system

Abstract

Provide a system. A means for receiving input from a user and analyzing the details of the diet-related consultation; means for generating appropriate meal suggestions based on the user's past history and preferences; means for presenting meal suggestions to a user and receiving consent thereto; a means for notifying a partner restaurant of a meal order after receiving consent from the user; A means for issuing delivery instructions to a delivery service based on the cooking completion notification received from the restaurant; means for notifying the user of the delivery status; A system including:

Description

[Technical Field]

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

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

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

[0004] In modern society, elderly people living alone and those living in depopulated areas often have difficulty obtaining food due to the lack of a nearby supermarket. Furthermore, specialized knowledge is required for these shoppers to prepare nutritionally balanced meals, which presents an additional hurdle. Under these circumstances, there is a need for a system that allows people to receive dietary advice, receive appropriate meal suggestions, and easily access them. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. First, it provides a means for receiving input from a user and analyzing the details of the meal-related inquiry. Next, it provides a means for generating appropriate meal suggestions based on the user's past history and preferences. Then, it provides a means for presenting the meal suggestions to the user and receiving their consent. After receiving consent, it includes a means for notifying a partner restaurant of the meal order. Furthermore, it provides a means for issuing delivery instructions to a delivery service based on the cooking completion notification received from the restaurant, and finally notifying the user of the delivery status, thereby building a system that allows users to easily obtain nutritionally balanced meals.

[0006] "User" refers to an individual who utilizes the system to suggest and order meals.

[0007] "Input" refers to information that a user provides to the system regarding dietary consultations and requests.

[0008] "Meal suggestions" refers to meal menu suggestions generated by the system based on the user's preferences and nutritional balance.

[0009] "Agreement" refers to the user's act of expressing approval of the system's meal suggestions.

[0010] "Affiliated restaurant" refers to a restaurant that cooperates with the system to provide meals ordered by users.

[0011] "Ordering" refers to the act of requesting a partner restaurant to prepare and deliver a specific meal menu item with the user's consent.

[0012] "Cooking completion notification" refers to information that notifies the server that the affiliated restaurant has completed cooking the ordered meal.

[0013] "Delivery service" refers to a logistics service for delivering ordered meals to users.

[0014] "Delivery status" refers to information about the progress of an ordered meal until it is delivered to the user.

[0015] "Nutritional balance" refers to a state in which essential nutrients are ingested in appropriate proportions for the purpose of maintaining or improving the user's health. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention is implemented by a system consisting of a user terminal, a server, affiliated restaurant terminals, and a delivery service. How each component works together will be described in detail below.

[0038] Operation via user terminal

[0039] Users access the system using their smartphones or tablet devices. First, they input their dietary concerns, such as "What should I eat today?" into the device. The user's device then sends this input to the server, which then imports the user's dietary concerns into the system.

[0040] Server processing

[0041] The server first analyzes the inquiry received from the user. Based on the user ID, the server retrieves the user's past eating history and preferences from a database. For example, if the user has a history of liking "healthy meals," the server generates meal suggestions based on that information.

[0042] The server then creates meal suggestions that take into account the user's preferences and nutritional balance. These suggestions are automatically generated by a meal suggestion algorithm, which selects the optimal meal menu. The results are then sent to the user's device and presented to them.

[0043] User Consent and Order Notification

[0044] If the user is satisfied with the meal suggestions, they agree to the suggestions. This agreement is sent from the user's terminal to the server. The server receives this agreement and notifies the affiliated restaurant of the meal order. Specifically, the order details are sent to the affiliated restaurant's terminal and confirmed by the restaurant.

[0045] Cooking and notification by partner restaurants

[0046] The partner restaurant starts cooking the meal based on the order details received from the server. When cooking is complete, the restaurant terminal sends a cooking completion notification to the server, which lets the server know that the order is ready.

[0047] Delivery arrangements and notifications

[0048] After receiving the notification that the food is ready, the server sends a delivery instruction to the partner delivery service. The delivery service then departs to deliver the ordered meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time, allowing the user to know the current status of their order.

[0049] Notifying the user of delivery completion

[0050] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0051] Specific examples

[0052] As a concrete example, consider the case where a user asks "What should I eat today?" and the server suggests a "warm pork soup and rice set" based on past orders. If the user agrees to this suggestion, the order is sent to a partner restaurant, and the delivery service delivers the meal to the user. The user can wait with peace of mind as they are notified of the delivery status, and finally, they receive a notification that the meal has arrived safely and that delivery has been completed.

[0053] In this way, the present invention provides a system that allows users to easily select, order, and receive nutritionally balanced meals at home.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] On the user terminal, the user inputs "What should I eat today?" The terminal sends this input to the server.

[0057] Step 2:

[0058] The server analyzes the question received from the user and retrieves the user's past eating history and preferences from the database using the user ID.

[0059] Step 3:

[0060] The server generates meal suggestions based on the acquired information and executes a meal suggestion algorithm that takes into account the user's preferences and nutritional balance.

[0061] Step 4:

[0062] The server sends the generated meal suggestions to the user's terminal, which displays the suggestions to the user.

[0063] Step 5:

[0064] If the user agrees with the proposal, the user terminal sends the consent information to the server. The user can also add more specific requests.

[0065] Step 6:

[0066] The server receives the user's consent and notifies the affiliated restaurant of the meal order. The restaurant terminal receives and confirms the order details.

[0067] Step 7:

[0068] The partner restaurant will begin cooking the meal based on the received order. After the cooking is complete, the restaurant terminal will send a cooking completion notification to the server.

[0069] Step 8:

[0070] The server receives a notification that the food is ready and sends a delivery instruction to a partner delivery service, which then delivers the meal from the restaurant to the user.

[0071] Step 9:

[0072] The server tracks the progress of the delivery and updates the information in real time to the user's device, allowing the user to check the delivery status.

[0073] Step 10:

[0074] The delivery person delivers the meal to the user's home. After the delivery is completed, the server receives a delivery completion notification and sends a delivery completion message to the user's terminal.

[0075] This processing step creates a system that allows users to easily select, order, and receive meals at home.

[0076] Example 1

[0077] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0078] Conventional systems make it difficult for users to choose their own meal plans or consider nutritional balance, and do not provide appropriate meal suggestions. Furthermore, there were issues with insufficient notification and tracking for users during the ordering process from partner restaurants and the subsequent delivery process, making it difficult for users to grasp the current situation. Furthermore, it was not possible to track the delivery progress in real time, and the system did not provide an environment where users could wait with peace of mind.

[0079] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0080] In this invention, the server includes means for receiving input from a user and analyzing the details of the meal-related consultation, means for generating appropriate meal suggestions based on the user's past history and preferences, means for presenting the meal suggestions to the user and receiving consent, means for notifying an affiliated restaurant of a meal order after receiving the user's consent, means for issuing delivery instructions to a delivery service based on a cooking completion notification received from the restaurant, means for tracking the delivery progress in real time and notifying the user, and means for notifying the user that delivery has been completed. This allows users to easily select nutritionally balanced meals and confidently keep track of the order and delivery status.

[0081] "User" refers to an individual who uses this system to consult about meals and receive meal suggestions.

[0082] "Input" refers to the act of a user sending dietary consultation details to the system using a smartphone or tablet device.

[0083] "Analysis" refers to the process by which the server understands the user's input based on information in the database and generates appropriate meal suggestions.

[0084] "Past history" refers to data on the user's previous selections, meal details, and order history.

[0085] "Preferences" refers to data that indicates the user's preferences for ingredients and dishes.

[0086] "Meal suggestions" refers to appropriate meal menus generated by the server based on the user's past history and preferences.

[0087] "Agreement" refers to the user's act of approving the meal menu proposed by the server.

[0088] "Affiliated restaurant" refers to a restaurant that participates in the system and accepts and prepares orders from users.

[0089] "Cooking Completion Notification" refers to information that notifies the server that an affiliated restaurant has completed cooking the ordered meal.

[0090] "Delivery service" refers to a service that delivers meals ordered from affiliated restaurants to users.

[0091] "Delivery Progress" refers to information that tracks the progress of an ordered meal in real time as the delivery service delivers it to you.

[0092] "Delivery completion notification" refers to information sent to the server after the delivery service has delivered the meal to the user's home.

[0093] The present invention is implemented by a system comprising a user terminal, a server, terminals of affiliated restaurants, and a delivery service. The specific operation of the system will be described in detail below.

[0094] First, the user accesses the system using their smartphone or tablet. The user enters "What should I eat today?" and this input data is sent from the user's device to the server. In this case, a dedicated application must be installed on the user's device.

[0095] The server has software for analyzing the inquiries received from the user. Specifically, the server retrieves past dietary history and preferences from a database based on the user ID. For example, the database uses MySQL (registered trademark), and the analysis can use Python programs and natural language processing algorithms. If the user has a history of preferring "healthy meals," the server can generate meal suggestions based on that information.

[0096] The server then generates meal suggestions that take into account the user's nutritional balance. These suggestions are automatically created by a meal suggestion algorithm. For example, a generative AI model may be used to select the optimal meal menu based on the user's past dietary data and current health status. The results are then sent to the user's device and presented to them.

[0097] If the user is satisfied with the meal suggestions, they agree to the suggestions. This consent information is sent from the user's terminal to the server. The server receives the consent and notifies the affiliated restaurant of the meal order. Specifically, the order details are sent to the affiliated restaurant's terminal, where they are confirmed. At this stage, the affiliated restaurant's terminal also needs to be connected to the Internet.

[0098] The affiliated restaurant begins cooking the ordered meal based on the order details received from the server. Once cooking is complete, the restaurant terminal sends a cooking completion notification to the server, which lets the server know that the order is ready. After receiving the cooking completion notification, the server issues delivery instructions to the affiliated delivery service. The delivery service then departs to deliver the ordered meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time.

[0099] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0100] As a concrete example, consider the case where a user asks, "What shall I eat today?" The server may suggest a "hot pork soup and rice set" based on past history. If the user agrees to this suggestion, an order for this meal is sent to a partner restaurant. After that, the meal is cooked and delivered to the user by a delivery service. The user can wait with peace of mind as they are notified of the delivery status, and eventually the meal arrives safely and they receive a notification that the delivery has been completed.

[0101] Examples of prompts to input to a generative AI model include:

[0102] "When a user asks, 'What should I eat today?', please explain the system that suggests the best meal based on their past eating history and preferences, orders that meal from a partner restaurant, and notifies them of the delivery status in real time."

[0103] In this way, the present invention provides a system that allows users to easily select, order, and receive nutritionally balanced meals at home.

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1:

[0106] The user uses their smartphone or tablet to type, "What should I eat today?"

[0107] Input: User's dietary consultation.

[0108] Output: Input data sent from the user device to the server.

[0109] Specific operation: The user launches the dedicated application, enters "What should I eat today?" in the input field, and taps the send button. The user device sends this input data to the server.

[0110] Step 2:

[0111] The server analyzes the consultation content received from the user.

[0112] Input: User's consultation content, user ID.

[0113] Output: Analysis results, user's past eating history and preferences.

[0114] Specific operation: The server retrieves past meal history and preferences from a database based on the user ID. For example, the database uses MySQL, and the analysis is performed using Python programs and natural language processing algorithms.

[0115] Step 3:

[0116] The server generates meal suggestions that take into account the user's nutritional balance.

[0117] Input: User's past diet history, preference data, and nutritional balance information.

[0118] Output: Meal suggestions.

[0119] Specific operation: The server uses the generative AI model to generate an optimal meal menu that takes into account the user's past dietary data and nutritional balance. The results are sent to the user's device.

[0120] Step 4:

[0121] The user checks the meal proposal and, if he / she agrees, sends the consent information to the server.

[0122] Input: Meal suggestions from the server.

[0123] Output: Sending user consent information.

[0124] Specific operation: The user checks the proposal on the device and taps the "Agree" button. The user device then sends the consent information to the server.

[0125] Step 5:

[0126] The server receives the user's consent and notifies the affiliated restaurant of the meal order.

[0127] Input: User consent information.

[0128] Output: Order notification to partner restaurant.

[0129] Specific operation: The server receives the user's consent, generates and sends order information to the terminal of the affiliated restaurant.

[0130] Step 6:

[0131] The affiliated restaurant starts cooking based on the order details received from the server and sends a cooking completion notification to the server.

[0132] Input: Order information from the server.

[0133] Output: Cooking completion notification.

[0134] Specific operation: The restaurant confirms the order and starts cooking. When cooking is complete, the restaurant terminal sends a cooking completion notification to the server.

[0135] Step 7:

[0136] The server receives the cooking completion notification and issues delivery instructions to the partner delivery service.

[0137] Input: Cooking complete notification.

[0138] Output: Delivery instructions, delivery progress.

[0139] Specific operation: The server receives the cooking completion notification and generates a delivery instruction for the delivery service. The delivery service leaves the restaurant and heads to the user's location. The server tracks the delivery progress and notifies the user of the delivery status in real time.

[0140] Step 8:

[0141] The delivery person delivers the meal to the user's home and sends a completion notification to the server.

[0142] Input: Delivery completion notification.

[0143] Output: Delivery success message to the user.

[0144] Specific operation: After the delivery person delivers the meal to the user's home, they send a completion notification to the server. The server receives the completion notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0145] (Application example 1)

[0146] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0147] Conventional meal recommendation systems have had difficulty proposing appropriate meal menus that take into account individual user preferences and nutritional balance, and have also had issues with the lack of smooth ordering and delivery management based on such menus, making it difficult for users to obtain healthy, balanced meals easily and quickly.

[0148] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0149] In this invention, the server includes means for receiving input from a user and analyzing the details of the dietary consultation, means for generating appropriate dietary suggestions based on the user's past history and preferences, means for presenting the dietary suggestions to the user and receiving consent, means for generating dietary suggestions that take into account the user's nutritional balance using a generative AI model, and means for querying the generative AI model using prompt sentences. This enables appropriate dietary suggestions that take into account the user's preferences and nutritional balance, and realizes smooth ordering and delivery management based on the suggestions.

[0150] "Input from the user" refers to information regarding meal consultations and orders made by the user using their own terminal.

[0151] "Diet-related consultation content" is information including questions and requests from the user regarding what to eat.

[0152] "User's past history" is data relating to meals the user has had and menu items they have ordered.

[0153] "Preferences" is information indicating the ingredients, types of dishes, and seasonings that the user particularly likes.

[0154] "Meal suggestions" are meal menus that are suggested taking into consideration the user's preferences, past history, and nutritional balance.

[0155] The "means for receiving consent" is a function for receiving an operation by the user to consent to the proposed meal menu and reflecting that in the system.

[0156] An "affiliated restaurant" is a restaurant that is affiliated with this system and provides meals based on orders from users.

[0157] The "cooking completion notification" is a notification to the server that the affiliated restaurant has completed cooking the specified meal.

[0158] A "delivery service" is a service that delivers meals prepared by affiliated restaurants to users.

[0159] "Delivery status" is information indicating the progress of the ordered meal until it is delivered to the user.

[0160] A "generative AI model" is an artificial intelligence model that analyzes user input and past history to make optimal meal suggestions.

[0161] A "prompt sentence" is a sentence used to query a generative AI model, and is a sentence that gives the model specific instructions or questions.

[0162] As an embodiment of the present invention, a system is constructed that includes a user terminal, a server, terminals of affiliated restaurants, and a delivery service. How this system operates will be described below.

[0163] Hardware and Software

[0164] The system is implemented using the following hardware and software:

[0165] Hardware: Smartphones, servers, partner restaurant terminals, delivery staff terminals

[0166] Software: Mobile app (iOS / ANDROID (registered trademark)), server side (Node.js, Python), database (PostgreSQL), generative AI model (TENSORFLOW (registered trademark), PyTorch)

[0167] User Input and Server Processing

[0168] When a user types "What should I eat?" via a smartphone application, the information is sent to a server. The server analyzes the input and generates optimal meal suggestions based on the user's past eating history and preferences. This is done using a generative AI model. This model analyzes the input data and makes suggestions after taking into account the user's preferences and nutritional balance.

[0169] An example of a prompt for the generative AI model is a text prompt such as, "Please suggest a nutritionally balanced meal menu based on user ID: 1234's past eating history and their question about what they want to eat today."

[0170] Meal suggestions and user consent

[0171] The generated meal suggestions are displayed on the user's smartphone. If the user is satisfied with the suggestions, they send their consent to the server via the application. Upon receiving this consent, the server automatically notifies the partner restaurant of the meal order. The restaurant then begins cooking based on the order.

[0172] Cooking completion notification and delivery arrangement

[0173] When the restaurant finishes cooking, a completion notification is sent from the restaurant terminal to the server. The server receives this notification and issues a delivery instruction to an affiliated delivery service. The delivery service then delivers the ordered meal from the restaurant to the user.

[0174] Delivery status notification and delivery completion

[0175] The delivery progress is tracked in real time by the server and notified to the user, allowing the user to understand the current status of their order. When the delivery person successfully delivers the meal to the user, a delivery completion notification is sent to the server, and finally a delivery completion message is displayed on the user's smartphone.

[0176] Specific examples

[0177] As a concrete example, when a user types "What should I eat today?" into a smartphone app, the generative AI model analyzes the user's past eating history and suggests a "warm pork soup and rice set." If the user agrees to this suggestion, the order is automatically sent to a partner restaurant, and once cooking is complete, instructions are sent to the delivery service. The user is notified of the delivery status in real time, and is eventually notified that delivery is complete, allowing them to receive their meal with peace of mind.

[0178] As described above, this invention is a system that makes meal suggestions based on the user's preferences and nutritional balance, automates the entire process from ordering to delivery, and smoothly manages it.

[0179] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0180] Step 1:

[0181] The user starts the smartphone application and inputs the question, "What should we eat?" The input data is sent from the smartphone to the server. Specifically, the user ID and the question are sent as data to the server.

[0182] Step 2:

[0183] The server analyzes the input received from the user. The server extracts keywords from the received consultation content and retrieves the corresponding user's past eating history and preferences from the database. Each piece of data is searched using the user ID as a key.

[0184] Step 3:

[0185] The server sends a prompt to the generative AI model based on the extracted keywords and past history data. An example of a prompt might be, "Please suggest a nutritionally balanced meal menu based on user ID: 1234's past meal history and what they want to eat today."

[0186] Step 4:

[0187] A generative AI model analyzes the prompt and generates appropriate meal suggestions. This AI model was built using TensorFlow and PyTorch, and suggests menu items while taking into account the user's nutritional balance. The generated meal suggestions are returned to the server as data including specific menu names and details.

[0188] Step 5:

[0189] The server receives the meal suggestions returned by the generative AI model and displays them on the user's smartphone. The user then considers the displayed meal suggestions and sends their agreement or disagreement to the server via the application. Details of the suggestions, including nutritional information, are also displayed here.

[0190] Step 6:

[0191] If the user agrees to the meal suggestion, the consent data is sent to the server. The server then notifies the partner restaurant of the meal order based on the consent data. Specifically, the order details, user ID, delivery address information, etc. are sent as data to the restaurant terminal.

[0192] Step 7:

[0193] The partner restaurant will start cooking the meal based on the order data received from the server. When cooking is complete, the restaurant terminal will send a cooking completion notification to the server. This notification will include the order ID, cooking completion time, etc.

[0194] Step 8:

[0195] After the server receives the cooking completion notification, it issues a delivery instruction to the partner delivery service. The delivery service then arranges for the meal to be delivered from the restaurant to the user and sends a delivery start notification to the server, which includes information about the delivery person and the estimated delivery time.

[0196] Step 9:

[0197] The server receives a delivery start notification from the delivery service and tracks the delivery status in real time. The server then notifies the user of the delivery progress via their smartphone app, allowing the user to check the current delivery status.

[0198] Step 10:

[0199] When the delivery person delivers the meal to the user, a delivery completion notification is sent from the delivery person's terminal to the server. The server receives the delivery completion notification and displays a delivery completion message on the user's smartphone. This allows the user to confirm that the ordered meal has arrived safely.

[0200] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0201] This invention is implemented by combining an emotion engine with a system consisting of a user terminal, a server, affiliated restaurant terminals, and a delivery service. How each component works together will be described in detail below.

[0202] Operation via user terminal

[0203] Users access the system using their smartphone or tablet device. First, they input their dietary concerns, such as "What should I eat today?" into the device. At this time, the user can also input their emotions (such as satisfaction or fatigue). The user device sends this input to the server, and the user's dietary concerns and emotional data are then imported into the system.

[0204] Server processing

[0205] The server first analyzes the question and emotion data received from the user and recognizes the user's emotion using an emotion engine. Based on the user ID, the server retrieves the user's past eating history and preferences from a database.

[0206] The server then generates meal suggestions based on the acquired information and emotional data. For example, if a user inputs "I'm feeling stressed," the server will suggest meals with a relaxing effect (e.g., herbal tea or a nutritious snack). The meal suggestion algorithm automatically generates an appropriate meal menu, taking into account the user's preferences, nutritional balance, and emotional level.

[0207] User Consent and Order Notification

[0208] The server sends the generated meal suggestions to the user's terminal. The user's terminal displays the suggestions to the user, and if the user is satisfied with the suggestions, it sends consent to the server. The user can also add more specific requests (e.g., "I want something sweeter").

[0209] Cooking and notification by partner restaurants

[0210] The server receives the user's consent and notifies the affiliated restaurant of the meal order. The restaurant terminal receives and confirms the order details. The affiliated restaurant begins cooking the meal based on the received order details. After cooking is complete, the restaurant terminal sends a cooking completion notification to the server.

[0211] Delivery arrangements and notifications

[0212] The server receives a notification that the food is ready and sends a delivery instruction to the partner delivery service. The delivery service then delivers the meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time, allowing the user to know the current status of their order.

[0213] Notifying the user of delivery completion

[0214] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0215] Specific examples

[0216] As a concrete example, consider the case where a user asks "What should I eat today?" and inputs "I'm feeling stressed." The server considers the user's preferences and nutritional balance from past history and suggests a "warm herbal tea and light salad set" to help relieve stress. If the user agrees to this suggestion, the order is sent to a partner restaurant, and the delivery service delivers the meal to the user. The user can wait with peace of mind as they are notified of the delivery status, and eventually the meal arrives safely and they receive a notification that the delivery has been completed.

[0217] In this way, the present invention realizes a system for meal suggestion and ordering that takes into account the user's emotions, allowing the user to easily select, order, and receive a nutritionally balanced meal at home, while also responding to their emotional state at any given time.

[0218] The processing flow will be explained below.

[0219] Step 1:

[0220] The user accesses the terminal and inputs the question "What should I eat today?" and their current feelings (e.g., "I'm tired" or "I'm stressed"). The terminal then sends this data to the server.

[0221] Step 2:

[0222] The server analyzes the questions and emotion data received from the user and uses an emotion engine to recognize the user's emotional state.

[0223] Step 3:

[0224] The server retrieves the user's past eating history and preferences from the database based on the user ID. For example, if the user has a history of preferring "healthy meals," that information is taken into account.

[0225] Step 4:

[0226] The server generates meal suggestions based on the emotional data, past meal history, and preferences. For example, if a user inputs the emotion "I feel stressed," the server will suggest meals that have a relaxing effect (e.g., warm herbal tea or a nutritious snack).

[0227] Step 5:

[0228] The server transmits the generated meal suggestions to the user terminal, which displays the meal suggestions to the user.

[0229] Step 6:

[0230] If the user agrees to the proposal, the user's device will send the consent information to the server. The user can also add more specific requests.

[0231] Step 7:

[0232] The server receives the user's consent and notifies the affiliated restaurant of the meal order. The restaurant terminal receives and confirms the order details.

[0233] Step 8:

[0234] The partner restaurant will begin cooking the meal based on the order details. Once cooking is complete, the restaurant terminal will send a cooking completion notification to the server.

[0235] Step 9:

[0236] The server receives the notification that the food is ready and sends a delivery instruction to the partner delivery service, which then prepares the food for delivery from the restaurant to the user.

[0237] Step 10:

[0238] The server tracks the delivery progress and sends the information to the user's device in real time, allowing the user to check the progress of their order.

[0239] Step 11:

[0240] The delivery person delivers the meal to the user's home. When the delivery is complete, the delivery person sends a completion notification to the server. The server receives the completion notification and sends a delivery completion message to the user's device.

[0241] In this way, users can conduct meal consultations, receive emotion-based suggestions, place orders, and finally have meals delivered to their homes.

[0242] Example 2

[0243] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0244] Conventional meal recommendation systems only provide suggestions based on a user's eating history and preferences, and do not consider the user's emotional state. This has resulted in problems such as users being unable to select meals that reflect their emotional state, and therefore unable to fully improve their satisfaction and health. Furthermore, there is an issue that the system does not adequately notify users of the delivery status of their meals in real time, making it difficult for users to grasp the delivery status.

[0245] The specific processing by the specific 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 receiving input from a user and analyzing the meal-related consultation content and emotional data; means for generating appropriate meal suggestions based on the analyzed emotional data and the user's past history and preferences; and means for presenting the generated meal suggestions to the user and receiving consent. This enables meal suggestions that take the user's emotional state into consideration. The server also includes means for notifying a partner restaurant of a meal order based on the meal suggestions, issuing delivery instructions to a delivery service based on a cooking completion notification received from the restaurant, means for notifying the user of the delivery status in real time, and means for notifying the user of delivery completion upon receiving a delivery completion notification. This allows the user to understand the delivery status in real time and wait with peace of mind for the entire process from ordering to delivery completion.

[0246] A "user" is someone who uses this system and makes meal suggestions and orders using a device such as a smartphone or tablet.

[0247] A "user terminal" is a device used by a user, such as a smartphone or tablet, that is used to access the system.

[0248] A "server" is a central computer that receives data from user terminals and performs analysis and processing, and is a major component that includes a database and analysis software.

[0249] "Emotion data" refers to information about the user's own emotions and moods entered by the user, and includes data about stress, satisfaction, and the like.

[0250] An "emotion engine" is software or algorithms for analyzing emotion data, a technology used to recognize a user's emotional state.

[0251] "Meal suggestions" are meal menus and recommendations generated by the server based on the user's emotional data, past history, and preferences.

[0252] "Affiliated restaurant" refers to a restaurant that has a contract with the system to provide meals to users, and is a business that receives orders and cooks the food.

[0253] A "delivery service" is a service company or business that delivers meals from affiliated restaurants to users, and includes a function to track the progress of deliveries.

[0254] An "order notification" is a communication to inform affiliated restaurants of the details of a meal order based on the user's consent information.

[0255] The "cooking completion notification" is a notification to inform the server that the affiliated restaurant has completed cooking the meal.

[0256] "Delivery instruction" is an operation performed by the server to instruct the delivery service to deliver the meal to the user after the server receives notification that the meal is ready.

[0257] "Delivery status" is information that indicates the progress and status of the meal from the start of cooking until it reaches the user.

[0258] The "delivery completion notification" is a notification sent to the server when the delivery person from the delivery service has delivered the meal to the user.

[0259] "User consent" refers to an operation by the user indicating their willingness to accept the proposed meal menu.

[0260] An "additional request" is when a user inputs more specific requests or wishes for a meal suggestion.

[0261] MODE FOR CARRYING OUT THE INVENTION

[0262] This invention combines a user terminal, a server, affiliated restaurant terminals, and a delivery service to realize a meal recommendation system that takes into account the user's emotions.

[0263] Hardware and Software Used

[0264] This system uses the following hardware and software:

[0265] User devices: iOS and Android smartphones and tablet devices

[0266] Dedicated application software: FoodMood app

[0267] Server: High-performance cloud service (e.g., AWS or Google Cloud)

[0268] Database software: MySQL or PostgreSQL

[0269] Emotion engine: IBM Watson(R) Emotion Analysis

[0270] Machine Learning Model: Diet Recommendation Algorithm in Python

[0271] Partner restaurant terminal: POS system

[0272] Delivery services: Delivery systems such as Uber Eats and DoorDash

[0273] System Description

[0274] User device operation

[0275] Users access a dedicated app using their smartphone or tablet. Through the application interface, they input their dietary concerns, such as "What should I eat today?", along with their emotions (e.g., feeling stressed or tired). This allows users to send their dietary concerns and emotional data to the system.

[0276] Server Processing

[0277] The server receives the data sent by the user. It analyzes the received data using an emotion engine (e.g., IBM Watson Emotion Analysis) to recognize the user's emotional state. It then retrieves the user's past eating history and preference data from a database. It then uses a meal recommendation algorithm (e.g., a Python machine learning model) to generate optimal meal recommendations based on the emotional and historical data.

[0278] Presenting proposals and obtaining consent

[0279] The generated meal suggestions are sent to the user's terminal via the server again and presented to the user. The user checks the suggestions on the application screen and either agrees or enters a specific request (e.g., "I want something more sweet"). This information is then returned to the server.

[0280] Order notification to partner restaurants

[0281] The server sends the order details to the partner restaurant based on the received consent information and additional requests. The partner restaurant's terminal (e.g., POS system) receives the order and begins cooking. Once cooking is complete, the restaurant sends a cooking completion notification to the server.

[0282] Delivery arrangements and notifications

[0283] After receiving the cooking completion notification, the server issues a delivery instruction to the partner delivery service. The delivery service picks up the meal from the restaurant and begins delivering it to the user. The delivery progress is tracked in real time by the server and notified to the user's device. This allows the user to know the status of their order in real time.

[0284] Delivery completion notification

[0285] Finally, when the delivery service delivers the meal to the user's home, a completion notification is sent to the server. The server receives this notification and sends a delivery completion message to the user's terminal, allowing the user to confirm that the meal they ordered has arrived safely.

[0286] Examples of concrete examples and prompts

[0287] For example, suppose a user asks "What should I eat today?" and inputs "I'm feeling stressed." If the server knows from the user's past eating history that "I like sweets," it will suggest "warm herbal tea, a light salad set, and chocolate cake for dessert" based on the emotion engine and food suggestion algorithm. The user agrees with this suggestion and makes an additional request, saying "I'd like something sweeter." The server then notifies partner restaurants and arranges for cooking and delivery.

[0288] Example prompts for generative AI models

[0289] Below are some example prompts to input to a generative AI model:

[0290] System configuration: user terminal, server, partner restaurant terminal, delivery service, emotion engine. When a user inputs "What should I eat today?" and then "I'm feeling stressed," the system takes into account the user's past eating history and preferences to suggest meals that will help relieve stress. If the user agrees to the suggestions, an order is placed, cooking begins at the partner restaurant, and the meal is delivered to the user by the delivery service. Delivery progress is notified in real time, and a final delivery completion notification is sent.

[0291] This invention not only enables meal suggestions based on the user's emotions, but also provides a system that provides users with a sense of security and satisfaction by including real-time tracking and notifications of delivery status.

[0292] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0293] Step 1:

[0294] Users access a dedicated application using their smartphone or tablet. On the application's input screen, they enter a question such as "What should I eat today?" and their feelings (e.g., "I'm feeling stressed"). This input is then sent from the user's device to the server.

[0295] Input: User question and emotion data

[0296] Output: Data packets sent from the user device to the server

[0297] Step 2:

[0298] The server analyzes the data packets received from the user device and uses an emotion engine (e.g., IBM Watson Emotion Analysis) to recognize the user's emotional state. In parallel, it retrieves past meal history and preference data from a database based on the user ID.

[0299] Input: User question and emotion data

[0300] Output: User's emotional state data and past history data

[0301] Step 3:

[0302] The server generates meal suggestions using an AI algorithm (e.g., a machine learning model using Python) based on the results of the sentiment analysis and past meal history. If the emotional state is "stressed," the server suggests a relaxing "herbal tea and light salad set."

[0303] Input: Emotional state data, past history data

[0304] Output: Meal suggestion data (e.g., "Herbal tea and light salad set")

[0305] Step 4:

[0306] The server sends the generated meal suggestions to the user's device, which then displays the suggestions on the application screen.

[0307] Input: Meal suggestion data

[0308] Output: Meal suggestions displayed on the user's device

[0309] Step 5:

[0310] If the user agrees with the suggestions, they can enter their consent into the application. They can also add specific requests (e.g., "I want more sweets.") This consent information and additional requests are sent from the user's device to the server.

[0311] Input: User consent information and additional requests

[0312] Output: Consent information and additional requests sent to the server

[0313] Step 6:

[0314] The server receives the user's consent information and additional request, and notifies the affiliated restaurant of the order details. The affiliated restaurant's terminal receives and confirms the order.

[0315] Input: User consent information and additional requests

[0316] Output: Order notification to partner restaurant

[0317] Step 7:

[0318] The partner restaurant will start cooking based on the order details. Once cooking is complete, the restaurant terminal will send a cooking completion notification to the server.

[0319] Input: Restaurant cooking instructions

[0320] Output: Notification to server that cooking is complete

[0321] Step 8:

[0322] The server receives a notification that the food is ready and sends a delivery instruction to the partner delivery service. A delivery request is automatically sent to the delivery service's system (e.g., Uber Eats or DoorDash).

[0323] Input: Cooking complete notification

[0324] Output: Delivery instructions to the delivery service

[0325] Step 9:

[0326] The delivery service receives the meal from the restaurant and delivers it to the user's address. The delivery progress is sent to the server in real time, and the server transmits the information to the user's terminal.

[0327] Input: Restaurant pickup information

[0328] Output: Delivery progress notification to user terminal

[0329] Step 10:

[0330] When the delivery person has delivered the meal to the user's home, they send a completion notification to the server, which receives this notification and sends a delivery completion message to the user's terminal.

[0331] Input: Delivery completion notification

[0332] Output: Delivery completion message to user terminal

[0333] In this way, the entire process from user input to meal suggestions, cooking, and delivery is carried out through a series of steps, allowing users to easily suggest and order meals that suit their mood at the time and have them delivered to their home.

[0334] (Application example 2)

[0335] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0336] In modern society, many people live with emotions such as stress and fatigue, and healthy and satisfying meal choices are needed to address these feelings. However, conventional meal recommendation systems have difficulty taking users' emotions into account, resulting in an inability to fully meet users' needs. Furthermore, there are limited means to grasp the status of a user's ordered meal in real time. Therefore, there is a need for a method that can both recommend appropriate meals based on the user's emotions and preferences, and manage subsequent smooth ordering and delivery.

[0337] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving input from a user and analyzing meal-related consultation details and emotion data; means for generating appropriate meal suggestions based on the user's past history and preferences; and means for presenting meal suggestions to the user and receiving consent. This enables real-time generation of meal suggestions based on the user's emotions and increases user satisfaction through collaboration with affiliated restaurants. The server also includes means for notifying affiliated restaurants of meal orders, means for issuing delivery instructions to a delivery service based on cooking completion notifications received from affiliated restaurants, means for notifying the user of delivery status, and means incorporating a generative AI model that uses an emotion engine to generate meal suggestions based on the user's emotions. This enables more personalized meal suggestions based on emotion data and smooth delivery management.

[0338] "User input" refers to the recording of diet-related consultation details and emotional data that users make using their smartphones or tablet devices.

[0339] "Diet-related consultation content and emotion data" is information about emotions such as stress and fatigue felt by the user, and questions and requests about diet based on those emotions.

[0340] "Appropriate meal suggestions" refer to meal menu suggestions that suit the user, generated based on information such as the user's past eating history, preferences, and emotional data.

[0341] "Means for generating meal suggestions" refers to algorithms or functions that use a user's historical and emotional data to recommend optimal meals.

[0342] An "emotion engine" is software or a system that recognizes a user's emotions and reacts accordingly.

[0343] A "generative AI model" is an artificial intelligence model that automatically generates meal suggestions based on a user's emotions and preferences.

[0344] The "means for notifying partner restaurants of meal orders" refers to a system for transmitting the order details to partner restaurants with the user's consent.

[0345] The "means for issuing delivery instructions to a delivery service based on a cooking completion notification" is a function for issuing meal delivery instructions to a delivery service upon receiving a cooking completion notification from an affiliated store.

[0346] "Means for notifying users of delivery status" refers to systems or functions for notifying users of delivery progress in real time.

[0347] This invention is implemented by combining an emotion engine and a generative AI model with a system consisting of a user terminal, a server, a partner store terminal, and a delivery service. How each component works together is described in detail below.

[0348] Operation via user terminal

[0349] Users access the system using their smartphone or tablet device. First, they input their dietary concerns, such as "What should I eat today?" into the device. At this time, the user can also input their emotions (such as satisfaction or fatigue). The user device sends this input to the server, and the user's dietary concerns and emotional data are then imported into the system.

[0350] Server processing

[0351] The server first analyzes the question and emotional data received from the user and uses an emotional engine to recognize the user's emotions. Then, based on the user ID, it retrieves the user's past eating history and preference data from a database. Next, it uses a generative AI model to generate meal suggestions based on the retrieved information and emotional data. For example, if the user inputs "I feel stressed," it will suggest meals that have a relaxing effect (e.g., herbal tea or a nutritionally balanced snack). The generative AI model automatically generates an appropriate meal menu taking into account the user's preferences, nutritional balance, and emotional level.

[0352] User Consent and Order Notification

[0353] The server sends the generated meal suggestions to the user's terminal. The user's terminal displays the suggestions to the user, and if the user is satisfied with the suggestions, the user sends consent to the server. The user can also add more specific requests (e.g., "I want something sweeter").

[0354] Cooking and notification by partner stores

[0355] The server receives the user's consent and notifies the affiliated store of the meal order. The affiliated store's terminal receives and confirms the order details. The affiliated store begins cooking the meal based on the received order details. After cooking is complete, the store's terminal sends a cooking completion notification to the server.

[0356] Delivery arrangements and notifications

[0357] The server receives a notification that the food is ready and sends a delivery instruction to the partner delivery service. The delivery service then delivers the food from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time, allowing the user to know the status of their order.

[0358] Notifying the user of delivery completion

[0359] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0360] Specific examples

[0361] As a concrete example, consider the case where a user asks "What should I eat today?" and inputs "I'm feeling stressed." The server considers the user's preferences and nutritional balance from past history and suggests "warm herbal tea and a light salad set," which is useful for relieving stress. If the user agrees to this suggestion, the order is sent to the partner store, and the delivery service delivers the meal to the user. The user can wait with peace of mind as they are notified of the delivery status, and eventually the meal arrives safely and they receive a notification that the delivery has been completed.

[0362] Prompt Sentence Examples

[0363] "Provide optimal meal suggestions if the user is experiencing the following emotions:

[0364] Emotion: I'm stressed

[0365] Preferences: Based on past history, I like herbal tea and light snacks.

[0366] Request: I want something sweeter."

[0367] In this way, the present invention realizes a system for meal suggestion and ordering that takes into account the user's emotions, allowing the user to easily select, order, and receive a nutritionally balanced meal at home, while also responding to their emotional state at any given time.

[0368] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0369] Step 1:

[0370] Users access the system using a smartphone or tablet device and input their meal-related questions, such as "What should I eat today?", along with emotional data (e.g., stress, satisfaction, etc.). The input data includes the user ID, emotional state, and specific requests (e.g., "I want something more sweet"). This data is sent from the user device to the server.

[0371] Step 2:

[0372] The server analyzes the questions and emotional data received from the user. At this time, it uses an emotion engine to recognize data related to the user's emotions. The server then retrieves data on the user's past eating history and preferences from a database based on the user ID. The input is the user's dietary consultation details and emotional data, and the output is the user's past eating history and preference data.

[0373] Step 3:

[0374] The server uses a generative AI model to generate meal suggestions based on the emotion data recognized by the emotion engine and past meal history and preferences retrieved from the database. For example, if a user inputs "I'm feeling stressed," the server will suggest a relaxing "warm herbal tea and light salad set." The input is the user's emotion data and past history data, and the output is a meal suggestion menu.

[0375] Step 4:

[0376] The server sends the generated meal suggestions to the user's device, and the user confirms the suggestions. If the user agrees with the suggestions and adds a more specific request (e.g., "I want something sweeter"), the server sends that information to the server. The input is the meal suggestions and the user's agreement, and the output is order information including the user's optional requests.

[0377] Step 5:

[0378] The server receives the user's consent and request and notifies the affiliated store of the meal order. The affiliated store terminal receives and confirms the order details. The input is the user's order information, and the output is an order notification to the affiliated store.

[0379] Step 6:

[0380] The affiliated store starts cooking the meal based on the received order details, and once cooking is complete, it sends a cooking completion notification from the store terminal to the server. The input is the order details notified to the store, and the output is the cooking completion notification to the server.

[0381] Step 7:

[0382] The server receives the cooking completion notification and issues delivery instructions to the partner delivery service. The delivery service then delivers the meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time. The input is the cooking completion notification and delivery instruction information, and the output is tracking data of the delivery progress.

[0383] Step 8:

[0384] After the delivery person delivers the meal to the user's home, they send a delivery completion notification to the server. The server receives this notification and sends a delivery completion message to the user's terminal. The input is the delivery completion notification, and the output is the delivery completion message.

[0385] This processing flow enables a seamless series of operations, from meal suggestions based on the user's emotions and preferences to ordering and delivery.

[0386] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0387] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0388] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0389] [Second embodiment]

[0390] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0391] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0392] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0393] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0394] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0395] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0396] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0397] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0398] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0399] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0400] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0401] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0402] The present invention is implemented by a system consisting of a user terminal, a server, affiliated restaurant terminals, and a delivery service. How each component works together will be described in detail below.

[0403] Operation via user terminal

[0404] Users access the system using their smartphones or tablet devices. First, they input their dietary concerns, such as "What should I eat today?" into the device. The user's device then sends this input to the server, which then imports the user's dietary concerns into the system.

[0405] Server processing

[0406] The server first analyzes the inquiry received from the user. Based on the user ID, the server retrieves the user's past eating history and preferences from a database. For example, if the user has a history of liking "healthy meals," the server generates meal suggestions based on that information.

[0407] The server then creates meal suggestions that take into account the user's preferences and nutritional balance. These suggestions are automatically generated by a meal suggestion algorithm, which selects the optimal meal menu. The results are then sent to the user's device and presented to them.

[0408] User Consent and Order Notification

[0409] If the user is satisfied with the meal suggestions, they agree to the suggestions. This agreement is sent from the user's terminal to the server. The server receives this agreement and notifies the affiliated restaurant of the meal order. Specifically, the order details are sent to the affiliated restaurant's terminal and confirmed by the restaurant.

[0410] Cooking and notification by partner restaurants

[0411] The partner restaurant starts cooking the meal based on the order details received from the server. When cooking is complete, the restaurant terminal sends a cooking completion notification to the server, which lets the server know that the order is ready.

[0412] Delivery arrangements and notifications

[0413] After receiving the notification that the food is ready, the server sends a delivery instruction to the partner delivery service. The delivery service then departs to deliver the ordered meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time, allowing the user to know the current status of their order.

[0414] Notifying the user of delivery completion

[0415] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0416] Specific examples

[0417] As a concrete example, consider the case where a user asks "What should I eat today?" and the server suggests a "warm pork soup and rice set" based on past orders. If the user agrees to this suggestion, the order is sent to a partner restaurant, and the delivery service delivers the meal to the user. The user can wait with peace of mind as they are notified of the delivery status, and finally, they receive a notification that the meal has arrived safely and that delivery has been completed.

[0418] In this way, the present invention provides a system that allows users to easily select, order, and receive nutritionally balanced meals at home.

[0419] The processing flow will be explained below.

[0420] Step 1:

[0421] On the user terminal, the user inputs "What should I eat today?" The terminal sends this input to the server.

[0422] Step 2:

[0423] The server analyzes the question received from the user and retrieves the user's past eating history and preferences from the database using the user ID.

[0424] Step 3:

[0425] The server generates meal suggestions based on the acquired information and executes a meal suggestion algorithm that takes into account the user's preferences and nutritional balance.

[0426] Step 4:

[0427] The server sends the generated meal suggestions to the user's terminal, which displays the suggestions to the user.

[0428] Step 5:

[0429] If the user agrees with the proposal, the user terminal sends the consent information to the server. The user can also add more specific requests.

[0430] Step 6:

[0431] The server receives the user's consent and notifies the affiliated restaurant of the meal order. The restaurant terminal receives and confirms the order details.

[0432] Step 7:

[0433] The partner restaurant will begin cooking the meal based on the received order. After the cooking is complete, the restaurant terminal will send a cooking completion notification to the server.

[0434] Step 8:

[0435] The server receives a notification that the food is ready and sends a delivery instruction to a partner delivery service, which then delivers the meal from the restaurant to the user.

[0436] Step 9:

[0437] The server tracks the progress of the delivery and updates the information in real time to the user's device, allowing the user to check the delivery status.

[0438] Step 10:

[0439] The delivery person delivers the meal to the user's home. After the delivery is completed, the server receives a delivery completion notification and sends a delivery completion message to the user's terminal.

[0440] This processing step creates a system that allows users to easily select, order, and receive meals at home.

[0441] Example 1

[0442] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0443] Conventional systems make it difficult for users to choose their own meal plans or consider nutritional balance, and do not provide appropriate meal suggestions. Furthermore, there were issues with insufficient notification and tracking for users during the ordering process from partner restaurants and the subsequent delivery process, making it difficult for users to grasp the current situation. Furthermore, it was not possible to track the delivery progress in real time, and the system did not provide an environment where users could wait with peace of mind.

[0444] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0445] In this invention, the server includes means for receiving input from a user and analyzing the details of the meal-related consultation, means for generating appropriate meal suggestions based on the user's past history and preferences, means for presenting the meal suggestions to the user and receiving consent, means for notifying an affiliated restaurant of a meal order after receiving the user's consent, means for issuing delivery instructions to a delivery service based on a cooking completion notification received from the restaurant, means for tracking the delivery progress in real time and notifying the user, and means for notifying the user that delivery has been completed. This allows users to easily select nutritionally balanced meals and confidently keep track of the order and delivery status.

[0446] "User" refers to an individual who uses this system to consult about meals and receive meal suggestions.

[0447] "Input" refers to the act of a user sending dietary consultation details to the system using a smartphone or tablet device.

[0448] "Analysis" refers to the process by which the server understands the user's input based on information in the database and generates appropriate meal suggestions.

[0449] "Past history" refers to data on the user's previous selections, meal details, and order history.

[0450] "Preferences" refers to data that indicates the user's preferences for ingredients and dishes.

[0451] "Meal suggestions" refers to appropriate meal menus generated by the server based on the user's past history and preferences.

[0452] "Agreement" refers to the user's act of approving the meal menu proposed by the server.

[0453] "Affiliated restaurant" refers to a restaurant that participates in the system and accepts and prepares orders from users.

[0454] "Cooking Completion Notification" refers to information that notifies the server that an affiliated restaurant has completed cooking the ordered meal.

[0455] "Delivery service" refers to a service that delivers meals ordered from affiliated restaurants to users.

[0456] "Delivery Progress" refers to information that tracks the progress of an ordered meal in real time as the delivery service delivers it to you.

[0457] "Delivery completion notification" refers to information sent to the server after the delivery service has delivered the meal to the user's home.

[0458] The present invention is implemented by a system comprising a user terminal, a server, terminals of affiliated restaurants, and a delivery service. The specific operation of the system will be described in detail below.

[0459] First, the user accesses the system using their smartphone or tablet. The user enters "What should I eat today?" and this input data is sent from the user's device to the server. In this case, a dedicated application must be installed on the user's device.

[0460] The server has software for analyzing the inquiries received from users. Specifically, the server retrieves past dietary history and preferences from a database based on the user ID. For example, the database can use MySQL, and the analysis can use Python programs and natural language processing algorithms. If the user has a history of preferring "healthy meals," the server can generate meal suggestions based on that information.

[0461] The server then generates meal suggestions that take into account the user's nutritional balance. These suggestions are automatically created by a meal suggestion algorithm. For example, a generative AI model may be used to select the optimal meal menu based on the user's past dietary data and current health status. The results are then sent to the user's device and presented to them.

[0462] If the user is satisfied with the meal suggestions, they agree to the suggestions. This consent information is sent from the user's terminal to the server. The server receives the consent and notifies the affiliated restaurant of the meal order. Specifically, the order details are sent to the affiliated restaurant's terminal, where they are confirmed. At this stage, the affiliated restaurant's terminal also needs to be connected to the Internet.

[0463] The affiliated restaurant begins cooking the ordered meal based on the order details received from the server. Once cooking is complete, the restaurant terminal sends a cooking completion notification to the server, which lets the server know that the order is ready. After receiving the cooking completion notification, the server issues delivery instructions to the affiliated delivery service. The delivery service then departs to deliver the ordered meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time.

[0464] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0465] As a concrete example, consider the case where a user asks, "What shall I eat today?" The server may suggest a "hot pork soup and rice set" based on past history. If the user agrees to this suggestion, an order for this meal is sent to a partner restaurant. After that, the meal is cooked and delivered to the user by a delivery service. The user can wait with peace of mind as they are notified of the delivery status, and eventually the meal arrives safely and they receive a notification that the delivery has been completed.

[0466] Examples of prompts to input to a generative AI model include:

[0467] "When a user asks, 'What should I eat today?', please explain the system that suggests the best meal based on their past eating history and preferences, orders that meal from a partner restaurant, and notifies them of the delivery status in real time."

[0468] In this way, the present invention provides a system that allows users to easily select, order, and receive nutritionally balanced meals at home.

[0469] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0470] Step 1:

[0471] The user uses their smartphone or tablet to type, "What should I eat today?"

[0472] Input: User's dietary consultation.

[0473] Output: Input data sent from the user device to the server.

[0474] Specific operation: The user launches the dedicated application, enters "What should I eat today?" in the input field, and taps the send button. The user device sends this input data to the server.

[0475] Step 2:

[0476] The server analyzes the consultation content received from the user.

[0477] Input: User's consultation content, user ID.

[0478] Output: Analysis results, user's past eating history and preferences.

[0479] Specific operation: The server retrieves past meal history and preferences from a database based on the user ID. For example, the database uses MySQL, and the analysis is performed using Python programs and natural language processing algorithms.

[0480] Step 3:

[0481] The server generates meal suggestions that take into account the user's nutritional balance.

[0482] Input: User's past diet history, preference data, and nutritional balance information.

[0483] Output: Meal suggestions.

[0484] Specific operation: The server uses the generative AI model to generate an optimal meal menu that takes into account the user's past dietary data and nutritional balance. The results are sent to the user's device.

[0485] Step 4:

[0486] The user checks the meal proposal and, if he / she agrees, sends the consent information to the server.

[0487] Input: Meal suggestions from the server.

[0488] Output: Sending user consent information.

[0489] Specific operation: The user checks the proposal on the device and taps the "Agree" button. The user device then sends the consent information to the server.

[0490] Step 5:

[0491] The server receives the user's consent and notifies the affiliated restaurant of the meal order.

[0492] Input: User consent information.

[0493] Output: Order notification to partner restaurant.

[0494] Specific operation: The server receives the user's consent, generates and sends order information to the terminal of the affiliated restaurant.

[0495] Step 6:

[0496] The affiliated restaurant starts cooking based on the order details received from the server and sends a cooking completion notification to the server.

[0497] Input: Order information from the server.

[0498] Output: Cooking completion notification.

[0499] Specific operation: The restaurant confirms the order and starts cooking. When cooking is complete, the restaurant terminal sends a cooking completion notification to the server.

[0500] Step 7:

[0501] The server receives the cooking completion notification and issues delivery instructions to the partner delivery service.

[0502] Input: Cooking complete notification.

[0503] Output: Delivery instructions, delivery progress.

[0504] Specific operation: The server receives the cooking completion notification and generates a delivery instruction for the delivery service. The delivery service leaves the restaurant and heads to the user's location. The server tracks the delivery progress and notifies the user of the delivery status in real time.

[0505] Step 8:

[0506] The delivery person delivers the meal to the user's home and sends a completion notification to the server.

[0507] Input: Delivery completion notification.

[0508] Output: Delivery success message to the user.

[0509] Specific operation: After the delivery person delivers the meal to the user's home, they send a completion notification to the server. The server receives the completion notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0510] (Application example 1)

[0511] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0512] Conventional meal recommendation systems have had difficulty proposing appropriate meal menus that take into account individual user preferences and nutritional balance, and have also had issues with the lack of smooth ordering and delivery management based on such menus, making it difficult for users to obtain healthy, balanced meals easily and quickly.

[0513] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0514] In this invention, the server includes means for receiving input from a user and analyzing the details of the dietary consultation, means for generating appropriate dietary suggestions based on the user's past history and preferences, means for presenting the dietary suggestions to the user and receiving consent, means for generating dietary suggestions that take into account the user's nutritional balance using a generative AI model, and means for querying the generative AI model using prompt sentences. This enables appropriate dietary suggestions that take into account the user's preferences and nutritional balance, and realizes smooth ordering and delivery management based on the suggestions.

[0515] "Input from the user" refers to information regarding meal consultations and orders made by the user using their own terminal.

[0516] "Diet-related consultation content" is information including questions and requests from the user regarding what to eat.

[0517] "User's past history" is data relating to meals the user has had and menu items they have ordered.

[0518] "Preferences" is information indicating the ingredients, types of dishes, and seasonings that the user particularly likes.

[0519] "Meal suggestions" are meal menus that are suggested taking into consideration the user's preferences, past history, and nutritional balance.

[0520] The "means for receiving consent" is a function for receiving an operation by the user to consent to the proposed meal menu and reflecting that in the system.

[0521] An "affiliated restaurant" is a restaurant that is affiliated with this system and provides meals based on orders from users.

[0522] The "cooking completion notification" is a notification to the server that the affiliated restaurant has completed cooking the specified meal.

[0523] A "delivery service" is a service that delivers meals prepared by affiliated restaurants to users.

[0524] "Delivery status" is information indicating the progress of the ordered meal until it is delivered to the user.

[0525] A "generative AI model" is an artificial intelligence model that analyzes user input and past history to make optimal meal suggestions.

[0526] A "prompt sentence" is a sentence used to query a generative AI model, and is a sentence that gives the model specific instructions or questions.

[0527] As an embodiment of the present invention, a system is constructed that includes a user terminal, a server, terminals of affiliated restaurants, and a delivery service. How this system operates will be described below.

[0528] Hardware and Software

[0529] The system is implemented using the following hardware and software:

[0530] Hardware: Smartphones, servers, partner restaurant terminals, delivery staff terminals

[0531] Software: Mobile app (iOS / Android), server side (Node.js, Python), database (PostgreSQL), generative AI model (TensorFlow, PyTorch)

[0532] User Input and Server Processing

[0533] When a user types "What should I eat?" via a smartphone application, the information is sent to a server. The server analyzes the input and generates optimal meal suggestions based on the user's past eating history and preferences. This is done using a generative AI model. This model analyzes the input data and makes suggestions after taking into account the user's preferences and nutritional balance.

[0534] An example of a prompt for the generative AI model is a text prompt such as, "Please suggest a nutritionally balanced meal menu based on user ID: 1234's past eating history and their question about what they want to eat today."

[0535] Meal suggestions and user consent

[0536] The generated meal suggestions are displayed on the user's smartphone. If the user is satisfied with the suggestions, they send their consent to the server via the application. Upon receiving this consent, the server automatically notifies the partner restaurant of the meal order. The restaurant then begins cooking based on the order.

[0537] Cooking completion notification and delivery arrangement

[0538] When the restaurant finishes cooking, a completion notification is sent from the restaurant terminal to the server. The server receives this notification and issues a delivery instruction to an affiliated delivery service. The delivery service then delivers the ordered meal from the restaurant to the user.

[0539] Delivery status notification and delivery completion

[0540] The delivery progress is tracked in real time by the server and notified to the user, allowing the user to understand the current status of their order. When the delivery person successfully delivers the meal to the user, a delivery completion notification is sent to the server, and finally a delivery completion message is displayed on the user's smartphone.

[0541] Specific examples

[0542] As a concrete example, when a user types "What should I eat today?" into a smartphone app, the generative AI model analyzes the user's past eating history and suggests a "warm pork soup and rice set." If the user agrees to this suggestion, the order is automatically sent to a partner restaurant, and once cooking is complete, instructions are sent to the delivery service. The user is notified of the delivery status in real time, and is eventually notified that delivery is complete, allowing them to receive their meal with peace of mind.

[0543] As described above, this invention is a system that makes meal suggestions based on the user's preferences and nutritional balance, automates the entire process from ordering to delivery, and smoothly manages it.

[0544] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0545] Step 1:

[0546] The user starts the smartphone application and inputs the question, "What should we eat?" The input data is sent from the smartphone to the server. Specifically, the user ID and the question are sent as data to the server.

[0547] Step 2:

[0548] The server analyzes the input received from the user. The server extracts keywords from the received consultation content and retrieves the corresponding user's past eating history and preferences from the database. Each piece of data is searched using the user ID as a key.

[0549] Step 3:

[0550] The server sends a prompt to the generative AI model based on the extracted keywords and past history data. An example of a prompt might be, "Please suggest a nutritionally balanced meal menu based on user ID: 1234's past meal history and what they want to eat today."

[0551] Step 4:

[0552] A generative AI model analyzes the prompt and generates appropriate meal suggestions. This AI model was built using TensorFlow and PyTorch, and suggests menu items while taking into account the user's nutritional balance. The generated meal suggestions are returned to the server as data including specific menu names and details.

[0553] Step 5:

[0554] The server receives the meal suggestions returned by the generative AI model and displays them on the user's smartphone. The user then considers the displayed meal suggestions and sends their agreement or disagreement to the server via the application. Details of the suggestions, including nutritional information, are also displayed here.

[0555] Step 6:

[0556] If the user agrees to the meal suggestion, the consent data is sent to the server. The server then notifies the partner restaurant of the meal order based on the consent data. Specifically, the order details, user ID, delivery address information, etc. are sent as data to the restaurant terminal.

[0557] Step 7:

[0558] The partner restaurant will start cooking the meal based on the order data received from the server. When cooking is complete, the restaurant terminal will send a cooking completion notification to the server. This notification will include the order ID, cooking completion time, etc.

[0559] Step 8:

[0560] After the server receives the cooking completion notification, it issues a delivery instruction to the partner delivery service. The delivery service then arranges for the meal to be delivered from the restaurant to the user and sends a delivery start notification to the server, which includes information about the delivery person and the estimated delivery time.

[0561] Step 9:

[0562] The server receives a delivery start notification from the delivery service and tracks the delivery status in real time. The server then notifies the user of the delivery progress via their smartphone app, allowing the user to check the current delivery status.

[0563] Step 10:

[0564] When the delivery person delivers the meal to the user, a delivery completion notification is sent from the delivery person's terminal to the server. The server receives the delivery completion notification and displays a delivery completion message on the user's smartphone. This allows the user to confirm that the ordered meal has arrived safely.

[0565] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0566] This invention is implemented by combining an emotion engine with a system consisting of a user terminal, a server, affiliated restaurant terminals, and a delivery service. How each component works together will be described in detail below.

[0567] Operation via user terminal

[0568] Users access the system using their smartphone or tablet device. First, they input their dietary concerns, such as "What should I eat today?" into the device. At this time, the user can also input their emotions (such as satisfaction or fatigue). The user device sends this input to the server, and the user's dietary concerns and emotional data are then imported into the system.

[0569] Server processing

[0570] The server first analyzes the question and emotion data received from the user and recognizes the user's emotion using an emotion engine. Based on the user ID, the server retrieves the user's past eating history and preferences from a database.

[0571] The server then generates meal suggestions based on the acquired information and emotional data. For example, if a user inputs "I'm feeling stressed," the server will suggest meals with a relaxing effect (e.g., herbal tea or a nutritious snack). The meal suggestion algorithm automatically generates an appropriate meal menu, taking into account the user's preferences, nutritional balance, and emotional level.

[0572] User Consent and Order Notification

[0573] The server sends the generated meal suggestions to the user's terminal. The user's terminal displays the suggestions to the user, and if the user is satisfied with the suggestions, it sends consent to the server. The user can also add more specific requests (e.g., "I want something sweeter").

[0574] Cooking and notification by partner restaurants

[0575] The server receives the user's consent and notifies the affiliated restaurant of the meal order. The restaurant terminal receives and confirms the order details. The affiliated restaurant begins cooking the meal based on the received order details. After cooking is complete, the restaurant terminal sends a cooking completion notification to the server.

[0576] Delivery arrangements and notifications

[0577] The server receives a notification that the food is ready and sends a delivery instruction to the partner delivery service. The delivery service then delivers the meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time, allowing the user to know the current status of their order.

[0578] Notifying the user of delivery completion

[0579] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0580] Specific examples

[0581] As a concrete example, consider the case where a user asks "What should I eat today?" and inputs "I'm feeling stressed." The server considers the user's preferences and nutritional balance from past history and suggests a "warm herbal tea and light salad set" to help relieve stress. If the user agrees to this suggestion, the order is sent to a partner restaurant, and the delivery service delivers the meal to the user. The user can wait with peace of mind as they are notified of the delivery status, and eventually the meal arrives safely and they receive a notification that the delivery has been completed.

[0582] In this way, the present invention realizes a system for meal suggestion and ordering that takes into account the user's emotions, allowing the user to easily select, order, and receive a nutritionally balanced meal at home, while also responding to their emotional state at any given time.

[0583] The processing flow will be explained below.

[0584] Step 1:

[0585] The user accesses the terminal and inputs the question "What should I eat today?" and their current feelings (e.g., "I'm tired" or "I'm stressed"). The terminal then sends this data to the server.

[0586] Step 2:

[0587] The server analyzes the questions and emotion data received from the user and uses an emotion engine to recognize the user's emotional state.

[0588] Step 3:

[0589] The server retrieves the user's past eating history and preferences from the database based on the user ID. For example, if the user has a history of preferring "healthy meals," that information is taken into account.

[0590] Step 4:

[0591] The server generates meal suggestions based on the emotional data, past meal history, and preferences. For example, if a user inputs the emotion "I feel stressed," the server will suggest meals that have a relaxing effect (e.g., warm herbal tea or a nutritious snack).

[0592] Step 5:

[0593] The server transmits the generated meal suggestions to the user terminal, which displays the meal suggestions to the user.

[0594] Step 6:

[0595] If the user agrees to the proposal, the user's device will send the consent information to the server. The user can also add more specific requests.

[0596] Step 7:

[0597] The server receives the user's consent and notifies the affiliated restaurant of the meal order. The restaurant terminal receives and confirms the order details.

[0598] Step 8:

[0599] The partner restaurant will begin cooking the meal based on the order details. Once cooking is complete, the restaurant terminal will send a cooking completion notification to the server.

[0600] Step 9:

[0601] The server receives the notification that the food is ready and sends a delivery instruction to the partner delivery service, which then prepares the food for delivery from the restaurant to the user.

[0602] Step 10:

[0603] The server tracks the delivery progress and sends the information to the user's device in real time, allowing the user to check the progress of their order.

[0604] Step 11:

[0605] The delivery person delivers the meal to the user's home. When the delivery is complete, the delivery person sends a completion notification to the server. The server receives the completion notification and sends a delivery completion message to the user's device.

[0606] In this way, users can conduct meal consultations, receive emotion-based suggestions, place orders, and finally have meals delivered to their homes.

[0607] Example 2

[0608] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0609] Conventional meal recommendation systems only provide suggestions based on a user's eating history and preferences, and do not consider the user's emotional state. This has resulted in problems such as users being unable to select meals that reflect their emotional state, and therefore unable to fully improve their satisfaction and health. Furthermore, there is an issue that the system does not adequately notify users of the delivery status of their meals in real time, making it difficult for users to grasp the delivery status.

[0610] The specific processing by the specific 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 receiving input from a user and analyzing the meal-related consultation content and emotional data; means for generating appropriate meal suggestions based on the analyzed emotional data and the user's past history and preferences; and means for presenting the generated meal suggestions to the user and receiving consent. This enables meal suggestions that take the user's emotional state into consideration. The server also includes means for notifying a partner restaurant of a meal order based on the meal suggestions, issuing delivery instructions to a delivery service based on a cooking completion notification received from the restaurant, means for notifying the user of the delivery status in real time, and means for notifying the user of delivery completion upon receiving a delivery completion notification. This allows the user to understand the delivery status in real time and wait with peace of mind for the entire process from ordering to delivery completion.

[0611] A "user" is someone who uses this system and makes meal suggestions and orders using a device such as a smartphone or tablet.

[0612] A "user terminal" is a device used by a user, such as a smartphone or tablet, that is used to access the system.

[0613] A "server" is a central computer that receives data from user terminals and performs analysis and processing, and is a major component that includes a database and analysis software.

[0614] "Emotion data" refers to information about the user's own emotions and moods entered by the user, and includes data about stress, satisfaction, and the like.

[0615] An "emotion engine" is software or algorithms for analyzing emotion data, a technology used to recognize a user's emotional state.

[0616] "Meal suggestions" are meal menus and recommendations generated by the server based on the user's emotional data, past history, and preferences.

[0617] "Affiliated restaurant" refers to a restaurant that has a contract with the system to provide meals to users, and is a business that receives orders and cooks the food.

[0618] A "delivery service" is a service company or business that delivers meals from affiliated restaurants to users, and includes a function to track the progress of deliveries.

[0619] An "order notification" is a communication to inform affiliated restaurants of the details of a meal order based on the user's consent information.

[0620] The "cooking completion notification" is a notification to inform the server that the affiliated restaurant has completed cooking the meal.

[0621] "Delivery instruction" is an operation performed by the server to instruct the delivery service to deliver the meal to the user after the server receives notification that the meal is ready.

[0622] "Delivery status" is information that indicates the progress and status of the meal from the start of cooking until it reaches the user.

[0623] The "delivery completion notification" is a notification sent to the server when the delivery person from the delivery service has delivered the meal to the user.

[0624] "User consent" refers to an operation by the user indicating their willingness to accept the proposed meal menu.

[0625] An "additional request" is when a user inputs more specific requests or wishes for a meal suggestion.

[0626] MODE FOR CARRYING OUT THE INVENTION

[0627] This invention combines a user terminal, a server, affiliated restaurant terminals, and a delivery service to realize a meal recommendation system that takes into account the user's emotions.

[0628] Hardware and Software Used

[0629] This system uses the following hardware and software:

[0630] User devices: iOS and Android smartphones and tablet devices

[0631] Dedicated application software: FoodMood app

[0632] Server: High-performance cloud service (e.g. AWS or Google Cloud)

[0633] Database software: MySQL or PostgreSQL

[0634] Emotion engine: IBM Watson Emotion Analysis

[0635] Machine Learning Model: Diet Recommendation Algorithm in Python

[0636] Partner restaurant terminal: POS system

[0637] Delivery services: Delivery systems such as Uber Eats and DoorDash

[0638] System Description

[0639] User device operation

[0640] Users access a dedicated app using their smartphone or tablet. Through the application interface, they input their dietary concerns, such as "What should I eat today?", along with their emotions (e.g., feeling stressed or tired). This allows users to send their dietary concerns and emotional data to the system.

[0641] Server Processing

[0642] The server receives the data sent by the user. It analyzes the received data using an emotion engine (e.g., IBM Watson Emotion Analysis) to recognize the user's emotional state. It then retrieves the user's past eating history and preference data from a database. It then uses a meal recommendation algorithm (e.g., a Python machine learning model) to generate optimal meal recommendations based on the emotional and historical data.

[0643] Presenting proposals and obtaining consent

[0644] The generated meal suggestions are sent to the user's terminal via the server again and presented to the user. The user checks the suggestions on the application screen and either agrees or enters a specific request (e.g., "I want something more sweet"). This information is then returned to the server.

[0645] Order notification to partner restaurants

[0646] The server sends the order details to the partner restaurant based on the received consent information and additional requests. The partner restaurant's terminal (e.g., POS system) receives the order and begins cooking. Once cooking is complete, the restaurant sends a cooking completion notification to the server.

[0647] Delivery arrangements and notifications

[0648] After receiving the cooking completion notification, the server issues a delivery instruction to the partner delivery service. The delivery service picks up the meal from the restaurant and begins delivering it to the user. The delivery progress is tracked in real time by the server and notified to the user's device. This allows the user to know the status of their order in real time.

[0649] Delivery completion notification

[0650] Finally, when the delivery service delivers the meal to the user's home, a completion notification is sent to the server. The server receives this notification and sends a delivery completion message to the user's terminal, allowing the user to confirm that the meal they ordered has arrived safely.

[0651] Examples of concrete examples and prompts

[0652] For example, suppose a user asks "What should I eat today?" and inputs "I'm feeling stressed." If the server knows from the user's past eating history that "I like sweets," it will suggest "warm herbal tea, a light salad set, and chocolate cake for dessert" based on the emotion engine and food suggestion algorithm. The user agrees with this suggestion and makes an additional request, saying "I'd like something sweeter." The server then notifies partner restaurants and arranges for cooking and delivery.

[0653] Example prompts for generative AI models

[0654] Below are some example prompts to input to a generative AI model:

[0655] System configuration: user terminal, server, partner restaurant terminal, delivery service, emotion engine. When a user inputs "What should I eat today?" and then "I'm feeling stressed," the system takes into account the user's past eating history and preferences to suggest meals that will help relieve stress. If the user agrees to the suggestions, an order is placed, cooking begins at the partner restaurant, and the meal is delivered to the user by the delivery service. Delivery progress is notified in real time, and a final delivery completion notification is sent.

[0656] This invention not only enables meal suggestions based on the user's emotions, but also provides a system that provides users with a sense of security and satisfaction by including real-time tracking and notifications of delivery status.

[0657] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0658] Step 1:

[0659] Users access a dedicated application using their smartphone or tablet. On the application's input screen, they enter a question such as "What should I eat today?" and their feelings (e.g., "I'm feeling stressed"). This input is then sent from the user's device to the server.

[0660] Input: User question and emotion data

[0661] Output: Data packets sent from the user device to the server

[0662] Step 2:

[0663] The server analyzes the data packets received from the user device and uses an emotion engine (e.g., IBM Watson Emotion Analysis) to recognize the user's emotional state. In parallel, it retrieves past meal history and preference data from a database based on the user ID.

[0664] Input: User question and emotion data

[0665] Output: User's emotional state data and past history data

[0666] Step 3:

[0667] The server generates meal suggestions using an AI algorithm (e.g., a machine learning model using Python) based on the results of the sentiment analysis and past meal history. If the emotional state is "stressed," the server suggests a relaxing "herbal tea and light salad set."

[0668] Input: Emotional state data, past history data

[0669] Output: Meal suggestion data (e.g., "Herbal tea and light salad set")

[0670] Step 4:

[0671] The server sends the generated meal suggestions to the user's device, which then displays the suggestions on the application screen.

[0672] Input: Meal suggestion data

[0673] Output: Meal suggestions displayed on the user's device

[0674] Step 5:

[0675] If the user agrees with the suggestions, they can enter their consent into the application. They can also add specific requests (e.g., "I want more sweets.") This consent information and additional requests are sent from the user's device to the server.

[0676] Input: User consent information and additional requests

[0677] Output: Consent information and additional requests sent to the server

[0678] Step 6:

[0679] The server receives the user's consent information and additional request, and notifies the affiliated restaurant of the order details. The affiliated restaurant's terminal receives and confirms the order.

[0680] Input: User consent information and additional requests

[0681] Output: Order notification to partner restaurant

[0682] Step 7:

[0683] The partner restaurant will start cooking based on the order details. Once cooking is complete, the restaurant terminal will send a cooking completion notification to the server.

[0684] Input: Restaurant cooking instructions

[0685] Output: Notification to server that cooking is complete

[0686] Step 8:

[0687] The server receives a notification that the food is ready and sends a delivery instruction to the partner delivery service. A delivery request is automatically sent to the delivery service's system (e.g., Uber Eats or DoorDash).

[0688] Input: Cooking complete notification

[0689] Output: Delivery instructions to the delivery service

[0690] Step 9:

[0691] The delivery service receives the meal from the restaurant and delivers it to the user's address. The delivery progress is sent to the server in real time, and the server transmits the information to the user's terminal.

[0692] Input: Restaurant pickup information

[0693] Output: Delivery progress notification to user terminal

[0694] Step 10:

[0695] When the delivery person has delivered the meal to the user's home, they send a completion notification to the server, which receives this notification and sends a delivery completion message to the user's terminal.

[0696] Input: Delivery completion notification

[0697] Output: Delivery completion message to user terminal

[0698] In this way, the entire process from user input to meal suggestions, cooking, and delivery is carried out through a series of steps, allowing users to easily suggest and order meals that suit their mood at the time and have them delivered to their home.

[0699] (Application example 2)

[0700] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0701] In modern society, many people live with emotions such as stress and fatigue, and healthy and satisfying meal choices are needed to address these feelings. However, conventional meal recommendation systems have difficulty taking users' emotions into account, resulting in an inability to fully meet users' needs. Furthermore, there are limited means to grasp the status of a user's ordered meal in real time. Therefore, there is a need for a method that can both recommend appropriate meals based on the user's emotions and preferences, and manage subsequent smooth ordering and delivery.

[0702] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving input from a user and analyzing meal-related consultation details and emotion data; means for generating appropriate meal suggestions based on the user's past history and preferences; and means for presenting meal suggestions to the user and receiving consent. This enables real-time generation of meal suggestions based on the user's emotions and increases user satisfaction through collaboration with affiliated restaurants. The server also includes means for notifying affiliated restaurants of meal orders, means for issuing delivery instructions to a delivery service based on cooking completion notifications received from affiliated restaurants, means for notifying the user of delivery status, and means incorporating a generative AI model that uses an emotion engine to generate meal suggestions based on the user's emotions. This enables more personalized meal suggestions based on emotion data and smooth delivery management.

[0703] "User input" refers to the recording of diet-related consultation details and emotional data that users make using their smartphones or tablet devices.

[0704] "Diet-related consultation content and emotion data" is information about emotions such as stress and fatigue felt by the user, and questions and requests about diet based on those emotions.

[0705] "Appropriate meal suggestions" refer to meal menu suggestions that suit the user, generated based on information such as the user's past eating history, preferences, and emotional data.

[0706] "Means for generating meal suggestions" refers to algorithms or functions that use a user's historical and emotional data to recommend optimal meals.

[0707] An "emotion engine" is software or a system that recognizes a user's emotions and reacts accordingly.

[0708] A "generative AI model" is an artificial intelligence model that automatically generates meal suggestions based on a user's emotions and preferences.

[0709] The "means for notifying partner restaurants of meal orders" refers to a system for transmitting the order details to partner restaurants with the user's consent.

[0710] The "means for issuing delivery instructions to a delivery service based on a cooking completion notification" is a function for issuing meal delivery instructions to a delivery service upon receiving a cooking completion notification from an affiliated store.

[0711] "Means for notifying users of delivery status" refers to systems or functions for notifying users of delivery progress in real time.

[0712] This invention is implemented by combining an emotion engine and a generative AI model with a system consisting of a user terminal, a server, a partner store terminal, and a delivery service. How each component works together is described in detail below.

[0713] Operation via user terminal

[0714] Users access the system using their smartphone or tablet device. First, they input their dietary concerns, such as "What should I eat today?" into the device. At this time, the user can also input their emotions (such as satisfaction or fatigue). The user device sends this input to the server, and the user's dietary concerns and emotional data are then imported into the system.

[0715] Server processing

[0716] The server first analyzes the question and emotional data received from the user and uses an emotional engine to recognize the user's emotions. Then, based on the user ID, it retrieves the user's past eating history and preference data from a database. Next, it uses a generative AI model to generate meal suggestions based on the retrieved information and emotional data. For example, if the user inputs "I feel stressed," it will suggest meals that have a relaxing effect (e.g., herbal tea or a nutritionally balanced snack). The generative AI model automatically generates an appropriate meal menu taking into account the user's preferences, nutritional balance, and emotional level.

[0717] User Consent and Order Notification

[0718] The server sends the generated meal suggestions to the user's terminal. The user's terminal displays the suggestions to the user, and if the user is satisfied with the suggestions, the user sends consent to the server. The user can also add more specific requests (e.g., "I want something sweeter").

[0719] Cooking and notification by partner stores

[0720] The server receives the user's consent and notifies the affiliated store of the meal order. The affiliated store's terminal receives and confirms the order details. The affiliated store begins cooking the meal based on the received order details. After cooking is complete, the store's terminal sends a cooking completion notification to the server.

[0721] Delivery arrangements and notifications

[0722] The server receives a notification that the food is ready and sends a delivery instruction to the partner delivery service. The delivery service then delivers the food from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time, allowing the user to know the status of their order.

[0723] Notifying the user of delivery completion

[0724] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0725] Specific examples

[0726] As a concrete example, consider the case where a user asks "What should I eat today?" and inputs "I'm feeling stressed." The server considers the user's preferences and nutritional balance from past history and suggests "warm herbal tea and a light salad set," which is useful for relieving stress. If the user agrees to this suggestion, the order is sent to the partner store, and the delivery service delivers the meal to the user. The user can wait with peace of mind as they are notified of the delivery status, and eventually the meal arrives safely and they receive a notification that the delivery has been completed.

[0727] Prompt Sentence Examples

[0728] "Provide optimal meal suggestions if the user is experiencing the following emotions:

[0729] Emotion: I'm stressed

[0730] Preferences: Based on past history, I like herbal tea and light snacks.

[0731] Request: I want something sweeter."

[0732] In this way, the present invention realizes a system for meal suggestion and ordering that takes into account the user's emotions, allowing the user to easily select, order, and receive a nutritionally balanced meal at home, while also responding to their emotional state at any given time.

[0733] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0734] Step 1:

[0735] Users access the system using a smartphone or tablet device and input their meal-related questions, such as "What should I eat today?", along with emotional data (e.g., stress, satisfaction, etc.). The input data includes the user ID, emotional state, and specific requests (e.g., "I want something more sweet"). This data is sent from the user device to the server.

[0736] Step 2:

[0737] The server analyzes the questions and emotional data received from the user. At this time, it uses an emotion engine to recognize data related to the user's emotions. The server then retrieves data on the user's past eating history and preferences from a database based on the user ID. The input is the user's dietary consultation details and emotional data, and the output is the user's past eating history and preference data.

[0738] Step 3:

[0739] The server uses a generative AI model to generate meal suggestions based on the emotion data recognized by the emotion engine and past meal history and preferences retrieved from the database. For example, if a user inputs "I'm feeling stressed," the server will suggest a relaxing "warm herbal tea and light salad set." The input is the user's emotion data and past history data, and the output is a meal suggestion menu.

[0740] Step 4:

[0741] The server sends the generated meal suggestions to the user's device, and the user confirms the suggestions. If the user agrees with the suggestions and adds a more specific request (e.g., "I want something sweeter"), the server sends that information to the server. The input is the meal suggestions and the user's agreement, and the output is order information including the user's optional requests.

[0742] Step 5:

[0743] The server receives the user's consent and request and notifies the affiliated store of the meal order. The affiliated store terminal receives and confirms the order details. The input is the user's order information, and the output is an order notification to the affiliated store.

[0744] Step 6:

[0745] The affiliated store starts cooking the meal based on the received order details, and once cooking is complete, it sends a cooking completion notification from the store terminal to the server. The input is the order details notified to the store, and the output is the cooking completion notification to the server.

[0746] Step 7:

[0747] The server receives the cooking completion notification and issues delivery instructions to the partner delivery service. The delivery service then delivers the meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time. The input is the cooking completion notification and delivery instruction information, and the output is tracking data of the delivery progress.

[0748] Step 8:

[0749] After the delivery person delivers the meal to the user's home, they send a delivery completion notification to the server. The server receives this notification and sends a delivery completion message to the user's terminal. The input is the delivery completion notification, and the output is the delivery completion message.

[0750] This processing flow enables a seamless series of operations, from meal suggestions based on the user's emotions and preferences to ordering and delivery.

[0751] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0752] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0753] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0754] [Third embodiment]

[0755] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0756] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0757] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0758] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0759] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0760] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0761] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0762] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0763] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0764] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0765] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0766] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0767] The present invention is implemented by a system consisting of a user terminal, a server, affiliated restaurant terminals, and a delivery service. How each component works together will be described in detail below.

[0768] Operation via user terminal

[0769] Users access the system using their smartphones or tablet devices. First, they input their dietary concerns, such as "What should I eat today?" into the device. The user's device then sends this input to the server, which then imports the user's dietary concerns into the system.

[0770] Server processing

[0771] The server first analyzes the inquiry received from the user. Based on the user ID, the server retrieves the user's past eating history and preferences from a database. For example, if the user has a history of liking "healthy meals," the server generates meal suggestions based on that information.

[0772] The server then creates meal suggestions that take into account the user's preferences and nutritional balance. These suggestions are automatically generated by a meal suggestion algorithm, which selects the optimal meal menu. The results are then sent to the user's device and presented to them.

[0773] User Consent and Order Notification

[0774] If the user is satisfied with the meal suggestions, they agree to the suggestions. This agreement is sent from the user's terminal to the server. The server receives this agreement and notifies the affiliated restaurant of the meal order. Specifically, the order details are sent to the affiliated restaurant's terminal and confirmed by the restaurant.

[0775] Cooking and notification by partner restaurants

[0776] The partner restaurant starts cooking the meal based on the order details received from the server. When cooking is complete, the restaurant terminal sends a cooking completion notification to the server, which lets the server know that the order is ready.

[0777] Delivery arrangements and notifications

[0778] After receiving the notification that the food is ready, the server sends a delivery instruction to the partner delivery service. The delivery service then departs to deliver the ordered meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time, allowing the user to know the current status of their order.

[0779] Notifying the user of delivery completion

[0780] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0781] Specific examples

[0782] As a concrete example, consider the case where a user asks "What should I eat today?" and the server suggests a "warm pork soup and rice set" based on past orders. If the user agrees to this suggestion, the order is sent to a partner restaurant, and the delivery service delivers the meal to the user. The user can wait with peace of mind as they are notified of the delivery status, and finally, they receive a notification that the meal has arrived safely and that delivery has been completed.

[0783] In this way, the present invention provides a system that allows users to easily select, order, and receive nutritionally balanced meals at home.

[0784] The processing flow will be explained below.

[0785] Step 1:

[0786] On the user terminal, the user inputs "What should I eat today?" The terminal sends this input to the server.

[0787] Step 2:

[0788] The server analyzes the question received from the user and retrieves the user's past eating history and preferences from the database using the user ID.

[0789] Step 3:

[0790] The server generates meal suggestions based on the acquired information and executes a meal suggestion algorithm that takes into account the user's preferences and nutritional balance.

[0791] Step 4:

[0792] The server sends the generated meal suggestions to the user's terminal, which displays the suggestions to the user.

[0793] Step 5:

[0794] If the user agrees with the proposal, the user terminal sends the consent information to the server. The user can also add more specific requests.

[0795] Step 6:

[0796] The server receives the user's consent and notifies the affiliated restaurant of the meal order. The restaurant terminal receives and confirms the order details.

[0797] Step 7:

[0798] The partner restaurant will begin cooking the meal based on the received order. After the cooking is complete, the restaurant terminal will send a cooking completion notification to the server.

[0799] Step 8:

[0800] The server receives a notification that the food is ready and sends a delivery instruction to a partner delivery service, which then delivers the meal from the restaurant to the user.

[0801] Step 9:

[0802] The server tracks the progress of the delivery and updates the information in real time to the user's device, allowing the user to check the delivery status.

[0803] Step 10:

[0804] The delivery person delivers the meal to the user's home. After the delivery is completed, the server receives a delivery completion notification and sends a delivery completion message to the user's terminal.

[0805] This processing step creates a system that allows users to easily select, order, and receive meals at home.

[0806] Example 1

[0807] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0808] Conventional systems make it difficult for users to choose their own meal plans or consider nutritional balance, and do not provide appropriate meal suggestions. Furthermore, there were issues with insufficient notification and tracking for users during the ordering process from partner restaurants and the subsequent delivery process, making it difficult for users to grasp the current situation. Furthermore, it was not possible to track the delivery progress in real time, and the system did not provide an environment where users could wait with peace of mind.

[0809] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0810] In this invention, the server includes means for receiving input from a user and analyzing the details of the meal-related consultation, means for generating appropriate meal suggestions based on the user's past history and preferences, means for presenting the meal suggestions to the user and receiving consent, means for notifying an affiliated restaurant of a meal order after receiving the user's consent, means for issuing delivery instructions to a delivery service based on a cooking completion notification received from the restaurant, means for tracking the delivery progress in real time and notifying the user, and means for notifying the user that delivery has been completed. This allows users to easily select nutritionally balanced meals and confidently keep track of the order and delivery status.

[0811] "User" refers to an individual who uses this system to consult about meals and receive meal suggestions.

[0812] "Input" refers to the act of a user sending dietary consultation details to the system using a smartphone or tablet device.

[0813] "Analysis" refers to the process by which the server understands the user's input based on information in the database and generates appropriate meal suggestions.

[0814] "Past history" refers to data on the user's previous selections, meal details, and order history.

[0815] "Preferences" refers to data that indicates the user's preferences for ingredients and dishes.

[0816] "Meal suggestions" refers to appropriate meal menus generated by the server based on the user's past history and preferences.

[0817] "Agreement" refers to the user's act of approving the meal menu proposed by the server.

[0818] "Affiliated restaurant" refers to a restaurant that participates in the system and accepts and prepares orders from users.

[0819] "Cooking Completion Notification" refers to information that notifies the server that an affiliated restaurant has completed cooking the ordered meal.

[0820] "Delivery service" refers to a service that delivers meals ordered from affiliated restaurants to users.

[0821] "Delivery Progress" refers to information that tracks the progress of an ordered meal in real time as the delivery service delivers it to you.

[0822] "Delivery completion notification" refers to information sent to the server after the delivery service has delivered the meal to the user's home.

[0823] The present invention is implemented by a system comprising a user terminal, a server, terminals of affiliated restaurants, and a delivery service. The specific operation of the system will be described in detail below.

[0824] First, the user accesses the system using their smartphone or tablet. The user enters "What should I eat today?" and this input data is sent from the user's device to the server. In this case, a dedicated application must be installed on the user's device.

[0825] The server has software for analyzing the inquiries received from users. Specifically, the server retrieves past dietary history and preferences from a database based on the user ID. For example, the database can use MySQL, and the analysis can use Python programs and natural language processing algorithms. If the user has a history of preferring "healthy meals," the server can generate meal suggestions based on that information.

[0826] The server then generates meal suggestions that take into account the user's nutritional balance. These suggestions are automatically created by a meal suggestion algorithm. For example, a generative AI model may be used to select the optimal meal menu based on the user's past dietary data and current health status. The results are then sent to the user's device and presented to them.

[0827] If the user is satisfied with the meal suggestions, they agree to the suggestions. This consent information is sent from the user's terminal to the server. The server receives the consent and notifies the affiliated restaurant of the meal order. Specifically, the order details are sent to the affiliated restaurant's terminal, where they are confirmed. At this stage, the affiliated restaurant's terminal also needs to be connected to the Internet.

[0828] The affiliated restaurant begins cooking the ordered meal based on the order details received from the server. Once cooking is complete, the restaurant terminal sends a cooking completion notification to the server, which lets the server know that the order is ready. After receiving the cooking completion notification, the server issues delivery instructions to the affiliated delivery service. The delivery service then departs to deliver the ordered meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time.

[0829] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0830] As a concrete example, consider the case where a user asks, "What shall I eat today?" The server may suggest a "hot pork soup and rice set" based on past history. If the user agrees to this suggestion, an order for this meal is sent to a partner restaurant. After that, the meal is cooked and delivered to the user by a delivery service. The user can wait with peace of mind as they are notified of the delivery status, and eventually the meal arrives safely and they receive a notification that the delivery has been completed.

[0831] Examples of prompts to input to a generative AI model include:

[0832] "When a user asks, 'What should I eat today?', please explain the system that suggests the best meal based on their past eating history and preferences, orders that meal from a partner restaurant, and notifies them of the delivery status in real time."

[0833] In this way, the present invention provides a system that allows users to easily select, order, and receive nutritionally balanced meals at home.

[0834] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0835] Step 1:

[0836] The user uses their smartphone or tablet to type, "What should I eat today?"

[0837] Input: User's dietary consultation.

[0838] Output: Input data sent from the user device to the server.

[0839] Specific operation: The user launches the dedicated application, enters "What should I eat today?" in the input field, and taps the send button. The user device sends this input data to the server.

[0840] Step 2:

[0841] The server analyzes the consultation content received from the user.

[0842] Input: User's consultation content, user ID.

[0843] Output: Analysis results, user's past eating history and preferences.

[0844] Specific operation: The server retrieves past meal history and preferences from a database based on the user ID. For example, the database uses MySQL, and the analysis is performed using Python programs and natural language processing algorithms.

[0845] Step 3:

[0846] The server generates meal suggestions that take into account the user's nutritional balance.

[0847] Input: User's past diet history, preference data, and nutritional balance information.

[0848] Output: Meal suggestions.

[0849] Specific operation: The server uses the generative AI model to generate an optimal meal menu that takes into account the user's past dietary data and nutritional balance. The results are sent to the user's device.

[0850] Step 4:

[0851] The user checks the meal proposal and, if he / she agrees, sends the consent information to the server.

[0852] Input: Meal suggestions from the server.

[0853] Output: Sending user consent information.

[0854] Specific operation: The user checks the proposal on the device and taps the "Agree" button. The user device then sends the consent information to the server.

[0855] Step 5:

[0856] The server receives the user's consent and notifies the affiliated restaurant of the meal order.

[0857] Input: User consent information.

[0858] Output: Order notification to partner restaurant.

[0859] Specific operation: The server receives the user's consent, generates and sends order information to the terminal of the affiliated restaurant.

[0860] Step 6:

[0861] The affiliated restaurant starts cooking based on the order details received from the server and sends a cooking completion notification to the server.

[0862] Input: Order information from the server.

[0863] Output: Cooking completion notification.

[0864] Specific operation: The restaurant confirms the order and starts cooking. When cooking is complete, the restaurant terminal sends a cooking completion notification to the server.

[0865] Step 7:

[0866] The server receives the cooking completion notification and issues delivery instructions to the partner delivery service.

[0867] Input: Cooking complete notification.

[0868] Output: Delivery instructions, delivery progress.

[0869] Specific operation: The server receives the cooking completion notification and generates a delivery instruction for the delivery service. The delivery service leaves the restaurant and heads to the user's location. The server tracks the delivery progress and notifies the user of the delivery status in real time.

[0870] Step 8:

[0871] The delivery person delivers the meal to the user's home and sends a completion notification to the server.

[0872] Input: Delivery completion notification.

[0873] Output: Delivery success message to the user.

[0874] Specific operation: After the delivery person delivers the meal to the user's home, they send a completion notification to the server. The server receives the completion notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0875] (Application example 1)

[0876] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0877] Conventional meal recommendation systems have had difficulty proposing appropriate meal menus that take into account individual user preferences and nutritional balance, and have also had issues with the lack of smooth ordering and delivery management based on such menus, making it difficult for users to obtain healthy, balanced meals easily and quickly.

[0878] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0879] In this invention, the server includes means for receiving input from a user and analyzing the details of the dietary consultation, means for generating appropriate dietary suggestions based on the user's past history and preferences, means for presenting the dietary suggestions to the user and receiving consent, means for generating dietary suggestions that take into account the user's nutritional balance using a generative AI model, and means for querying the generative AI model using prompt sentences. This enables appropriate dietary suggestions that take into account the user's preferences and nutritional balance, and realizes smooth ordering and delivery management based on the suggestions.

[0880] "Input from the user" refers to information regarding meal consultations and orders made by the user using their own terminal.

[0881] "Diet-related consultation content" is information including questions and requests from the user regarding what to eat.

[0882] "User's past history" is data relating to meals the user has had and menu items they have ordered.

[0883] "Preferences" is information indicating the ingredients, types of dishes, and seasonings that the user particularly likes.

[0884] "Meal suggestions" are meal menus that are suggested taking into consideration the user's preferences, past history, and nutritional balance.

[0885] The "means for receiving consent" is a function for receiving an operation by the user to consent to the proposed meal menu and reflecting that in the system.

[0886] An "affiliated restaurant" is a restaurant that is affiliated with this system and provides meals based on orders from users.

[0887] The "cooking completion notification" is a notification to the server that the affiliated restaurant has completed cooking the specified meal.

[0888] A "delivery service" is a service that delivers meals prepared by affiliated restaurants to users.

[0889] "Delivery status" is information indicating the progress of the ordered meal until it is delivered to the user.

[0890] A "generative AI model" is an artificial intelligence model that analyzes user input and past history to make optimal meal suggestions.

[0891] A "prompt sentence" is a sentence used to query a generative AI model, and is a sentence that gives the model specific instructions or questions.

[0892] As an embodiment of the present invention, a system is constructed that includes a user terminal, a server, terminals of affiliated restaurants, and a delivery service. How this system operates will be described below.

[0893] Hardware and Software

[0894] The system is implemented using the following hardware and software:

[0895] Hardware: Smartphones, servers, partner restaurant terminals, delivery staff terminals

[0896] Software: Mobile app (iOS / Android), server side (Node.js, Python), database (PostgreSQL), generative AI model (TensorFlow, PyTorch)

[0897] User Input and Server Processing

[0898] When a user types "What should I eat?" via a smartphone application, the information is sent to a server. The server analyzes the input and generates optimal meal suggestions based on the user's past eating history and preferences. This is done using a generative AI model. This model analyzes the input data and makes suggestions after taking into account the user's preferences and nutritional balance.

[0899] An example of a prompt for the generative AI model is a text prompt such as, "Please suggest a nutritionally balanced meal menu based on user ID: 1234's past eating history and their question about what they want to eat today."

[0900] Meal suggestions and user consent

[0901] The generated meal suggestions are displayed on the user's smartphone. If the user is satisfied with the suggestions, they send their consent to the server via the application. Upon receiving this consent, the server automatically notifies the partner restaurant of the meal order. The restaurant then begins cooking based on the order.

[0902] Cooking completion notification and delivery arrangement

[0903] When the restaurant finishes cooking, a completion notification is sent from the restaurant terminal to the server. The server receives this notification and issues a delivery instruction to an affiliated delivery service. The delivery service then delivers the ordered meal from the restaurant to the user.

[0904] Delivery status notification and delivery completion

[0905] The delivery progress is tracked in real time by the server and notified to the user, allowing the user to understand the current status of their order. When the delivery person successfully delivers the meal to the user, a delivery completion notification is sent to the server, and finally a delivery completion message is displayed on the user's smartphone.

[0906] Specific examples

[0907] As a concrete example, when a user types "What should I eat today?" into a smartphone app, the generative AI model analyzes the user's past eating history and suggests a "warm pork soup and rice set." If the user agrees to this suggestion, the order is automatically sent to a partner restaurant, and once cooking is complete, instructions are sent to the delivery service. The user is notified of the delivery status in real time, and is eventually notified that delivery is complete, allowing them to receive their meal with peace of mind.

[0908] As described above, this invention is a system that makes meal suggestions based on the user's preferences and nutritional balance, automates the entire process from ordering to delivery, and smoothly manages it.

[0909] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0910] Step 1:

[0911] The user starts the smartphone application and inputs the question, "What should we eat?" The input data is sent from the smartphone to the server. Specifically, the user ID and the question are sent as data to the server.

[0912] Step 2:

[0913] The server analyzes the input received from the user. The server extracts keywords from the received consultation content and retrieves the corresponding user's past eating history and preferences from the database. Each piece of data is searched using the user ID as a key.

[0914] Step 3:

[0915] The server sends a prompt to the generative AI model based on the extracted keywords and past history data. An example of a prompt might be, "Please suggest a nutritionally balanced meal menu based on user ID: 1234's past meal history and what they want to eat today."

[0916] Step 4:

[0917] A generative AI model analyzes the prompt and generates appropriate meal suggestions. This AI model was built using TensorFlow and PyTorch, and suggests menu items while taking into account the user's nutritional balance. The generated meal suggestions are returned to the server as data including specific menu names and details.

[0918] Step 5:

[0919] The server receives the meal suggestions returned by the generative AI model and displays them on the user's smartphone. The user then considers the displayed meal suggestions and sends their agreement or disagreement to the server via the application. Details of the suggestions, including nutritional information, are also displayed here.

[0920] Step 6:

[0921] If the user agrees to the meal suggestion, the consent data is sent to the server. The server then notifies the partner restaurant of the meal order based on the consent data. Specifically, the order details, user ID, delivery address information, etc. are sent as data to the restaurant terminal.

[0922] Step 7:

[0923] The partner restaurant will start cooking the meal based on the order data received from the server. When cooking is complete, the restaurant terminal will send a cooking completion notification to the server. This notification will include the order ID, cooking completion time, etc.

[0924] Step 8:

[0925] After the server receives the cooking completion notification, it issues a delivery instruction to the partner delivery service. The delivery service then arranges for the meal to be delivered from the restaurant to the user and sends a delivery start notification to the server, which includes information about the delivery person and the estimated delivery time.

[0926] Step 9:

[0927] The server receives a delivery start notification from the delivery service and tracks the delivery status in real time. The server then notifies the user of the delivery progress via their smartphone app, allowing the user to check the current delivery status.

[0928] Step 10:

[0929] When the delivery person delivers the meal to the user, a delivery completion notification is sent from the delivery person's terminal to the server. The server receives the delivery completion notification and displays a delivery completion message on the user's smartphone. This allows the user to confirm that the ordered meal has arrived safely.

[0930] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0931] This invention is implemented by combining an emotion engine with a system consisting of a user terminal, a server, affiliated restaurant terminals, and a delivery service. How each component works together will be described in detail below.

[0932] Operation via user terminal

[0933] Users access the system using their smartphone or tablet device. First, they input their dietary concerns, such as "What should I eat today?" into the device. At this time, the user can also input their emotions (such as satisfaction or fatigue). The user device sends this input to the server, and the user's dietary concerns and emotional data are then imported into the system.

[0934] Server processing

[0935] The server first analyzes the question and emotion data received from the user and recognizes the user's emotion using an emotion engine. Based on the user ID, the server retrieves the user's past eating history and preferences from a database.

[0936] The server then generates meal suggestions based on the acquired information and emotional data. For example, if a user inputs "I'm feeling stressed," the server will suggest meals with a relaxing effect (e.g., herbal tea or a nutritious snack). The meal suggestion algorithm automatically generates an appropriate meal menu, taking into account the user's preferences, nutritional balance, and emotional level.

[0937] User Consent and Order Notification

[0938] The server sends the generated meal suggestions to the user's terminal. The user's terminal displays the suggestions to the user, and if the user is satisfied with the suggestions, it sends consent to the server. The user can also add more specific requests (e.g., "I want something sweeter").

[0939] Cooking and notification by partner restaurants

[0940] The server receives the user's consent and notifies the affiliated restaurant of the meal order. The restaurant terminal receives and confirms the order details. The affiliated restaurant begins cooking the meal based on the received order details. After cooking is complete, the restaurant terminal sends a cooking completion notification to the server.

[0941] Delivery arrangements and notifications

[0942] The server receives a notification that the food is ready and sends a delivery instruction to the partner delivery service. The delivery service then delivers the meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time, allowing the user to know the current status of their order.

[0943] Notifying the user of delivery completion

[0944] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[0945] Specific examples

[0946] As a concrete example, consider the case where a user asks "What should I eat today?" and inputs "I'm feeling stressed." The server considers the user's preferences and nutritional balance from past history and suggests a "warm herbal tea and light salad set" to help relieve stress. If the user agrees to this suggestion, the order is sent to a partner restaurant, and the delivery service delivers the meal to the user. The user can wait with peace of mind as they are notified of the delivery status, and eventually the meal arrives safely and they receive a notification that the delivery has been completed.

[0947] In this way, the present invention realizes a system for meal suggestion and ordering that takes into account the user's emotions, allowing the user to easily select, order, and receive a nutritionally balanced meal at home, while also responding to their emotional state at any given time.

[0948] The processing flow will be explained below.

[0949] Step 1:

[0950] The user accesses the terminal and inputs the question "What should I eat today?" and their current feelings (e.g., "I'm tired" or "I'm stressed"). The terminal then sends this data to the server.

[0951] Step 2:

[0952] The server analyzes the questions and emotion data received from the user and uses an emotion engine to recognize the user's emotional state.

[0953] Step 3:

[0954] The server retrieves the user's past eating history and preferences from the database based on the user ID. For example, if the user has a history of preferring "healthy meals," that information is taken into account.

[0955] Step 4:

[0956] The server generates meal suggestions based on the emotional data, past meal history, and preferences. For example, if a user inputs the emotion "I feel stressed," the server will suggest meals that have a relaxing effect (e.g., warm herbal tea or a nutritious snack).

[0957] Step 5:

[0958] The server transmits the generated meal suggestions to the user terminal, which displays the meal suggestions to the user.

[0959] Step 6:

[0960] If the user agrees to the proposal, the user's device will send the consent information to the server. The user can also add more specific requests.

[0961] Step 7:

[0962] The server receives the user's consent and notifies the affiliated restaurant of the meal order. The restaurant terminal receives and confirms the order details.

[0963] Step 8:

[0964] The partner restaurant will begin cooking the meal based on the order details. Once cooking is complete, the restaurant terminal will send a cooking completion notification to the server.

[0965] Step 9:

[0966] The server receives the notification that the food is ready and sends a delivery instruction to the partner delivery service, which then prepares the food for delivery from the restaurant to the user.

[0967] Step 10:

[0968] The server tracks the delivery progress and sends the information to the user's device in real time, allowing the user to check the progress of their order.

[0969] Step 11:

[0970] The delivery person delivers the meal to the user's home. When the delivery is complete, the delivery person sends a completion notification to the server. The server receives the completion notification and sends a delivery completion message to the user's device.

[0971] In this way, users can conduct meal consultations, receive emotion-based suggestions, place orders, and finally have meals delivered to their homes.

[0972] Example 2

[0973] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0974] Conventional meal recommendation systems only provide suggestions based on a user's eating history and preferences, and do not consider the user's emotional state. This has resulted in problems such as users being unable to select meals that reflect their emotional state, and therefore unable to fully improve their satisfaction and health. Furthermore, there is an issue that the system does not adequately notify users of the delivery status of their meals in real time, making it difficult for users to grasp the delivery status.

[0975] The specific processing by the specific 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 receiving input from a user and analyzing the meal-related consultation content and emotional data; means for generating appropriate meal suggestions based on the analyzed emotional data and the user's past history and preferences; and means for presenting the generated meal suggestions to the user and receiving consent. This enables meal suggestions that take the user's emotional state into consideration. The server also includes means for notifying a partner restaurant of a meal order based on the meal suggestions, issuing delivery instructions to a delivery service based on a cooking completion notification received from the restaurant, means for notifying the user of the delivery status in real time, and means for notifying the user of delivery completion upon receiving a delivery completion notification. This allows the user to understand the delivery status in real time and wait with peace of mind for the entire process from ordering to delivery completion.

[0976] A "user" is someone who uses this system and makes meal suggestions and orders using a device such as a smartphone or tablet.

[0977] A "user terminal" is a device used by a user, such as a smartphone or tablet, that is used to access the system.

[0978] A "server" is a central computer that receives data from user terminals and performs analysis and processing, and is a major component that includes a database and analysis software.

[0979] "Emotion data" refers to information about the user's own emotions and moods entered by the user, and includes data about stress, satisfaction, and the like.

[0980] An "emotion engine" is software or algorithms for analyzing emotion data, a technology used to recognize a user's emotional state.

[0981] "Meal suggestions" are meal menus and recommendations generated by the server based on the user's emotional data, past history, and preferences.

[0982] "Affiliated restaurant" refers to a restaurant that has a contract with the system to provide meals to users, and is a business that receives orders and cooks the food.

[0983] A "delivery service" is a service company or business that delivers meals from affiliated restaurants to users, and includes a function to track the progress of deliveries.

[0984] An "order notification" is a communication to inform affiliated restaurants of the details of a meal order based on the user's consent information.

[0985] The "cooking completion notification" is a notification to inform the server that the affiliated restaurant has completed cooking the meal.

[0986] "Delivery instruction" is an operation performed by the server to instruct the delivery service to deliver the meal to the user after the server receives notification that the meal is ready.

[0987] "Delivery status" is information that indicates the progress and status of the meal from the start of cooking until it reaches the user.

[0988] The "delivery completion notification" is a notification sent to the server when the delivery person from the delivery service has delivered the meal to the user.

[0989] "User consent" refers to an operation by the user indicating their willingness to accept the proposed meal menu.

[0990] An "additional request" is when a user inputs more specific requests or wishes for a meal suggestion.

[0991] MODE FOR CARRYING OUT THE INVENTION

[0992] This invention combines a user terminal, a server, affiliated restaurant terminals, and a delivery service to realize a meal recommendation system that takes into account the user's emotions.

[0993] Hardware and Software Used

[0994] This system uses the following hardware and software:

[0995] User devices: iOS and Android smartphones and tablet devices

[0996] Dedicated application software: FoodMood app

[0997] Server: High-performance cloud service (e.g. AWS or Google Cloud)

[0998] Database software: MySQL or PostgreSQL

[0999] Emotion engine: IBM Watson Emotion Analysis

[1000] Machine Learning Model: Diet Recommendation Algorithm in Python

[1001] Partner restaurant terminal: POS system

[1002] Delivery services: Delivery systems such as Uber Eats and DoorDash

[1003] System Description

[1004] User device operation

[1005] Users access a dedicated app using their smartphone or tablet. Through the application interface, they input their dietary concerns, such as "What should I eat today?", along with their emotions (e.g., feeling stressed or tired). This allows users to send their dietary concerns and emotional data to the system.

[1006] Server Processing

[1007] The server receives the data sent by the user. It analyzes the received data using an emotion engine (e.g., IBM Watson Emotion Analysis) to recognize the user's emotional state. It then retrieves the user's past eating history and preference data from a database. It then uses a meal recommendation algorithm (e.g., a Python machine learning model) to generate optimal meal recommendations based on the emotional and historical data.

[1008] Presenting proposals and obtaining consent

[1009] The generated meal suggestions are sent to the user's terminal via the server again and presented to the user. The user checks the suggestions on the application screen and either agrees or enters a specific request (e.g., "I want something more sweet"). This information is then returned to the server.

[1010] Order notification to partner restaurants

[1011] The server sends the order details to the partner restaurant based on the received consent information and additional requests. The partner restaurant's terminal (e.g., POS system) receives the order and begins cooking. Once cooking is complete, the restaurant sends a cooking completion notification to the server.

[1012] Delivery arrangements and notifications

[1013] After receiving the cooking completion notification, the server issues a delivery instruction to the partner delivery service. The delivery service picks up the meal from the restaurant and begins delivering it to the user. The delivery progress is tracked in real time by the server and notified to the user's device. This allows the user to know the status of their order in real time.

[1014] Delivery completion notification

[1015] Finally, when the delivery service delivers the meal to the user's home, a completion notification is sent to the server. The server receives this notification and sends a delivery completion message to the user's terminal, allowing the user to confirm that the meal they ordered has arrived safely.

[1016] Examples of concrete examples and prompts

[1017] For example, suppose a user asks "What should I eat today?" and inputs "I'm feeling stressed." If the server knows from the user's past eating history that "I like sweets," it will suggest "warm herbal tea, a light salad set, and chocolate cake for dessert" based on the emotion engine and food suggestion algorithm. The user agrees with this suggestion and makes an additional request, saying "I'd like something sweeter." The server then notifies partner restaurants and arranges for cooking and delivery.

[1018] Example prompts for generative AI models

[1019] Below are some example prompts to input to a generative AI model:

[1020] System configuration: user terminal, server, partner restaurant terminal, delivery service, emotion engine. When a user inputs "What should I eat today?" and then "I'm feeling stressed," the system takes into account the user's past eating history and preferences to suggest meals that will help relieve stress. If the user agrees to the suggestions, an order is placed, cooking begins at the partner restaurant, and the meal is delivered to the user by the delivery service. Delivery progress is notified in real time, and a final delivery completion notification is sent.

[1021] This invention not only enables meal suggestions based on the user's emotions, but also provides a system that provides users with a sense of security and satisfaction by including real-time tracking and notifications of delivery status.

[1022] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1023] Step 1:

[1024] Users access a dedicated application using their smartphone or tablet. On the application's input screen, they enter a question such as "What should I eat today?" and their feelings (e.g., "I'm feeling stressed"). This input is then sent from the user's device to the server.

[1025] Input: User question and emotion data

[1026] Output: Data packets sent from the user device to the server

[1027] Step 2:

[1028] The server analyzes the data packets received from the user device and uses an emotion engine (e.g., IBM Watson Emotion Analysis) to recognize the user's emotional state. In parallel, it retrieves past meal history and preference data from a database based on the user ID.

[1029] Input: User question and emotion data

[1030] Output: User's emotional state data and past history data

[1031] Step 3:

[1032] The server generates meal suggestions using an AI algorithm (e.g., a machine learning model using Python) based on the results of the sentiment analysis and past meal history. If the emotional state is "stressed," the server suggests a relaxing "herbal tea and light salad set."

[1033] Input: Emotional state data, past history data

[1034] Output: Meal suggestion data (e.g., "Herbal tea and light salad set")

[1035] Step 4:

[1036] The server sends the generated meal suggestions to the user's device, which then displays the suggestions on the application screen.

[1037] Input: Meal suggestion data

[1038] Output: Meal suggestions displayed on the user's device

[1039] Step 5:

[1040] If the user agrees with the suggestions, they can enter their consent into the application. They can also add specific requests (e.g., "I want more sweets.") This consent information and additional requests are sent from the user's device to the server.

[1041] Input: User consent information and additional requests

[1042] Output: Consent information and additional requests sent to the server

[1043] Step 6:

[1044] The server receives the user's consent information and additional request, and notifies the affiliated restaurant of the order details. The affiliated restaurant's terminal receives and confirms the order.

[1045] Input: User consent information and additional requests

[1046] Output: Order notification to partner restaurant

[1047] Step 7:

[1048] The partner restaurant will start cooking based on the order details. Once cooking is complete, the restaurant terminal will send a cooking completion notification to the server.

[1049] Input: Restaurant cooking instructions

[1050] Output: Notification to server that cooking is complete

[1051] Step 8:

[1052] The server receives a notification that the food is ready and sends a delivery instruction to the partner delivery service. A delivery request is automatically sent to the delivery service's system (e.g., Uber Eats or DoorDash).

[1053] Input: Cooking complete notification

[1054] Output: Delivery instructions to the delivery service

[1055] Step 9:

[1056] The delivery service receives the meal from the restaurant and delivers it to the user's address. The delivery progress is sent to the server in real time, and the server transmits the information to the user's terminal.

[1057] Input: Restaurant pickup information

[1058] Output: Delivery progress notification to user terminal

[1059] Step 10:

[1060] When the delivery person has delivered the meal to the user's home, they send a completion notification to the server, which receives this notification and sends a delivery completion message to the user's terminal.

[1061] Input: Delivery completion notification

[1062] Output: Delivery completion message to user terminal

[1063] In this way, the entire process from user input to meal suggestions, cooking, and delivery is carried out through a series of steps, allowing users to easily suggest and order meals that suit their mood at the time and have them delivered to their home.

[1064] (Application example 2)

[1065] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1066] In modern society, many people live with emotions such as stress and fatigue, and healthy and satisfying meal choices are needed to address these feelings. However, conventional meal recommendation systems have difficulty taking users' emotions into account, resulting in an inability to fully meet users' needs. Furthermore, there are limited means to grasp the status of a user's ordered meal in real time. Therefore, there is a need for a method that can both recommend appropriate meals based on the user's emotions and preferences, and manage subsequent smooth ordering and delivery.

[1067] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving input from a user and analyzing meal-related consultation details and emotion data; means for generating appropriate meal suggestions based on the user's past history and preferences; and means for presenting meal suggestions to the user and receiving consent. This enables real-time generation of meal suggestions based on the user's emotions and increases user satisfaction through collaboration with affiliated restaurants. The server also includes means for notifying affiliated restaurants of meal orders, means for issuing delivery instructions to a delivery service based on cooking completion notifications received from affiliated restaurants, means for notifying the user of delivery status, and means incorporating a generative AI model that uses an emotion engine to generate meal suggestions based on the user's emotions. This enables more personalized meal suggestions based on emotion data and smooth delivery management.

[1068] "User input" refers to the recording of diet-related consultation details and emotional data that users make using their smartphones or tablet devices.

[1069] "Diet-related consultation content and emotion data" is information about emotions such as stress and fatigue felt by the user, and questions and requests about diet based on those emotions.

[1070] "Appropriate meal suggestions" refer to meal menu suggestions that suit the user, generated based on information such as the user's past eating history, preferences, and emotional data.

[1071] "Means for generating meal suggestions" refers to algorithms or functions that use a user's historical and emotional data to recommend optimal meals.

[1072] An "emotion engine" is software or a system that recognizes a user's emotions and reacts accordingly.

[1073] A "generative AI model" is an artificial intelligence model that automatically generates meal suggestions based on a user's emotions and preferences.

[1074] The "means for notifying partner restaurants of meal orders" refers to a system for transmitting the order details to partner restaurants with the user's consent.

[1075] The "means for issuing delivery instructions to a delivery service based on a cooking completion notification" is a function for issuing meal delivery instructions to a delivery service upon receiving a cooking completion notification from an affiliated store.

[1076] "Means for notifying users of delivery status" refers to systems or functions for notifying users of delivery progress in real time.

[1077] This invention is implemented by combining an emotion engine and a generative AI model with a system consisting of a user terminal, a server, a partner store terminal, and a delivery service. How each component works together is described in detail below.

[1078] Operation via user terminal

[1079] Users access the system using their smartphone or tablet device. First, they input their dietary concerns, such as "What should I eat today?" into the device. At this time, the user can also input their emotions (such as satisfaction or fatigue). The user device sends this input to the server, and the user's dietary concerns and emotional data are then imported into the system.

[1080] Server processing

[1081] The server first analyzes the question and emotional data received from the user and uses an emotional engine to recognize the user's emotions. Then, based on the user ID, it retrieves the user's past eating history and preference data from a database. Next, it uses a generative AI model to generate meal suggestions based on the retrieved information and emotional data. For example, if the user inputs "I feel stressed," it will suggest meals that have a relaxing effect (e.g., herbal tea or a nutritionally balanced snack). The generative AI model automatically generates an appropriate meal menu taking into account the user's preferences, nutritional balance, and emotional level.

[1082] User Consent and Order Notification

[1083] The server sends the generated meal suggestions to the user's terminal. The user's terminal displays the suggestions to the user, and if the user is satisfied with the suggestions, the user sends consent to the server. The user can also add more specific requests (e.g., "I want something sweeter").

[1084] Cooking and notification by partner stores

[1085] The server receives the user's consent and notifies the affiliated store of the meal order. The affiliated store's terminal receives and confirms the order details. The affiliated store begins cooking the meal based on the received order details. After cooking is complete, the store's terminal sends a cooking completion notification to the server.

[1086] Delivery arrangements and notifications

[1087] The server receives a notification that the food is ready and sends a delivery instruction to the partner delivery service. The delivery service then delivers the food from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time, allowing the user to know the status of their order.

[1088] Notifying the user of delivery completion

[1089] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[1090] Specific examples

[1091] As a concrete example, consider the case where a user asks "What should I eat today?" and inputs "I'm feeling stressed." The server considers the user's preferences and nutritional balance from past history and suggests "warm herbal tea and a light salad set," which is useful for relieving stress. If the user agrees to this suggestion, the order is sent to the partner store, and the delivery service delivers the meal to the user. The user can wait with peace of mind as they are notified of the delivery status, and eventually the meal arrives safely and they receive a notification that the delivery has been completed.

[1092] Prompt Sentence Examples

[1093] "Provide optimal meal suggestions if the user is experiencing the following emotions:

[1094] Emotion: I'm stressed

[1095] Preferences: Based on past history, I like herbal tea and light snacks.

[1096] Request: I want something sweeter."

[1097] In this way, the present invention realizes a system for meal suggestion and ordering that takes into account the user's emotions, allowing the user to easily select, order, and receive a nutritionally balanced meal at home, while also responding to their emotional state at any given time.

[1098] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1099] Step 1:

[1100] Users access the system using a smartphone or tablet device and input their meal-related questions, such as "What should I eat today?", along with emotional data (e.g., stress, satisfaction, etc.). The input data includes the user ID, emotional state, and specific requests (e.g., "I want something more sweet"). This data is sent from the user device to the server.

[1101] Step 2:

[1102] The server analyzes the questions and emotional data received from the user. At this time, it uses an emotion engine to recognize data related to the user's emotions. The server then retrieves data on the user's past eating history and preferences from a database based on the user ID. The input is the user's dietary consultation details and emotional data, and the output is the user's past eating history and preference data.

[1103] Step 3:

[1104] The server uses a generative AI model to generate meal suggestions based on the emotion data recognized by the emotion engine and past meal history and preferences retrieved from the database. For example, if a user inputs "I'm feeling stressed," the server will suggest a relaxing "warm herbal tea and light salad set." The input is the user's emotion data and past history data, and the output is a meal suggestion menu.

[1105] Step 4:

[1106] The server sends the generated meal suggestions to the user's device, and the user confirms the suggestions. If the user agrees with the suggestions and adds a more specific request (e.g., "I want something sweeter"), the server sends that information to the server. The input is the meal suggestions and the user's agreement, and the output is order information including the user's optional requests.

[1107] Step 5:

[1108] The server receives the user's consent and request and notifies the affiliated store of the meal order. The affiliated store terminal receives and confirms the order details. The input is the user's order information, and the output is an order notification to the affiliated store.

[1109] Step 6:

[1110] The affiliated store starts cooking the meal based on the received order details, and once cooking is complete, it sends a cooking completion notification from the store terminal to the server. The input is the order details notified to the store, and the output is the cooking completion notification to the server.

[1111] Step 7:

[1112] The server receives the cooking completion notification and issues delivery instructions to the partner delivery service. The delivery service then delivers the meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time. The input is the cooking completion notification and delivery instruction information, and the output is tracking data of the delivery progress.

[1113] Step 8:

[1114] After the delivery person delivers the meal to the user's home, they send a delivery completion notification to the server. The server receives this notification and sends a delivery completion message to the user's terminal. The input is the delivery completion notification, and the output is the delivery completion message.

[1115] This processing flow enables a seamless series of operations, from meal suggestions based on the user's emotions and preferences to ordering and delivery.

[1116] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1117] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1118] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1119] [Fourth embodiment]

[1120] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1121] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1122] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1123] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1124] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1125] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1126] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1127] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1128] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1129] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1131] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1132] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1133] The present invention is implemented by a system consisting of a user terminal, a server, affiliated restaurant terminals, and a delivery service. How each component works together will be described in detail below.

[1134] Operation via user terminal

[1135] Users access the system using their smartphones or tablet devices. First, they input their dietary concerns, such as "What should I eat today?" into the device. The user's device then sends this input to the server, which then imports the user's dietary concerns into the system.

[1136] Server processing

[1137] The server first analyzes the inquiry received from the user. Based on the user ID, the server retrieves the user's past eating history and preferences from a database. For example, if the user has a history of liking "healthy meals," the server generates meal suggestions based on that information.

[1138] The server then creates meal suggestions that take into account the user's preferences and nutritional balance. These suggestions are automatically generated by a meal suggestion algorithm, which selects the optimal meal menu. The results are then sent to the user's device and presented to them.

[1139] User Consent and Order Notification

[1140] If the user is satisfied with the meal suggestions, they agree to the suggestions. This agreement is sent from the user's terminal to the server. The server receives this agreement and notifies the affiliated restaurant of the meal order. Specifically, the order details are sent to the affiliated restaurant's terminal and confirmed by the restaurant.

[1141] Cooking and notification by partner restaurants

[1142] The partner restaurant starts cooking the meal based on the order details received from the server. When cooking is complete, the restaurant terminal sends a cooking completion notification to the server, which lets the server know that the order is ready.

[1143] Delivery arrangements and notifications

[1144] After receiving the notification that the food is ready, the server sends a delivery instruction to the partner delivery service. The delivery service then departs to deliver the ordered meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time, allowing the user to know the current status of their order.

[1145] Notifying the user of delivery completion

[1146] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[1147] Specific examples

[1148] As a concrete example, consider the case where a user asks "What should I eat today?" and the server suggests a "warm pork soup and rice set" based on past orders. If the user agrees to this suggestion, the order is sent to a partner restaurant, and the delivery service delivers the meal to the user. The user can wait with peace of mind as they are notified of the delivery status, and finally, they receive a notification that the meal has arrived safely and that delivery has been completed.

[1149] In this way, the present invention provides a system that allows users to easily select, order, and receive nutritionally balanced meals at home.

[1150] The processing flow will be explained below.

[1151] Step 1:

[1152] On the user terminal, the user inputs "What should I eat today?" The terminal sends this input to the server.

[1153] Step 2:

[1154] The server analyzes the question received from the user and retrieves the user's past eating history and preferences from the database using the user ID.

[1155] Step 3:

[1156] The server generates meal suggestions based on the acquired information and executes a meal suggestion algorithm that takes into account the user's preferences and nutritional balance.

[1157] Step 4:

[1158] The server sends the generated meal suggestions to the user's terminal, which displays the suggestions to the user.

[1159] Step 5:

[1160] If the user agrees with the proposal, the user terminal sends the consent information to the server. The user can also add more specific requests.

[1161] Step 6:

[1162] The server receives the user's consent and notifies the affiliated restaurant of the meal order. The restaurant terminal receives and confirms the order details.

[1163] Step 7:

[1164] The partner restaurant will begin cooking the meal based on the received order. After the cooking is complete, the restaurant terminal will send a cooking completion notification to the server.

[1165] Step 8:

[1166] The server receives a notification that the food is ready and sends a delivery instruction to a partner delivery service, which then delivers the meal from the restaurant to the user.

[1167] Step 9:

[1168] The server tracks the progress of the delivery and updates the information in real time to the user's device, allowing the user to check the delivery status.

[1169] Step 10:

[1170] The delivery person delivers the meal to the user's home. After the delivery is completed, the server receives a delivery completion notification and sends a delivery completion message to the user's terminal.

[1171] This processing step creates a system that allows users to easily select, order, and receive meals at home.

[1172] Example 1

[1173] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1174] Conventional systems make it difficult for users to choose their own meal plans or consider nutritional balance, and do not provide appropriate meal suggestions. Furthermore, there were issues with insufficient notification and tracking for users during the ordering process from partner restaurants and the subsequent delivery process, making it difficult for users to grasp the current situation. Furthermore, it was not possible to track the delivery progress in real time, and the system did not provide an environment where users could wait with peace of mind.

[1175] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1176] In this invention, the server includes means for receiving input from a user and analyzing the details of the meal-related consultation, means for generating appropriate meal suggestions based on the user's past history and preferences, means for presenting the meal suggestions to the user and receiving consent, means for notifying an affiliated restaurant of a meal order after receiving the user's consent, means for issuing delivery instructions to a delivery service based on a cooking completion notification received from the restaurant, means for tracking the delivery progress in real time and notifying the user, and means for notifying the user that delivery has been completed. This allows users to easily select nutritionally balanced meals and confidently keep track of the order and delivery status.

[1177] "User" refers to an individual who uses this system to consult about meals and receive meal suggestions.

[1178] "Input" refers to the act of a user sending dietary consultation details to the system using a smartphone or tablet device.

[1179] "Analysis" refers to the process by which the server understands the user's input based on information in the database and generates appropriate meal suggestions.

[1180] "Past history" refers to data on the user's previous selections, meal details, and order history.

[1181] "Preferences" refers to data that indicates the user's preferences for ingredients and dishes.

[1182] "Meal suggestions" refers to appropriate meal menus generated by the server based on the user's past history and preferences.

[1183] "Agreement" refers to the user's act of approving the meal menu proposed by the server.

[1184] "Affiliated restaurant" refers to a restaurant that participates in the system and accepts and prepares orders from users.

[1185] "Cooking Completion Notification" refers to information that notifies the server that an affiliated restaurant has completed cooking the ordered meal.

[1186] "Delivery service" refers to a service that delivers meals ordered from affiliated restaurants to users.

[1187] "Delivery Progress" refers to information that tracks the progress of an ordered meal in real time as the delivery service delivers it to you.

[1188] "Delivery completion notification" refers to information sent to the server after the delivery service has delivered the meal to the user's home.

[1189] The present invention is implemented by a system comprising a user terminal, a server, terminals of affiliated restaurants, and a delivery service. The specific operation of the system will be described in detail below.

[1190] First, the user accesses the system using their smartphone or tablet. The user enters "What should I eat today?" and this input data is sent from the user's device to the server. In this case, a dedicated application must be installed on the user's device.

[1191] The server has software for analyzing the inquiries received from users. Specifically, the server retrieves past dietary history and preferences from a database based on the user ID. For example, the database can use MySQL, and the analysis can use Python programs and natural language processing algorithms. If the user has a history of preferring "healthy meals," the server can generate meal suggestions based on that information.

[1192] The server then generates meal suggestions that take into account the user's nutritional balance. These suggestions are automatically created by a meal suggestion algorithm. For example, a generative AI model may be used to select the optimal meal menu based on the user's past dietary data and current health status. The results are then sent to the user's device and presented to them.

[1193] If the user is satisfied with the meal suggestions, they agree to the suggestions. This consent information is sent from the user's terminal to the server. The server receives the consent and notifies the affiliated restaurant of the meal order. Specifically, the order details are sent to the affiliated restaurant's terminal, where they are confirmed. At this stage, the affiliated restaurant's terminal also needs to be connected to the Internet.

[1194] The affiliated restaurant begins cooking the ordered meal based on the order details received from the server. Once cooking is complete, the restaurant terminal sends a cooking completion notification to the server, which lets the server know that the order is ready. After receiving the cooking completion notification, the server issues delivery instructions to the affiliated delivery service. The delivery service then departs to deliver the ordered meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time.

[1195] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[1196] As a concrete example, consider the case where a user asks, "What shall I eat today?" The server may suggest a "hot pork soup and rice set" based on past history. If the user agrees to this suggestion, an order for this meal is sent to a partner restaurant. After that, the meal is cooked and delivered to the user by a delivery service. The user can wait with peace of mind as they are notified of the delivery status, and eventually the meal arrives safely and they receive a notification that the delivery has been completed.

[1197] Examples of prompts to input to a generative AI model include:

[1198] "When a user asks, 'What should I eat today?', please explain the system that suggests the best meal based on their past eating history and preferences, orders that meal from a partner restaurant, and notifies them of the delivery status in real time."

[1199] In this way, the present invention provides a system that allows users to easily select, order, and receive nutritionally balanced meals at home.

[1200] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1201] Step 1:

[1202] The user uses their smartphone or tablet to type, "What should I eat today?"

[1203] Input: User's dietary consultation.

[1204] Output: Input data sent from the user device to the server.

[1205] Specific operation: The user launches the dedicated application, enters "What should I eat today?" in the input field, and taps the send button. The user device sends this input data to the server.

[1206] Step 2:

[1207] The server analyzes the consultation content received from the user.

[1208] Input: User's consultation content, user ID.

[1209] Output: Analysis results, user's past eating history and preferences.

[1210] Specific operation: The server retrieves past meal history and preferences from a database based on the user ID. For example, the database uses MySQL, and the analysis is performed using Python programs and natural language processing algorithms.

[1211] Step 3:

[1212] The server generates meal suggestions that take into account the user's nutritional balance.

[1213] Input: User's past diet history, preference data, and nutritional balance information.

[1214] Output: Meal suggestions.

[1215] Specific operation: The server uses the generative AI model to generate an optimal meal menu that takes into account the user's past dietary data and nutritional balance. The results are sent to the user's device.

[1216] Step 4:

[1217] The user checks the meal proposal and, if he / she agrees, sends the consent information to the server.

[1218] Input: Meal suggestions from the server.

[1219] Output: Sending user consent information.

[1220] Specific operation: The user checks the proposal on the device and taps the "Agree" button. The user device then sends the consent information to the server.

[1221] Step 5:

[1222] The server receives the user's consent and notifies the affiliated restaurant of the meal order.

[1223] Input: User consent information.

[1224] Output: Order notification to partner restaurant.

[1225] Specific operation: The server receives the user's consent, generates and sends order information to the terminal of the affiliated restaurant.

[1226] Step 6:

[1227] The affiliated restaurant starts cooking based on the order details received from the server and sends a cooking completion notification to the server.

[1228] Input: Order information from the server.

[1229] Output: Cooking completion notification.

[1230] Specific operation: The restaurant confirms the order and starts cooking. When cooking is complete, the restaurant terminal sends a cooking completion notification to the server.

[1231] Step 7:

[1232] The server receives the cooking completion notification and issues delivery instructions to the partner delivery service.

[1233] Input: Cooking complete notification.

[1234] Output: Delivery instructions, delivery progress.

[1235] Specific operation: The server receives the cooking completion notification and generates a delivery instruction for the delivery service. The delivery service leaves the restaurant and heads to the user's location. The server tracks the delivery progress and notifies the user of the delivery status in real time.

[1236] Step 8:

[1237] The delivery person delivers the meal to the user's home and sends a completion notification to the server.

[1238] Input: Delivery completion notification.

[1239] Output: Delivery success message to the user.

[1240] Specific operation: After the delivery person delivers the meal to the user's home, they send a completion notification to the server. The server receives the completion notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[1241] (Application example 1)

[1242] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1243] Conventional meal recommendation systems have had difficulty proposing appropriate meal menus that take into account individual user preferences and nutritional balance, and have also had issues with the lack of smooth ordering and delivery management based on such menus, making it difficult for users to obtain healthy, balanced meals easily and quickly.

[1244] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1245] In this invention, the server includes means for receiving input from a user and analyzing the details of the dietary consultation, means for generating appropriate dietary suggestions based on the user's past history and preferences, means for presenting the dietary suggestions to the user and receiving consent, means for generating dietary suggestions that take into account the user's nutritional balance using a generative AI model, and means for querying the generative AI model using prompt sentences. This enables appropriate dietary suggestions that take into account the user's preferences and nutritional balance, and realizes smooth ordering and delivery management based on the suggestions.

[1246] "Input from the user" refers to information regarding meal consultations and orders made by the user using their own terminal.

[1247] "Diet-related consultation content" is information including questions and requests from the user regarding what to eat.

[1248] "User's past history" is data relating to meals the user has had and menu items they have ordered.

[1249] "Preferences" is information indicating the ingredients, types of dishes, and seasonings that the user particularly likes.

[1250] "Meal suggestions" are meal menus that are suggested taking into consideration the user's preferences, past history, and nutritional balance.

[1251] The "means for receiving consent" is a function for receiving an operation by the user to consent to the proposed meal menu and reflecting that in the system.

[1252] An "affiliated restaurant" is a restaurant that is affiliated with this system and provides meals based on orders from users.

[1253] The "cooking completion notification" is a notification to the server that the affiliated restaurant has completed cooking the specified meal.

[1254] A "delivery service" is a service that delivers meals prepared by affiliated restaurants to users.

[1255] "Delivery status" is information indicating the progress of the ordered meal until it is delivered to the user.

[1256] A "generative AI model" is an artificial intelligence model that analyzes user input and past history to make optimal meal suggestions.

[1257] A "prompt sentence" is a sentence used to query a generative AI model, and is a sentence that gives the model specific instructions or questions.

[1258] As an embodiment of the present invention, a system is constructed that includes a user terminal, a server, terminals of affiliated restaurants, and a delivery service. How this system operates will be described below.

[1259] Hardware and Software

[1260] The system is implemented using the following hardware and software:

[1261] Hardware: Smartphones, servers, partner restaurant terminals, delivery staff terminals

[1262] Software: Mobile app (iOS / Android), server side (Node.js, Python), database (PostgreSQL), generative AI model (TensorFlow, PyTorch)

[1263] User Input and Server Processing

[1264] When a user types "What should I eat?" via a smartphone application, the information is sent to a server. The server analyzes the input and generates optimal meal suggestions based on the user's past eating history and preferences. This is done using a generative AI model. This model analyzes the input data and makes suggestions after taking into account the user's preferences and nutritional balance.

[1265] An example of a prompt for the generative AI model is a text prompt such as, "Please suggest a nutritionally balanced meal menu based on user ID: 1234's past eating history and their question about what they want to eat today."

[1266] Meal suggestions and user consent

[1267] The generated meal suggestions are displayed on the user's smartphone. If the user is satisfied with the suggestions, they send their consent to the server via the application. Upon receiving this consent, the server automatically notifies the partner restaurant of the meal order. The restaurant then begins cooking based on the order.

[1268] Cooking completion notification and delivery arrangement

[1269] When the restaurant finishes cooking, a completion notification is sent from the restaurant terminal to the server. The server receives this notification and issues a delivery instruction to an affiliated delivery service. The delivery service then delivers the ordered meal from the restaurant to the user.

[1270] Delivery status notification and delivery completion

[1271] The delivery progress is tracked in real time by the server and notified to the user, allowing the user to understand the current status of their order. When the delivery person successfully delivers the meal to the user, a delivery completion notification is sent to the server, and finally a delivery completion message is displayed on the user's smartphone.

[1272] Specific examples

[1273] As a concrete example, when a user types "What should I eat today?" into a smartphone app, the generative AI model analyzes the user's past eating history and suggests a "warm pork soup and rice set." If the user agrees to this suggestion, the order is automatically sent to a partner restaurant, and once cooking is complete, instructions are sent to the delivery service. The user is notified of the delivery status in real time, and is eventually notified that delivery is complete, allowing them to receive their meal with peace of mind.

[1274] As described above, this invention is a system that makes meal suggestions based on the user's preferences and nutritional balance, automates the entire process from ordering to delivery, and smoothly manages it.

[1275] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1276] Step 1:

[1277] The user starts the smartphone application and inputs the question, "What should we eat?" The input data is sent from the smartphone to the server. Specifically, the user ID and the question are sent as data to the server.

[1278] Step 2:

[1279] The server analyzes the input received from the user. The server extracts keywords from the received consultation content and retrieves the corresponding user's past eating history and preferences from the database. Each piece of data is searched using the user ID as a key.

[1280] Step 3:

[1281] The server sends a prompt to the generative AI model based on the extracted keywords and past history data. An example of a prompt might be, "Please suggest a nutritionally balanced meal menu based on user ID: 1234's past meal history and what they want to eat today."

[1282] Step 4:

[1283] A generative AI model analyzes the prompt and generates appropriate meal suggestions. This AI model was built using TensorFlow and PyTorch, and suggests menu items while taking into account the user's nutritional balance. The generated meal suggestions are returned to the server as data including specific menu names and details.

[1284] Step 5:

[1285] The server receives the meal suggestions returned by the generative AI model and displays them on the user's smartphone. The user then considers the displayed meal suggestions and sends their agreement or disagreement to the server via the application. Details of the suggestions, including nutritional information, are also displayed here.

[1286] Step 6:

[1287] If the user agrees to the meal suggestion, the consent data is sent to the server. The server then notifies the partner restaurant of the meal order based on the consent data. Specifically, the order details, user ID, delivery address information, etc. are sent as data to the restaurant terminal.

[1288] Step 7:

[1289] The partner restaurant will start cooking the meal based on the order data received from the server. When cooking is complete, the restaurant terminal will send a cooking completion notification to the server. This notification will include the order ID, cooking completion time, etc.

[1290] Step 8:

[1291] After the server receives the cooking completion notification, it issues a delivery instruction to the partner delivery service. The delivery service then arranges for the meal to be delivered from the restaurant to the user and sends a delivery start notification to the server, which includes information about the delivery person and the estimated delivery time.

[1292] Step 9:

[1293] The server receives a delivery start notification from the delivery service and tracks the delivery status in real time. The server then notifies the user of the delivery progress via their smartphone app, allowing the user to check the current delivery status.

[1294] Step 10:

[1295] When the delivery person delivers the meal to the user, a delivery completion notification is sent from the delivery person's terminal to the server. The server receives the delivery completion notification and displays a delivery completion message on the user's smartphone. This allows the user to confirm that the ordered meal has arrived safely.

[1296] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1297] This invention is implemented by combining an emotion engine with a system consisting of a user terminal, a server, affiliated restaurant terminals, and a delivery service. How each component works together will be described in detail below.

[1298] Operation via user terminal

[1299] Users access the system using their smartphone or tablet device. First, they input their dietary concerns, such as "What should I eat today?" into the device. At this time, the user can also input their emotions (such as satisfaction or fatigue). The user device sends this input to the server, and the user's dietary concerns and emotional data are then imported into the system.

[1300] Server processing

[1301] The server first analyzes the question and emotion data received from the user and recognizes the user's emotion using an emotion engine. Based on the user ID, the server retrieves the user's past eating history and preferences from a database.

[1302] The server then generates meal suggestions based on the acquired information and emotional data. For example, if a user inputs "I'm feeling stressed," the server will suggest meals with a relaxing effect (e.g., herbal tea or a nutritious snack). The meal suggestion algorithm automatically generates an appropriate meal menu, taking into account the user's preferences, nutritional balance, and emotional level.

[1303] User Consent and Order Notification

[1304] The server sends the generated meal suggestions to the user's terminal. The user's terminal displays the suggestions to the user, and if the user is satisfied with the suggestions, it sends consent to the server. The user can also add more specific requests (e.g., "I want something sweeter").

[1305] Cooking and notification by partner restaurants

[1306] The server receives the user's consent and notifies the affiliated restaurant of the meal order. The restaurant terminal receives and confirms the order details. The affiliated restaurant begins cooking the meal based on the received order details. After cooking is complete, the restaurant terminal sends a cooking completion notification to the server.

[1307] Delivery arrangements and notifications

[1308] The server receives a notification that the food is ready and sends a delivery instruction to the partner delivery service. The delivery service then delivers the meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time, allowing the user to know the current status of their order.

[1309] Notifying the user of delivery completion

[1310] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[1311] Specific examples

[1312] As a concrete example, consider the case where a user asks "What should I eat today?" and inputs "I'm feeling stressed." The server considers the user's preferences and nutritional balance from past history and suggests a "warm herbal tea and light salad set" to help relieve stress. If the user agrees to this suggestion, the order is sent to a partner restaurant, and the delivery service delivers the meal to the user. The user can wait with peace of mind as they are notified of the delivery status, and eventually the meal arrives safely and they receive a notification that the delivery has been completed.

[1313] In this way, the present invention realizes a system for meal suggestion and ordering that takes into account the user's emotions, allowing the user to easily select, order, and receive a nutritionally balanced meal at home, while also responding to their emotional state at any given time.

[1314] The processing flow will be explained below.

[1315] Step 1:

[1316] The user accesses the terminal and inputs the question "What should I eat today?" and their current feelings (e.g., "I'm tired" or "I'm stressed"). The terminal then sends this data to the server.

[1317] Step 2:

[1318] The server analyzes the questions and emotion data received from the user and uses an emotion engine to recognize the user's emotional state.

[1319] Step 3:

[1320] The server retrieves the user's past eating history and preferences from the database based on the user ID. For example, if the user has a history of preferring "healthy meals," that information is taken into account.

[1321] Step 4:

[1322] The server generates meal suggestions based on the emotional data, past meal history, and preferences. For example, if a user inputs the emotion "I feel stressed," the server will suggest meals that have a relaxing effect (e.g., warm herbal tea or a nutritious snack).

[1323] Step 5:

[1324] The server transmits the generated meal suggestions to the user terminal, which displays the meal suggestions to the user.

[1325] Step 6:

[1326] If the user agrees to the proposal, the user's device will send the consent information to the server. The user can also add more specific requests.

[1327] Step 7:

[1328] The server receives the user's consent and notifies the affiliated restaurant of the meal order. The restaurant terminal receives and confirms the order details.

[1329] Step 8:

[1330] The partner restaurant will begin cooking the meal based on the order details. Once cooking is complete, the restaurant terminal will send a cooking completion notification to the server.

[1331] Step 9:

[1332] The server receives the notification that the food is ready and sends a delivery instruction to the partner delivery service, which then prepares the food for delivery from the restaurant to the user.

[1333] Step 10:

[1334] The server tracks the delivery progress and sends the information to the user's device in real time, allowing the user to check the progress of their order.

[1335] Step 11:

[1336] The delivery person delivers the meal to the user's home. When the delivery is complete, the delivery person sends a completion notification to the server. The server receives the completion notification and sends a delivery completion message to the user's device.

[1337] In this way, users can conduct meal consultations, receive emotion-based suggestions, place orders, and finally have meals delivered to their homes.

[1338] Example 2

[1339] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1340] Conventional meal recommendation systems only provide suggestions based on a user's eating history and preferences, and do not consider the user's emotional state. This has resulted in problems such as users being unable to select meals that reflect their emotional state, and therefore unable to fully improve their satisfaction and health. Furthermore, there is an issue that the system does not adequately notify users of the delivery status of their meals in real time, making it difficult for users to grasp the delivery status.

[1341] The specific processing by the specific 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 receiving input from a user and analyzing the meal-related consultation content and emotional data; means for generating appropriate meal suggestions based on the analyzed emotional data and the user's past history and preferences; and means for presenting the generated meal suggestions to the user and receiving consent. This enables meal suggestions that take the user's emotional state into consideration. The server also includes means for notifying a partner restaurant of a meal order based on the meal suggestions, issuing delivery instructions to a delivery service based on a cooking completion notification received from the restaurant, means for notifying the user of the delivery status in real time, and means for notifying the user of delivery completion upon receiving a delivery completion notification. This allows the user to understand the delivery status in real time and wait with peace of mind for the entire process from ordering to delivery completion.

[1342] A "user" is someone who uses this system and makes meal suggestions and orders using a device such as a smartphone or tablet.

[1343] A "user terminal" is a device used by a user, such as a smartphone or tablet, that is used to access the system.

[1344] A "server" is a central computer that receives data from user terminals and performs analysis and processing, and is a major component that includes a database and analysis software.

[1345] "Emotion data" refers to information about the user's own emotions and moods entered by the user, and includes data about stress, satisfaction, and the like.

[1346] An "emotion engine" is software or algorithms for analyzing emotion data, a technology used to recognize a user's emotional state.

[1347] "Meal suggestions" are meal menus and recommendations generated by the server based on the user's emotional data, past history, and preferences.

[1348] "Affiliated restaurant" refers to a restaurant that has a contract with the system to provide meals to users, and is a business that receives orders and cooks the food.

[1349] A "delivery service" is a service company or business that delivers meals from affiliated restaurants to users, and includes a function to track the progress of deliveries.

[1350] An "order notification" is a communication to inform affiliated restaurants of the details of a meal order based on the user's consent information.

[1351] The "cooking completion notification" is a notification to inform the server that the affiliated restaurant has completed cooking the meal.

[1352] "Delivery instruction" is an operation performed by the server to instruct the delivery service to deliver the meal to the user after the server receives notification that the meal is ready.

[1353] "Delivery status" is information that indicates the progress and status of the meal from the start of cooking until it reaches the user.

[1354] The "delivery completion notification" is a notification sent to the server when the delivery person from the delivery service has delivered the meal to the user.

[1355] "User consent" refers to an operation by the user indicating their willingness to accept the proposed meal menu.

[1356] An "additional request" is when a user inputs more specific requests or wishes for a meal suggestion.

[1357] MODE FOR CARRYING OUT THE INVENTION

[1358] This invention combines a user terminal, a server, affiliated restaurant terminals, and a delivery service to realize a meal recommendation system that takes into account the user's emotions.

[1359] Hardware and Software Used

[1360] This system uses the following hardware and software:

[1361] User devices: iOS and Android smartphones and tablet devices

[1362] Dedicated application software: FoodMood app

[1363] Server: High-performance cloud service (e.g. AWS or Google Cloud)

[1364] Database software: MySQL or PostgreSQL

[1365] Emotion engine: IBM Watson Emotion Analysis

[1366] Machine Learning Model: Diet Recommendation Algorithm in Python

[1367] Partner restaurant terminal: POS system

[1368] Delivery services: Delivery systems such as Uber Eats and DoorDash

[1369] System Description

[1370] User device operation

[1371] Users access a dedicated app using their smartphone or tablet. Through the application interface, they input their dietary concerns, such as "What should I eat today?", along with their emotions (e.g., feeling stressed or tired). This allows users to send their dietary concerns and emotional data to the system.

[1372] Server Processing

[1373] The server receives the data sent by the user. It analyzes the received data using an emotion engine (e.g., IBM Watson Emotion Analysis) to recognize the user's emotional state. It then retrieves the user's past eating history and preference data from a database. It then uses a meal recommendation algorithm (e.g., a Python machine learning model) to generate optimal meal recommendations based on the emotional and historical data.

[1374] Presenting proposals and obtaining consent

[1375] The generated meal suggestions are sent to the user's terminal via the server again and presented to the user. The user checks the suggestions on the application screen and either agrees or enters a specific request (e.g., "I want something more sweet"). This information is then returned to the server.

[1376] Order notification to partner restaurants

[1377] The server sends the order details to the partner restaurant based on the received consent information and additional requests. The partner restaurant's terminal (e.g., POS system) receives the order and begins cooking. Once cooking is complete, the restaurant sends a cooking completion notification to the server.

[1378] Delivery arrangements and notifications

[1379] After receiving the cooking completion notification, the server issues a delivery instruction to the partner delivery service. The delivery service picks up the meal from the restaurant and begins delivering it to the user. The delivery progress is tracked in real time by the server and notified to the user's device. This allows the user to know the status of their order in real time.

[1380] Delivery completion notification

[1381] Finally, when the delivery service delivers the meal to the user's home, a completion notification is sent to the server. The server receives this notification and sends a delivery completion message to the user's terminal, allowing the user to confirm that the meal they ordered has arrived safely.

[1382] Examples of concrete examples and prompts

[1383] For example, suppose a user asks "What should I eat today?" and inputs "I'm feeling stressed." If the server knows from the user's past eating history that "I like sweets," it will suggest "warm herbal tea, a light salad set, and chocolate cake for dessert" based on the emotion engine and food suggestion algorithm. The user agrees with this suggestion and makes an additional request, saying "I'd like something sweeter." The server then notifies partner restaurants and arranges for cooking and delivery.

[1384] Example prompts for generative AI models

[1385] Below are some example prompts to input to a generative AI model:

[1386] System configuration: user terminal, server, partner restaurant terminal, delivery service, emotion engine. When a user inputs "What should I eat today?" and then "I'm feeling stressed," the system takes into account the user's past eating history and preferences to suggest meals that will help relieve stress. If the user agrees to the suggestions, an order is placed, cooking begins at the partner restaurant, and the meal is delivered to the user by the delivery service. Delivery progress is notified in real time, and a final delivery completion notification is sent.

[1387] This invention not only enables meal suggestions based on the user's emotions, but also provides a system that provides users with a sense of security and satisfaction by including real-time tracking and notifications of delivery status.

[1388] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1389] Step 1:

[1390] Users access a dedicated application using their smartphone or tablet. On the application's input screen, they enter a question such as "What should I eat today?" and their feelings (e.g., "I'm feeling stressed"). This input is then sent from the user's device to the server.

[1391] Input: User question and emotion data

[1392] Output: Data packets sent from the user device to the server

[1393] Step 2:

[1394] The server analyzes the data packets received from the user device and uses an emotion engine (e.g., IBM Watson Emotion Analysis) to recognize the user's emotional state. In parallel, it retrieves past meal history and preference data from a database based on the user ID.

[1395] Input: User question and emotion data

[1396] Output: User's emotional state data and past history data

[1397] Step 3:

[1398] The server generates meal suggestions using an AI algorithm (e.g., a machine learning model using Python) based on the results of the sentiment analysis and past meal history. If the emotional state is "stressed," the server suggests a relaxing "herbal tea and light salad set."

[1399] Input: Emotional state data, past history data

[1400] Output: Meal suggestion data (e.g., "Herbal tea and light salad set")

[1401] Step 4:

[1402] The server sends the generated meal suggestions to the user's device, which then displays the suggestions on the application screen.

[1403] Input: Meal suggestion data

[1404] Output: Meal suggestions displayed on the user's device

[1405] Step 5:

[1406] If the user agrees with the suggestions, they can enter their consent into the application. They can also add specific requests (e.g., "I want more sweets.") This consent information and additional requests are sent from the user's device to the server.

[1407] Input: User consent information and additional requests

[1408] Output: Consent information and additional requests sent to the server

[1409] Step 6:

[1410] The server receives the user's consent information and additional request, and notifies the affiliated restaurant of the order details. The affiliated restaurant's terminal receives and confirms the order.

[1411] Input: User consent information and additional requests

[1412] Output: Order notification to partner restaurant

[1413] Step 7:

[1414] The partner restaurant will start cooking based on the order details. Once cooking is complete, the restaurant terminal will send a cooking completion notification to the server.

[1415] Input: Restaurant cooking instructions

[1416] Output: Notification to server that cooking is complete

[1417] Step 8:

[1418] The server receives a notification that the food is ready and sends a delivery instruction to the partner delivery service. A delivery request is automatically sent to the delivery service's system (e.g., Uber Eats or DoorDash).

[1419] Input: Cooking complete notification

[1420] Output: Delivery instructions to the delivery service

[1421] Step 9:

[1422] The delivery service receives the meal from the restaurant and delivers it to the user's address. The delivery progress is sent to the server in real time, and the server transmits the information to the user's terminal.

[1423] Input: Restaurant pickup information

[1424] Output: Delivery progress notification to user terminal

[1425] Step 10:

[1426] When the delivery person has delivered the meal to the user's home, they send a completion notification to the server, which receives this notification and sends a delivery completion message to the user's terminal.

[1427] Input: Delivery completion notification

[1428] Output: Delivery completion message to user terminal

[1429] In this way, the entire process from user input to meal suggestions, cooking, and delivery is carried out through a series of steps, allowing users to easily suggest and order meals that suit their mood at the time and have them delivered to their home.

[1430] (Application example 2)

[1431] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1432] In modern society, many people live with emotions such as stress and fatigue, and healthy and satisfying meal choices are needed to address these feelings. However, conventional meal recommendation systems have difficulty taking users' emotions into account, resulting in an inability to fully meet users' needs. Furthermore, there are limited means to grasp the status of a user's ordered meal in real time. Therefore, there is a need for a method that can both recommend appropriate meals based on the user's emotions and preferences, and manage subsequent smooth ordering and delivery.

[1433] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving input from a user and analyzing meal-related consultation details and emotion data; means for generating appropriate meal suggestions based on the user's past history and preferences; and means for presenting meal suggestions to the user and receiving consent. This enables real-time generation of meal suggestions based on the user's emotions and increases user satisfaction through collaboration with affiliated restaurants. The server also includes means for notifying affiliated restaurants of meal orders, means for issuing delivery instructions to a delivery service based on cooking completion notifications received from affiliated restaurants, means for notifying the user of delivery status, and means incorporating a generative AI model that uses an emotion engine to generate meal suggestions based on the user's emotions. This enables more personalized meal suggestions based on emotion data and smooth delivery management.

[1434] "User input" refers to the recording of diet-related consultation details and emotional data that users make using their smartphones or tablet devices.

[1435] "Diet-related consultation content and emotion data" is information about emotions such as stress and fatigue felt by the user, and questions and requests about diet based on those emotions.

[1436] "Appropriate meal suggestions" refer to meal menu suggestions that suit the user, generated based on information such as the user's past eating history, preferences, and emotional data.

[1437] "Means for generating meal suggestions" refers to algorithms or functions that use a user's historical and emotional data to recommend optimal meals.

[1438] An "emotion engine" is software or a system that recognizes a user's emotions and reacts accordingly.

[1439] A "generative AI model" is an artificial intelligence model that automatically generates meal suggestions based on a user's emotions and preferences.

[1440] The "means for notifying partner restaurants of meal orders" refers to a system for transmitting the order details to partner restaurants with the user's consent.

[1441] The "means for issuing delivery instructions to a delivery service based on a cooking completion notification" is a function for issuing meal delivery instructions to a delivery service upon receiving a cooking completion notification from an affiliated store.

[1442] "Means for notifying users of delivery status" refers to systems or functions for notifying users of delivery progress in real time.

[1443] This invention is implemented by combining an emotion engine and a generative AI model with a system consisting of a user terminal, a server, a partner store terminal, and a delivery service. How each component works together is described in detail below.

[1444] Operation via user terminal

[1445] Users access the system using their smartphone or tablet device. First, they input their dietary concerns, such as "What should I eat today?" into the device. At this time, the user can also input their emotions (such as satisfaction or fatigue). The user device sends this input to the server, and the user's dietary concerns and emotional data are then imported into the system.

[1446] Server processing

[1447] The server first analyzes the question and emotional data received from the user and uses an emotional engine to recognize the user's emotions. Then, based on the user ID, it retrieves the user's past eating history and preference data from a database. Next, it uses a generative AI model to generate meal suggestions based on the retrieved information and emotional data. For example, if the user inputs "I feel stressed," it will suggest meals that have a relaxing effect (e.g., herbal tea or a nutritionally balanced snack). The generative AI model automatically generates an appropriate meal menu taking into account the user's preferences, nutritional balance, and emotional level.

[1448] User Consent and Order Notification

[1449] The server sends the generated meal suggestions to the user's terminal. The user's terminal displays the suggestions to the user, and if the user is satisfied with the suggestions, the user sends consent to the server. The user can also add more specific requests (e.g., "I want something sweeter").

[1450] Cooking and notification by partner stores

[1451] The server receives the user's consent and notifies the affiliated store of the meal order. The affiliated store's terminal receives and confirms the order details. The affiliated store begins cooking the meal based on the received order details. After cooking is complete, the store's terminal sends a cooking completion notification to the server.

[1452] Delivery arrangements and notifications

[1453] The server receives a notification that the food is ready and sends a delivery instruction to the partner delivery service. The delivery service then delivers the food from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time, allowing the user to know the status of their order.

[1454] Notifying the user of delivery completion

[1455] Finally, the delivery person delivers the meal to the user's home. Once the delivery is complete, the delivery person sends a completion notification to the server. The server receives this notification and sends a delivery completion message to the user's device. This allows the user to confirm that the ordered meal has been delivered safely.

[1456] Specific examples

[1457] As a concrete example, consider the case where a user asks "What should I eat today?" and inputs "I'm feeling stressed." The server considers the user's preferences and nutritional balance from past history and suggests "warm herbal tea and a light salad set," which is useful for relieving stress. If the user agrees to this suggestion, the order is sent to the partner store, and the delivery service delivers the meal to the user. The user can wait with peace of mind as they are notified of the delivery status, and eventually the meal arrives safely and they receive a notification that the delivery has been completed.

[1458] Prompt Sentence Examples

[1459] "Provide optimal meal suggestions if the user is experiencing the following emotions:

[1460] Emotion: I'm stressed

[1461] Preferences: Based on past history, I like herbal tea and light snacks.

[1462] Request: I want something sweeter."

[1463] In this way, the present invention realizes a system for meal suggestion and ordering that takes into account the user's emotions, allowing the user to easily select, order, and receive a nutritionally balanced meal at home, while also responding to their emotional state at any given time.

[1464] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1465] Step 1:

[1466] Users access the system using a smartphone or tablet device and input their meal-related questions, such as "What should I eat today?", along with emotional data (e.g., stress, satisfaction, etc.). The input data includes the user ID, emotional state, and specific requests (e.g., "I want something more sweet"). This data is sent from the user device to the server.

[1467] Step 2:

[1468] The server analyzes the questions and emotional data received from the user. At this time, it uses an emotion engine to recognize data related to the user's emotions. The server then retrieves data on the user's past eating history and preferences from a database based on the user ID. The input is the user's dietary consultation details and emotional data, and the output is the user's past eating history and preference data.

[1469] Step 3:

[1470] The server uses a generative AI model to generate meal suggestions based on the emotion data recognized by the emotion engine and past meal history and preferences retrieved from the database. For example, if a user inputs "I'm feeling stressed," the server will suggest a relaxing "warm herbal tea and light salad set." The input is the user's emotion data and past history data, and the output is a meal suggestion menu.

[1471] Step 4:

[1472] The server sends the generated meal suggestions to the user's device, and the user confirms the suggestions. If the user agrees with the suggestions and adds a more specific request (e.g., "I want something sweeter"), the server sends that information to the server. The input is the meal suggestions and the user's agreement, and the output is order information including the user's optional requests.

[1473] Step 5:

[1474] The server receives the user's consent and request and notifies the affiliated store of the meal order. The affiliated store terminal receives and confirms the order details. The input is the user's order information, and the output is an order notification to the affiliated store.

[1475] Step 6:

[1476] The affiliated store starts cooking the meal based on the received order details, and once cooking is complete, it sends a cooking completion notification from the store terminal to the server. The input is the order details notified to the store, and the output is the cooking completion notification to the server.

[1477] Step 7:

[1478] The server receives the cooking completion notification and issues delivery instructions to the partner delivery service. The delivery service then delivers the meal from the restaurant to the user. The server tracks the delivery progress and notifies the user in real time. The input is the cooking completion notification and delivery instruction information, and the output is tracking data of the delivery progress.

[1479] Step 8:

[1480] After the delivery person delivers the meal to the user's home, they send a delivery completion notification to the server. The server receives this notification and sends a delivery completion message to the user's terminal. The input is the delivery completion notification, and the output is the delivery completion message.

[1481] This processing flow enables a seamless series of operations, from meal suggestions based on the user's emotions and preferences to ordering and delivery.

[1482] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1483] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1484] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1485] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1486] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1487] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1488] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1489] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1490] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1491] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1492] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1493] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1494] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1495] 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.

[1496] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1497] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1498] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1499] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1500] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1501] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1502] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1503] The following is further disclosed regarding the above embodiment.

[1504] (Claim 1)

[1505] means for receiving input from a user and analyzing dietary consultation content;

[1506] means for generating appropriate meal suggestions based on the user's past history and preferences;

[1507] means for presenting meal suggestions to a user and receiving consent thereto;

[1508] a means for notifying a partner restaurant of a meal order after receiving consent from the user;

[1509] A means for issuing delivery instructions to a delivery service based on the cooking completion notification received from the restaurant;

[1510] means for notifying the user of the delivery status;

[1511] A system including:

[1512] (Claim 2)

[1513] The system according to claim 1, wherein meal suggestions are generated taking into consideration the nutritional balance of the user.

[1514] (Claim 3)

[1515] 10. The system of claim 1, wherein meal suggestions are generated by analyzing a user's preferences and past meal history.

[1516] "Example 1"

[1517] (Claim 1)

[1518] means for receiving input from a user and analyzing dietary consultation content;

[1519] means for generating appropriate meal suggestions based on the user's past history and preferences;

[1520] means for presenting meal suggestions to a user and receiving consent thereto;

[1521] After receiving the user's consent, a means for notifying the affiliated restaurant of the meal order;

[1522] A means for issuing delivery instructions to a delivery service based on the cooking completion notification received from the restaurant;

[1523] a means of tracking and notifying the user of the progress of the delivery in real time;

[1524] means for notifying the user that the delivery has been completed;

[1525] A system including:

[1526] (Claim 2)

[1527] The system according to claim 1, wherein meal suggestions are generated taking into consideration the nutritional balance of the user.

[1528] (Claim 3)

[1529] 10. The system of claim 1, wherein meal suggestions are generated by analyzing a user's preferences and past meal history.

[1530] "Application Example 1"

[1531] (Claim 1)

[1532] means for receiving input from a user and analyzing dietary consultation content;

[1533] means for generating appropriate meal suggestions based on the user's past history and preferences;

[1534] means for presenting meal suggestions to a user and receiving consent thereto;

[1535] a means for notifying a partner restaurant of a meal order after receiving consent from the user;

[1536] A means for issuing delivery instructions to a delivery service based on the cooking completion notification received from the restaurant;

[1537] means for notifying the user of the delivery status;

[1538] A means for generating meal suggestions that take into account the user's nutritional balance using a generative AI model;

[1539] a means for querying the generative AI model using prompt sentences;

[1540] A system including:

[1541] (Claim 2)

[1542] The system of claim 1 receives user input through a smartphone app and generates meal suggestions using a generative AI model.

[1543] (Claim 3)

[1544] 10. The system of claim 1, which tracks delivery status in real time and notifies the user.

[1545] "Example 2: Combining Emotion Engines"

[1546] Claims

[1547] (Claim 1)

[1548] means for receiving input from a user and analyzing diet-related consultation content and emotion data;

[1549] means for generating appropriate meal suggestions based on the analyzed emotion data and the user's past history and preferences;

[1550] means for presenting the generated meal suggestions to the user and receiving consent thereto;

[1551] After receiving the user's consent and additional request, a means for notifying the affiliated restaurant of the meal order;

[1552] A means for issuing delivery instructions to a delivery service based on the cooking completion notification received from the restaurant;

[1553] a means for notifying the user of the delivery status in real time;

[1554] a means for receiving a delivery completion notification and notifying the user of the delivery completion;

[1555] A system including:

[1556] (Claim 2)

[1557] 10. The system of claim 1, wherein the system analyzes the emotional state of the user and generates meal suggestions according to the emotional level.

[1558] (Claim 3)

[1559] 10. The system of claim 1, wherein the system tracks delivery status in real time and notifies the user of progress.

[1560] "Application example 2 when combining emotion engines"

[1561] (Claim 1)

[1562] means for receiving input from a user and analyzing diet-related consultation content and emotion data;

[1563] means for generating appropriate meal suggestions based on the user's past history and preferences;

[1564] means for presenting meal suggestions to a user and receiving consent thereto;

[1565] a means for notifying a partner restaurant of a meal order after receiving consent from the user;

[1566] A means for issuing delivery instructions to a delivery service based on the cooking completion notification received from the partner store;

[1567] means for notifying the user of the delivery status;

[1568] a means incorporating a generative AI model that uses an emotion engine to generate meal suggestions according to the user's emotions;

[1569] A system including:

[1570] (Claim 2)

[1571] The system according to claim 1, wherein meal suggestions are generated taking into consideration the nutritional balance of the user.

[1572] (Claim 3)

[1573] 10. The system of claim 1, wherein meal suggestions are generated by analyzing a user's preferences and past meal history. [Explanation of symbols]

[1574] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving input from a user and analyzing dietary consultation content; means for generating appropriate meal suggestions based on the user's past history and preferences; means for presenting meal suggestions to a user and receiving consent thereto; a means for notifying a partner restaurant of a meal order after receiving consent from the user; A means for issuing delivery instructions to a delivery service based on the cooking completion notification received from the restaurant; means for notifying the user of the delivery status; A system including:

2. The system according to claim 1 , wherein meal suggestions are generated taking into account the nutritional balance of the user.

3. The system of claim 1 , wherein meal suggestions are generated by analyzing a user's preferences and past meal history.

Images