provided, allowing users to enter rating scores and comments. This rating data is sent to a server and stored in a database.

[0593] Input: User rating data

[0594] Data processing: Evaluation data storage

[0595] Output: Saved evaluation data

[0596] Step 8: Reflect evaluation data

[0597] The server will incorporate the previous evaluation data when generating subsequent lunch plans. This will enable the provision of more accurate lunch plans that better match the user's preferences.

[0598] Input: Evaluation data

[0599] Data processing: Reflection in lunch plan generation

[0600] Output: Highly accurate lunch plan

[0601] The above describes the processing flow of this system's program.

[0602] (Application Example 1)

[0603] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0604] In modern society, it is a challenging task to easily and quickly propose lunch plans that take into account individual user preferences, health conditions, dietary restrictions, and budgets. Furthermore, there is a lack of systems that can reliably deliver satisfactory plans while simultaneously strengthening collaborations with local restaurants. In particular, generating optimal lunch plans for individual users requires sophisticated processing based on vast amounts of data, thus necessitating the provision of an efficient and effective system.

[0605] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0606] In this invention, the server includes means for prompting the user to input preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and rating information from nearby restaurants based on the input data and location information; means for generating a lunch plan using a generative AI model based on the collected data and the user's input data; and means for sending the generated lunch plan as a prompt message to the generative AI model and notifying the user. This makes it possible to quickly generate and notify the user of an optimal lunch plan that is suitable for each user's preferences and conditions.

[0607] A "user" refers to an individual who uses this system and is the entity that provides information such as preferences, dietary restrictions, and health data.

[0608] "Preferences" refer to the user's favorite ingredients and types of cuisine.

[0609] "Dietary restrictions" refer to foods or dishes that should be avoided due to allergies or health reasons.

[0610] "Health data" refers to the user's physical information, such as weight, target weight, and height.

[0611] "Budget" refers to the maximum amount of money a user plans to spend per meal.

[0612] "Location information" refers to the geographical information of the place where the user is eating.

[0613] "Menu information" refers to information that describes the dishes offered by a restaurant.

[0614] "Price information" refers to information that shows the selling price of each menu item at a restaurant.

[0615] "Nutritional information" refers to information that shows the nutritional components and calories contained in each menu item.

[0616] "Rating information" refers to information that shows the ratings and reviews that past users have given to a restaurant or its menu.

[0617] A "generative AI model" refers to an artificial intelligence model used to generate lunch plans based on user preferences, health data, budget, and location information.

[0618] A "prompt statement" refers to an input statement provided to a generative AI model.

[0619] "Means of notification" refers to the means of informing users of the generated lunch plan.

[0620] A "coupon" refers to a discount voucher that can be used at a specific restaurant.

[0621] A "discount offer" refers to a service offered by a restaurant that reduces the price of specific items.

[0622] "Methods for making reservations" refers to the means by which users can secure seats and menu items at restaurants in advance based on a lunch plan that has been generated.

[0623] The system of the present invention is designed to generate and provide customized lunch plans to users based on their individual preferences, health data, budget, and location information.

[0624] 1. Account creation and initial setup

[0625] Users first create an account using their own device (such as a smartphone or computer). The following information is required when creating an account:

[0626] Basic information: Name, email address, password

[0627] Tastes: Favorite ingredients and dishes

[0628] Dietary restrictions: Foods and dishes to avoid for allergies or health reasons.

[0629] Health data: weight, target weight, height, etc.

[0630] Budget: Maximum budget per meal

[0631] Location information: The place where we plan to have lunch

[0632] 2. Information Gathering

[0633] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on user input data and location information. This includes data acquisition through the use of external APIs and web scraping.

[0634] 3. Creating a lunch plan

[0635] The server uses a generative AI model to generate lunch plans based on the user's preferences, dietary restrictions, health data, budget, and information on nearby restaurants. Specific prompts are sent to the generative AI model, and its responses are collected as lunch plans.

[0636] Example of a prompt

[0637] "The user's preference is for Japanese food, their budget is 1000 yen, and their dietary restriction is gluten-free. Their current location is Tokyo. Here is some information on nearby restaurants..."

[0638] 4. Notification of lunch plan

[0639] The generated lunch plan will be notified to the user's device. Specifically, the user will receive an email or an in-app notification.

[0640] 5. Provision of benefits

[0641] The server uses collected data to provide coupons and discount offers to specific restaurants. These offers are included in lunch plans, allowing users to receive discounts when paying at the restaurant.

[0642] 6. Booking and Reviews

[0643] Users can make restaurant reservations within the app based on the generated lunch plan. After enjoying their lunch, users can also rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. When generating future lunch plans, this rating data is reflected, providing plans that better match the user's preferences.

[0644] The above describes a specific embodiment of the present invention. This system enables users to efficiently enjoy lunch that is perfectly suited to their individual preferences and circumstances.

[0645] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0646] Step 1:

[0647] Users create an account using their own device (such as a smartphone or computer). During account creation, users enter their name, email address, password, preferences, dietary restrictions, health data, budget, and location information. This information is sent from the device to the server and stored in the database.

[0648] Input: Name, email address, password, preferences, dietary restrictions, health data, budget, location information

[0649] Output: Saving user information to the database

[0650] Step 2:

[0651] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the user's location. This collection utilizes external APIs and web scraping. The collected information is stored in a database and updated in real time.

[0652] Input: User's location information

[0653] Output: Saving restaurant information to a database

[0654] Step 3:

[0655] The server generates lunch plans using a generative AI model based on the entered user information and collected restaurant information. During this process, the generative AI model receives prompt messages and retrieves the most suitable lunch plan as its response.

[0656] Input: User information, restaurant information

[0657] Output: Generated lunch plan

[0658] Specific operation: The system generates a prompt message such as, "User preference: Japanese food, budget: 1000 yen, dietary restrictions: gluten-free. Current location: Tokyo. Nearby restaurant information:..." and sends it to the AI ​​model. In response, the AI ​​model retrieves the optimal lunch plan (for example, "Grilled Chicken Salad at Restaurant A").

[0659] Step 4:

[0660] Once a lunch plan is generated, the server notifies the user. This notification is sent to the user's device via email or in-app notification.

[0661] Input: Generated lunch plan

[0662] Output: Notification to the user's device

[0663] Step 5:

[0664] The server suggests coupons and discount offers for specific restaurants based on the collected data. These offers are included in the generated lunch plan, which the user can then utilize.

[0665] Input: Collected data, generated lunch plan

[0666] Output: Coupons and discounts included in the lunch plan

[0667] Step 6:

[0668] Users can make restaurant reservations using their devices based on the provided lunch plans. Reservation information is sent to a server for coordination with the restaurants.

[0669] Input: Lunch plan, user reservation information

[0670] Output: Reservation notification to restaurant

[0671] Step 7:

[0672] After users enjoy their lunch, they enter their ratings of the restaurant and menu within the app. This rating data is sent to the server and stored in a database. This rating data is then used to generate future lunch plans.

[0673] Input: User rating information

[0674] Output: Saving evaluation data to a database

[0675] The above outlines the specific processing steps and flow of this system.

[0676] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0677] A specific embodiment of the present invention will now be described. This system generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information, and also recognizes the user's emotions to customize the lunch plan. The user first creates an account using a device (such as a smartphone or personal computer) and completes the initial setup.

[0678] 1. Account creation and initial setup

[0679] Users access the system and enter basic information (name, email address, password), preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (where they will have lunch) on the account creation page. After completing the input, the information is sent from the device to the server and stored in the database.

[0680] 2. Gathering store information

[0681] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on location data. Collection methods include using external APIs and web scraping. The collected data is stored in the server's database and updated in real time.

[0682] 3. Utilizing the Emotional Engine

[0683] When a user accesses the system from their device, the emotion engine uses the built-in camera and microphone to recognize the user's emotions. The emotion engine analyzes the user's facial expressions, tone of voice, and word choice to determine their current emotional state. For example, it can determine whether the user is stressed or relaxed.

[0684] 4. Creating a lunch plan

[0685] The server, taking into account the user's emotional data recognized by the emotion engine, retrieves user profile information and store information from the database. Based on this, the generative AI generates a lunch plan. The generative AI takes the following factors into consideration:

[0686] Nutritional balance: Calculating necessary nutrients and calories

[0687] User preferences and dietary restrictions

[0688] Budget: The set upper limit per meal.

[0689] Reviews and ratings: Collected review information

[0690] Emotional state: Selecting the most suitable menu or store based on the user's current emotional state.

[0691] For example, if the user is tired, a relaxing cafe or a light meal might be suggested. If the user is excited, a meal that will replenish their energy might be suggested.

[0692] 5. Notification of lunch plan and provision of benefits

[0693] The server notifies users of the generated lunch plans. Notifications are sent via email or in-app notifications. In addition, certain restaurants are given coupons and discounts, which users can use to receive discounts. The server manages these coupons and discounts, and generates revenue by collecting a monthly fee from the restaurants.

[0694] 6. Booking and Reviews

[0695] Users can make restaurant reservations within the app based on the provided lunch plan. After enjoying their lunch, users enter their ratings for the restaurant and menu within the app. This rating data is sent to the server and stored in a database. This rating data will be reflected when generating future lunch plans.

[0696] Specific example

[0697] For example, suppose Ms. Tanaka creates an account and sets her preferences as Japanese food, dietary restrictions as gluten-free, and budget as under 1000 yen per meal. One day, when Ms. Tanaka is feeling stressed, she requests a lunch plan. The server's emotion engine recognizes her stress level and suggests a menu from a relaxing restaurant. For example, it might select a restaurant that serves Japanese food and offers a gluten-free "chicken mince and soft-boiled egg salad" (800 yen) and offer a 10% discount coupon as a perk. Ms. Tanaka chooses this plan, makes a reservation at the restaurant, and enters a review after lunch.

[0698] The above describes a specific embodiment of the present invention. This system allows users to enjoy an optimal lunch tailored to their emotional state on any given day, and to maintain a healthy diet.

[0699] The following describes the processing flow.

[0700] Step 1:

[0701] The user accesses the account creation page. Here, they enter basic information (name, email address, password), preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (location of workplace or school).

[0702] Step 2:

[0703] The terminal sends the entered information to the server. The transmitted data is stored in a database by the server, and a custom profile is created for each user.

[0704] Step 3:

[0705] The server uses the user's location information to collect menu, price, nutritional information, and ratings from nearby restaurants. Data collection methods include using external APIs and web scraping. The collected data is stored in a database and updated in real time.

[0706] Step 4:

[0707] (When a user requests the generation of a lunch plan, the device uses devices such as the camera and microphone to identify the user's emotional state using an emotion engine. The emotion engine analyzes the user's emotions through facial expression analysis, voice tone analysis, and word choice. For example, it can identify whether the user is stressed or relaxed.)

[0708] Step 5:

[0709] The server retrieves user profile information and store information from the database, along with emotional state data from the emotion engine. Based on this data, the generating AI generates a lunch plan considering the following factors:

[0710] Nutritional balance: Calculating necessary nutrients and calories

[0711] User preferences and dietary restrictions

[0712] Budget: The set upper limit per meal.

[0713] Reviews and ratings: Collected review information

[0714] Emotional state: Users select menus and restaurants that match their current emotions.

[0715] For example, if a user is tired, the system might suggest a relaxing cafe or a light meal; if a user is excited, it might suggest a meal that will replenish their energy.

[0716] Step 6:

[0717] The server generates lunch plans and notifies users. Notifications are sent via email or in-app notifications. In addition, coupons and discounts are offered at certain restaurants, which users can use to receive discounts.

[0718] Step 7:

[0719] When a user makes a restaurant reservation based on a provided lunch plan, the reservation process is performed within the app.

[0720] Step 8:

[0721] The server notifies the restaurant of the user's reservation information and confirms the reservation.

[0722] Step 9:

[0723] Users enjoy the suggested lunch and enter their ratings for the restaurant and menu within the app.

[0724] Step 10:

[0725] The server receives user evaluation data and stores it in the database. This evaluation data will be used to generate the next lunch plan.

[0726] Step 11:

[0727] The server regularly updates its database of restaurants, maintaining the latest menus, prices, and ratings, ensuring that information is always up-to-date.

[0728] Through the specific processing steps described above, users are offered a lunch plan best suited to their emotional state on that day. For example, when Ms. Tanaka is feeling stressed, a restaurant offering a gluten-free Japanese-style "chicken mince and soft-boiled egg salad" is suggested, and she can also obtain a discount coupon. Ms. Tanaka chooses this plan, makes a reservation, enjoys her lunch, and then gives a high rating. As a result, the next lunch plan will be even more appropriate.

[0729] (Example 2)

[0730] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0731] Conventional lunch plan generation systems typically provide plans based on static data such as user preferences, dietary restrictions, and budget, and are particularly unable to provide lunch plans that respond to users' dynamic emotional states. Therefore, it was difficult to provide the optimal lunch plan according to the user's mood and emotions at any given time. Furthermore, there was no mechanism in place to incorporate evaluation data into subsequent plans, making continuous improvement to increase user satisfaction difficult.

[0732] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting the user's preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and evaluation information from nearby restaurants based on the input data and location information; means for analyzing emotional data using the terminal's camera and microphone to recognize the user's emotional state; generation AI means for generating a lunch plan based on the collected data, the user's input data, and the emotional data; means for notifying the user of the generated lunch plan; means for providing coupons and discount benefits to specific restaurants; and means for the user to make a reservation based on the lunch plan. This makes it possible to provide a lunch plan that is optimal not only for the user's preferences and dietary restrictions, but also for their emotional state at the time, and furthermore, by reflecting the evaluation data in the generation of plans in the future, user satisfaction can be continuously improved.

[0733] A "user" refers to someone who inputs basic information, preferences, and emotional states to generate a lunch plan using the system.

[0734] "Preferences" refers to information about the ingredients and types of cuisine that users prefer.

[0735] "Dietary restrictions" refers to information about foods that users should avoid or allergens they may have.

[0736] "Health data" refers to the user's physical information, such as weight, target weight, and height.

[0737] "Budget" refers to the maximum amount of money a user can spend per meal.

[0738] "Location information" refers to the geographical information of where the user is having lunch.

[0739] "Food service facilities" refer to establishments in the surrounding area that provide meals, such as restaurants and eateries.

[0740] "Menu" refers to the list of dishes offered at each food service establishment.

[0741] "Price" refers to the cost of each dish listed on the menu.

[0742] "Nutritional information" refers to health-related data such as the nutrients and calories contained in each menu item.

[0743] "Rating information" refers to user ratings and reviews of food service establishments and the menus they offer.

[0744] "Emotional state" refers to the psychological state obtained by analyzing the user's facial expressions, tone of voice, and other factors.

[0745] "Emotional data" refers to information about the user's emotions that has been analyzed by the emotion engine.

[0746] "Generative AI" refers to artificial intelligence technology that generates lunch plans based on data.

[0747] A "lunch plan" refers to meal suggestions provided based on collected data and user input.

[0748] A "coupon" refers to a discount voucher that can be used at a specific restaurant.

[0749] A "discount offer" refers to a discount service that a user can receive under specific conditions.

[0750] "Reservation" refers to the act of a user securing a restaurant in advance based on a suggested lunch plan.

[0751] "Rating data" refers to information about the evaluations that users have given to food service establishments and menus.

[0752] This invention is a system that generates and notifies / provides a lunch plan to the user based on the user's preferences, dietary restrictions, health data, budget, location information, and emotional state. This system is realized by utilizing the elements of a server, terminal, and user.

[0753] Account creation and initial setup

[0754] First, users access the system using a device (such as a smartphone or computer). After entering basic information (name, email address, password) on the account creation page, they enter their preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (where they will eat lunch). The device sends this information to the server, where it is stored in the server's database.

[0755] Gathering store information

[0756] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the location information set by the user. This is done using external APIs such as the Google Maps API and web scraping techniques. The collected data is stored in the server's database and updated in real time.

[0757] Utilizing the Emotion Engine

[0758] When a user requests to generate a lunch plan, the emotion engine uses the device's built-in camera and microphone to recognize the user's emotions. The emotion engine uses, for example, Google Cloud Vision's facial recognition API or Amazon Rekognition's facial analysis API to analyze facial expressions and tone of voice to determine the user's emotional state.

[0759] Creating a lunch plan

[0760] The server retrieves user profile information and collected store information from the database, taking into account the user's emotional data recognized by the emotion engine. It then generates a lunch plan using a generative AI (e.g., OpenAI GPT-4). The generative AI provides the optimal plan by considering factors such as nutritional balance, preferences, dietary restrictions, budget, evaluation information, and emotional state.

[0761] Lunch plan notification and special offer

[0762] The server notifies users of the generated lunch plans. Notifications are sent via email or in-app notifications. In addition, coupons and discounts are provided to certain establishments, which users can use to receive discounts. The server manages these coupons and discounts, and revenue is generated by collecting a monthly fee from the establishments.

[0763] Reservations and Reviews

[0764] Users can make reservations at restaurants within the app based on the provided lunch plan. After enjoying their lunch, users can rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. This rating data will be reflected when future lunch plans are generated.

[0765] As a concrete example, consider a case where a user creates an account by entering the following information using a device.

[0766] Name: Taro Tanaka

[0767] Email address: taro@example.com

[0768] Preferred ingredients and cuisine type: Japanese food

[0769] Dietary restrictions: Gluten-free

[0770] Health data: 70kg, target weight 65kg, height 175cm

[0771] Budget: 1000 yen

[0772] Location information: Around Tokyo Station

[0773] When Ms. Tanaka requests a lunch plan while feeling stressed, the emotional engine recognizes her stress level and suggests a plan that includes a relaxing cafe or a light meal. For example, a restaurant offering a "minced chicken and soft-boiled egg salad" (800 yen) is selected, and a 10% discount coupon is provided.

[0774] Examples of prompt statements are as follows:

[0775] Please create a program for a system that generates the optimal lunch plan based on the user's preferences, dietary restrictions, health data, budget, location, and emotional state.

[0776] This system not only allows users to enjoy the perfect lunch tailored to their emotional state on any given day, but also enables continuous improvement in satisfaction by incorporating evaluation data into future plan generation.

[0777] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0778] Step 1:

[0779] Users access the system using their devices and enter basic information (name, email address, password), preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (where they will have lunch) on the account creation page.

[0780] Input: All information entered by the user.

[0781] Output: Information transmission from the terminal to the server.

[0782] Step 2:

[0783] The terminal sends the information entered by the user to the server, where it is stored in the server's database.

[0784] Input: User input information.

[0785] Output: Sending data to the server and saving it to the database.

[0786] Specific operation: The terminal sends data to the server using a data transmission protocol (e.g., HTTPS), and the server stores the received information in a database.

[0787] Step 3:

[0788] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the location information set by the user. For this purpose, it utilizes the Google Maps API and web scraping techniques.

[0789] Input: User's location information.

[0790] Output: Data collection and database updates for surrounding facilities.

[0791] Specific operation: Use the Google Maps API to retrieve information about nearby restaurants based on location data, and save that information to the server's database.

[0792] Step 4:

[0793] When a user requests a lunch plan to be generated, the emotion engine uses the device's built-in camera and microphone to recognize the user's emotions. The emotion engine uses Google Cloud Vision's facial recognition API and Amazon Rekognition's facial analysis API to analyze facial expressions and tone of voice.

[0794] Input: User's facial image and voice data.

[0795] Output: User emotional state data.

[0796] Specific operation: The camera captures the user's facial expressions, and the emotion engine performs image analysis to generate emotion data.

[0797] Step 5:

[0798] The server uses the emotion data recognized by the emotion engine to retrieve user profile information and store information from the database, and generates a lunch plan using a generative AI (e.g., OpenAI GPT-4). The generative AI takes into account emotion data, nutritional balance, preferences, dietary restrictions, budget, and rating information.

[0799] Input: Sentimental data, user profile information, store information.

[0800] Output: The optimal lunch plan.

[0801] Specific operation: Retrieve necessary information from the database, input it into the generating AI, and generate a lunch plan.

[0802] Step 6:

[0803] The server notifies the user of the generated lunch plan. Notifications are sent via email or in-app notifications.

[0804] Input: Generated lunch plan.

[0805] Output: Notification to the user.

[0806] Specific operation: The server sends notifications to the user via the mail server or push notification server.

[0807] Step 7:

[0808] Users can make reservations at restaurants within the app based on the provided lunch plans.

[0809] Input: Lunch plan, user reservation request.

[0810] Output: Reservation information for the facility.

[0811] Specific operation: The app sends the reservation information to another service (reservation system API) to confirm the reservation.

[0812] Step 8:

[0813] After enjoying their lunch, users can leave a review of the facilities and menu within the app.

[0814] Input: User ratings.

[0815] Output: Evaluation data sent to the server.

[0816] Specific operation: User ratings are saved to a database and reflected in future lunch plan generation.

[0817] (Application Example 2)

[0818] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0819] While systems already exist that provide lunch plans based on user preferences, dietary restrictions, health data, budget, and location, these systems do not consider the user's emotional state. Therefore, they fail to provide meal plans that are optimal for the user's immediate emotional state, making it difficult to increase user satisfaction. There is a need for a system that provides more personalized lunch plans tailored to the user's emotional state on any given day.

[0820] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0821] In this invention, the server includes means for receiving user preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and rating information from nearby restaurants based on the input data and location information; means for generating a lunch plan based on the collected data and user input data; means for recognizing the user's emotions using a built-in camera and microphone and supplying the emotion data to the generation means; and means for notifying the user of the generated lunch plan. This makes it possible to provide the optimal lunch plan in real time according to the user's emotional state.

[0822] "Preferences" refer to the types of ingredients and cuisines that users enjoy.

[0823] "Dietary restrictions" refers to information about foods that users should avoid or foods they are allergic to.

[0824] "Health data" refers to health-related information such as the user's weight, height, and target weight.

[0825] "Budget" refers to the maximum amount a user can spend per meal.

[0826] "Location information" refers to information about the place where the user plans to have lunch.

[0827] A "menu" is a list of dishes offered by a restaurant.

[0828] "Price" refers to the cost of a menu item offered by a restaurant.

[0829] "Nutritional information" refers to information such as calories and nutrients included in the menu.

[0830] "Rating information" refers to user reviews and ratings of nearby restaurants and their menus.

[0831] The "generation method" refers to the means of creating a lunch plan based on user input data and collected data.

[0832] "Emotions" refer to the user's current psychological state.

[0833] "Emotional data" refers to information about a user's emotional state.

[0834] A "built-in camera" is a camera that is built into the user's device.

[0835] A "microphone" is an audio input device built into a user's device.

[0836] "Notification method" refers to the means of informing users of the generated lunch plan.

[0837] The system of this invention generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information. Furthermore, it analyzes the user's emotional state using an emotion engine and uses that data to further personalize the lunch plan.

[0838] Hardware and software to be used

[0839] Smartphones: Collect user input data and use the camera and microphone to acquire emotional data.

[0840] Server: Generates a lunch plan based on input and collected data and notifies the user.

[0841] Emotion Engine: Software for analyzing a user's emotional state. It uses facial expression analysis and voice analysis.

[0842] Generative AI Model: Generates the optimal lunch plan based on the user's profile and sentiment data.

[0843] External APIs and web scraping: Methods for collecting restaurant menus, prices, nutritional information, and ratings.

[0844] Data processing and data calculation

[0845] First, users enter basic information, preferences, dietary restrictions, health data, budget, and location information via their smartphones. This information is sent to a server and stored in a database.

[0846] When a user requests a lunch plan, an emotion engine uses the smartphone's camera and microphone to analyze the user's emotions. The analyzed emotion data is sent to a server and input into a generative AI model along with data about the restaurant.

[0847] The generative AI model generates the optimal lunch plan based on preferences, dietary restrictions, health data, budget, location, and emotional data. This lunch plan takes into account nutritional balance, budget, and current emotional state.

[0848] The generated lunch plan is notified to the user via smartphone. At the same time, coupons and discounts are also offered for specific restaurants.

[0849] Specific example

[0850] For example, suppose a user prefers Japanese food, sets a gluten-free diet as a restriction, and sets a budget of under 1000 yen per meal. When the user requests a lunch plan via smartphone, the emotion engine detects a state of stress. Based on this information, the generative AI model suggests a relaxing Japanese menu, such as a "chicken mince and soft-boiled egg salad" (800 yen). Furthermore, a 10% discount coupon is offered.

[0851] Example of a prompt

[0852] The user's preferences are Japanese food, dietary restrictions are gluten-free, and budget is 1000 yen per meal. Their location is Tokyo, and their emotional state is stressed. Based on this, please propose the optimal lunch plan.

[0853] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0854] Step 1:

[0855] Users enter basic information, preferences, dietary restrictions, health data, budget, and location information via their smartphones.

[0856] Input data: User's basic information, preferences, dietary restrictions, health data, budget, and location information.

[0857] Output data: The input data is sent to the server and stored in the database.

[0858] Step 2:

[0859] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the user's location.

[0860] Input data: User's location information

[0861] Data processing: Collect restaurant information using external APIs and web scraping.

[0862] Output data: The collected restaurant menus, prices, nutritional information, and ratings are stored in a database.

[0863] Step 3:

[0864] When a user requests a lunch plan via their smartphone, the emotion engine uses the built-in camera and microphone to analyze the user's emotions.

[0865] Input data: User's lunch plan request, user's facial image data, audio data

[0866] Data processing: The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[0867] Output data: The analyzed emotion data is sent to the server.

[0868] Step 4:

[0869] The server uses a generative AI model to generate lunch plans based on collected data and sentiment data.

[0870] Input data: User preferences, dietary restrictions, health data, budget, location information, sentiment data, information on nearby restaurants.

[0871] Data Calculation: A generative AI model analyzes the input data and generates the optimal lunch plan.

[0872] Output data: The generated lunch plan is stored on the server.

[0873] Step 5:

[0874] The server notifies the user of the generated lunch plan. The lunch plan is displayed on the smartphone, and coupons and discounts for specific restaurants are also offered.

[0875] Input data: Generated lunch plans, coupons and discount offers for specific stores.

[0876] Output data: Lunch plans, coupons, and discount offers are sent to the user's smartphone.

[0877] Step 6:

[0878] Users make restaurant reservations based on lunch plans. The reservation process is completed through a smartphone application.

[0879] Input data: Lunch plan selected by the user

[0880] Data processing: Generating reservation information, sending reservation requests to stores.

[0881] Output data: A reservation completion notification is displayed on the user's smartphone.

[0882] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0883] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0884] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0885] [Third Embodiment]

[0886] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0887] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0888] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0889] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0890] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0891] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0892] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0893] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0894] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0895] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0896] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0897] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0898] A specific embodiment of the present invention will now be described. This system generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information. The user first creates an account using a device (such as a smartphone or personal computer) and completes the initial setup.

[0899] 1. Account creation and initial setup

[0900] The user accesses the system and proceeds to the account creation page. Here, the user enters the following information:

[0901] Basic information: Name, email address, password

[0902] Preferences: Preferred ingredients and cuisine types (e.g., Japanese food, Chinese food, vegetarian)

[0903] Dietary restrictions: Foods and dishes to avoid for allergies or health reasons.

[0904] Health data: weight, target weight, height, etc.

[0905] Budget: Maximum budget per meal

[0906] Location information: Places where you eat lunch, such as your workplace or school.

[0907] This information is sent from the terminal to the server and stored in the database.

[0908] 2. Gathering store information

[0909] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on location data. This includes using external APIs and obtaining data through web scraping. The collected data is stored in a database and updated in real time.

[0910] 3. Creating a lunch plan

[0911] The server retrieves user profile information and store information from the database and uses a generation AI to generate a lunch plan that takes the following factors into consideration:

[0912] Nutritional balance: Calculating necessary nutrients and calories

[0913] User preferences and dietary restrictions

[0914] Budget: The set upper limit per meal.

[0915] Reviews and ratings: Selected based on collected review information.

[0916] The generated lunch plan will be notified to the user via email or in-app notification.

[0917] 4. Offering benefits and monetization

[0918] The generated lunch plans include coupons and discounts for specific restaurants. Users can use these to receive discounts when paying at the restaurants. The server manages these coupons and discounts. Additionally, a monthly fee is charged to the restaurants to generate revenue.

[0919] 5. Booking and Reviews

[0920] Users can make restaurant reservations within the app based on the provided lunch plan. After enjoying their lunch, users can rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. When generating future lunch plans, this rating data is reflected, providing plans that better match the user's preferences.

[0921] Specific example

[0922] For example, suppose Ms. Tanaka creates an account and sets her preferences as Japanese food, dietary restrictions as gluten-free, and budget as under 1000 yen per meal. The server collects information from restaurants around Ms. Tanaka's workplace, including information on Japanese food and gluten-free menus. Based on the collected data, the generating AI suggests the following as a Monday lunch plan, taking into account nutritional balance, budget, and customer reviews:

[0923] Store A: Grilled Chicken Salad (600 yen)

[0924] Store B: Gluten-free salmon sushi (800 yen)

[0925] Ms. Tanaka will also be offered a 10% discount coupon for Restaurant A. Ms. Tanaka will choose this plan, make a reservation at Restaurant A, and enter a review after lunch. This review will be reflected in future lunch plans.

[0926] The above describes specific embodiments of the present invention. This system allows users to easily and efficiently enjoy a healthy lunch.

[0927] The following describes the processing flow.

[0928] Step 1:

[0929] The user accesses the account creation page and enters the required information. This includes basic information, preferences, dietary restrictions, health data, budget, and location information. After completing the input, the device sends the information to the server.

[0930] Step 2:

[0931] The server stores the received user information in a database and creates a custom profile for each user.

[0932] Step 3:

[0933] The server uses the user's location information to collect menu, price, nutritional information, and ratings from nearby restaurants. This data is collected through APIs and web scraping. The collected data is stored in the server's database.

[0934] Step 4:

[0935] The server retrieves user profile information and store information from the database. Based on this, a generating AI creates a lunch plan. The generating AI takes into account nutritional balance, user preferences and dietary restrictions, budget, and rating information.

[0936] Step 5:

[0937] The server generates a lunch plan and notifies the user. The notification is sent via email or in-app notification.

[0938] Step 6:

[0939] When a user reviews the lunch plan and wants to reserve their desired menu item from the options, they make the reservation within the app.

[0940] Step 7:

[0941] The server notifies the restaurant of the user's reservation information, and the reservation is confirmed.

[0942] Step 8:

[0943] Users enjoy the suggested lunch and enter their ratings for the restaurant and menu within the app.

[0944] Step 9:

[0945] The server receives user evaluation data and stores it in the database. This evaluation data will be used to generate the next lunch plan.

[0946] Step 10:

[0947] The server provides coupons and discount offers to specific restaurants, allowing users to receive discounts.

[0948] Step 11:

[0949] The server regularly updates the restaurant data it collects, ensuring that it always maintains the latest menu, prices, and ratings.

[0950] (Example 1)

[0951] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0952] In today's busy lifestyle, easily choosing healthy and nutritionally balanced meals is crucial. However, finding the perfect lunch that suits individual dietary restrictions, preferences, and budgets is not easy. In addition, the time and effort required to gather necessary information from a wide variety of restaurants is a significant burden. Furthermore, there is a lack of systems that incorporate each user's rating into future selections to provide lunch plans that better suit their preferences.

[0953] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0954] In this invention, the server includes means for prompting the user to input their preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and rating information from nearby restaurants based on the input data and location information; means for generating a lunch plan using a generative AI model based on the collected data and the user's input data; means for notifying the user of the generated lunch plan; means for creating prompt sentences to be used in generating the lunch plan; and means for reflecting the previous rating data when generating a possible next lunch plan. This makes it possible to easily and efficiently provide a healthy lunch that matches the user's preferences, restrictions, and budget.

[0955] "User preferences" refer to the types of ingredients and cuisines that users like, and represent their individual tastes in food choices.

[0956] "Dietary restrictions" refer to foods and dishes that users should avoid for allergies or health reasons.

[0957] "Health data" refers to information about a user's health, such as their weight, target weight, and height.

[0958] "Budget" refers to the maximum amount of money a user can spend per meal.

[0959] "Location information" refers to the geographical information of where the user plans to have lunch.

[0960] "Input data" refers to information that users provide to the system, such as preferences, dietary restrictions, health data, budget, and location information.

[0961] "Store information" refers to menu, price, nutritional information, and ratings information collected from nearby restaurants.

[0962] "Collected data" refers to restaurant menus, prices, nutritional information, and ratings collected based on location information.

[0963] A "generative AI model" refers to an artificial intelligence model that generates the optimal lunch plan based on user input data and store information.

[0964] A "prompt" refers to a pre-designed set of questions or commands intended for input into a generative AI model.

[0965] A "lunch plan" refers to meal suggestions generated considering the user's preferences, dietary restrictions, budget, and location.

[0966] "Evaluation data" refers to user ratings and feedback on stores and menus they have used.

[0967] A "coupon" refers to a discount voucher or special offer that can be used at a specific store.

[0968] "Notification method" refers to the means of informing users of the generated lunch plan, and includes email and in-app notifications.

[0969] A specific embodiment of the present invention will now be described. This system generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information. The details are described below.

[0970] Account creation and initial setup

[0971] Users access the system using a device (such as a smartphone or computer) and proceed to the account creation page. Here, users enter their name, email address, password, preferred foods and cuisine types, dietary restrictions, health data such as weight, target weight, and height, a budget limit per meal, and location information such as their workplace or school. This information is sent from the device to the server and stored in the database.

[0972] Gathering store information

[0973] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the user's location. This collection includes data acquisition using external APIs such as the Google Places API and Yelp API, as well as web scraping techniques (using tools such as BeautifulSoup and Scrapy). The collected data is stored in a database and updated in real time.

[0974] Creating a lunch plan

[0975] The server retrieves user profile information and store information from the database and creates prompts for a generative AI model (e.g., OpenAI's GPT-3). These prompts include user preferences, dietary restrictions, nutritional balance, budget, ratings, and customer reviews. Examples of prompt statements include:

[0976] The user prefers Japanese food, has a gluten-free diet, and a budget of under 1000 yen per meal. Please propose the optimal lunch plan.

[0977] The server uses this prompt to run a generation AI model and generate the optimal lunch plan. The generated lunch plan is then notified to the user via email or in-app notification.

[0978] Offering benefits and monetization

[0979] The generated lunch plans include coupons and discounts for specific restaurants. Users can use these to receive discounts when paying at the restaurants. The server manages these coupons and discounts and generates revenue by collecting a monthly fee from the restaurants.

[0980] Reservations and Reviews

[0981] Users can make restaurant reservations within the app based on the provided lunch plan. After enjoying their lunch, users can rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. When generating future lunch plans, this rating data is reflected, providing plans that better suit the user's preferences.

[0982] Specific example

[0983] For example, a user creates an account and sets their preferences as Japanese food, dietary restrictions as gluten-free, and budget as under 1000 yen per meal. The server collects information from restaurants around the user's workplace, including information on Japanese food and gluten-free menus. Based on the collected data, the generating AI proposes a lunch plan like the following, taking into account nutritional balance, budget, and customer reviews:

[0984] Store A: Grilled Chicken Salad (600 yen)

[0985] Store B: Gluten-free salmon sushi (800 yen)

[0986] Along with notifying users of this plan, they will be offered a 10% discount coupon for Restaurant A. Users will choose this plan, make a reservation at Restaurant A, enjoy their lunch, and then enter a review within the app. This review will be reflected in future lunch plans.

[0987] The above describes specific embodiments of the present invention. This system allows users to easily and efficiently enjoy a healthy lunch.

[0988] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0989] Step 1: Account creation and initial setup

[0990] Users access the system using their devices (smartphones or computers) and proceed to the account creation page. They fill out a form with their name, email address, password, preferred foods and cuisine types, dietary restrictions, health data such as weight, target weight, and height, a budget limit per meal, and location information. This entered data is sent from the device to the server and stored in a database.

[0991] Step 2: Gathering store information

[0992] The server uses the user's location information to collect menu, price, nutritional information, and rating information from nearby restaurants. Specifically, it uses external APIs such as the Google Places API and the Yelp API to obtain data. It also uses web scraping techniques to collect necessary information from restaurant websites. The collected restaurant information is stored in a database.

[0993] Input: Location information

[0994] Data processing: Data is obtained using external APIs or web scraping.

[0995] Output: Store Information Database

[0996] Step 3: Generate a lunch plan

[0997] The server retrieves user profile information and store information from the database and creates prompts to input into the generated AI model. These prompts include user preferences, dietary restrictions, nutritional balance, budget, ratings, and customer reviews. Examples of specific prompt statements:

[0998] The user prefers Japanese food, has a gluten-free diet, and a budget of under 1000 yen per meal. Please propose the optimal lunch plan.

[0999] The generation AI model generates the optimal lunch plan based on prompts. The generated lunch plan is saved by the server.

[1000] Input: User profile information, store information

[1001] Data processing: Execution of generative AI models

[1002] Output: Generated lunch plan

[1003] Step 4: Notification of lunch plan

[1004] The server notifies the user of the generated lunch plan. The notification is sent via email or in-app notification, making it easy for the user to check their lunch plan.

[1005] Input: Generated lunch plan

[1006] Data processing: Creating and sending notifications

[1007] Output: Notification to the user

[1008] Step 5: Offering perks and monetization

[1009] The server adds coupons and discounts for specific restaurants to the generated lunch plans. This includes generating and managing coupon codes. When users utilize these discounts, the system collects a monthly fee from the restaurants, generating revenue.

[1010] Input: Lunch plan, store information

[1011] Data processing: Coupon code generation

[1012] Output: Granting of discount benefits

[1013] Step 6: Make a reservation

[1014] Users make restaurant reservations within the app based on the provided lunch plans. The reservation function works in conjunction with the restaurant's reservation system, allowing users to complete reservations smoothly.

[1015] Input: Lunch plan

[1016] Data processing: Integration with the reservation system

[1017] Output: Restaurant reservation confirmation

[1018] Step 7: Enter your evaluation

[1019] After users enjoy their lunch, they can rate the restaurant and menu within the app. A rating form is provided, allowing users to enter rating scores and comments. This rating data is sent to a server and stored in a database.

[1020] Input: User rating data

[1021] Data processing: Evaluation data storage

[1022] Output: Saved evaluation data

[1023] Step 8: Reflect evaluation data

[1024] The server will incorporate the previous evaluation data when generating subsequent lunch plans. This will enable the provision of more accurate lunch plans that better match the user's preferences.

[1025] Input: Evaluation data

[1026] Data processing: Reflection in lunch plan generation

[1027] Output: Highly accurate lunch plan

[1028] The above describes the processing flow of this system's program.

[1029] (Application Example 1)

[1030] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1031] In modern society, it is a challenging task to easily and quickly propose lunch plans that take into account individual user preferences, health conditions, dietary restrictions, and budgets. Furthermore, there is a lack of systems that can reliably deliver satisfactory plans while simultaneously strengthening collaborations with local restaurants. In particular, generating optimal lunch plans for individual users requires sophisticated processing based on vast amounts of data, thus necessitating the provision of an efficient and effective system.

[1032] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1033] In this invention, the server includes means for prompting the user to input preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and rating information from nearby restaurants based on the input data and location information; means for generating a lunch plan using a generative AI model based on the collected data and the user's input data; and means for sending the generated lunch plan as a prompt message to the generative AI model and notifying the user. This makes it possible to quickly generate and notify the user of an optimal lunch plan that is suitable for each user's preferences and conditions.

[1034] A "user" refers to an individual who uses this system and is the entity that provides information such as preferences, dietary restrictions, and health data.

[1035] "Preferences" refer to the user's favorite ingredients and types of cuisine.

[1036] "Dietary restrictions" refer to foods or dishes that should be avoided due to allergies or health reasons.

[1037] "Health data" refers to the user's physical information, such as weight, target weight, and height.

[1038] "Budget" refers to the maximum amount of money a user plans to spend per meal.

[1039] "Location information" refers to the geographical information of the place where the user is eating.

[1040] "Menu information" refers to information that describes the dishes offered by a restaurant.

[1041] "Price information" refers to information that shows the selling price of each menu item at a restaurant.

[1042] "Nutritional information" refers to information that shows the nutritional components and calories contained in each menu item.

[1043] "Rating information" refers to information that shows the ratings and reviews that past users have given to a restaurant or its menu.

[1044] A "generative AI model" refers to an artificial intelligence model used to generate lunch plans based on user preferences, health data, budget, and location information.

[1045] A "prompt statement" refers to an input statement provided to a generative AI model.

[1046] "Means of notification" refers to the means of informing users of the generated lunch plan.

[1047] A "coupon" refers to a discount voucher that can be used at a specific restaurant.

[1048] A "discount offer" refers to a service offered by a restaurant that reduces the price of specific items.

[1049] "Methods for making reservations" refers to the means by which users can secure seats and menu items at restaurants in advance based on a lunch plan that has been generated.

[1050] The system of the present invention is designed to generate and provide customized lunch plans to users based on their individual preferences, health data, budget, and location information.

[1051] 1. Account creation and initial setup

[1052] Users first create an account using their own device (such as a smartphone or computer). The following information is required when creating an account:

[1053] Basic information: Name, email address, password

[1054] Tastes: Favorite ingredients and dishes

[1055] Dietary restrictions: Foods and dishes to avoid for allergies or health reasons.

[1056] Health data: weight, target weight, height, etc.

[1057] Budget: Maximum budget per meal

[1058] Location information: The place where we plan to have lunch

[1059] 2. Information Gathering

[1060] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on user input data and location information. This includes data acquisition through the use of external APIs and web scraping.

[1061] 3. Creating a lunch plan

[1062] The server uses a generative AI model to generate lunch plans based on the user's preferences, dietary restrictions, health data, budget, and information on nearby restaurants. Specific prompts are sent to the generative AI model, and its responses are collected as lunch plans.

[1063] Example of a prompt

[1064] "The user's preference is for Japanese food, their budget is 1000 yen, and their dietary restriction is gluten-free. Their current location is Tokyo. Here is some information on nearby restaurants..."

[1065] 4. Notification of lunch plan

[1066] The generated lunch plan will be notified to the user's device. Specifically, the user will receive an email or an in-app notification.

[1067] 5. Provision of benefits

[1068] The server uses collected data to provide coupons and discount offers to specific restaurants. These offers are included in lunch plans, allowing users to receive discounts when paying at the restaurant.

[1069] 6. Booking and Reviews

[1070] Users can make restaurant reservations within the app based on the generated lunch plan. After enjoying their lunch, users can also rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. When generating future lunch plans, this rating data is reflected, providing plans that better match the user's preferences.

[1071] The above describes a specific embodiment of the present invention. This system enables users to efficiently enjoy lunch that is perfectly suited to their individual preferences and circumstances.

[1072] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1073] Step 1:

[1074] Users create an account using their own device (such as a smartphone or computer). During account creation, users enter their name, email address, password, preferences, dietary restrictions, health data, budget, and location information. This information is sent from the device to the server and stored in the database.

[1075] Input: Name, email address, password, preferences, dietary restrictions, health data, budget, location information

[1076] Output: Saving user information to the database

[1077] Step 2:

[1078] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the user's location. This collection utilizes external APIs and web scraping. The collected information is stored in a database and updated in real time.

[1079] Input: User's location information

[1080] Output: Saving restaurant information to a database

[1081] Step 3:

[1082] The server generates lunch plans using a generative AI model based on the entered user information and collected restaurant information. During this process, the generative AI model receives prompt messages and retrieves the most suitable lunch plan as its response.

[1083] Input: User information, restaurant information

[1084] Output: Generated lunch plan

[1085] Specific operation: The system generates a prompt message such as, "User preference: Japanese food, budget: 1000 yen, dietary restrictions: gluten-free. Current location: Tokyo. Nearby restaurant information:..." and sends it to the AI ​​model. In response, the AI ​​model retrieves the optimal lunch plan (for example, "Grilled Chicken Salad at Restaurant A").

[1086] Step 4:

[1087] Once a lunch plan is generated, the server notifies the user. This notification is sent to the user's device via email or in-app notification.

[1088] Input: Generated lunch plan

[1089] Output: Notification to the user's device

[1090] Step 5:

[1091] The server suggests coupons and discount offers for specific restaurants based on the collected data. These offers are included in the generated lunch plan, which the user can then utilize.

[1092] Input: Collected data, generated lunch plan

[1093] Output: Coupons and discounts included in the lunch plan

[1094] Step 6:

[1095] Users can make restaurant reservations using their devices based on the provided lunch plans. Reservation information is sent to a server for coordination with the restaurants.

[1096] Input: Lunch plan, user reservation information

[1097] Output: Reservation notification to restaurant

[1098] Step 7:

[1099] After users enjoy their lunch, they enter their ratings of the restaurant and menu within the app. This rating data is sent to the server and stored in a database. This rating data is then used to generate future lunch plans.

[1100] Input: User rating information

[1101] Output: Saving evaluation data to a database

[1102] The above outlines the specific processing steps and flow of this system.

[1103] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1104] A specific embodiment of the present invention will now be described. This system generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information, and also recognizes the user's emotions to customize the lunch plan. The user first creates an account using a device (such as a smartphone or personal computer) and completes the initial setup.

[1105] 1. Account creation and initial setup

[1106] Users access the system and enter basic information (name, email address, password), preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (where they will have lunch) on the account creation page. After completing the input, the information is sent from the device to the server and stored in the database.

[1107] 2. Gathering store information

[1108] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on location data. Collection methods include using external APIs and web scraping. The collected data is stored in the server's database and updated in real time.

[1109] 3. Utilizing the Emotional Engine

[1110] When a user accesses the system from their device, the emotion engine uses the built-in camera and microphone to recognize the user's emotions. The emotion engine analyzes the user's facial expressions, tone of voice, and word choice to determine their current emotional state. For example, it can determine whether the user is stressed or relaxed.

[1111] 4. Creating a lunch plan

[1112] The server, taking into account the user's emotional data recognized by the emotion engine, retrieves user profile information and store information from the database. Based on this, the generative AI generates a lunch plan. The generative AI takes the following factors into consideration:

[1113] Nutritional balance: Calculating necessary nutrients and calories

[1114] User preferences and dietary restrictions

[1115] Budget: The set upper limit per meal.

[1116] Reviews and ratings: Collected review information

[1117] Emotional state: Selecting the most suitable menu or store based on the user's current emotional state.

[1118] For example, if the user is tired, a relaxing cafe or a light meal might be suggested. If the user is excited, a meal that will replenish their energy might be suggested.

[1119] 5. Notification of lunch plan and provision of benefits

[1120] The server notifies users of the generated lunch plans. Notifications are sent via email or in-app notifications. In addition, certain restaurants are given coupons and discounts, which users can use to receive discounts. The server manages these coupons and discounts, and generates revenue by collecting a monthly fee from the restaurants.

[1121] 6. Booking and Reviews

[1122] Users can make restaurant reservations within the app based on the provided lunch plan. After enjoying their lunch, users enter their ratings for the restaurant and menu within the app. This rating data is sent to the server and stored in a database. This rating data will be reflected when generating future lunch plans.

[1123] Specific example

[1124] For example, suppose Ms. Tanaka creates an account and sets her preferences as Japanese food, dietary restrictions as gluten-free, and budget as under 1000 yen per meal. One day, when Ms. Tanaka is feeling stressed, she requests a lunch plan. The server's emotion engine recognizes her stress level and suggests a menu from a relaxing restaurant. For example, it might select a restaurant that serves Japanese food and offers a gluten-free "chicken mince and soft-boiled egg salad" (800 yen) and offer a 10% discount coupon as a perk. Ms. Tanaka chooses this plan, makes a reservation at the restaurant, and enters a review after lunch.

[1125] The above describes a specific embodiment of the present invention. This system allows users to enjoy an optimal lunch tailored to their emotional state on any given day, and to maintain a healthy diet.

[1126] The following describes the processing flow.

[1127] Step 1:

[1128] The user accesses the account creation page. Here, they enter basic information (name, email address, password), preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (location of workplace or school).

[1129] Step 2:

[1130] The terminal sends the entered information to the server. The transmitted data is stored in a database by the server, and a custom profile is created for each user.

[1131] Step 3:

[1132] The server uses the user's location information to collect menu, price, nutritional information, and ratings from nearby restaurants. Data collection methods include using external APIs and web scraping. The collected data is stored in a database and updated in real time.

[1133] Step 4:

[1134] (When a user requests the generation of a lunch plan, the device uses devices such as the camera and microphone to identify the user's emotional state using an emotion engine. The emotion engine analyzes the user's emotions through facial expression analysis, voice tone analysis, and word choice. For example, it can identify whether the user is stressed or relaxed.)

[1135] Step 5:

[1136] The server retrieves user profile information and store information from the database, along with emotional state data from the emotion engine. Based on this data, the generating AI generates a lunch plan considering the following factors:

[1137] Nutritional balance: Calculating necessary nutrients and calories

[1138] User preferences and dietary restrictions

[1139] Budget: The set upper limit per meal.

[1140] Reviews and ratings: Collected review information

[1141] Emotional state: Users select menus and restaurants that match their current emotions.

[1142] For example, if a user is tired, the system might suggest a relaxing cafe or a light meal; if a user is excited, it might suggest a meal that will replenish their energy.

[1143] Step 6:

[1144] The server generates lunch plans and notifies users. Notifications are sent via email or in-app notifications. In addition, coupons and discounts are offered at certain restaurants, which users can use to receive discounts.

[1145] Step 7:

[1146] When a user makes a restaurant reservation based on a provided lunch plan, the reservation process is performed within the app.

[1147] Step 8:

[1148] The server notifies the restaurant of the user's reservation information and confirms the reservation.

[1149] Step 9:

[1150] Users enjoy the suggested lunch and enter their ratings for the restaurant and menu within the app.

[1151] Step 10:

[1152] The server receives user evaluation data and stores it in the database. This evaluation data will be used to generate the next lunch plan.

[1153] Step 11:

[1154] The server regularly updates its database of restaurants, maintaining the latest menus, prices, and ratings, ensuring that information is always up-to-date.

[1155] Through the specific processing steps described above, users are offered a lunch plan best suited to their emotional state on that day. For example, when Ms. Tanaka is feeling stressed, a restaurant offering a gluten-free Japanese-style "chicken mince and soft-boiled egg salad" is suggested, and she can also obtain a discount coupon. Ms. Tanaka chooses this plan, makes a reservation, enjoys her lunch, and then gives a high rating. As a result, the next lunch plan will be even more appropriate.

[1156] (Example 2)

[1157] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1158] Conventional lunch plan generation systems typically provide plans based on static data such as user preferences, dietary restrictions, and budget, and are particularly unable to provide lunch plans that respond to users' dynamic emotional states. Therefore, it was difficult to provide the optimal lunch plan according to the user's mood and emotions at any given time. Furthermore, there was no mechanism in place to incorporate evaluation data into subsequent plans, making continuous improvement to increase user satisfaction difficult.

[1159] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting the user's preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and evaluation information from nearby restaurants based on the input data and location information; means for analyzing emotional data using the terminal's camera and microphone to recognize the user's emotional state; generation AI means for generating a lunch plan based on the collected data, the user's input data, and the emotional data; means for notifying the user of the generated lunch plan; means for providing coupons and discount benefits to specific restaurants; and means for the user to make a reservation based on the lunch plan. This makes it possible to provide a lunch plan that is optimal not only for the user's preferences and dietary restrictions, but also for their emotional state at the time, and furthermore, by reflecting the evaluation data in the generation of plans in the future, user satisfaction can be continuously improved.

[1160] A "user" refers to someone who inputs basic information, preferences, and emotional states to generate a lunch plan using the system.

[1161] "Preferences" refers to information about the ingredients and types of cuisine that users prefer.

[1162] "Dietary restrictions" refers to information about foods that users should avoid or allergens they may have.

[1163] "Health data" refers to the user's physical information, such as weight, target weight, and height.

[1164] "Budget" refers to the maximum amount of money a user can spend per meal.

[1165] "Location information" refers to the geographical information of where the user is having lunch.

[1166] "Food service facilities" refer to establishments in the surrounding area that provide meals, such as restaurants and eateries.

[1167] "Menu" refers to the list of dishes offered at each food service establishment.

[1168] "Price" refers to the cost of each dish listed on the menu.

[1169] "Nutritional information" refers to health-related data such as the nutrients and calories contained in each menu item.

[1170] "Rating information" refers to user ratings and reviews of food service establishments and the menus they offer.

[1171] "Emotional state" refers to the psychological state obtained by analyzing the user's facial expressions, tone of voice, and other factors.

[1172] "Emotional data" refers to information about the user's emotions that has been analyzed by the emotion engine.

[1173] "Generative AI" refers to artificial intelligence technology that generates lunch plans based on data.

[1174] A "lunch plan" refers to meal suggestions provided based on collected data and user input.

[1175] A "coupon" refers to a discount voucher that can be used at a specific restaurant.

[1176] A "discount offer" refers to a discount service that a user can receive under specific conditions.

[1177] "Reservation" refers to the act of a user securing a restaurant in advance based on a suggested lunch plan.

[1178] "Rating data" refers to information about the evaluations that users have given to food service establishments and menus.

[1179] This invention is a system that generates and notifies / provides a lunch plan to the user based on the user's preferences, dietary restrictions, health data, budget, location information, and emotional state. This system is realized by utilizing the elements of a server, terminal, and user.

[1180] Account creation and initial setup

[1181] First, users access the system using a device (such as a smartphone or computer). After entering basic information (name, email address, password) on the account creation page, they enter their preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (where they will eat lunch). The device sends this information to the server, where it is stored in the server's database.

[1182] Gathering store information

[1183] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the location information set by the user. This is done using external APIs such as the Google Maps API and web scraping techniques. The collected data is stored in the server's database and updated in real time.

[1184] Utilizing the Emotion Engine

[1185] When a user requests to generate a lunch plan, the emotion engine uses the device's built-in camera and microphone to recognize the user's emotions. The emotion engine uses, for example, Google Cloud Vision's facial recognition API or Amazon Rekognition's facial analysis API to analyze facial expressions and tone of voice to determine the user's emotional state.

[1186] Creating a lunch plan

[1187] The server retrieves user profile information and collected store information from the database, taking into account the user's emotional data recognized by the emotion engine. It then generates a lunch plan using a generative AI (e.g., OpenAI GPT-4). The generative AI provides the optimal plan by considering factors such as nutritional balance, preferences, dietary restrictions, budget, evaluation information, and emotional state.

[1188] Lunch plan notification and special offer

[1189] The server notifies users of the generated lunch plans. Notifications are sent via email or in-app notifications. In addition, coupons and discounts are provided to certain establishments, which users can use to receive discounts. The server manages these coupons and discounts, and revenue is generated by collecting a monthly fee from the establishments.

[1190] Reservations and Reviews

[1191] Users can make reservations at restaurants within the app based on the provided lunch plan. After enjoying their lunch, users can rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. This rating data will be reflected when future lunch plans are generated.

[1192] As a concrete example, consider a case where a user creates an account by entering the following information using a device.

[1193] Name: Taro Tanaka

[1194] Email address: taro@example.com

[1195] Preferred ingredients and cuisine type: Japanese food

[1196] Dietary restrictions: Gluten-free

[1197] Health data: 70kg, target weight 65kg, height 175cm

[1198] Budget: 1000 yen

[1199] Location information: Around Tokyo Station

[1200] When Ms. Tanaka requests a lunch plan while feeling stressed, the emotional engine recognizes her stress level and suggests a plan that includes a relaxing cafe or a light meal. For example, a restaurant offering a "minced chicken and soft-boiled egg salad" (800 yen) is selected, and a 10% discount coupon is provided.

[1201] Examples of prompt statements are as follows:

[1202] Please create a program for a system that generates the optimal lunch plan based on the user's preferences, dietary restrictions, health data, budget, location, and emotional state.

[1203] This system not only allows users to enjoy the perfect lunch tailored to their emotional state on any given day, but also enables continuous improvement in satisfaction by incorporating evaluation data into future plan generation.

[1204] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1205] Step 1:

[1206] Users access the system using their devices and enter basic information (name, email address, password), preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (where they will have lunch) on the account creation page.

[1207] Input: All information entered by the user.

[1208] Output: Information transmission from the terminal to the server.

[1209] Step 2:

[1210] The terminal sends the information entered by the user to the server, where it is stored in the server's database.

[1211] Input: User input information.

[1212] Output: Sending data to the server and saving it to the database.

[1213] Specific operation: The terminal sends data to the server using a data transmission protocol (e.g., HTTPS), and the server stores the received information in a database.

[1214] Step 3:

[1215] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the location information set by the user. For this purpose, it utilizes the Google Maps API and web scraping techniques.

[1216] Input: User's location information.

[1217] Output: Data collection and database updates for surrounding facilities.

[1218] Specific operation: Use the Google Maps API to retrieve information about nearby restaurants based on location data, and save that information to the server's database.

[1219] Step 4:

[1220] When a user requests a lunch plan to be generated, the emotion engine uses the device's built-in camera and microphone to recognize the user's emotions. The emotion engine uses Google Cloud Vision's facial recognition API and Amazon Rekognition's facial analysis API to analyze facial expressions and tone of voice.

[1221] Input: User's facial image and voice data.

[1222] Output: User emotional state data.

[1223] Specific operation: The camera captures the user's facial expressions, and the emotion engine performs image analysis to generate emotion data.

[1224] Step 5:

[1225] The server uses the emotion data recognized by the emotion engine to retrieve user profile information and store information from the database, and generates a lunch plan using a generative AI (e.g., OpenAI GPT-4). The generative AI takes into account emotion data, nutritional balance, preferences, dietary restrictions, budget, and rating information.

[1226] Input: Sentimental data, user profile information, store information.

[1227] Output: The optimal lunch plan.

[1228] Specific operation: Retrieve necessary information from the database, input it into the generating AI, and generate a lunch plan.

[1229] Step 6:

[1230] The server notifies the user of the generated lunch plan. Notifications are sent via email or in-app notifications.

[1231] Input: Generated lunch plan.

[1232] Output: Notification to the user.

[1233] Specific operation: The server sends notifications to the user via the mail server or push notification server.

[1234] Step 7:

[1235] Users can make reservations at restaurants within the app based on the provided lunch plans.

[1236] Input: Lunch plan, user reservation request.

[1237] Output: Reservation information for the facility.

[1238] Specific operation: The app sends the reservation information to another service (reservation system API) to confirm the reservation.

[1239] Step 8:

[1240] After enjoying their lunch, users can leave a review of the facilities and menu within the app.

[1241] Input: User ratings.

[1242] Output: Evaluation data sent to the server.

[1243] Specific operation: User ratings are saved to a database and reflected in future lunch plan generation.

[1244] (Application Example 2)

[1245] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1246] While systems already exist that provide lunch plans based on user preferences, dietary restrictions, health data, budget, and location, these systems do not consider the user's emotional state. Therefore, they fail to provide meal plans that are optimal for the user's immediate emotional state, making it difficult to increase user satisfaction. There is a need for a system that provides more personalized lunch plans tailored to the user's emotional state on any given day.

[1247] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1248] In this invention, the server includes means for receiving user preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and rating information from nearby restaurants based on the input data and location information; means for generating a lunch plan based on the collected data and user input data; means for recognizing the user's emotions using a built-in camera and microphone and supplying the emotion data to the generation means; and means for notifying the user of the generated lunch plan. This makes it possible to provide the optimal lunch plan in real time according to the user's emotional state.

[1249] "Preferences" refer to the types of ingredients and cuisines that users enjoy.

[1250] "Dietary restrictions" refers to information about foods that users should avoid or foods they are allergic to.

[1251] "Health data" refers to health-related information such as the user's weight, height, and target weight.

[1252] "Budget" refers to the maximum amount a user can spend per meal.

[1253] "Location information" refers to information about the place where the user plans to have lunch.

[1254] A "menu" is a list of dishes offered by a restaurant.

[1255] "Price" refers to the cost of a menu item offered by a restaurant.

[1256] "Nutritional information" refers to information such as calories and nutrients included in the menu.

[1257] "Rating information" refers to user reviews and ratings of nearby restaurants and their menus.

[1258] The "generation method" refers to the means of creating a lunch plan based on user input data and collected data.

[1259] "Emotions" refer to the user's current psychological state.

[1260] "Emotional data" refers to information about a user's emotional state.

[1261] A "built-in camera" is a camera that is built into the user's device.

[1262] A "microphone" is an audio input device built into a user's device.

[1263] "Notification method" refers to the means of informing users of the generated lunch plan.

[1264] The system of this invention generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information. Furthermore, it analyzes the user's emotional state using an emotion engine and uses that data to further personalize the lunch plan.

[1265] Hardware and software to be used

[1266] Smartphones: Collect user input data and use the camera and microphone to acquire emotional data.

[1267] Server: Generates a lunch plan based on input and collected data and notifies the user.

[1268] Emotion Engine: Software for analyzing a user's emotional state. It uses facial expression analysis and voice analysis.

[1269] Generative AI Model: Generates the optimal lunch plan based on the user's profile and sentiment data.

[1270] External APIs and web scraping: Methods for collecting restaurant menus, prices, nutritional information, and ratings.

[1271] Data processing and data calculation

[1272] First, users enter basic information, preferences, dietary restrictions, health data, budget, and location information via their smartphones. This information is sent to a server and stored in a database.

[1273] When a user requests a lunch plan, an emotion engine uses the smartphone's camera and microphone to analyze the user's emotions. The analyzed emotion data is sent to a server and input into a generative AI model along with data about the restaurant.

[1274] The generative AI model generates the optimal lunch plan based on preferences, dietary restrictions, health data, budget, location, and emotional data. This lunch plan takes into account nutritional balance, budget, and current emotional state.

[1275] The generated lunch plan is notified to the user via smartphone. At the same time, coupons and discounts are also offered for specific restaurants.

[1276] Specific example

[1277] For example, suppose a user prefers Japanese food, sets a gluten-free diet as a restriction, and sets a budget of under 1000 yen per meal. When the user requests a lunch plan via smartphone, the emotion engine detects a state of stress. Based on this information, the generative AI model suggests a relaxing Japanese menu, such as a "chicken mince and soft-boiled egg salad" (800 yen). Furthermore, a 10% discount coupon is offered.

[1278] Example of a prompt

[1279] The user's preferences are Japanese food, dietary restrictions are gluten-free, and budget is 1000 yen per meal. Their location is Tokyo, and their emotional state is stressed. Based on this, please propose the optimal lunch plan.

[1280] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1281] Step 1:

[1282] Users enter basic information, preferences, dietary restrictions, health data, budget, and location information via their smartphones.

[1283] Input data: User's basic information, preferences, dietary restrictions, health data, budget, and location information.

[1284] Output data: The input data is sent to the server and stored in the database.

[1285] Step 2:

[1286] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the user's location.

[1287] Input data: User's location information

[1288] Data processing: Collect restaurant information using external APIs and web scraping.

[1289] Output data: The collected restaurant menus, prices, nutritional information, and ratings are stored in a database.

[1290] Step 3:

[1291] When a user requests a lunch plan via their smartphone, the emotion engine uses the built-in camera and microphone to analyze the user's emotions.

[1292] Input data: User's lunch plan request, user's facial image data, audio data

[1293] Data processing: The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[1294] Output data: The analyzed emotion data is sent to the server.

[1295] Step 4:

[1296] The server uses a generative AI model to generate lunch plans based on collected data and sentiment data.

[1297] Input data: User preferences, dietary restrictions, health data, budget, location information, sentiment data, information on nearby restaurants.

[1298] Data Calculation: A generative AI model analyzes the input data and generates the optimal lunch plan.

[1299] Output data: The generated lunch plan is stored on the server.

[1300] Step 5:

[1301] The server notifies the user of the generated lunch plan. The lunch plan is displayed on the smartphone, and coupons and discounts for specific restaurants are also offered.

[1302] Input data: Generated lunch plans, coupons and discount offers for specific stores.

[1303] Output data: Lunch plans, coupons, and discount offers are sent to the user's smartphone.

[1304] Step 6:

[1305] Users make restaurant reservations based on lunch plans. The reservation process is completed through a smartphone application.

[1306] Input data: Lunch plan selected by the user

[1307] Data processing: Generating reservation information, sending reservation requests to stores.

[1308] Output data: A reservation completion notification is displayed on the user's smartphone.

[1309] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1310] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1311] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1312] [Fourth Embodiment]

[1313] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1314] As shown in Figure 7, the 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.

[1315] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1316] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1317] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1318] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1319] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1320] The controlled 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1321] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1322] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1323] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1324] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1325] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1326] A specific embodiment of the present invention will now be described. This system generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information. The user first creates an account using a device (such as a smartphone or personal computer) and completes the initial setup.

[1327] 1. Account creation and initial setup

[1328] The user accesses the system and proceeds to the account creation page. Here, the user enters the following information:

[1329] Basic information: Name, email address, password

[1330] Preferences: Preferred ingredients and cuisine types (e.g., Japanese food, Chinese food, vegetarian)

[1331] Dietary restrictions: Foods and dishes to avoid for allergies or health reasons.

[1332] Health data: weight, target weight, height, etc.

[1333] Budget: Maximum budget per meal

[1334] Location information: Places where you eat lunch, such as your workplace or school.

[1335] This information is sent from the terminal to the server and stored in the database.

[1336] 2. Gathering store information

[1337] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on location data. This includes using external APIs and obtaining data through web scraping. The collected data is stored in a database and updated in real time.

[1338] 3. Creating a lunch plan

[1339] The server retrieves user profile information and store information from the database and uses a generation AI to generate a lunch plan that takes the following factors into consideration:

[1340] Nutritional balance: Calculating necessary nutrients and calories

[1341] User preferences and dietary restrictions

[1342] Budget: The set upper limit per meal.

[1343] Reviews and ratings: Selected based on collected review information.

[1344] The generated lunch plan will be notified to the user via email or in-app notification.

[1345] 4. Offering benefits and monetization

[1346] The generated lunch plans include coupons and discounts for specific restaurants. Users can use these to receive discounts when paying at the restaurants. The server manages these coupons and discounts. Additionally, a monthly fee is charged to the restaurants to generate revenue.

[1347] 5. Booking and Reviews

[1348] Users can make restaurant reservations within the app based on the provided lunch plan. After enjoying their lunch, users can rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. When generating future lunch plans, this rating data is reflected, providing plans that better match the user's preferences.

[1349] Specific example

[1350] For example, suppose Ms. Tanaka creates an account and sets her preferences as Japanese food, dietary restrictions as gluten-free, and budget as under 1000 yen per meal. The server collects information from restaurants around Ms. Tanaka's workplace, including information on Japanese food and gluten-free menus. Based on the collected data, the generating AI suggests the following as a Monday lunch plan, taking into account nutritional balance, budget, and customer reviews:

[1351] Store A: Grilled Chicken Salad (600 yen)

[1352] Store B: Gluten-free salmon sushi (800 yen)

[1353] Ms. Tanaka will also be offered a 10% discount coupon for Restaurant A. Ms. Tanaka will choose this plan, make a reservation at Restaurant A, and enter a review after lunch. This review will be reflected in future lunch plans.

[1354] The above describes specific embodiments of the present invention. This system allows users to easily and efficiently enjoy a healthy lunch.

[1355] The following describes the processing flow.

[1356] Step 1:

[1357] The user accesses the account creation page and enters the required information. This includes basic information, preferences, dietary restrictions, health data, budget, and location information. After completing the input, the device sends the information to the server.

[1358] Step 2:

[1359] The server stores the received user information in a database and creates a custom profile for each user.

[1360] Step 3:

[1361] The server uses the user's location information to collect menu, price, nutritional information, and ratings from nearby restaurants. This data is collected through APIs and web scraping. The collected data is stored in the server's database.

[1362] Step 4:

[1363] The server retrieves user profile information and store information from the database. Based on this, a generating AI creates a lunch plan. The generating AI takes into account nutritional balance, user preferences and dietary restrictions, budget, and rating information.

[1364] Step 5:

[1365] The server generates a lunch plan and notifies the user. The notification is sent via email or in-app notification.

[1366] Step 6:

[1367] When a user reviews the lunch plan and wants to reserve their desired menu item from the options, they make the reservation within the app.

[1368] Step 7:

[1369] The server notifies the restaurant of the user's reservation information, and the reservation is confirmed.

[1370] Step 8:

[1371] Users enjoy the suggested lunch and enter their ratings for the restaurant and menu within the app.

[1372] Step 9:

[1373] The server receives user evaluation data and stores it in the database. This evaluation data will be used to generate the next lunch plan.

[1374] Step 10:

[1375] The server provides coupons and discount offers to specific restaurants, allowing users to receive discounts.

[1376] Step 11:

[1377] The server regularly updates the restaurant data it collects, ensuring that it always maintains the latest menu, prices, and ratings.

[1378] (Example 1)

[1379] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1380] In today's busy lifestyle, easily choosing healthy and nutritionally balanced meals is crucial. However, finding the perfect lunch that suits individual dietary restrictions, preferences, and budgets is not easy. In addition, the time and effort required to gather necessary information from a wide variety of restaurants is a significant burden. Furthermore, there is a lack of systems that incorporate each user's rating into future selections to provide lunch plans that better suit their preferences.

[1381] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1382] In this invention, the server includes means for prompting the user to input their preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and rating information from nearby restaurants based on the input data and location information; means for generating a lunch plan using a generative AI model based on the collected data and the user's input data; means for notifying the user of the generated lunch plan; means for creating prompt sentences to be used in generating the lunch plan; and means for reflecting the previous rating data when generating a possible next lunch plan. This makes it possible to easily and efficiently provide a healthy lunch that matches the user's preferences, restrictions, and budget.

[1383] "User preferences" refer to the types of ingredients and cuisines that users like, and represent their individual tastes in food choices.

[1384] "Dietary restrictions" refer to foods and dishes that users should avoid for allergies or health reasons.

[1385] "Health data" refers to information about a user's health, such as their weight, target weight, and height.

[1386] "Budget" refers to the maximum amount of money a user can spend per meal.

[1387] "Location information" refers to the geographical information of where the user plans to have lunch.

[1388] "Input data" refers to information that users provide to the system, such as preferences, dietary restrictions, health data, budget, and location information.

[1389] "Store information" refers to menu, price, nutritional information, and ratings information collected from nearby restaurants.

[1390] "Collected data" refers to restaurant menus, prices, nutritional information, and ratings collected based on location information.

[1391] A "generative AI model" refers to an artificial intelligence model that generates the optimal lunch plan based on user input data and store information.

[1392] A "prompt" refers to a pre-designed set of questions or commands intended for input into a generative AI model.

[1393] A "lunch plan" refers to meal suggestions generated considering the user's preferences, dietary restrictions, budget, and location.

[1394] "Evaluation data" refers to user ratings and feedback on stores and menus they have used.

[1395] A "coupon" refers to a discount voucher or special offer that can be used at a specific store.

[1396] "Notification method" refers to the means of informing users of the generated lunch plan, and includes email and in-app notifications.

[1397] A specific embodiment of the present invention will now be described. This system generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information. The details are described below.

[1398] Account creation and initial setup

[1399] Users access the system using a device (such as a smartphone or computer) and proceed to the account creation page. Here, users enter their name, email address, password, preferred foods and cuisine types, dietary restrictions, health data such as weight, target weight, and height, a budget limit per meal, and location information such as their workplace or school. This information is sent from the device to the server and stored in the database.

[1400] Gathering store information

[1401] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the user's location. This collection includes data acquisition using external APIs such as the Google Places API and Yelp API, as well as web scraping techniques (using tools such as BeautifulSoup and Scrapy). The collected data is stored in a database and updated in real time.

[1402] Creating a lunch plan

[1403] The server retrieves user profile information and store information from the database and creates prompts for a generative AI model (e.g., OpenAI's GPT-3). These prompts include user preferences, dietary restrictions, nutritional balance, budget, ratings, and customer reviews. Examples of prompt statements include:

[1404] The user prefers Japanese food, has a gluten-free diet, and a budget of under 1000 yen per meal. Please propose the optimal lunch plan.

[1405] The server uses this prompt to run a generation AI model and generate the optimal lunch plan. The generated lunch plan is then notified to the user via email or in-app notification.

[1406] Offering benefits and monetization

[1407] The generated lunch plans include coupons and discounts for specific restaurants. Users can use these to receive discounts when paying at the restaurants. The server manages these coupons and discounts and generates revenue by collecting a monthly fee from the restaurants.

[1408] Reservations and Reviews

[1409] Users can make restaurant reservations within the app based on the provided lunch plan. After enjoying their lunch, users can rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. When generating future lunch plans, this rating data is reflected, providing plans that better suit the user's preferences.

[1410] Specific example

[1411] For example, a user creates an account and sets their preferences as Japanese food, dietary restrictions as gluten-free, and budget as under 1000 yen per meal. The server collects information from restaurants around the user's workplace, including information on Japanese food and gluten-free menus. Based on the collected data, the generating AI proposes a lunch plan like the following, taking into account nutritional balance, budget, and customer reviews:

[1412] Store A: Grilled Chicken Salad (600 yen)

[1413] Store B: Gluten-free salmon sushi (800 yen)

[1414] Along with notifying users of this plan, they will be offered a 10% discount coupon for Restaurant A. Users will choose this plan, make a reservation at Restaurant A, enjoy their lunch, and then enter a review within the app. This review will be reflected in future lunch plans.

[1415] The above describes specific embodiments of the present invention. This system allows users to easily and efficiently enjoy a healthy lunch.

[1416] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1417] Step 1: Account creation and initial setup

[1418] Users access the system using their devices (smartphones or computers) and proceed to the account creation page. They fill out a form with their name, email address, password, preferred foods and cuisine types, dietary restrictions, health data such as weight, target weight, and height, a budget limit per meal, and location information. This entered data is sent from the device to the server and stored in a database.

[1419] Step 2: Gathering store information

[1420] The server uses the user's location information to collect menu, price, nutritional information, and rating information from nearby restaurants. Specifically, it uses external APIs such as the Google Places API and the Yelp API to obtain data. It also uses web scraping techniques to collect necessary information from restaurant websites. The collected restaurant information is stored in a database.

[1421] Input: Location information

[1422] Data processing: Data is obtained using external APIs or web scraping.

[1423] Output: Store Information Database

[1424] Step 3: Generate a lunch plan

[1425] The server retrieves user profile information and store information from the database and creates prompts to input into the generated AI model. These prompts include user preferences, dietary restrictions, nutritional balance, budget, ratings, and customer reviews. Examples of specific prompt statements:

[1426] The user prefers Japanese food, has a gluten-free diet, and a budget of under 1000 yen per meal. Please propose the optimal lunch plan.

[1427] The generation AI model generates the optimal lunch plan based on prompts. The generated lunch plan is saved by the server.

[1428] Input: User profile information, store information

[1429] Data processing: Execution of generative AI models

[1430] Output: Generated lunch plan

[1431] Step 4: Notification of lunch plan

[1432] The server notifies the user of the generated lunch plan. The notification is sent via email or in-app notification, making it easy for the user to check their lunch plan.

[1433] Input: Generated lunch plan

[1434] Data processing: Creating and sending notifications

[1435] Output: Notification to the user

[1436] Step 5: Offering perks and monetization

[1437] The server adds coupons and discounts for specific restaurants to the generated lunch plans. This includes generating and managing coupon codes. When users utilize these discounts, the system collects a monthly fee from the restaurants, generating revenue.

[1438] Input: Lunch plan, store information

[1439] Data processing: Coupon code generation

[1440] Output: Granting of discount benefits

[1441] Step 6: Make a reservation

[1442] Users make restaurant reservations within the app based on the provided lunch plans. The reservation function works in conjunction with the restaurant's reservation system, allowing users to complete reservations smoothly.

[1443] Input: Lunch plan

[1444] Data processing: Integration with the reservation system

[1445] Output: Restaurant reservation confirmation

[1446] Step 7: Enter your evaluation

[1447] After users enjoy their lunch, they can rate the restaurant and menu within the app. A rating form is provided, allowing users to enter rating scores and comments. This rating data is sent to a server and stored in a database.

[1448] Input: User rating data

[1449] Data processing: Evaluation data storage

[1450] Output: Saved evaluation data

[1451] Step 8: Reflect evaluation data

[1452] The server will incorporate the previous evaluation data when generating subsequent lunch plans. This will enable the provision of more accurate lunch plans that better match the user's preferences.

[1453] Input: Evaluation data

[1454] Data processing: Reflection in lunch plan generation

[1455] Output: Highly accurate lunch plan

[1456] The above describes the processing flow of this system's program.

[1457] (Application Example 1)

[1458] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1459] In modern society, it is a challenging task to easily and quickly propose lunch plans that take into account individual user preferences, health conditions, dietary restrictions, and budgets. Furthermore, there is a lack of systems that can reliably deliver satisfactory plans while simultaneously strengthening collaborations with local restaurants. In particular, generating optimal lunch plans for individual users requires sophisticated processing based on vast amounts of data, thus necessitating the provision of an efficient and effective system.

[1460] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1461] In this invention, the server includes means for prompting the user to input preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and rating information from nearby restaurants based on the input data and location information; means for generating a lunch plan using a generative AI model based on the collected data and the user's input data; and means for sending the generated lunch plan as a prompt message to the generative AI model and notifying the user. This makes it possible to quickly generate and notify the user of an optimal lunch plan that is suitable for each user's preferences and conditions.

[1462] A "user" refers to an individual who uses this system and is the entity that provides information such as preferences, dietary restrictions, and health data.

[1463] "Preferences" refer to the user's favorite ingredients and types of cuisine.

[1464] "Dietary restrictions" refer to foods or dishes that should be avoided due to allergies or health reasons.

[1465] "Health data" refers to the user's physical information, such as weight, target weight, and height.

[1466] "Budget" refers to the maximum amount of money a user plans to spend per meal.

[1467] "Location information" refers to the geographical information of the place where the user is eating.

[1468] "Menu information" refers to information that describes the dishes offered by a restaurant.

[1469] "Price information" refers to information that shows the selling price of each menu item at a restaurant.

[1470] "Nutritional information" refers to information that shows the nutritional components and calories contained in each menu item.

[1471] "Rating information" refers to information that shows the ratings and reviews that past users have given to a restaurant or its menu.

[1472] A "generative AI model" refers to an artificial intelligence model used to generate lunch plans based on user preferences, health data, budget, and location information.

[1473] A "prompt statement" refers to an input statement provided to a generative AI model.

[1474] "Means of notification" refers to the means of informing users of the generated lunch plan.

[1475] A "coupon" refers to a discount voucher that can be used at a specific restaurant.

[1476] A "discount offer" refers to a service offered by a restaurant that reduces the price of specific items.

[1477] "Methods for making reservations" refers to the means by which users can secure seats and menu items at restaurants in advance based on a lunch plan that has been generated.

[1478] The system of the present invention is designed to generate and provide customized lunch plans to users based on their individual preferences, health data, budget, and location information.

[1479] 1. Account creation and initial setup

[1480] Users first create an account using their own device (such as a smartphone or computer). The following information is required when creating an account:

[1481] Basic information: Name, email address, password

[1482] Tastes: Favorite ingredients and dishes

[1483] Dietary restrictions: Foods and dishes to avoid for allergies or health reasons.

[1484] Health data: weight, target weight, height, etc.

[1485] Budget: Maximum budget per meal

[1486] Location information: The place where we plan to have lunch

[1487] 2. Information Gathering

[1488] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on user input data and location information. This includes data acquisition through the use of external APIs and web scraping.

[1489] 3. Creating a lunch plan

[1490] The server uses a generative AI model to generate lunch plans based on the user's preferences, dietary restrictions, health data, budget, and information on nearby restaurants. Specific prompts are sent to the generative AI model, and its responses are collected as lunch plans.

[1491] Example of a prompt

[1492] "The user's preference is for Japanese food, their budget is 1000 yen, and their dietary restriction is gluten-free. Their current location is Tokyo. Here is some information on nearby restaurants..."

[1493] 4. Notification of lunch plan

[1494] The generated lunch plan will be notified to the user's device. Specifically, the user will receive an email or an in-app notification.

[1495] 5. Provision of benefits

[1496] The server uses collected data to provide coupons and discount offers to specific restaurants. These offers are included in lunch plans, allowing users to receive discounts when paying at the restaurant.

[1497] 6. Booking and Reviews

[1498] Users can make restaurant reservations within the app based on the generated lunch plan. After enjoying their lunch, users can also rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. When generating future lunch plans, this rating data is reflected, providing plans that better match the user's preferences.

[1499] The above describes a specific embodiment of the present invention. This system enables users to efficiently enjoy lunch that is perfectly suited to their individual preferences and circumstances.

[1500] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1501] Step 1:

[1502] Users create an account using their own device (such as a smartphone or computer). During account creation, users enter their name, email address, password, preferences, dietary restrictions, health data, budget, and location information. This information is sent from the device to the server and stored in the database.

[1503] Input: Name, email address, password, preferences, dietary restrictions, health data, budget, location information

[1504] Output: Saving user information to the database

[1505] Step 2:

[1506] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the user's location. This collection utilizes external APIs and web scraping. The collected information is stored in a database and updated in real time.

[1507] Input: User's location information

[1508] Output: Saving restaurant information to a database

[1509] Step 3:

[1510] The server generates lunch plans using a generative AI model based on the entered user information and collected restaurant information. During this process, the generative AI model receives prompt messages and retrieves the most suitable lunch plan as its response.

[1511] Input: User information, restaurant information

[1512] Output: Generated lunch plan

[1513] Specific operation: The system generates a prompt message such as, "User preference: Japanese food, budget: 1000 yen, dietary restrictions: gluten-free. Current location: Tokyo. Nearby restaurant information:..." and sends it to the AI ​​model. In response, the AI ​​model retrieves the optimal lunch plan (for example, "Grilled Chicken Salad at Restaurant A").

[1514] Step 4:

[1515] Once a lunch plan is generated, the server notifies the user. This notification is sent to the user's device via email or in-app notification.

[1516] Input: Generated lunch plan

[1517] Output: Notification to the user's device

[1518] Step 5:

[1519] The server suggests coupons and discount offers for specific restaurants based on the collected data. These offers are included in the generated lunch plan, which the user can then utilize.

[1520] Input: Collected data, generated lunch plan

[1521] Output: Coupons and discounts included in the lunch plan

[1522] Step 6:

[1523] Users can make restaurant reservations using their devices based on the provided lunch plans. Reservation information is sent to a server for coordination with the restaurants.

[1524] Input: Lunch plan, user reservation information

[1525] Output: Reservation notification to restaurant

[1526] Step 7:

[1527] After users enjoy their lunch, they enter their ratings of the restaurant and menu within the app. This rating data is sent to the server and stored in a database. This rating data is then used to generate future lunch plans.

[1528] Input: User rating information

[1529] Output: Saving evaluation data to a database

[1530] The above outlines the specific processing steps and flow of this system.

[1531] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1532] A specific embodiment of the present invention will now be described. This system generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information, and also recognizes the user's emotions to customize the lunch plan. The user first creates an account using a device (such as a smartphone or personal computer) and completes the initial setup.

[1533] 1. Account creation and initial setup

[1534] Users access the system and enter basic information (name, email address, password), preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (where they will have lunch) on the account creation page. After completing the input, the information is sent from the device to the server and stored in the database.

[1535] 2. Gathering store information

[1536] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on location data. Collection methods include using external APIs and web scraping. The collected data is stored in the server's database and updated in real time.

[1537] 3. Utilizing the Emotional Engine

[1538] When a user accesses the system from their device, the emotion engine uses the built-in camera and microphone to recognize the user's emotions. The emotion engine analyzes the user's facial expressions, tone of voice, and word choice to determine their current emotional state. For example, it can determine whether the user is stressed or relaxed.

[1539] 4. Creating a lunch plan

[1540] The server, taking into account the user's emotional data recognized by the emotion engine, retrieves user profile information and store information from the database. Based on this, the generative AI generates a lunch plan. The generative AI takes the following factors into consideration:

[1541] Nutritional balance: Calculating necessary nutrients and calories

[1542] User preferences and dietary restrictions

[1543] Budget: The set upper limit per meal.

[1544] Reviews and ratings: Collected review information

[1545] Emotional state: Selecting the most suitable menu or store based on the user's current emotional state.

[1546] For example, if the user is tired, a relaxing cafe or a light meal might be suggested. If the user is excited, a meal that will replenish their energy might be suggested.

[1547] 5. Notification of lunch plan and provision of benefits

[1548] The server notifies users of the generated lunch plans. Notifications are sent via email or in-app notifications. In addition, certain restaurants are given coupons and discounts, which users can use to receive discounts. The server manages these coupons and discounts, and generates revenue by collecting a monthly fee from the restaurants.

[1549] 6. Booking and Reviews

[1550] Users can make restaurant reservations within the app based on the provided lunch plan. After enjoying their lunch, users enter their ratings for the restaurant and menu within the app. This rating data is sent to the server and stored in a database. This rating data will be reflected when generating future lunch plans.

[1551] Specific example

[1552] For example, suppose Ms. Tanaka creates an account and sets her preferences as Japanese food, dietary restrictions as gluten-free, and budget as under 1000 yen per meal. One day, when Ms. Tanaka is feeling stressed, she requests a lunch plan. The server's emotion engine recognizes her stress level and suggests a menu from a relaxing restaurant. For example, it might select a restaurant that serves Japanese food and offers a gluten-free "chicken mince and soft-boiled egg salad" (800 yen) and offer a 10% discount coupon as a perk. Ms. Tanaka chooses this plan, makes a reservation at the restaurant, and enters a review after lunch.

[1553] The above describes a specific embodiment of the present invention. This system allows users to enjoy an optimal lunch tailored to their emotional state on any given day, and to maintain a healthy diet.

[1554] The following describes the processing flow.

[1555] Step 1:

[1556] The user accesses the account creation page. Here, they enter basic information (name, email address, password), preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (location of workplace or school).

[1557] Step 2:

[1558] The terminal sends the entered information to the server. The transmitted data is stored in a database by the server, and a custom profile is created for each user.

[1559] Step 3:

[1560] The server uses the user's location information to collect menu, price, nutritional information, and ratings from nearby restaurants. Data collection methods include using external APIs and web scraping. The collected data is stored in a database and updated in real time.

[1561] Step 4:

[1562] (When a user requests the generation of a lunch plan, the device uses devices such as the camera and microphone to identify the user's emotional state using an emotion engine. The emotion engine analyzes the user's emotions through facial expression analysis, voice tone analysis, and word choice. For example, it can identify whether the user is stressed or relaxed.)

[1563] Step 5:

[1564] The server retrieves user profile information and store information from the database, along with emotional state data from the emotion engine. Based on this data, the generating AI generates a lunch plan considering the following factors:

[1565] Nutritional balance: Calculating necessary nutrients and calories

[1566] User preferences and dietary restrictions

[1567] Budget: The set upper limit per meal.

[1568] Reviews and ratings: Collected review information

[1569] Emotional state: Users select menus and restaurants that match their current emotions.

[1570] For example, if a user is tired, the system might suggest a relaxing cafe or a light meal; if a user is excited, it might suggest a meal that will replenish their energy.

[1571] Step 6:

[1572] The server generates lunch plans and notifies users. Notifications are sent via email or in-app notifications. In addition, coupons and discounts are offered at certain restaurants, which users can use to receive discounts.

[1573] Step 7:

[1574] When a user makes a restaurant reservation based on a provided lunch plan, the reservation process is performed within the app.

[1575] Step 8:

[1576] The server notifies the restaurant of the user's reservation information and confirms the reservation.

[1577] Step 9:

[1578] Users enjoy the suggested lunch and enter their ratings for the restaurant and menu within the app.

[1579] Step 10:

[1580] The server receives user evaluation data and stores it in the database. This evaluation data will be used to generate the next lunch plan.

[1581] Step 11:

[1582] The server regularly updates its database of restaurants, maintaining the latest menus, prices, and ratings, ensuring that information is always up-to-date.

[1583] Through the specific processing steps described above, users are offered a lunch plan best suited to their emotional state on that day. For example, when Ms. Tanaka is feeling stressed, a restaurant offering a gluten-free Japanese-style "chicken mince and soft-boiled egg salad" is suggested, and she can also obtain a discount coupon. Ms. Tanaka chooses this plan, makes a reservation, enjoys her lunch, and then gives a high rating. As a result, the next lunch plan will be even more appropriate.

[1584] (Example 2)

[1585] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1586] Conventional lunch plan generation systems typically provide plans based on static data such as user preferences, dietary restrictions, and budget, and are particularly unable to provide lunch plans that respond to users' dynamic emotional states. Therefore, it was difficult to provide the optimal lunch plan according to the user's mood and emotions at any given time. Furthermore, there was no mechanism in place to incorporate evaluation data into subsequent plans, making continuous improvement to increase user satisfaction difficult.

[1587] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting the user's preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and evaluation information from nearby restaurants based on the input data and location information; means for analyzing emotional data using the terminal's camera and microphone to recognize the user's emotional state; generation AI means for generating a lunch plan based on the collected data, the user's input data, and the emotional data; means for notifying the user of the generated lunch plan; means for providing coupons and discount benefits to specific restaurants; and means for the user to make a reservation based on the lunch plan. This makes it possible to provide a lunch plan that is optimal not only for the user's preferences and dietary restrictions, but also for their emotional state at the time, and furthermore, by reflecting the evaluation data in the generation of plans in the future, user satisfaction can be continuously improved.

[1588] A "user" refers to someone who inputs basic information, preferences, and emotional states to generate a lunch plan using the system.

[1589] "Preferences" refers to information about the ingredients and types of cuisine that users prefer.

[1590] "Dietary restrictions" refers to information about foods that users should avoid or allergens they may have.

[1591] "Health data" refers to the user's physical information, such as weight, target weight, and height.

[1592] "Budget" refers to the maximum amount of money a user can spend per meal.

[1593] "Location information" refers to the geographical information of where the user is having lunch.

[1594] "Food service facilities" refer to establishments in the surrounding area that provide meals, such as restaurants and eateries.

[1595] "Menu" refers to the list of dishes offered at each food service establishment.

[1596] "Price" refers to the cost of each dish listed on the menu.

[1597] "Nutritional information" refers to health-related data such as the nutrients and calories contained in each menu item.

[1598] "Rating information" refers to user ratings and reviews of food service establishments and the menus they offer.

[1599] "Emotional state" refers to the psychological state obtained by analyzing the user's facial expressions, tone of voice, and other factors.

[1600] "Emotional data" refers to information about the user's emotions that has been analyzed by the emotion engine.

[1601] "Generative AI" refers to artificial intelligence technology that generates lunch plans based on data.

[1602] A "lunch plan" refers to meal suggestions provided based on collected data and user input.

[1603] A "coupon" refers to a discount voucher that can be used at a specific restaurant.

[1604] A "discount offer" refers to a discount service that a user can receive under specific conditions.

[1605] "Reservation" refers to the act of a user securing a restaurant in advance based on a suggested lunch plan.

[1606] "Rating data" refers to information about the evaluations that users have given to food service establishments and menus.

[1607] This invention is a system that generates and notifies / provides a lunch plan to the user based on the user's preferences, dietary restrictions, health data, budget, location information, and emotional state. This system is realized by utilizing the elements of a server, terminal, and user.

[1608] Account creation and initial setup

[1609] First, users access the system using a device (such as a smartphone or computer). After entering basic information (name, email address, password) on the account creation page, they enter their preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (where they will eat lunch). The device sends this information to the server, where it is stored in the server's database.

[1610] Gathering store information

[1611] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the location information set by the user. This is done using external APIs such as the Google Maps API and web scraping techniques. The collected data is stored in the server's database and updated in real time.

[1612] Utilizing the Emotion Engine

[1613] When a user requests to generate a lunch plan, the emotion engine uses the device's built-in camera and microphone to recognize the user's emotions. The emotion engine uses, for example, Google Cloud Vision's facial recognition API or Amazon Rekognition's facial analysis API to analyze facial expressions and tone of voice to determine the user's emotional state.

[1614] Creating a lunch plan

[1615] The server retrieves user profile information and collected store information from the database, taking into account the user's emotional data recognized by the emotion engine. It then generates a lunch plan using a generative AI (e.g., OpenAI GPT-4). The generative AI provides the optimal plan by considering factors such as nutritional balance, preferences, dietary restrictions, budget, evaluation information, and emotional state.

[1616] Lunch plan notification and special offer

[1617] The server notifies users of the generated lunch plans. Notifications are sent via email or in-app notifications. In addition, coupons and discounts are provided to certain establishments, which users can use to receive discounts. The server manages these coupons and discounts, and revenue is generated by collecting a monthly fee from the establishments.

[1618] Reservations and Reviews

[1619] Users can make reservations at restaurants within the app based on the provided lunch plan. After enjoying their lunch, users can rate the restaurant and menu within the app. This rating data is sent to the server and stored in a database. This rating data will be reflected when future lunch plans are generated.

[1620] As a concrete example, consider a case where a user creates an account by entering the following information using a device.

[1621] Name: Taro Tanaka

[1622] Email address: taro@example.com

[1623] Preferred ingredients and cuisine type: Japanese food

[1624] Dietary restrictions: Gluten-free

[1625] Health data: 70kg, target weight 65kg, height 175cm

[1626] Budget: 1000 yen

[1627] Location information: Around Tokyo Station

[1628] When Ms. Tanaka requests a lunch plan while feeling stressed, the emotional engine recognizes her stress level and suggests a plan that includes a relaxing cafe or a light meal. For example, a restaurant offering a "minced chicken and soft-boiled egg salad" (800 yen) is selected, and a 10% discount coupon is provided.

[1629] Examples of prompt statements are as follows:

[1630] Please create a program for a system that generates the optimal lunch plan based on the user's preferences, dietary restrictions, health data, budget, location, and emotional state.

[1631] This system not only allows users to enjoy the perfect lunch tailored to their emotional state on any given day, but also enables continuous improvement in satisfaction by incorporating evaluation data into future plan generation.

[1632] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1633] Step 1:

[1634] Users access the system using their devices and enter basic information (name, email address, password), preferences (favorite foods and cuisine types), dietary restrictions (allergies and foods to avoid), health data (weight, target weight, height), budget (maximum budget per meal), and location information (where they will have lunch) on the account creation page.

[1635] Input: All information entered by the user.

[1636] Output: Information transmission from the terminal to the server.

[1637] Step 2:

[1638] The terminal sends the information entered by the user to the server, where it is stored in the server's database.

[1639] Input: User input information.

[1640] Output: Sending data to the server and saving it to the database.

[1641] Specific operation: The terminal sends data to the server using a data transmission protocol (e.g., HTTPS), and the server stores the received information in a database.

[1642] Step 3:

[1643] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the location information set by the user. For this purpose, it utilizes the Google Maps API and web scraping techniques.

[1644] Input: User's location information.

[1645] Output: Data collection and database updates for surrounding facilities.

[1646] Specific operation: Use the Google Maps API to retrieve information about nearby restaurants based on location data, and save that information to the server's database.

[1647] Step 4:

[1648] When a user requests a lunch plan to be generated, the emotion engine uses the device's built-in camera and microphone to recognize the user's emotions. The emotion engine uses Google Cloud Vision's facial recognition API and Amazon Rekognition's facial analysis API to analyze facial expressions and tone of voice.

[1649] Input: User's facial image and voice data.

[1650] Output: User emotional state data.

[1651] Specific operation: The camera captures the user's facial expressions, and the emotion engine performs image analysis to generate emotion data.

[1652] Step 5:

[1653] The server uses the emotion data recognized by the emotion engine to retrieve user profile information and store information from the database, and generates a lunch plan using a generative AI (e.g., OpenAI GPT-4). The generative AI takes into account emotion data, nutritional balance, preferences, dietary restrictions, budget, and rating information.

[1654] Input: Sentimental data, user profile information, store information.

[1655] Output: The optimal lunch plan.

[1656] Specific operation: Retrieve necessary information from the database, input it into the generating AI, and generate a lunch plan.

[1657] Step 6:

[1658] The server notifies the user of the generated lunch plan. Notifications are sent via email or in-app notifications.

[1659] Input: Generated lunch plan.

[1660] Output: Notification to the user.

[1661] Specific operation: The server sends notifications to the user via the mail server or push notification server.

[1662] Step 7:

[1663] Users can make reservations at restaurants within the app based on the provided lunch plans.

[1664] Input: Lunch plan, user reservation request.

[1665] Output: Reservation information for the facility.

[1666] Specific operation: The app sends the reservation information to another service (reservation system API) to confirm the reservation.

[1667] Step 8:

[1668] After enjoying their lunch, users can leave a review of the facilities and menu within the app.

[1669] Input: User ratings.

[1670] Output: Evaluation data sent to the server.

[1671] Specific operation: User ratings are saved to a database and reflected in future lunch plan generation.

[1672] (Application Example 2)

[1673] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1674] While systems already exist that provide lunch plans based on user preferences, dietary restrictions, health data, budget, and location, these systems do not consider the user's emotional state. Therefore, they fail to provide meal plans that are optimal for the user's immediate emotional state, making it difficult to increase user satisfaction. There is a need for a system that provides more personalized lunch plans tailored to the user's emotional state on any given day.

[1675] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1676] In this invention, the server includes means for receiving user preferences, dietary restrictions, health data, budget, and location information; means for collecting menu, price, nutritional information, and rating information from nearby restaurants based on the input data and location information; means for generating a lunch plan based on the collected data and user input data; means for recognizing the user's emotions using a built-in camera and microphone and supplying the emotion data to the generation means; and means for notifying the user of the generated lunch plan. This makes it possible to provide the optimal lunch plan in real time according to the user's emotional state.

[1677] "Preferences" refer to the types of ingredients and cuisines that users enjoy.

[1678] "Dietary restrictions" refers to information about foods that users should avoid or foods they are allergic to.

[1679] "Health data" refers to health-related information such as the user's weight, height, and target weight.

[1680] "Budget" refers to the maximum amount a user can spend per meal.

[1681] "Location information" refers to information about the place where the user plans to have lunch.

[1682] A "menu" is a list of dishes offered by a restaurant.

[1683] "Price" refers to the cost of a menu item offered by a restaurant.

[1684] "Nutritional information" refers to information such as calories and nutrients included in the menu.

[1685] "Rating information" refers to user reviews and ratings of nearby restaurants and their menus.

[1686] The "generation method" refers to the means of creating a lunch plan based on user input data and collected data.

[1687] "Emotions" refer to the user's current psychological state.

[1688] "Emotional data" refers to information about a user's emotional state.

[1689] A "built-in camera" is a camera that is built into the user's device.

[1690] A "microphone" is an audio input device built into a user's device.

[1691] "Notification method" refers to the means of informing users of the generated lunch plan.

[1692] The system of this invention generates a lunch plan based on the user's preferences, dietary restrictions, health data, budget, and location information. Furthermore, it analyzes the user's emotional state using an emotion engine and uses that data to further personalize the lunch plan.

[1693] Hardware and software to be used

[1694] Smartphones: Collect user input data and use the camera and microphone to acquire emotional data.

[1695] Server: Generates a lunch plan based on input and collected data and notifies the user.

[1696] Emotion Engine: Software for analyzing a user's emotional state. It uses facial expression analysis and voice analysis.

[1697] Generative AI Model: Generates the optimal lunch plan based on the user's profile and sentiment data.

[1698] External APIs and web scraping: Methods for collecting restaurant menus, prices, nutritional information, and ratings.

[1699] Data processing and data calculation

[1700] First, users enter basic information, preferences, dietary restrictions, health data, budget, and location information via their smartphones. This information is sent to a server and stored in a database.

[1701] When a user requests a lunch plan, an emotion engine uses the smartphone's camera and microphone to analyze the user's emotions. The analyzed emotion data is sent to a server and input into a generative AI model along with data about the restaurant.

[1702] The generative AI model generates the optimal lunch plan based on preferences, dietary restrictions, health data, budget, location, and emotional data. This lunch plan takes into account nutritional balance, budget, and current emotional state.

[1703] The generated lunch plan is notified to the user via smartphone. At the same time, coupons and discounts are also offered for specific restaurants.

[1704] Specific example

[1705] For example, suppose a user prefers Japanese food, sets a gluten-free diet as a restriction, and sets a budget of under 1000 yen per meal. When the user requests a lunch plan via smartphone, the emotion engine detects a state of stress. Based on this information, the generative AI model suggests a relaxing Japanese menu, such as a "chicken mince and soft-boiled egg salad" (800 yen). Furthermore, a 10% discount coupon is offered.

[1706] Example of a prompt

[1707] The user's preferences are Japanese food, dietary restrictions are gluten-free, and budget is 1000 yen per meal. Their location is Tokyo, and their emotional state is stressed. Based on this, please propose the optimal lunch plan.

[1708] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1709] Step 1:

[1710] Users enter basic information, preferences, dietary restrictions, health data, budget, and location information via their smartphones.

[1711] Input data: User's basic information, preferences, dietary restrictions, health data, budget, and location information.

[1712] Output data: The input data is sent to the server and stored in the database.

[1713] Step 2:

[1714] The server collects menu, price, nutritional information, and ratings from nearby restaurants based on the user's location.

[1715] Input data: User's location information

[1716] Data processing: Collect restaurant information using external APIs and web scraping.

[1717] Output data: The collected restaurant menus, prices, nutritional information, and ratings are stored in a database.

[1718] Step 3:

[1719] When a user requests a lunch plan via their smartphone, the emotion engine uses the built-in camera and microphone to analyze the user's emotions.

[1720] Input data: User's lunch plan request, user's facial image data, audio data

[1721] Data processing: The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[1722] Output data: The analyzed emotion data is sent to the server.

[1723] Step 4:

[1724] The server uses a generative AI model to generate lunch plans based on collected data and sentiment data.

[1725] Input data: User preferences, dietary restrictions, health data, budget, location information, sentiment data, information on nearby restaurants.

[1726] Data Calculation: A generative AI model analyzes the input data and generates the optimal lunch plan.

[1727] Output data: The generated lunch plan is stored on the server.

[1728] Step 5:

[1729] The server notifies the user of the generated lunch plan. The lunch plan is displayed on the smartphone, and coupons and discounts for specific restaurants are also offered.

[1730] Input data: Generated lunch plans, coupons and discount offers for specific stores.

[1731] Output data: Lunch plans, coupons, and discount offers are sent to the user's smartphone.

[1732] Step 6:

[1733] Users make restaurant reservations based on lunch plans. The reservation process is completed through a smartphone application.

[1734] Input data: Lunch plan selected by the user

[1735] Data processing: Generating reservation information, sending reservation requests to stores.

[1736] Output data: A reservation completion notification is displayed on the user's smartphone.

[1737] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1738] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1739] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1740] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1741] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1742] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1743] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1744] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1745] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1746] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1747] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1748] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1749] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1750] 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.

[1751] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1752] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1753] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1754] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1755] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1756] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1757] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1758] The following is further disclosed regarding the embodiments described above.

[1759] (Claim 1)

[1760] A means of obtaining user preferences, dietary restrictions, health data, budget, and location information,

[1761] Based on the above input data and location information, a means for collecting menu, price, nutritional information, and rating information from nearby restaurants,

[1762] Based on the above collected data and user input data, a generation means for generating a lunch plan is provided.

[1763] A means for notifying the user of the generated lunch plan,

[1764] A system that includes this.

[1765] (Claim 2)

[1766] The system according to claim 1, further comprising means of providing users with coupons or discounts for specific stores based on collected data.

[1767] (Claim 3)

[1768] The system according to claim 1, further comprising means by which a user makes a reservation based on the generated lunch plan.

[1769] (Claim 4)

[1770] The system according to claim 1, further comprising means for collecting user evaluation data and reflecting it in the generation of the next lunch plan.

[1771] (Claim 5)

[1772] The system according to claim 1, further comprising means for periodically updating data collected from nearby restaurants.

[1773] "Example 1"

[1774] (Claim 1)

[1775] A means of obtaining user preferences, dietary restrictions, health data, budget, and location information,

[1776] Based on the above input data and location information, a means for collecting menu, price, nutritional information, and rating information from nearby restaurants,

[1777] A means for generating a lunch plan using a generation AI model based on the above collected data and user input data,

[1778] A means for notifying the user of the generated lunch plan,

[1779] A means of creating prompt statements to be used to generate a lunch plan,

[1780] A method to incorporate the previous evaluation data when generating the next possible lunch plan,

[1781] A system that includes this.

[1782] (Claim 2)

[1783] The system according to claim 1, further comprising means of providing users with coupons or discounts for specific stores based on collected data.

[1784] (Claim 3)

[1785] The system according to claim 1, further comprising means by which a user makes a reservation based on the generated lunch plan.

[1786] "Application Example 1"

[1787] (Claim 1)

[1788] A means of obtaining user preferences, dietary restrictions, health data, budget, and location information,

[1789] Based on the above input data and location information, a means for collecting menu, price, nutritional information, and rating information from nearby restaurants,

[1790] A means for generating a lunch plan using a generation AI model based on the above collected data and user input data,

[1791] A means of sending the generated lunch plan as a prompt message to the AI ​​model and notifying the user,

[1792] A system that includes this.

[1793] (Claim 2)

[1794] The system according to claim 1, further comprising means of providing users with coupons or discounts for specific stores based on collected data.

[1795] (Claim 3)

[1796] The system according to claim 1, further comprising means by which a user makes a reservation based on the generated lunch plan.

[1797] "Example 2 of combining an emotion engine"

[1798] (Claim 1)

[1799] A means of obtaining user preferences, dietary restrictions, health data, budget, and location information,

[1800] Based on the above input data and location information, a means for collecting menu, price, nutritional information, and evaluation information from nearby food service establishments,

[1801] A method for analyzing emotional data using the device's camera and microphone to recognize the user's emotional state,

[1802] Based on the above collected data, user input data, and sentiment data, a generation AI means for generating lunch plans is provided.

[1803] A means for notifying the user of the generated lunch plan,

[1804] A means of providing coupons or discounts to specific facilities,

[1805] A means for users to make reservations based on lunch plans,

[1806] A system that includes this.

[1807] (Claim 2)

[1808] The system according to claim 1, characterized in that the lunch plan generated based on the user's emotional state selects the menu that is best suited to the user's current emotional state.

[1809] (Claim 3)

[1810] The system according to claim 1, characterized in that it collects user evaluation data and reflects it when generating lunch plans for future occasions.

[1811] "Application example 2 when combining with an emotional engine"

[1812] (Claim 1)

[1813] A means of obtaining user preferences, dietary restrictions, health data, budget, and location information,

[1814] Based on the above input data and location information, a means for collecting menu, price, nutritional information, and rating information from nearby restaurants,

[1815] Based on the above collected data and user input data, a generation means for generating a lunch plan is provided.

[1816] A means for recognizing the user's emotions using a built-in camera and microphone, and supplying that emotion data to the generation means,

[1817] A means for notifying the user of the generated lunch plan,

[1818] A system that includes this.

[1819] (Claim 2)

[1820] The system according to claim 1, further comprising means for providing users with coupons or discounts for specific stores based on collected data.

[1821] (Claim 3)

[1822] The system according to claim 1, further comprising means for a user to make a reservation based on a generated lunch plan. [Explanation of Symbols]

[1823] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining user preferences, dietary restrictions, health data, budget, and location information, Based on the above input data and location information, a means for collecting menu, price, nutritional information, and rating information from nearby restaurants, Based on the above collected data and user input data, a generation means for generating a lunch plan is provided. A means for notifying the user of the generated lunch plan, A system that includes this.

2. The system according to claim 1, further comprising means of providing users with coupons or discounts for specific stores based on collected data.

3. The system according to claim 1, further comprising means for a user to make a reservation based on the generated lunch plan.

4. The system according to claim 1, further comprising means for collecting user evaluation data and reflecting it in the generation of the next lunch plan.

5. The system according to claim 1, further comprising means for periodically updating data collected from nearby restaurants.

Images