System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving dietary restriction information and allergy information input from a user terminal; means for searching for appropriate restaurant information from a database based on the dietary restriction information and the allergy information; means for analyzing a menu tendency and a past review of the appropriate restaurant information and evaluating a degree of safety; and means for presenting restaurants suitable for a user in a list format based on the evaluated degree of safety.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's world, not all restaurants clearly display information about dietary restrictions and allergies, making it difficult for people with dietary restrictions or allergies to find a restaurant that suits them. Furthermore, there is a lack of a system for evaluating the safety of restaurants that do not display this information. This limits customers' dining options, making it difficult for them to enjoy eating out with peace of mind. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for receiving dietary restriction information and allergy information input from a user terminal, a means for searching for appropriate restaurant information from a database based on the dietary restriction information and allergy information, a means for analyzing menu trends and past reviews of the appropriate restaurant information and evaluating safety, and a means for presenting a list of restaurants suitable for the user based on the evaluated safety. This increases the likelihood that restaurants that do not list allergy information and the like will be safe to use, ensuring a wider range of dining options for users. Furthermore, by providing a means for collecting feedback information from users and using it to improve the accuracy of the evaluated safety, the reliability of the entire system can be improved.

[0006] "Dietary restriction information" is information that a user inputs to avoid consuming specific ingredients or components.

[0007] "Allergy information" is information that a user inputs to avoid ingesting a specific allergen because the user has an allergic reaction to that allergen.

[0008] A "user terminal" is an electronic device, such as a computer or smartphone, that a user uses to enter information and receive restaurant suggestions.

[0009] A "database" is a system that stores and manages restaurant information, menus, allergen information, etc.

[0010] "Restaurant information" is a collection of data that indicates detailed information such as the restaurant's name, location, and menu.

[0011] "Analysis" is the process of examining data in detail to derive meaning and trends.

[0012] "Safety" is an evaluation index that indicates whether a restaurant or menu can be safely used by users with specific dietary restrictions or allergies.

[0013] "List format" is a display method in which information presented to the user is organized in bulleted or list format.

[0014] "Feedback information" refers to information such as impressions and opinions provided by users after using a restaurant.

[0015] "Reliability" is the property that describes the ability of a system to function correctly, consistently, and as expected. [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 showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[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 a system that suggests appropriate restaurants based on a user's dietary restrictions and allergy information. The program processing of this system will be described in detail below.

[0038] User terminal processing

[0039] 1. Enter information

[0040] A user opens a food app on their device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information such as nut allergies, gluten-free diets, or vegan diets into a form.

[0041] 2. Information Transmission

[0042] The device sends the information entered by the user to the server via API, including information on dietary restrictions and allergies.

[0043] Server Processing

[0044] 3. Receiving Information

[0045] The server receives the dietary restriction and allergy information sent by the user, and stores the received information in a database.

[0046] 4. Database Search

[0047] Based on the received information, the server searches for restaurant information in a database that includes restaurant names, locations, menu information, allergen information, etc.

[0048] 5. Safety Assessment

[0049] The server uses an AI analysis engine to analyze restaurant information suitable for the user. During the analysis process, the safety of the restaurant is evaluated based on the restaurant's menu trends and past reviews. For example, for a user with a nut allergy, a restaurant that offers nut-free menu items will be given a high safety rating.

[0050] 6. Recommendation Generation

[0051] The server generates a list of restaurants suitable for the user based on the safety rating. The generated restaurant list also includes the safety rating of each restaurant.

[0052] 7. Sending Recommendations

[0053] The restaurant list generated by the server is sent to the terminal via API.

[0054] User terminal processing (display)

[0055] 8. Receiving and Displaying Information

[0056] The device displays the restaurant list received from the server on the user interface (UI). The user can check the list to see which restaurants are safe for them.

[0057] User Action

[0058] 9. Restaurant Selection and Reservations

[0059] The user selects the restaurant they want from the list of restaurants presented, then makes a reservation within the app or visits the restaurant in person.

[0060] feedback

[0061] 10. Providing Feedback

[0062] After a user visits a restaurant and finishes their meal, they provide feedback within the app, including their satisfaction with the meal and their rating of allergy-related issues.

[0063] Server processing (feedback)

[0064] 11. Collect and use feedback

[0065] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[0066] In this way, the present invention allows users to easily find safe restaurants that take into account their dietary restrictions and allergies. Furthermore, by utilizing feedback, the reliability and accuracy of the overall system can be continuously improved.

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] A user opens a food app on a device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information like "nut allergy" or "dairy-free."

[0070] Step 2:

[0071] The device sends the dietary restriction and allergy information entered by the user to the server via the API. During the sending process, the entered information is structured in JSON format and sent as an HTTP request.

[0072] Step 3:

[0073] The server stores the received dietary restriction and allergy information in a database. This information is stored in association with the user's ID.

[0074] Step 4:

[0075] The server retrieves all restaurant information from the database and filters it based on the received dietary restrictions and allergy information. This filtering checks the ingredients and components contained in the restaurant menu and lists restaurants that meet the user's criteria.

[0076] Step 5:

[0077] The server uses an AI analysis engine to evaluate the safety of the listed restaurants, analyzing menu items, past reviews, ingredient information, and other factors to calculate an overall safety score.

[0078] Step 6:

[0079] The server generates a list of restaurants suitable for the user based on the safety rating, including the restaurant's name, safety score, location, and menu summary.

[0080] Step 7:

[0081] The server generates a list of restaurants and sends it to the terminal via the API. The response data is structured in JSON format.

[0082] Step 8:

[0083] The device displays the restaurant list received from the server on a user interface (UI). The UI is organized in a list format, allowing users to easily view detailed information and safety scores for each restaurant.

[0084] Step 9:

[0085] The user selects the restaurant they want from the list of restaurants presented, then makes a reservation within the app or visits the restaurant in person.

[0086] Step 10:

[0087] After a user visits a restaurant and finishes their meal, they provide feedback within the app, including their satisfaction with the meal and their rating of allergy-related issues.

[0088] Step 11:

[0089] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[0090] Example 1

[0091] 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."

[0092] Conventional restaurant search systems do not adequately consider users' dietary restrictions or allergies when suggesting restaurants, making it difficult for users to find restaurants they can trust. Furthermore, the reliability of the safety of the suggested restaurants is low, necessitating improvements to increase user satisfaction. Furthermore, there is a lack of a way to effectively utilize user feedback to improve the system's accuracy.

[0093] 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.

[0094] In this invention, the server includes: means for receiving dietary restriction information and allergy information input from a user terminal; means for searching for appropriate restaurant information from a database based on the dietary restriction information and allergy information; means for analyzing the menu trends and past reviews of the appropriate restaurant information using a generative AI model to evaluate safety; means for presenting a list of restaurants suitable for the user based on the evaluated safety; means for transmitting the list to the user terminal; and means for displaying the list through a user interface of the user terminal. This allows the system to present restaurants with a high safety rating based on the user's dietary restriction information and allergy information, enabling the user to easily find a restaurant they can use with confidence. Furthermore, the system can collect user feedback and use it to improve the accuracy of the evaluation, thereby continuously improving the reliability of the system and user satisfaction.

[0095] "User terminal" refers to a device such as a smartphone or PC used by a user, and is a device for inputting information and receiving output from a system.

[0096] "Dietary restriction information" refers to information that prevents a user from consuming certain foods or ingredients, including, for example, vegan or low-calorie restrictions.

[0097] "Allergy information" refers to information about foods that a user should avoid because they react to certain allergens, such as nut allergies or milk allergies.

[0098] A "database" is a system that refers to a collection of accumulated data that stores restaurant information, menu information, allergen information, etc.

[0099] A "generative AI model" refers to an analytical engine that uses artificial intelligence to analyze, predict, and classify data.

[0100] "Menu trends" refers to statistical trends regarding the types, frequency, and ingredients of meals served at a particular restaurant.

[0101] "Past Reviews" refers to a record of ratings and comments provided by a User in the past, including User's reactions to a restaurant or its services.

[0102] "Safety level" is an evaluation index that indicates whether a particular restaurant is safe for the user, taking into consideration the user's dietary restrictions and allergy information.

[0103] "List format" refers to the method of presenting restaurant information in bulleted or tabular form, in a way that is easy for users to visually check.

[0104] "User interface (UI)" refers to the screens and operating means that allow a user to interact with a system, including, for example, application screens and buttons.

[0105] "Feedback information" refers to information such as ratings and comments provided by users after they have actually used a service or product.

[0106] The present invention relates to a system for suggesting suitable restaurants based on a user's dietary restriction information and allergy information. Hereinafter, an embodiment of the present invention will be described in detail.

[0107] Hardware and software used

[0108] Hardware

[0109] User terminal: A device such as a smartphone or PC that allows a user to input information and receive output from the system.

[0110] Server: A device that manages the entire system, processes and analyzes data, and manages databases.

[0111] software

[0112] Food app: An application installed on a user's device that allows them to enter information about dietary restrictions and allergies and display suggested restaurant information.

[0113] API: An interface for exchanging information between a user terminal and a server.

[0114] Database management system: A system for storing and managing restaurant information and user information.

[0115] AI analysis engine: A system that uses generative AI models to analyze data and evaluate restaurant safety.

[0116] Explanation of program processing

[0117] User terminal processing

[0118] First, the user launches the food app on their smartphone or PC and enters information about dietary restrictions and allergies. For example, they enter information such as "nut allergy," "gluten-free," or "vegan" into the input form. The device then sends the entered information to the server via an API. The sent information is in JSON format, and includes information about dietary restrictions and allergies.

[0119] Server Processing

[0120] The server receives the user's dietary restriction and allergy information via the API and stores it in a database. It then searches the database for appropriate restaurant information based on the stored information. The server then uses a generative AI model to analyze the menu trends and past reviews of the searched restaurant information and evaluates its safety. Specifically, for a user with a nut allergy, the server rates restaurants that offer nut-free menus highly as safe. Based on the evaluation results, it generates a list of restaurants suitable for the user and sends this list to the user's device.

[0121] User terminal processing (display)

[0122] The user device displays the restaurant list received from the server on the user interface (UI). The user can select the restaurant they want from the displayed list and make a reservation within the app or visit the restaurant in person.

[0123] User feedback

[0124] After a user visits a restaurant and finishes their meal, they provide feedback within the app. This feedback includes their satisfaction with the meal and an evaluation of whether the restaurant handled allergies. The server collects the feedback information provided by the user and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[0125] Examples of specific examples and prompts

[0126] As a concrete example, consider a case where a user with a nut allergy uses a food app to search for a suitable restaurant. The user enters "nut allergy" and the device sends this information to the server. The server searches for restaurants that offer nut-free menus and evaluates their safety. Based on the evaluation results, a list of appropriate restaurants is generated and sent to the user's device. The user then selects the desired restaurant from the displayed list and makes a reservation.

[0127] Example prompt sentence:

[0128] "Please suggest restaurants that are suitable for users with nut allergies."

[0129] "Search for and list vegan-friendly restaurants."

[0130] The above is an embodiment of the present invention. Taking into account the user's dietary restrictions and allergy information, it is possible to easily find a restaurant that is safe to use. Furthermore, by utilizing feedback from users, the reliability and evaluation accuracy of the entire system can be continuously improved.

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Step 1:

[0133] Enter information

[0134] Users launch the food app on their smartphone or PC and enter information about dietary restrictions and allergies.

[0135] Input: Nut allergy, gluten-free, vegan, etc. information.

[0136] How it works: A user fills out an application form and clicks the "Submit" button.

[0137] Output: The entered dietary restriction information and allergy information is saved on the device.

[0138] Step 2:

[0139] Information transmission

[0140] The device sends the entered dietary restriction and allergy information to the server via API.

[0141] Input: User-entered dietary restrictions and allergy information.

[0142] How it works: The device sends information to the server as a JSON-formatted API request.

[0143] Output: Dietary restrictions and allergy information sent to the server.

[0144] Step 3:

[0145] Receiving information

[0146] The server stores the dietary restriction and allergy information received via the API in a database.

[0147] Input: Dietary restriction and allergy information sent from your device.

[0148] How it works: The server parses the API request and stores the received information in a database.

[0149] Output: User's dietary restrictions and allergies stored in a database.

[0150] Step 4:

[0151] Database search

[0152] The server searches the database for appropriate restaurant information based on the stored user information.

[0153] Input: User's dietary restrictions and allergies stored in the database.

[0154] How it works: The server uses an SQL query to extract restaurant information from a database that matches the criteria.

[0155] Output: A list of restaurants that match the user's criteria.

[0156] Step 5:

[0157] Safety Rating

[0158] The server uses an AI analysis engine to analyze the menu trends and past reviews of the searched restaurant information and evaluate its safety.

[0159] Input: Restaurant information extracted from the database, menu trends, and past reviews.

[0160] How it works: Using a generative AI model, we analyze and evaluate the safety of restaurants. For example, we can evaluate a restaurant that offers nut-free menu items as being safe for a user with a nut allergy.

[0161] Output: A list of restaurant information with safety rating results.

[0162] Step 6:

[0163] Recommendation Generation

[0164] The server generates a list of restaurants suitable for the user based on the evaluated safety level.

[0165] Input: A list of restaurant information with safety rating results.

[0166] How it works: The server generates a list of restaurants based on the rating results and adds a safety rating for each restaurant to the list.

[0167] Output: The generated restaurant list.

[0168] Step 7:

[0169] Sending Recommendations

[0170] The server sends the generated restaurant list to the terminal via API.

[0171] Input: The generated restaurant list.

[0172] How it works: The server sends a list of restaurants to the device as a JSON-formatted API response.

[0173] Output: The restaurant list sent to the device.

[0174] Step 8:

[0175] Information reception and display

[0176] The terminal displays the restaurant list received from the server on a user interface (UI).

[0177] Input: A list of restaurants sent by the server.

[0178] Operation: The device analyzes the received information and displays it in a list format on the user interface. The user can then select a restaurant from the displayed list.

[0179] Output: The restaurant list displayed in a user interface.

[0180] Step 9:

[0181] Restaurant selection and reservations

[0182] Users can select the restaurant they want from the displayed list and make a reservation within the app, or visit the restaurant in person.

[0183] Input: A list of restaurants displayed in a user interface.

[0184] How it works: The user selects the restaurant they want, then uses the reservation feature to enter the date, time, and number of people to confirm the reservation, or visits the selected restaurant in person.

[0185] Output: The reservation is confirmed or information to visit the restaurant is displayed.

[0186] Step 10:

[0187] Providing Feedback

[0188] Users visit the restaurant in person, eat there and then provide feedback within the app.

[0189] Input: User's impressions and ratings after their visit. For example, this includes satisfaction with the food and ratings of allergy-related issues.

[0190] Action: A user fills in the feedback form and clicks the "Submit" button.

[0191] Output: The user's feedback information is saved on the device.

[0192] Step 11:

[0193] Collecting and using feedback

[0194] The server collects feedback information provided by users and stores it in a database. This feedback information is then used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[0195] Input: User feedback information sent from the device.

[0196] How it works: The server receives feedback information, stores it in a database, analyzes the stored feedback information, and provides feedback to the AI ​​analysis engine to improve the accuracy of the evaluation.

[0197] Output: An AI analysis engine with improved evaluation accuracy and an updated database.

[0198] (Application example 1)

[0199] 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."

[0200] Previously, it was difficult for users with dietary restrictions or allergies to find suitable restaurants, which posed a risk of accidents and problems. Furthermore, there was a lack of a mechanism for improving the system based on feedback from users after they had actually visited the restaurant, making it difficult to recommend restaurants with high accuracy. Another issue was how smoothly users could make reservations at recommended restaurants.

[0201] 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.

[0202] In this invention, the server includes means for receiving dietary restriction information and allergy information input from a user terminal, means for searching for appropriate dining facility information from a database based on the dietary restriction information and allergy information, means for analyzing menu trends and past reviews of the appropriate dining facility information and evaluating its safety, means for making reservations on the user terminal based on the evaluated safety, means for collecting feedback information from users and using it to improve the accuracy of the evaluated safety, and means for displaying the appropriate dining facility information through a user interface. This allows users with dietary restrictions or allergies to easily and safely find suitable dining facilities and make reservations smoothly. Furthermore, the accuracy of the system can be constantly improved through feedback.

[0203] "User terminal" refers to electronic devices used by users in general, including smartphones, tablets, personal computers, etc.

[0204] "Dining establishment information" refers to information necessary for users, such as the name of the dining establishment, its location, the menu items offered, and allergen information.

[0205] "Dietary restriction information" refers to a user's individual requirements for restricting certain ingredients or nutrients, and includes, for example, information such as gluten-free or low-carb.

[0206] "Allergy Information" refers to information about specific foods or ingredients to which a user has an allergic reaction.

[0207] "Search means" refers to software or a system that searches a database for appropriate restaurant information based on the user's dietary restrictions and allergy information.

[0208] "Means of analysis" refers to software and algorithms that evaluate the menu trends and past ratings of restaurant information and determine the safety level for users.

[0209] "Safety assessment method" refers to the process or system used to determine how safe a restaurant is in relation to a user's dietary restrictions or allergy information.

[0210] "Means for presenting in list format" refers to a user interface or display method for displaying a list of suitable dining establishments on a user's terminal.

[0211] "Means for making a reservation" refers to functionality or software that allows a user to make a reservation at a dining establishment selected by the user.

[0212] "Feedback information" refers to information such as ratings, comments, and satisfaction levels of restaurants and bars that users have actually visited.

[0213] "Means for displaying through a user interface" refers to a screen or interface for visually displaying dining establishment information on a user terminal.

[0214] This invention is a system that allows users to input information about dietary restrictions and allergies using a user terminal, searches for and suggests appropriate dining facilities via a server, and then makes reservations.

[0215] System Configuration

[0216] User terminal

[0217] The user device refers to an electronic device such as a smartphone, tablet, or personal computer, on which a mobile app using React Native is installed. This application allows users to input information about dietary restrictions and allergies and send it to the server.

[0218] server

[0219] The server receives the information sent from the user's device, searches the database, and provides appropriate restaurant information using AI analysis engines such as Google Cloud Machine Learning and Azure Machine Learning.

[0220] Program Overview

[0221] 1. Enter and submit information

[0222] Users open the smartphone app and enter their dietary restrictions (e.g., gluten-free or vegan) and allergy information (e.g., nut allergy) into a form. Once the information is complete, the user's device sends this information to the server using Axious.

[0223] 2. Database Search and Analysis

[0224] The server searches the database for appropriate restaurant information based on the received information. It uses an AI analysis engine to analyze menu trends and past reviews and evaluate safety. The safety evaluation criteria are based on whether the information meets the user's dietary restrictions and allergies.

[0225] 3. Generate and display a restaurant list

[0226] Based on the analysis results, the server generates a list of restaurants suitable for the user and sends it back to the user's device as an HTTP response. The user's device then displays the received list in list format within the app.

[0227] 4. Booking and Feedback

[0228] Users can select a restaurant from the list and make a reservation within the app. After visiting, users can provide feedback within the app. The collected feedback information is sent to the server and used to improve the accuracy of the system.

[0229] Specific examples

[0230] For example, if a user has a nut allergy and a vegan diet, they would enter the following information:

[0231] plaintext

[0232] Allergy Information: Nut allergy

[0233] Dietary Restrictions:Vegan

[0234] Based on this information, the server searches the database for restaurants that meet the user's requirements and generates a prompt like the following:

[0235] plaintext

[0236] Please suggest safe dining options based on the allergy information and dietary restrictions below:

[0237] Allergy Information: Nut allergy

[0238] Dietary Restrictions:Vegan

[0239] Proposed dining establishments should include the following information:

[0240] Name of restaurant

[0241] location

[0242] Menu Information

[0243] Safety level

[0244] Based on this prompt, the AI ​​analysis engine evaluates and selects suitable dining options and presents them to the user in a list format. The user can then select one from the list, make a reservation, and provide feedback after the visit.

[0245] This system allows users to easily find safe restaurants that meet their dietary restrictions and allergies, allowing them to enjoy meals safely. Furthermore, by improving the system's accuracy based on collected feedback, more reliable recommendations can be achieved.

[0246] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0247] Step 1:

[0248] The user opens the smartphone app. On the app interface, the user enters their dietary restrictions (e.g., gluten-free) and allergy information (e.g., nut allergy). After entering the information, the user presses the "Submit" button to proceed to the next step. This prepares the input data.

[0249] Step 2:

[0250] The user device sends the entered dietary restriction and allergy information to the server as an HTTP POST request using Axious. The server analyzes the received data and prepares a database search. The input is the user's dietary restriction and allergy information, and the output is JSON format data received by the server.

[0251] Step 3:

[0252] The server searches the database based on the received dietary restriction and allergy information. Specifically, it compares the menus of each restaurant in the database with the user's requirements and narrows down the list to restaurants that meet all the requirements. The input is the database stored on the server, and the output is a list of restaurant information that matches the requirements.

[0253] Step 4:

[0254] The server then uses an AI analysis engine to further analyze the narrowed-down restaurant information. During the analysis process, it evaluates the restaurant's menu trends and past reviews and calculates the safety rating of each restaurant. The input is restaurant information, and the output is a list of restaurants with a safety rating.

[0255] Step 5:

[0256] The server generates a list of restaurants that are most suitable for the user based on the safety assessment and sends it to the user's device as a list in an HTTP response. The output is a JSON-formatted list of restaurants that is sent to the user's device.

[0257] Step 6:

[0258] The user device receives the list of restaurants and displays it in list format within the app. The user selects the restaurant they are interested in from the displayed list. The input is the restaurant list data from the server, and the output is the restaurant information displayed in list format.

[0259] Step 7:

[0260] The user makes a reservation for the selected restaurant within the app. The reservation information is sent to the server using Axious. The server receives the reservation information and sends a reservation request to the restaurant. The input is the reservation information, and the output is the reservation confirmation data.

[0261] Step 8:

[0262] After a user visits a restaurant and finishes their meal, they provide feedback within the app. The feedback information is then sent to the server using Axious. The server stores the received feedback information in a database and uses it to improve the evaluation accuracy of the AI ​​analysis engine. The input is the feedback information, and the output is learning data for improving accuracy.

[0263] By going through the above steps, users can easily find and safely use restaurants that meet their dietary restrictions and allergies. The collected feedback information improves the system's evaluation accuracy, resulting in more reliable recommendations.

[0264] 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.

[0265] The present invention is a system that suggests appropriate restaurants based on a user's dietary restrictions and allergies, and also combines it with an emotion engine that recognizes the user's emotions to improve the accuracy of restaurant suggestions and the user experience. The program processing of this system is described in detail below.

[0266] User terminal processing

[0267] 1. Enter information

[0268] A user opens a food app on a device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information like "nut allergy" or "dairy-free."

[0269] 2. Emotion recognition

[0270] The emotion engine installed in the device acquires emotion data from the user's input, operations, facial expressions, tone of voice, etc. This emotion data indicates the user's current emotional state.

[0271] 3. Information Transmission

[0272] The device sends the dietary restriction information, allergy information, and emotional data entered by the user to the server via the API. During the sending process, the entered information and emotional data are structured in JSON format and sent as an HTTP request.

[0273] Server Processing

[0274] 4. Receiving Information

[0275] The server receives information about dietary restrictions, allergies, and emotional data sent by the user, and stores the received information in a database.

[0276] 5. Database Search

[0277] Based on the received information, the server searches for restaurant information in a database that includes restaurant names, locations, menu information, allergen information, etc., and filters restaurants that match the user's criteria.

[0278] 6. Safety Assessment

[0279] The server uses an AI analysis engine to evaluate the safety of the listed restaurants, analyzing menu items, past reviews, ingredient information, and other factors to calculate an overall safety score.

[0280] 7. Utilizing Emotional Data

[0281] The server analyzes the emotion data acquired by the emotion engine and makes suggestions according to the user's emotional state, such as suggesting restaurants with a more relaxing environment if the user is feeling stressed.

[0282] 8. Recommendation Generation

[0283] The server generates a list of restaurants suitable for the user based on the safety rating and emotion data. The list includes the restaurant's name, safety score, location, menu summary, and emotional response suggestions.

[0284] 9. Sending Recommendations

[0285] The server generates a list of restaurants and sends it to the terminal via the API. The response data is structured in JSON format.

[0286] User terminal processing (display)

[0287] 10. Receiving and Displaying Information

[0288] The device displays the restaurant list received from the server in a user interface (UI). The UI is organized in a list format, allowing users to easily view detailed information, safety scores, and emotional response suggestions for each restaurant.

[0289] User Action

[0290] 11. Restaurant Selection and Reservations

[0291] The user selects the desired restaurant from the presented restaurant list and makes a reservation within the app or visits the restaurant in person.

[0292] feedback

[0293] 12. Providing Feedback

[0294] After users visit a restaurant and finish their meal, they provide in-app feedback, including satisfaction with the meal, a rating of allergy accommodations, and emotional reactions to the suggested restaurant.

[0295] Server processing (feedback)

[0296] 13. Collect and use feedback

[0297] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine and emotion engine.

[0298] In this way, the present invention allows users to easily find safe restaurants that take into account their emotional state as well as their dietary restrictions and allergies. Furthermore, by utilizing feedback, the reliability and accuracy of the overall system can be continuously improved.

[0299] The processing flow will be explained below.

[0300] Step 1:

[0301] A user opens a food app on a device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information like "nut allergy" or "dairy-free."

[0302] Step 2:

[0303] The device acquires emotional data from the user's input, operations, facial expressions, tone of voice, etc. At this time, the emotion engine analyzes the user's emotions in real time and determines their emotional state, such as stress, satisfaction, or joy.

[0304] Step 3:

[0305] The device converts the dietary restriction information, allergy information, and emotional data entered by the user into JSON format and sends it to the server via an API.

[0306] Step 4:

[0307] The server receives information on dietary restrictions, allergies, and emotional data from the user, associates each piece of information, and stores it in a database. The stored information is linked to the user ID.

[0308] Step 5:

[0309] The server retrieves all restaurant information from the database and filters it based on dietary restrictions and allergies. This filtering involves checking the ingredients and components contained in restaurant menus and listing restaurants that meet the user's criteria.

[0310] Step 6:

[0311] The server uses an AI analysis engine to evaluate the safety of the listed restaurants, calculating an overall safety score based on the restaurant's menu items, past reviews, and ingredient information.

[0312] Step 7:

[0313] The server then uses the emotion data to suggest restaurants that correspond to the user's emotional state. For example, if the user is feeling stressed, it will prioritize restaurants that offer a high level of relaxation.

[0314] Step 8:

[0315] The server generates a list of restaurants suitable for the user based on the safety rating and emotion data. The list includes the restaurant's name, safety score, location, menu summary, and emotional response suggestions.

[0316] Step 9:

[0317] The server generates a list of restaurants and sends it to the device via API. The data is structured in JSON format.

[0318] Step 10:

[0319] The device displays the restaurant list received from the server in a user interface (UI). The UI is organized in a list format, allowing users to easily view detailed information, safety scores, and emotional response suggestions for each restaurant.

[0320] Step 11:

[0321] The user selects the restaurant they want from the presented list, makes a reservation within the app, or visits the restaurant in person.

[0322] Step 12:

[0323] After users visit a restaurant and finish their meal, they provide feedback within the app, including their satisfaction with the meal, their rating of allergy accommodations, and their emotional reaction to the suggested restaurant.

[0324] Step 13:

[0325] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine and emotion engine. This will improve the accuracy and reliability of future suggestions.

[0326] Example 2

[0327] 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."

[0328] Conventional restaurant search systems were able to suggest appropriate restaurants based on a user's dietary restrictions and allergies. However, they did not take into account the user's emotional state, limiting the improvement of the user experience. Furthermore, there was no mechanism in place to fully utilize feedback information when rating the safety of the suggested restaurants, leaving challenges in improving the accuracy of the ratings.

[0329] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving dietary restriction information and allergy information input from a user terminal; means for searching for appropriate facility information from a database based on the dietary restriction information and allergy information; means for analyzing menu trends and past reviews of the appropriate facility information and evaluating safety; means for presenting a list of facilities suitable for the user based on the evaluated safety level and the user's emotional data; means for analyzing the user's input content and facial expressions using an emotion recognition engine installed in the user terminal and acquiring emotional data; and means for analyzing the acquired emotional data and preferentially suggesting facilities with a relaxing environment. This allows the user to easily find safe facilities that take into account not only their dietary restriction and allergy information but also their emotional state. Furthermore, the reliability and evaluation accuracy of the entire system can be continuously improved based on feedback information.

[0330] A "user terminal" is an electronic device used by a user, including a smartphone, a PC, etc.

[0331] "Dietary restriction information" is information about foods and ingredients that the user wants to avoid consuming.

[0332] "Allergy information" is information about foods or ingredients to which the user is allergic.

[0333] An "emotion recognition engine" is software that includes technology for acquiring emotional data from a user's facial expressions, tone of voice, etc.

[0334] A "server" is a central computer system responsible for processing and storing data.

[0335] A "database" is a system that stores information systematically and enables efficient searching and access.

[0336] "Appropriate facility information" is information about facilities (restaurants, etc.) that have been filtered based on the user's dietary restriction information and allergy information.

[0337] "Safety level" is a score that evaluates the safety of dietary restriction information and allergy information for the user.

[0338] The "means for presenting in list form" is a method for displaying the evaluated information to the user as a list.

[0339] "Feedback information" refers to evaluations and impressions based on actual experiences provided by users.

[0340] "Emotion data" is data that indicates the user's emotional state, and is obtained from the user's facial expression and tone of voice.

[0341] The present invention is a system that proposes appropriate facilities based on a user's dietary restriction information and allergy information, and also combines it with an emotion engine that recognizes the user's emotions to improve the accuracy of proposals and the user experience. An embodiment of the system of the present invention will be described in detail below.

[0342] System Overview

[0343] This system consists of a user terminal, a server, and a database. The user terminal is an electronic device such as a smartphone or PC, and is the device through which the user enters information about their dietary restrictions and allergies. The server is a central computer system responsible for processing and storing data, and the database is a system that systematically stores information and enables efficient search and access.

[0344] Hardware and software used

[0345] 1. User Device

[0346] A device such as a smartphone or PC that allows users to enter information about dietary restrictions and allergies.

[0347] Equipped with an emotion recognition engine (such as Microsoft Azure's Emotion API or Google Cloud's Vision AI).

[0348] 2. Server

[0349] A central computer system that processes and stores data.

[0350] Connect to a database (such as MySQL or PostgreSQL) to manage your data.

[0351] 3. Software and APIs

[0352] Data communication between user devices and servers is achieved through RESTful API.

[0353] Safety is evaluated using an AI analysis engine (a model using TensorFlow and PyTorch).

[0354] Data processing and calculation

[0355] 1. Enter information

[0356] The user opens a food app on their device and enters their dietary restrictions and allergies, such as "nut allergy" or "dairy-free."

[0357] 2. Emotion recognition

[0358] The device uses an emotion recognition engine to analyze the user's facial expressions and tone of voice to obtain emotional data, and measures the user's emotional state in real time through the camera and microphone.

[0359] 3. Information Transmission

[0360] The device structures the entered dietary restriction information and acquired emotional data into JSON format and sends it to the server via a RESTful API.

[0361] 4. Receiving Information

[0362] The server receives the data sent from the terminal in JSON format and stores it in a database.

[0363] 5. Database Search

[0364] The server searches a database based on the received dietary restriction and allergy information and extracts appropriate restaurant information.

[0365] 6. Safety Assessment

[0366] The server uses an AI analysis engine to evaluate safety, analyzing restaurant menu information and past reviews to calculate an overall safety score.

[0367] 7. Emotion Data Analysis

[0368] The server analyzes the acquired emotional data and gives priority to suggesting restaurants with a relaxing environment for the user.

[0369] 8. Recommendation Generation

[0370] The server generates a list of restaurants suitable for the user based on the safety score and sentiment data.

[0371] 9. Information Transmission and Display

[0372] The server structures the generated restaurant list in JSON format and sends it to the device via a RESTful API. The device then displays the received list on the user interface.

[0373] Specific examples

[0374] Suppose a user enters "nut allergy" and "dairy-free" into a food app, and the emotion recognition engine detects high stress levels. Based on this information, the server suggests restaurants with a high safety rating and a relaxing environment. For example, the server presents the user with a list of two restaurants: "Relax Bistro" and "Healthy Eats."

[0375] Prompt Sentence Examples

[0376] "When a user enters nut allergies and dairy-free diets and the emotion engine detects a stressed state, what type of restaurant should be suggested? Please explain, including the specific restaurant names and the reason for the suggestions."

[0377] In this way, users can easily find restaurants that fit their dietary restrictions and emotional state, and continuous feedback can be collected and utilized to improve the reliability and accuracy of the entire system.

[0378] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0379] Step 1:

[0380] The user enters the information.

[0381] Specific operation: A user opens a food app and enters their dietary restrictions and allergies into the device. For example, they enter "nut allergy" or "dairy-free" into the form.

[0382] Input: User's dietary restrictions and allergy information.

[0383] Output: Dietary restriction information and allergy information are saved on the device.

[0384] Step 2:

[0385] The device recognizes emotions.

[0386] How it works: The device uses an emotion recognition engine (such as Microsoft Azure's Emotion API) to analyze the user's facial expressions and tone of voice to obtain emotional data. The analysis is carried out in real time via the camera and microphone.

[0387] Input: User facial and voice data.

[0388] Output: The user's emotional data (e.g., stress level) is obtained.

[0389] Step 3:

[0390] The terminal transmits the information.

[0391] Specific operation: The device structures the acquired dietary restriction information, allergy information, and emotion data into JSON format and sends it to the server via a RESTful API.

[0392] Input: dietary restriction information, allergy information, emotional data.

[0393] Output: Data structured in JSON format is sent to the server.

[0394] Step 4:

[0395] The server receives the information.

[0396] Specific operation: The server receives the JSON data sent from the terminal, parses it, and saves it in the database.

[0397] Input: JSON formatted data from the terminal.

[0398] Output: Parsed data stored in a database.

[0399] Step 5:

[0400] The server searches the database.

[0401] What it does: The server searches for restaurant information in its database based on the dietary restrictions and allergies received, and uses an SQL query to find the appropriate restaurant.

[0402] Input: Facility information, dietary restrictions, and allergy information in the database.

[0403] Output: A list of restaurants that match the criteria.

[0404] Step 6:

[0405] The server evaluates the security level.

[0406] How it works: The server uses an AI analysis engine (e.g., a TensorFlow model) to evaluate the safety of the listed restaurants. It analyzes menu information, past reviews, ingredient lists, etc. to calculate a safety score.

[0407] Input: Listed restaurant information, menu information, past reviews, ingredient list.

[0408] Output: Safety score for each restaurant.

[0409] Step 7:

[0410] The server utilizes the emotion data.

[0411] Specific operation: The server analyzes the user's emotional state based on the acquired emotional data. For example, if the user is feeling stressed, it will prioritize and suggest restaurants with a relaxing environment.

[0412] Input: Sentiment data, safety score.

[0413] Output: A list of restaurants that match the user's emotional state.

[0414] Step 8:

[0415] The server generates the recommendations.

[0416] Specific operation: The server generates a list of restaurants suitable for the user based on the safety score and emotion data. The list includes the restaurant name, safety score, location, and menu summary.

[0417] Input: Safety score, sentiment data.

[0418] Output: A recommendation list.

[0419] Step 9:

[0420] The server sends the recommendations.

[0421] Specific operation: The server structures the generated recommendation list in JSON format and sends it to the terminal via a RESTful API.

[0422] Input: A recommendation list.

[0423] Output: Data structured in JSON format is sent to the terminal.

[0424] Step 10:

[0425] The terminal receives and displays the information.

[0426] Specific operation: The device receives the recommendation list sent from the server and displays it on the user interface (UI). The user can view detailed information about each restaurant, its safety score, and emotional response suggestions.

[0427] Input: Recommendation data in JSON format from the server.

[0428] Output: The recommendation list displayed in the user interface.

[0429] Step 11:

[0430] The user selects a restaurant and makes a reservation.

[0431] Specific behavior: The user selects the desired restaurant from the presented restaurant list and makes a reservation within the app or visits the restaurant in person.

[0432] Input: User selection.

[0433] Output: Booking completed or visit.

[0434] Step 12:

[0435] The user provides feedback.

[0436] Specific operation: The user actually visits a restaurant and, after finishing their meal, provides feedback within the app, including their satisfaction with the meal, their evaluation of allergy-related responses, and their emotional reactions to the suggested restaurant.

[0437] Input: User feedback.

[0438] Output: The feedback data is sent to the server.

[0439] Step 13:

[0440] The server collects and uses the feedback.

[0441] Specific operation: The server collects feedback information provided by users and stores it in a database. This feedback information is used to improve the evaluation accuracy of the AI ​​analysis engine and emotion engine.

[0442] Input: User feedback.

[0443] Output: Improved model and estimated accuracy.

[0444] (Application example 2)

[0445] 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."

[0446] Conventional restaurant recommendation systems primarily select restaurants based on dietary restrictions and allergies, but this approach fails to fully consider the user's emotional state and fails to provide an optimal user experience. In particular, for food delivery services, where a user's emotions have a significant impact on meal satisfaction, restaurant recommendation systems that take emotional data into account are needed.

[0447] The identification process by the identification 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 dietary restriction information and allergy information input from a user terminal, means for receiving emotion data, means for searching for appropriate restaurant information from a database based on the dietary restriction information, allergy information, and emotion data, means for analyzing menu trends and past reviews of the appropriate restaurant information and evaluating safety, and means for presenting a list of restaurants suitable for the user based on the evaluated safety and emotion data. This makes it possible to provide optimal restaurants and dishes tailored to the user's emotional state in addition to their dietary restriction and allergy information.

[0448] A "user terminal" is a device that a user operates to input information, and specifically refers to a smartphone, personal computer, etc.

[0449] "Dietary restriction information" is information about foods and ingredients that a user should avoid, such as vegetarians, vegans, or certain religious dietary restrictions.

[0450] "Allergy information" refers to information about foods or ingredients that may cause a user an allergic reaction, such as peanut allergies or dairy allergies.

[0451] "Emotion data" is information that indicates the user's current emotional state, and is data obtained from the user's facial expression, tone of voice, input content, and the like.

[0452] A "database" refers to a data structure that stores data such as restaurant information, menu items, and reviews, and can be used for searching and analysis.

[0453] "Appropriate restaurant information" is information about restaurants selected based on the user's dietary restriction information, allergy information, and emotional data, and specifically includes the restaurant name, location, menu information, and the like.

[0454] "Menu trends" refers to the general characteristics or patterns of food served at a particular restaurant.

[0455] "Past reviews" are ratings and comments provided by users who have previously visited the restaurant, and are important information for evaluating the quality of the restaurant and the user experience.

[0456] "Safety level" is an index that indicates the degree to which a particular restaurant or dish meets the user's dietary restriction information and allergy information.

[0457] "List format" refers to a format in which search results are organized and displayed so that they are easy for users to view, and usually refers to a list format in which the results are divided into categories.

[0458] A system for carrying out the present invention is realized by the cooperation of a user terminal, a server, and a database.

[0459] 1. User terminal processing

[0460] The user terminal can be a smartphone, tablet, or personal computer. The user inputs information about dietary restrictions and allergies, as well as emotional data into the application. Emotional data is obtained from the user's facial expressions, tone of voice, and input content. This information is structured in JSON format and sent to the server via an API.

[0461] 2. Server Processing

[0462] The server receives dietary restriction information, allergy information, and emotional data sent by the user. This data is stored in a database on the server. The server then searches the database for appropriate restaurant information and evaluates safety by analyzing menu trends and past reviews. In addition, based on the emotional data, it suggests restaurants that suit the user's emotions. These suggestions are generated in list form and sent to the user's device via API.

[0463] 3. Display on the user's device

[0464] The user device displays the restaurant list received from the server on the user interface. The list includes the name of each restaurant, its safety score, a menu summary, and emotional response suggestions. The user can select and reserve a restaurant based on this information.

[0465] Software and hardware used

[0466] Hardware: Smartphones, tablets, personal computers

[0467] Software: Python, RESTful API, requests library, emotion recognition engine

[0468] Specific examples of processing

[0469] For example, if User A inputs the dietary restrictions "vegan" and "nut allergy" and the emotional state "happy," the system will search for vegan-friendly restaurants that do not use nuts and suggest restaurants with the "fun" feeling that matches the emotional state. Similarly, if User B inputs the information "gluten-free" and "dairy allergy" and the feeling of "stress," the system will prioritize suggesting restaurants with a relaxing atmosphere.

[0470] Example prompts for generative AI models

[0471] Enter your emotional state, dietary restrictions, and allergy information. For example, "Emotional state: happy, dietary restrictions: vegan, allergy information: nuts." The system will then use this information to suggest the best restaurants and dishes.

[0472] In this way, the present invention can provide a more personalized restaurant recommendation and food delivery experience by taking into account not only a user's dietary restrictions and allergy information, but also their emotional state.

[0473] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0474] Step 1:

[0475] The user enters information about dietary restrictions, allergies, and emotional state from their device. Specifically, they open the application and enter information such as "vegan," "nut allergy," or "happy." The entered data is then properly formatted (JSON format) within the app.

[0476] Input: Dietary restriction information, allergy information, emotional state

[0477] Processing: Data entry and formatting

[0478] Output: User data in JSON format

[0479] Step 2:

[0480] The device sends the data formatted in step 1 to the server. At this time, it uses an HTTP request to send JSON formatted data via the API. After sending, it checks whether the request was processed correctly.

[0481] Input: User data in JSON format

[0482] Processing: Sending data via HTTP request

[0483] Output: A confirmation response for data transfer to the server

[0484] Step 3:

[0485] The server receives the user data sent from the device. The received data is first analyzed and then saved in a database. The database records user information associated with the user ID.

[0486] Input: User data in JSON format

[0487] Processing: Receiving and analyzing data, storing it in a database

[0488] Output: User information stored in the database

[0489] Step 4:

[0490] The server searches the database for appropriate restaurant information. The restaurant information is filtered based on dietary restrictions, allergies, and emotional state. Filtering is done using SQL queries, etc.

[0491] Input: User information stored in the database

[0492] Processing: Searching and filtering restaurant information using SQL queries, etc.

[0493] Output: A list of restaurants suitable for the user

[0494] Step 5:

[0495] The server performs AI analysis on the filtered restaurant information to evaluate its safety, analyzing past reviews and menu trends, and scoring the level of allergy-friendliness.

[0496] Input: Filtered restaurant information

[0497] Processing: Safety assessment using AI analysis

[0498] Output: Restaurant information with safety scores

[0499] Step 6:

[0500] The server evaluates which restaurant best suits the user's emotional state based on the emotional data, for example, choosing a restaurant with a relaxing atmosphere for a stressed user, or a restaurant with adventurous cuisine for a happy user.

[0501] Input: Restaurant information with safety scores and sentiment data

[0502] Processing: Selecting the best restaurant based on sentiment data

[0503] Output: Final restaurant list with sentiment-based suggestions

[0504] Step 7:

[0505] The server sends the final restaurant list to the device via the API, again using an HTTP request to transfer the data and returning it in the appropriate structure (JSON format).

[0506] Input: Final restaurant list with sentiment-based suggestions

[0507] Processing: Sending data via HTTP request

[0508] Output: Confirmation response of data transfer to the device

[0509] Step 8:

[0510] The device displays the restaurant list received from the server on a user interface, organized in a list format, and allows users to view detailed information about each restaurant, its safety score, and emotional response suggestions.

[0511] Input: The final restaurant list received from the server

[0512] Processing: Displaying data in the user interface

[0513] Output: The list of restaurants displayed to the user

[0514] In this way, users can receive restaurant and food recommendations that take into account their dietary restrictions, allergy information, and emotional state.

[0515] 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.

[0516] 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.

[0517] 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.

[0518] [Second embodiment]

[0519] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0520] 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.

[0521] 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).

[0522] 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.

[0523] 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.

[0524] 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).

[0525] 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.

[0526] 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.

[0527] 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.

[0528] 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.

[0529] 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.

[0530] 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."

[0531] The present invention is a system that suggests appropriate restaurants based on a user's dietary restrictions and allergy information. The program processing of this system will be described in detail below.

[0532] User terminal processing

[0533] 1. Enter information

[0534] A user opens a food app on their device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information such as nut allergies, gluten-free diets, or vegan diets into a form.

[0535] 2. Information Transmission

[0536] The device sends the information entered by the user to the server via API, including information on dietary restrictions and allergies.

[0537] Server Processing

[0538] 3. Receiving Information

[0539] The server receives the dietary restriction and allergy information sent by the user, and stores the received information in a database.

[0540] 4. Database Search

[0541] Based on the received information, the server searches for restaurant information in a database that includes restaurant names, locations, menu information, allergen information, etc.

[0542] 5. Safety Assessment

[0543] The server uses an AI analysis engine to analyze restaurant information suitable for the user. During the analysis process, the safety of the restaurant is evaluated based on the restaurant's menu trends and past reviews. For example, for a user with a nut allergy, a restaurant that offers nut-free menu items will be given a high safety rating.

[0544] 6. Recommendation Generation

[0545] The server generates a list of restaurants suitable for the user based on the safety rating. The generated restaurant list also includes the safety rating of each restaurant.

[0546] 7. Sending Recommendations

[0547] The restaurant list generated by the server is sent to the terminal via API.

[0548] User terminal processing (display)

[0549] 8. Receiving and Displaying Information

[0550] The device displays the restaurant list received from the server on the user interface (UI). The user can check the list to see which restaurants are safe for them.

[0551] User Action

[0552] 9. Restaurant Selection and Reservations

[0553] The user selects the restaurant they want from the list of restaurants presented, then makes a reservation within the app or visits the restaurant in person.

[0554] feedback

[0555] 10. Providing Feedback

[0556] After a user visits a restaurant and finishes their meal, they provide feedback within the app, including their satisfaction with the meal and their rating of allergy-related issues.

[0557] Server processing (feedback)

[0558] 11. Collect and use feedback

[0559] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[0560] In this way, the present invention allows users to easily find safe restaurants that take into account their dietary restrictions and allergies. Furthermore, by utilizing feedback, the reliability and accuracy of the overall system can be continuously improved.

[0561] The processing flow will be explained below.

[0562] Step 1:

[0563] A user opens a food app on a device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information like "nut allergy" or "dairy-free."

[0564] Step 2:

[0565] The device sends the dietary restriction and allergy information entered by the user to the server via the API. During the sending process, the entered information is structured in JSON format and sent as an HTTP request.

[0566] Step 3:

[0567] The server stores the received dietary restriction and allergy information in a database. This information is stored in association with the user's ID.

[0568] Step 4:

[0569] The server retrieves all restaurant information from the database and filters it based on the received dietary restrictions and allergy information. This filtering checks the ingredients and components contained in the restaurant menu and lists restaurants that meet the user's criteria.

[0570] Step 5:

[0571] The server uses an AI analysis engine to evaluate the safety of the listed restaurants, analyzing menu items, past reviews, ingredient information, and other factors to calculate an overall safety score.

[0572] Step 6:

[0573] The server generates a list of restaurants suitable for the user based on the safety rating, including the restaurant's name, safety score, location, and menu summary.

[0574] Step 7:

[0575] The server generates a list of restaurants and sends it to the terminal via the API. The response data is structured in JSON format.

[0576] Step 8:

[0577] The device displays the restaurant list received from the server on a user interface (UI). The UI is organized in a list format, allowing users to easily view detailed information and safety scores for each restaurant.

[0578] Step 9:

[0579] The user selects the restaurant they want from the list of restaurants presented, then makes a reservation within the app or visits the restaurant in person.

[0580] Step 10:

[0581] After a user visits a restaurant and finishes their meal, they provide feedback within the app, including their satisfaction with the meal and their rating of allergy-related issues.

[0582] Step 11:

[0583] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[0584] Example 1

[0585] 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."

[0586] Conventional restaurant search systems do not adequately consider users' dietary restrictions or allergies when suggesting restaurants, making it difficult for users to find restaurants they can trust. Furthermore, the reliability of the safety of the suggested restaurants is low, necessitating improvements to increase user satisfaction. Furthermore, there is a lack of a way to effectively utilize user feedback to improve the system's accuracy.

[0587] 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.

[0588] In this invention, the server includes: means for receiving dietary restriction information and allergy information input from a user terminal; means for searching for appropriate restaurant information from a database based on the dietary restriction information and allergy information; means for analyzing the menu trends and past reviews of the appropriate restaurant information using a generative AI model to evaluate safety; means for presenting a list of restaurants suitable for the user based on the evaluated safety; means for transmitting the list to the user terminal; and means for displaying the list through a user interface of the user terminal. This allows the system to present restaurants with a high safety rating based on the user's dietary restriction information and allergy information, enabling the user to easily find a restaurant they can use with confidence. Furthermore, the system can collect user feedback and use it to improve the accuracy of the evaluation, thereby continuously improving the reliability of the system and user satisfaction.

[0589] "User terminal" refers to a device such as a smartphone or PC used by a user, and is a device for inputting information and receiving output from a system.

[0590] "Dietary restriction information" refers to information that prevents a user from consuming certain foods or ingredients, including, for example, vegan or low-calorie restrictions.

[0591] "Allergy information" refers to information about foods that a user should avoid because they react to certain allergens, such as nut allergies or milk allergies.

[0592] A "database" is a system that refers to a collection of accumulated data that stores restaurant information, menu information, allergen information, etc.

[0593] A "generative AI model" refers to an analytical engine that uses artificial intelligence to analyze, predict, and classify data.

[0594] "Menu trends" refers to statistical trends regarding the types, frequency, and ingredients of meals served at a particular restaurant.

[0595] "Past Reviews" refers to a record of ratings and comments provided by a User in the past, including User's reactions to a restaurant or its services.

[0596] "Safety level" is an evaluation index that indicates whether a particular restaurant is safe for the user, taking into consideration the user's dietary restrictions and allergy information.

[0597] "List format" refers to the method of presenting restaurant information in bulleted or tabular form, in a way that is easy for users to visually check.

[0598] "User interface (UI)" refers to the screens and operating means that allow a user to interact with a system, including, for example, application screens and buttons.

[0599] "Feedback information" refers to information such as ratings and comments provided by users after they have actually used a service or product.

[0600] The present invention relates to a system for suggesting suitable restaurants based on a user's dietary restriction information and allergy information. Hereinafter, an embodiment of the present invention will be described in detail.

[0601] Hardware and software used

[0602] Hardware

[0603] User terminal: A device such as a smartphone or PC that allows a user to input information and receive output from the system.

[0604] Server: A device that manages the entire system, processes and analyzes data, and manages databases.

[0605] software

[0606] Food app: An application installed on a user's device that allows them to enter information about dietary restrictions and allergies and display suggested restaurant information.

[0607] API: An interface for exchanging information between a user terminal and a server.

[0608] Database management system: A system for storing and managing restaurant information and user information.

[0609] AI analysis engine: A system that uses generative AI models to analyze data and evaluate restaurant safety.

[0610] Explanation of program processing

[0611] User terminal processing

[0612] First, the user launches the food app on their smartphone or PC and enters information about dietary restrictions and allergies. For example, they enter information such as "nut allergy," "gluten-free," or "vegan" into the input form. The device then sends the entered information to the server via an API. The sent information is in JSON format, and includes information about dietary restrictions and allergies.

[0613] Server Processing

[0614] The server receives the user's dietary restriction and allergy information via the API and stores it in a database. It then searches the database for appropriate restaurant information based on the stored information. The server then uses a generative AI model to analyze the menu trends and past reviews of the searched restaurant information and evaluates its safety. Specifically, for a user with a nut allergy, the server rates restaurants that offer nut-free menus highly as safe. Based on the evaluation results, it generates a list of restaurants suitable for the user and sends this list to the user's device.

[0615] User terminal processing (display)

[0616] The user device displays the restaurant list received from the server on the user interface (UI). The user can select the restaurant they want from the displayed list and make a reservation within the app or visit the restaurant in person.

[0617] User feedback

[0618] After a user visits a restaurant and finishes their meal, they provide feedback within the app. This feedback includes their satisfaction with the meal and an evaluation of whether the restaurant handled allergies. The server collects the feedback information provided by the user and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[0619] Examples of specific examples and prompts

[0620] As a concrete example, consider a case where a user with a nut allergy uses a food app to search for a suitable restaurant. The user enters "nut allergy" and the device sends this information to the server. The server searches for restaurants that offer nut-free menus and evaluates their safety. Based on the evaluation results, a list of appropriate restaurants is generated and sent to the user's device. The user then selects the desired restaurant from the displayed list and makes a reservation.

[0621] Example prompt sentence:

[0622] "Please suggest restaurants that are suitable for users with nut allergies."

[0623] "Search for and list vegan-friendly restaurants."

[0624] The above is an embodiment of the present invention. Taking into account the user's dietary restrictions and allergy information, it is possible to easily find a restaurant that is safe to use. Furthermore, by utilizing feedback from users, the reliability and evaluation accuracy of the entire system can be continuously improved.

[0625] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0626] Step 1:

[0627] Enter information

[0628] Users launch the food app on their smartphone or PC and enter information about dietary restrictions and allergies.

[0629] Input: Nut allergy, gluten-free, vegan, etc. information.

[0630] How it works: A user fills out an application form and clicks the "Submit" button.

[0631] Output: The entered dietary restriction information and allergy information is saved on the device.

[0632] Step 2:

[0633] Information transmission

[0634] The device sends the entered dietary restriction and allergy information to the server via API.

[0635] Input: User-entered dietary restrictions and allergy information.

[0636] How it works: The device sends information to the server as a JSON-formatted API request.

[0637] Output: Dietary restrictions and allergy information sent to the server.

[0638] Step 3:

[0639] Receiving information

[0640] The server stores the dietary restriction and allergy information received via the API in a database.

[0641] Input: Dietary restriction and allergy information sent from your device.

[0642] How it works: The server parses the API request and stores the received information in a database.

[0643] Output: User's dietary restrictions and allergies stored in a database.

[0644] Step 4:

[0645] Database search

[0646] The server searches the database for appropriate restaurant information based on the stored user information.

[0647] Input: User's dietary restrictions and allergies stored in the database.

[0648] How it works: The server uses an SQL query to extract restaurant information from a database that matches the criteria.

[0649] Output: A list of restaurants that match the user's criteria.

[0650] Step 5:

[0651] Safety Rating

[0652] The server uses an AI analysis engine to analyze the menu trends and past reviews of the searched restaurant information and evaluate its safety.

[0653] Input: Restaurant information extracted from the database, menu trends, and past reviews.

[0654] How it works: Using a generative AI model, we analyze and evaluate the safety of restaurants. For example, we can evaluate a restaurant that offers nut-free menu items as being safe for a user with a nut allergy.

[0655] Output: A list of restaurant information with safety rating results.

[0656] Step 6:

[0657] Recommendation Generation

[0658] The server generates a list of restaurants suitable for the user based on the evaluated safety level.

[0659] Input: A list of restaurant information with safety rating results.

[0660] How it works: The server generates a list of restaurants based on the rating results and adds a safety rating for each restaurant to the list.

[0661] Output: The generated restaurant list.

[0662] Step 7:

[0663] Sending Recommendations

[0664] The server sends the generated restaurant list to the terminal via API.

[0665] Input: The generated restaurant list.

[0666] How it works: The server sends a list of restaurants to the device as a JSON-formatted API response.

[0667] Output: The restaurant list sent to the device.

[0668] Step 8:

[0669] Information reception and display

[0670] The terminal displays the restaurant list received from the server on a user interface (UI).

[0671] Input: A list of restaurants sent by the server.

[0672] Operation: The device analyzes the received information and displays it in a list format on the user interface. The user can then select a restaurant from the displayed list.

[0673] Output: The restaurant list displayed in a user interface.

[0674] Step 9:

[0675] Restaurant selection and reservations

[0676] Users can select the restaurant they want from the displayed list and make a reservation within the app, or visit the restaurant in person.

[0677] Input: A list of restaurants displayed in a user interface.

[0678] How it works: The user selects the restaurant they want, then uses the reservation feature to enter the date, time, and number of people to confirm the reservation, or visits the selected restaurant in person.

[0679] Output: The reservation is confirmed or information to visit the restaurant is displayed.

[0680] Step 10:

[0681] Providing Feedback

[0682] Users visit the restaurant in person, eat there and then provide feedback within the app.

[0683] Input: User's impressions and ratings after their visit. For example, this includes satisfaction with the food and ratings of allergy-related issues.

[0684] Action: A user fills in the feedback form and clicks the "Submit" button.

[0685] Output: The user's feedback information is saved on the device.

[0686] Step 11:

[0687] Collecting and using feedback

[0688] The server collects feedback information provided by users and stores it in a database. This feedback information is then used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[0689] Input: User feedback information sent from the device.

[0690] How it works: The server receives feedback information, stores it in a database, analyzes the stored feedback information, and provides feedback to the AI ​​analysis engine to improve the accuracy of the evaluation.

[0691] Output: An AI analysis engine with improved evaluation accuracy and an updated database.

[0692] (Application example 1)

[0693] 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."

[0694] Previously, it was difficult for users with dietary restrictions or allergies to find suitable restaurants, which posed a risk of accidents and problems. Furthermore, there was a lack of a mechanism for improving the system based on feedback from users after they had actually visited the restaurant, making it difficult to recommend restaurants with high accuracy. Another issue was how smoothly users could make reservations at recommended restaurants.

[0695] 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.

[0696] In this invention, the server includes means for receiving dietary restriction information and allergy information input from a user terminal, means for searching for appropriate dining facility information from a database based on the dietary restriction information and allergy information, means for analyzing menu trends and past reviews of the appropriate dining facility information and evaluating its safety, means for making reservations on the user terminal based on the evaluated safety, means for collecting feedback information from users and using it to improve the accuracy of the evaluated safety, and means for displaying the appropriate dining facility information through a user interface. This allows users with dietary restrictions or allergies to easily and safely find suitable dining facilities and make reservations smoothly. Furthermore, the accuracy of the system can be constantly improved through feedback.

[0697] "User terminal" refers to electronic devices used by users in general, including smartphones, tablets, personal computers, etc.

[0698] "Dining establishment information" refers to information necessary for users, such as the name of the dining establishment, its location, the menu items offered, and allergen information.

[0699] "Dietary restriction information" refers to a user's individual requirements for restricting certain ingredients or nutrients, and includes, for example, information such as gluten-free or low-carb.

[0700] "Allergy Information" refers to information about specific foods or ingredients to which a user has an allergic reaction.

[0701] "Search means" refers to software or a system that searches a database for appropriate restaurant information based on the user's dietary restrictions and allergy information.

[0702] "Means of analysis" refers to software and algorithms that evaluate the menu trends and past ratings of restaurant information and determine the safety level for users.

[0703] "Safety assessment method" refers to the process or system used to determine how safe a restaurant is in relation to a user's dietary restrictions or allergy information.

[0704] "Means for presenting in list format" refers to a user interface or display method for displaying a list of suitable dining establishments on a user's terminal.

[0705] "Means for making a reservation" refers to functionality or software that allows a user to make a reservation at a dining establishment selected by the user.

[0706] "Feedback information" refers to information such as ratings, comments, and satisfaction levels of restaurants and bars that users have actually visited.

[0707] "Means for displaying through a user interface" refers to a screen or interface for visually displaying dining establishment information on a user terminal.

[0708] This invention is a system that allows users to input information about dietary restrictions and allergies using a user terminal, searches for and suggests appropriate dining facilities via a server, and then makes reservations.

[0709] System Configuration

[0710] User terminal

[0711] The user device refers to an electronic device such as a smartphone, tablet, or personal computer, on which a mobile app using React Native is installed. This application allows users to input information about dietary restrictions and allergies and send it to the server.

[0712] server

[0713] The server receives the information sent from the user's device, searches the database, and provides appropriate restaurant information using AI analysis engines such as Google Cloud Machine Learning and Azure Machine Learning.

[0714] Program Overview

[0715] 1. Enter and submit information

[0716] Users open the smartphone app and enter their dietary restrictions (e.g., gluten-free or vegan) and allergy information (e.g., nut allergy) into a form. Once the information is complete, the user's device sends this information to the server using Axious.

[0717] 2. Database Search and Analysis

[0718] The server searches the database for appropriate restaurant information based on the received information. It uses an AI analysis engine to analyze menu trends and past reviews and evaluate safety. The safety evaluation criteria are based on whether the information meets the user's dietary restrictions and allergies.

[0719] 3. Generate and display a restaurant list

[0720] Based on the analysis results, the server generates a list of restaurants suitable for the user and sends it back to the user's device as an HTTP response. The user's device then displays the received list in list format within the app.

[0721] 4. Booking and Feedback

[0722] Users can select a restaurant from the list and make a reservation within the app. After visiting, users can provide feedback within the app. The collected feedback information is sent to the server and used to improve the accuracy of the system.

[0723] Specific examples

[0724] For example, if a user has a nut allergy and a vegan diet, they would enter the following information:

[0725] plaintext

[0726] Allergy Information: Nut allergy

[0727] Dietary Restrictions:Vegan

[0728] Based on this information, the server searches the database for restaurants that meet the user's requirements and generates a prompt like the following:

[0729] plaintext

[0730] Please suggest safe dining options based on the allergy information and dietary restrictions below:

[0731] Allergy Information: Nut allergy

[0732] Dietary Restrictions:Vegan

[0733] Proposed dining establishments should include the following information:

[0734] Name of restaurant

[0735] location

[0736] Menu Information

[0737] Safety level

[0738] Based on this prompt, the AI ​​analysis engine evaluates and selects suitable dining options and presents them to the user in a list format. The user can then select one from the list, make a reservation, and provide feedback after the visit.

[0739] This system allows users to easily find safe restaurants that meet their dietary restrictions and allergies, allowing them to enjoy meals safely. Furthermore, by improving the system's accuracy based on collected feedback, more reliable recommendations can be achieved.

[0740] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0741] Step 1:

[0742] The user opens the smartphone app. On the app interface, the user enters their dietary restrictions (e.g., gluten-free) and allergy information (e.g., nut allergy). After entering the information, the user presses the "Submit" button to proceed to the next step. This prepares the input data.

[0743] Step 2:

[0744] The user device sends the entered dietary restriction and allergy information to the server as an HTTP POST request using Axious. The server analyzes the received data and prepares a database search. The input is the user's dietary restriction and allergy information, and the output is JSON format data received by the server.

[0745] Step 3:

[0746] The server searches the database based on the received dietary restriction and allergy information. Specifically, it compares the menus of each restaurant in the database with the user's requirements and narrows down the list to restaurants that meet all the requirements. The input is the database stored on the server, and the output is a list of restaurant information that matches the requirements.

[0747] Step 4:

[0748] The server then uses an AI analysis engine to further analyze the narrowed-down restaurant information. During the analysis process, it evaluates the restaurant's menu trends and past reviews and calculates the safety rating of each restaurant. The input is restaurant information, and the output is a list of restaurants with a safety rating.

[0749] Step 5:

[0750] The server generates a list of restaurants that are most suitable for the user based on the safety assessment and sends it to the user's device as a list in an HTTP response. The output is a JSON-formatted list of restaurants that is sent to the user's device.

[0751] Step 6:

[0752] The user device receives the list of restaurants and displays it in list format within the app. The user selects the restaurant they are interested in from the displayed list. The input is the restaurant list data from the server, and the output is the restaurant information displayed in list format.

[0753] Step 7:

[0754] The user makes a reservation for the selected restaurant within the app. The reservation information is sent to the server using Axious. The server receives the reservation information and sends a reservation request to the restaurant. The input is the reservation information, and the output is the reservation confirmation data.

[0755] Step 8:

[0756] After a user visits a restaurant and finishes their meal, they provide feedback within the app. The feedback information is then sent to the server using Axious. The server stores the received feedback information in a database and uses it to improve the evaluation accuracy of the AI ​​analysis engine. The input is the feedback information, and the output is learning data for improving accuracy.

[0757] By going through the above steps, users can easily find and safely use restaurants that meet their dietary restrictions and allergies. The collected feedback information improves the system's evaluation accuracy, resulting in more reliable recommendations.

[0758] 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.

[0759] The present invention is a system that suggests appropriate restaurants based on a user's dietary restrictions and allergies, and also combines it with an emotion engine that recognizes the user's emotions to improve the accuracy of restaurant suggestions and the user experience. The program processing of this system is described in detail below.

[0760] User terminal processing

[0761] 1. Enter information

[0762] A user opens a food app on a device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information like "nut allergy" or "dairy-free."

[0763] 2. Emotion recognition

[0764] The emotion engine installed in the device acquires emotion data from the user's input, operations, facial expressions, tone of voice, etc. This emotion data indicates the user's current emotional state.

[0765] 3. Information Transmission

[0766] The device sends the dietary restriction information, allergy information, and emotional data entered by the user to the server via the API. During the sending process, the entered information and emotional data are structured in JSON format and sent as an HTTP request.

[0767] Server Processing

[0768] 4. Receiving Information

[0769] The server receives information about dietary restrictions, allergies, and emotional data sent by the user, and stores the received information in a database.

[0770] 5. Database Search

[0771] Based on the received information, the server searches for restaurant information in a database that includes restaurant names, locations, menu information, allergen information, etc., and filters restaurants that match the user's criteria.

[0772] 6. Safety Assessment

[0773] The server uses an AI analysis engine to evaluate the safety of the listed restaurants, analyzing menu items, past reviews, ingredient information, and other factors to calculate an overall safety score.

[0774] 7. Utilizing Emotional Data

[0775] The server analyzes the emotion data acquired by the emotion engine and makes suggestions according to the user's emotional state, such as suggesting restaurants with a more relaxing environment if the user is feeling stressed.

[0776] 8. Recommendation Generation

[0777] The server generates a list of restaurants suitable for the user based on the safety rating and emotion data. The list includes the restaurant's name, safety score, location, menu summary, and emotional response suggestions.

[0778] 9. Sending Recommendations

[0779] The server generates a list of restaurants and sends it to the terminal via the API. The response data is structured in JSON format.

[0780] User terminal processing (display)

[0781] 10. Receiving and Displaying Information

[0782] The device displays the restaurant list received from the server in a user interface (UI). The UI is organized in a list format, allowing users to easily view detailed information, safety scores, and emotional response suggestions for each restaurant.

[0783] User Action

[0784] 11. Restaurant Selection and Reservations

[0785] The user selects the desired restaurant from the presented restaurant list and makes a reservation within the app or visits the restaurant in person.

[0786] feedback

[0787] 12. Providing Feedback

[0788] After users visit a restaurant and finish their meal, they provide in-app feedback, including satisfaction with the meal, a rating of allergy accommodations, and emotional reactions to the suggested restaurant.

[0789] Server processing (feedback)

[0790] 13. Collect and use feedback

[0791] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine and emotion engine.

[0792] In this way, the present invention allows users to easily find safe restaurants that take into account their emotional state as well as their dietary restrictions and allergies. Furthermore, by utilizing feedback, the reliability and accuracy of the overall system can be continuously improved.

[0793] The processing flow will be explained below.

[0794] Step 1:

[0795] A user opens a food app on a device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information like "nut allergy" or "dairy-free."

[0796] Step 2:

[0797] The device acquires emotional data from the user's input, operations, facial expressions, tone of voice, etc. At this time, the emotion engine analyzes the user's emotions in real time and determines their emotional state, such as stress, satisfaction, or joy.

[0798] Step 3:

[0799] The device converts the dietary restriction information, allergy information, and emotional data entered by the user into JSON format and sends it to the server via an API.

[0800] Step 4:

[0801] The server receives information on dietary restrictions, allergies, and emotional data from the user, associates each piece of information, and stores it in a database. The stored information is linked to the user ID.

[0802] Step 5:

[0803] The server retrieves all restaurant information from the database and filters it based on dietary restrictions and allergies. This filtering involves checking the ingredients and components contained in restaurant menus and listing restaurants that meet the user's criteria.

[0804] Step 6:

[0805] The server uses an AI analysis engine to evaluate the safety of the listed restaurants, calculating an overall safety score based on the restaurant's menu items, past reviews, and ingredient information.

[0806] Step 7:

[0807] The server then uses the emotion data to suggest restaurants that correspond to the user's emotional state. For example, if the user is feeling stressed, it will prioritize restaurants that offer a high level of relaxation.

[0808] Step 8:

[0809] The server generates a list of restaurants suitable for the user based on the safety rating and emotion data. The list includes the restaurant's name, safety score, location, menu summary, and emotional response suggestions.

[0810] Step 9:

[0811] The server generates a list of restaurants and sends it to the device via API. The data is structured in JSON format.

[0812] Step 10:

[0813] The device displays the restaurant list received from the server in a user interface (UI). The UI is organized in a list format, allowing users to easily view detailed information, safety scores, and emotional response suggestions for each restaurant.

[0814] Step 11:

[0815] The user selects the restaurant they want from the presented list, makes a reservation within the app, or visits the restaurant in person.

[0816] Step 12:

[0817] After users visit a restaurant and finish their meal, they provide feedback within the app, including their satisfaction with the meal, their rating of allergy accommodations, and their emotional reaction to the suggested restaurant.

[0818] Step 13:

[0819] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine and emotion engine. This will improve the accuracy and reliability of future suggestions.

[0820] Example 2

[0821] 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."

[0822] Conventional restaurant search systems were able to suggest appropriate restaurants based on a user's dietary restrictions and allergies. However, they did not take into account the user's emotional state, limiting the improvement of the user experience. Furthermore, there was no mechanism in place to fully utilize feedback information when rating the safety of the suggested restaurants, leaving challenges in improving the accuracy of the ratings.

[0823] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving dietary restriction information and allergy information input from a user terminal; means for searching for appropriate facility information from a database based on the dietary restriction information and allergy information; means for analyzing menu trends and past reviews of the appropriate facility information and evaluating safety; means for presenting a list of facilities suitable for the user based on the evaluated safety level and the user's emotional data; means for analyzing the user's input content and facial expressions using an emotion recognition engine installed in the user terminal and acquiring emotional data; and means for analyzing the acquired emotional data and preferentially suggesting facilities with a relaxing environment. This allows the user to easily find safe facilities that take into account not only their dietary restriction and allergy information but also their emotional state. Furthermore, the reliability and evaluation accuracy of the entire system can be continuously improved based on feedback information.

[0824] A "user terminal" is an electronic device used by a user, including a smartphone, a PC, etc.

[0825] "Dietary restriction information" is information about foods and ingredients that the user wants to avoid consuming.

[0826] "Allergy information" is information about foods or ingredients to which the user is allergic.

[0827] An "emotion recognition engine" is software that includes technology for acquiring emotional data from a user's facial expressions, tone of voice, etc.

[0828] A "server" is a central computer system responsible for processing and storing data.

[0829] A "database" is a system that stores information systematically and enables efficient searching and access.

[0830] "Appropriate facility information" is information about facilities (restaurants, etc.) that have been filtered based on the user's dietary restriction information and allergy information.

[0831] "Safety level" is a score that evaluates the safety of dietary restriction information and allergy information for the user.

[0832] The "means for presenting in list form" is a method for displaying the evaluated information to the user as a list.

[0833] "Feedback information" refers to evaluations and impressions based on actual experiences provided by users.

[0834] "Emotion data" is data that indicates the user's emotional state, and is obtained from the user's facial expression and tone of voice.

[0835] The present invention is a system that proposes appropriate facilities based on a user's dietary restriction information and allergy information, and also combines it with an emotion engine that recognizes the user's emotions to improve the accuracy of proposals and the user experience. An embodiment of the system of the present invention will be described in detail below.

[0836] System Overview

[0837] This system consists of a user terminal, a server, and a database. The user terminal is an electronic device such as a smartphone or PC, and is the device through which the user enters information about their dietary restrictions and allergies. The server is a central computer system responsible for processing and storing data, and the database is a system that systematically stores information and enables efficient search and access.

[0838] Hardware and software used

[0839] 1. User Device

[0840] A device such as a smartphone or PC that allows users to enter information about dietary restrictions and allergies.

[0841] Equipped with an emotion recognition engine (such as Microsoft Azure's Emotion API or Google Cloud's Vision AI).

[0842] 2. Server

[0843] A central computer system that processes and stores data.

[0844] Connect to a database (such as MySQL or PostgreSQL) to manage your data.

[0845] 3. Software and APIs

[0846] Data communication between user devices and servers is achieved through RESTful API.

[0847] Safety is evaluated using an AI analysis engine (a model using TensorFlow and PyTorch).

[0848] Data processing and calculation

[0849] 1. Enter information

[0850] The user opens a food app on their device and enters their dietary restrictions and allergies, such as "nut allergy" or "dairy-free."

[0851] 2. Emotion recognition

[0852] The device uses an emotion recognition engine to analyze the user's facial expressions and tone of voice to obtain emotional data, and measures the user's emotional state in real time through the camera and microphone.

[0853] 3. Information Transmission

[0854] The device structures the entered dietary restriction information and acquired emotional data into JSON format and sends it to the server via a RESTful API.

[0855] 4. Receiving Information

[0856] The server receives the data sent from the terminal in JSON format and stores it in a database.

[0857] 5. Database Search

[0858] The server searches a database based on the received dietary restriction and allergy information and extracts appropriate restaurant information.

[0859] 6. Safety Assessment

[0860] The server uses an AI analysis engine to evaluate safety, analyzing restaurant menu information and past reviews to calculate an overall safety score.

[0861] 7. Emotion Data Analysis

[0862] The server analyzes the acquired emotional data and gives priority to suggesting restaurants with a relaxing environment for the user.

[0863] 8. Recommendation Generation

[0864] The server generates a list of restaurants suitable for the user based on the safety score and sentiment data.

[0865] 9. Information Transmission and Display

[0866] The server structures the generated restaurant list in JSON format and sends it to the device via a RESTful API. The device then displays the received list on the user interface.

[0867] Specific examples

[0868] Suppose a user enters "nut allergy" and "dairy-free" into a food app, and the emotion recognition engine detects high stress levels. Based on this information, the server suggests restaurants with a high safety rating and a relaxing environment. For example, the server presents the user with a list of two restaurants: "Relax Bistro" and "Healthy Eats."

[0869] Prompt Sentence Examples

[0870] "When a user enters nut allergies and dairy-free diets and the emotion engine detects a stressed state, what type of restaurant should be suggested? Please explain, including the specific restaurant names and the reason for the suggestions."

[0871] In this way, users can easily find restaurants that fit their dietary restrictions and emotional state, and continuous feedback can be collected and utilized to improve the reliability and accuracy of the entire system.

[0872] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0873] Step 1:

[0874] The user enters the information.

[0875] Specific operation: A user opens a food app and enters their dietary restrictions and allergies into the device. For example, they enter "nut allergy" or "dairy-free" into the form.

[0876] Input: User's dietary restrictions and allergy information.

[0877] Output: Dietary restriction information and allergy information are saved on the device.

[0878] Step 2:

[0879] The device recognizes emotions.

[0880] How it works: The device uses an emotion recognition engine (such as Microsoft Azure's Emotion API) to analyze the user's facial expressions and tone of voice to obtain emotional data. The analysis is carried out in real time via the camera and microphone.

[0881] Input: User facial and voice data.

[0882] Output: The user's emotional data (e.g., stress level) is obtained.

[0883] Step 3:

[0884] The terminal transmits the information.

[0885] Specific operation: The device structures the acquired dietary restriction information, allergy information, and emotion data into JSON format and sends it to the server via a RESTful API.

[0886] Input: dietary restriction information, allergy information, emotional data.

[0887] Output: Data structured in JSON format is sent to the server.

[0888] Step 4:

[0889] The server receives the information.

[0890] Specific operation: The server receives the JSON data sent from the terminal, parses it, and saves it in the database.

[0891] Input: JSON formatted data from the terminal.

[0892] Output: Parsed data stored in a database.

[0893] Step 5:

[0894] The server searches the database.

[0895] What it does: The server searches for restaurant information in its database based on the dietary restrictions and allergies received, and uses an SQL query to find the appropriate restaurant.

[0896] Input: Facility information, dietary restrictions, and allergy information in the database.

[0897] Output: A list of restaurants that match the criteria.

[0898] Step 6:

[0899] The server evaluates the security level.

[0900] How it works: The server uses an AI analysis engine (e.g., a TensorFlow model) to evaluate the safety of the listed restaurants. It analyzes menu information, past reviews, ingredient lists, etc. to calculate a safety score.

[0901] Input: Listed restaurant information, menu information, past reviews, ingredient list.

[0902] Output: Safety score for each restaurant.

[0903] Step 7:

[0904] The server utilizes the emotion data.

[0905] Specific operation: The server analyzes the user's emotional state based on the acquired emotional data. For example, if the user is feeling stressed, it will prioritize and suggest restaurants with a relaxing environment.

[0906] Input: Sentiment data, safety score.

[0907] Output: A list of restaurants that match the user's emotional state.

[0908] Step 8:

[0909] The server generates the recommendations.

[0910] Specific operation: The server generates a list of restaurants suitable for the user based on the safety score and emotion data. The list includes the restaurant name, safety score, location, and menu summary.

[0911] Input: Safety score, sentiment data.

[0912] Output: A recommendation list.

[0913] Step 9:

[0914] The server sends the recommendations.

[0915] Specific operation: The server structures the generated recommendation list in JSON format and sends it to the terminal via a RESTful API.

[0916] Input: A recommendation list.

[0917] Output: Data structured in JSON format is sent to the terminal.

[0918] Step 10:

[0919] The terminal receives and displays the information.

[0920] Specific operation: The device receives the recommendation list sent from the server and displays it on the user interface (UI). The user can view detailed information about each restaurant, its safety score, and emotional response suggestions.

[0921] Input: Recommendation data in JSON format from the server.

[0922] Output: The recommendation list displayed in the user interface.

[0923] Step 11:

[0924] The user selects a restaurant and makes a reservation.

[0925] Specific behavior: The user selects the desired restaurant from the presented restaurant list and makes a reservation within the app or visits the restaurant in person.

[0926] Input: User selection.

[0927] Output: Booking completed or visit.

[0928] Step 12:

[0929] The user provides feedback.

[0930] Specific operation: The user actually visits a restaurant and, after finishing their meal, provides feedback within the app, including their satisfaction with the meal, their evaluation of allergy-related responses, and their emotional reactions to the suggested restaurant.

[0931] Input: User feedback.

[0932] Output: The feedback data is sent to the server.

[0933] Step 13:

[0934] The server collects and uses the feedback.

[0935] Specific operation: The server collects feedback information provided by users and stores it in a database. This feedback information is used to improve the evaluation accuracy of the AI ​​analysis engine and emotion engine.

[0936] Input: User feedback.

[0937] Output: Improved model and estimated accuracy.

[0938] (Application example 2)

[0939] 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."

[0940] Conventional restaurant recommendation systems primarily select restaurants based on dietary restrictions and allergies, but this approach fails to fully consider the user's emotional state and fails to provide an optimal user experience. In particular, for food delivery services, where a user's emotions have a significant impact on meal satisfaction, restaurant recommendation systems that take emotional data into account are needed.

[0941] The identification process by the identification 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 dietary restriction information and allergy information input from a user terminal, means for receiving emotion data, means for searching for appropriate restaurant information from a database based on the dietary restriction information, allergy information, and emotion data, means for analyzing menu trends and past reviews of the appropriate restaurant information and evaluating safety, and means for presenting a list of restaurants suitable for the user based on the evaluated safety and emotion data. This makes it possible to provide optimal restaurants and dishes tailored to the user's emotional state in addition to their dietary restriction and allergy information.

[0942] A "user terminal" is a device that a user operates to input information, and specifically refers to a smartphone, personal computer, etc.

[0943] "Dietary restriction information" is information about foods and ingredients that a user should avoid, such as vegetarians, vegans, or certain religious dietary restrictions.

[0944] "Allergy information" refers to information about foods or ingredients that may cause a user an allergic reaction, such as peanut allergies or dairy allergies.

[0945] "Emotion data" is information that indicates the user's current emotional state, and is data obtained from the user's facial expression, tone of voice, input content, and the like.

[0946] A "database" refers to a data structure that stores data such as restaurant information, menu items, and reviews, and can be used for searching and analysis.

[0947] "Appropriate restaurant information" is information about restaurants selected based on the user's dietary restriction information, allergy information, and emotional data, and specifically includes the restaurant name, location, menu information, and the like.

[0948] "Menu trends" refers to the general characteristics or patterns of food served at a particular restaurant.

[0949] "Past reviews" are ratings and comments provided by users who have previously visited the restaurant, and are important information for evaluating the quality of the restaurant and the user experience.

[0950] "Safety level" is an index that indicates the degree to which a particular restaurant or dish meets the user's dietary restriction information and allergy information.

[0951] "List format" refers to a format in which search results are organized and displayed so that they are easy for users to view, and usually refers to a list format in which the results are divided into categories.

[0952] A system for carrying out the present invention is realized by the cooperation of a user terminal, a server, and a database.

[0953] 1. User terminal processing

[0954] The user terminal can be a smartphone, tablet, or personal computer. The user inputs information about dietary restrictions and allergies, as well as emotional data into the application. Emotional data is obtained from the user's facial expressions, tone of voice, and input content. This information is structured in JSON format and sent to the server via an API.

[0955] 2. Server Processing

[0956] The server receives dietary restriction information, allergy information, and emotional data sent by the user. This data is stored in a database on the server. The server then searches the database for appropriate restaurant information and evaluates safety by analyzing menu trends and past reviews. In addition, based on the emotional data, it suggests restaurants that suit the user's emotions. These suggestions are generated in list form and sent to the user's device via API.

[0957] 3. Display on the user's device

[0958] The user device displays the restaurant list received from the server on the user interface. The list includes the name of each restaurant, its safety score, a menu summary, and emotional response suggestions. The user can select and reserve a restaurant based on this information.

[0959] Software and hardware used

[0960] Hardware: Smartphones, tablets, personal computers

[0961] Software: Python, RESTful API, requests library, emotion recognition engine

[0962] Specific examples of processing

[0963] For example, if User A inputs the dietary restrictions "vegan" and "nut allergy" and the emotional state "happy," the system will search for vegan-friendly restaurants that do not use nuts and suggest restaurants with the "fun" feeling that matches the emotional state. Similarly, if User B inputs the information "gluten-free" and "dairy allergy" and the feeling of "stress," the system will prioritize suggesting restaurants with a relaxing atmosphere.

[0964] Example prompts for generative AI models

[0965] Enter your emotional state, dietary restrictions, and allergy information. For example, "Emotional state: happy, dietary restrictions: vegan, allergy information: nuts." The system will then use this information to suggest the best restaurants and dishes.

[0966] In this way, the present invention can provide a more personalized restaurant recommendation and food delivery experience by taking into account not only a user's dietary restrictions and allergy information, but also their emotional state.

[0967] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0968] Step 1:

[0969] The user enters information about dietary restrictions, allergies, and emotional state from their device. Specifically, they open the application and enter information such as "vegan," "nut allergy," or "happy." The entered data is then properly formatted (JSON format) within the app.

[0970] Input: Dietary restriction information, allergy information, emotional state

[0971] Processing: Data entry and formatting

[0972] Output: User data in JSON format

[0973] Step 2:

[0974] The device sends the data formatted in step 1 to the server. At this time, it uses an HTTP request to send JSON formatted data via the API. After sending, it checks whether the request was processed correctly.

[0975] Input: User data in JSON format

[0976] Processing: Sending data via HTTP request

[0977] Output: A confirmation response for data transfer to the server

[0978] Step 3:

[0979] The server receives the user data sent from the device. The received data is first analyzed and then saved in a database. The database records user information associated with the user ID.

[0980] Input: User data in JSON format

[0981] Processing: Receiving and analyzing data, storing it in a database

[0982] Output: User information stored in the database

[0983] Step 4:

[0984] The server searches the database for appropriate restaurant information. The restaurant information is filtered based on dietary restrictions, allergies, and emotional state. Filtering is done using SQL queries, etc.

[0985] Input: User information stored in the database

[0986] Processing: Searching and filtering restaurant information using SQL queries, etc.

[0987] Output: A list of restaurants suitable for the user

[0988] Step 5:

[0989] The server performs AI analysis on the filtered restaurant information to evaluate its safety, analyzing past reviews and menu trends, and scoring the level of allergy-friendliness.

[0990] Input: Filtered restaurant information

[0991] Processing: Safety assessment using AI analysis

[0992] Output: Restaurant information with safety scores

[0993] Step 6:

[0994] The server evaluates which restaurant best suits the user's emotional state based on the emotional data, for example, choosing a restaurant with a relaxing atmosphere for a stressed user, or a restaurant with adventurous cuisine for a happy user.

[0995] Input: Restaurant information with safety scores and sentiment data

[0996] Processing: Selecting the best restaurant based on sentiment data

[0997] Output: Final restaurant list with sentiment-based suggestions

[0998] Step 7:

[0999] The server sends the final restaurant list to the device via the API, again using an HTTP request to transfer the data and returning it in the appropriate structure (JSON format).

[1000] Input: Final restaurant list with sentiment-based suggestions

[1001] Processing: Sending data via HTTP request

[1002] Output: Confirmation response of data transfer to the device

[1003] Step 8:

[1004] The device displays the restaurant list received from the server on a user interface, organized in a list format, and allows users to view detailed information about each restaurant, its safety score, and emotional response suggestions.

[1005] Input: The final restaurant list received from the server

[1006] Processing: Displaying data in the user interface

[1007] Output: The list of restaurants displayed to the user

[1008] In this way, users can receive restaurant and food recommendations that take into account their dietary restrictions, allergy information, and emotional state.

[1009] 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.

[1010] 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.

[1011] 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.

[1012] [Third embodiment]

[1013] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1014] 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.

[1015] 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).

[1016] 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.

[1017] 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.

[1018] 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).

[1019] 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.

[1020] 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.

[1021] 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.

[1022] 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.

[1023] 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.

[1024] 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."

[1025] The present invention is a system that suggests appropriate restaurants based on a user's dietary restrictions and allergy information. The program processing of this system will be described in detail below.

[1026] User terminal processing

[1027] 1. Enter information

[1028] A user opens a food app on their device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information such as nut allergies, gluten-free diets, or vegan diets into a form.

[1029] 2. Information Transmission

[1030] The device sends the information entered by the user to the server via API, including information on dietary restrictions and allergies.

[1031] Server Processing

[1032] 3. Receiving Information

[1033] The server receives the dietary restriction and allergy information sent by the user, and stores the received information in a database.

[1034] 4. Database Search

[1035] Based on the received information, the server searches for restaurant information in a database that includes restaurant names, locations, menu information, allergen information, etc.

[1036] 5. Safety Assessment

[1037] The server uses an AI analysis engine to analyze restaurant information suitable for the user. During the analysis process, the safety of the restaurant is evaluated based on the restaurant's menu trends and past reviews. For example, for a user with a nut allergy, a restaurant that offers nut-free menu items will be given a high safety rating.

[1038] 6. Recommendation Generation

[1039] The server generates a list of restaurants suitable for the user based on the safety rating. The generated restaurant list also includes the safety rating of each restaurant.

[1040] 7. Sending Recommendations

[1041] The restaurant list generated by the server is sent to the terminal via API.

[1042] User terminal processing (display)

[1043] 8. Receiving and Displaying Information

[1044] The device displays the restaurant list received from the server on the user interface (UI). The user can check the list to see which restaurants are safe for them.

[1045] User Action

[1046] 9. Restaurant Selection and Reservations

[1047] The user selects the restaurant they want from the list of restaurants presented, then makes a reservation within the app or visits the restaurant in person.

[1048] feedback

[1049] 10. Providing Feedback

[1050] After a user visits a restaurant and finishes their meal, they provide feedback within the app, including their satisfaction with the meal and their rating of allergy-related issues.

[1051] Server processing (feedback)

[1052] 11. Collect and use feedback

[1053] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[1054] In this way, the present invention allows users to easily find safe restaurants that take into account their dietary restrictions and allergies. Furthermore, by utilizing feedback, the reliability and accuracy of the overall system can be continuously improved.

[1055] The processing flow will be explained below.

[1056] Step 1:

[1057] A user opens a food app on a device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information like "nut allergy" or "dairy-free."

[1058] Step 2:

[1059] The device sends the dietary restriction and allergy information entered by the user to the server via the API. During the sending process, the entered information is structured in JSON format and sent as an HTTP request.

[1060] Step 3:

[1061] The server stores the received dietary restriction and allergy information in a database. This information is stored in association with the user's ID.

[1062] Step 4:

[1063] The server retrieves all restaurant information from the database and filters it based on the received dietary restrictions and allergy information. This filtering checks the ingredients and components contained in the restaurant menu and lists restaurants that meet the user's criteria.

[1064] Step 5:

[1065] The server uses an AI analysis engine to evaluate the safety of the listed restaurants, analyzing menu items, past reviews, ingredient information, and other factors to calculate an overall safety score.

[1066] Step 6:

[1067] The server generates a list of restaurants suitable for the user based on the safety rating, including the restaurant's name, safety score, location, and menu summary.

[1068] Step 7:

[1069] The server generates a list of restaurants and sends it to the terminal via the API. The response data is structured in JSON format.

[1070] Step 8:

[1071] The device displays the restaurant list received from the server on a user interface (UI). The UI is organized in a list format, allowing users to easily view detailed information and safety scores for each restaurant.

[1072] Step 9:

[1073] The user selects the restaurant they want from the list of restaurants presented, then makes a reservation within the app or visits the restaurant in person.

[1074] Step 10:

[1075] After a user visits a restaurant and finishes their meal, they provide feedback within the app, including their satisfaction with the meal and their rating of allergy-related issues.

[1076] Step 11:

[1077] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[1078] Example 1

[1079] 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."

[1080] Conventional restaurant search systems do not adequately consider users' dietary restrictions or allergies when suggesting restaurants, making it difficult for users to find restaurants they can trust. Furthermore, the reliability of the safety of the suggested restaurants is low, necessitating improvements to increase user satisfaction. Furthermore, there is a lack of a way to effectively utilize user feedback to improve the system's accuracy.

[1081] 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.

[1082] In this invention, the server includes: means for receiving dietary restriction information and allergy information input from a user terminal; means for searching for appropriate restaurant information from a database based on the dietary restriction information and allergy information; means for analyzing the menu trends and past reviews of the appropriate restaurant information using a generative AI model to evaluate safety; means for presenting a list of restaurants suitable for the user based on the evaluated safety; means for transmitting the list to the user terminal; and means for displaying the list through a user interface of the user terminal. This allows the system to present restaurants with a high safety rating based on the user's dietary restriction information and allergy information, enabling the user to easily find a restaurant they can use with confidence. Furthermore, the system can collect user feedback and use it to improve the accuracy of the evaluation, thereby continuously improving the reliability of the system and user satisfaction.

[1083] "User terminal" refers to a device such as a smartphone or PC used by a user, and is a device for inputting information and receiving output from a system.

[1084] "Dietary restriction information" refers to information that prevents a user from consuming certain foods or ingredients, including, for example, vegan or low-calorie restrictions.

[1085] "Allergy information" refers to information about foods that a user should avoid because they react to certain allergens, such as nut allergies or milk allergies.

[1086] A "database" is a system that refers to a collection of accumulated data that stores restaurant information, menu information, allergen information, etc.

[1087] A "generative AI model" refers to an analytical engine that uses artificial intelligence to analyze, predict, and classify data.

[1088] "Menu trends" refers to statistical trends regarding the types, frequency, and ingredients of meals served at a particular restaurant.

[1089] "Past Reviews" refers to a record of ratings and comments provided by a User in the past, including User's reactions to a restaurant or its services.

[1090] "Safety level" is an evaluation index that indicates whether a particular restaurant is safe for the user, taking into consideration the user's dietary restrictions and allergy information.

[1091] "List format" refers to the method of presenting restaurant information in bulleted or tabular form, in a way that is easy for users to visually check.

[1092] "User interface (UI)" refers to the screens and operating means that allow a user to interact with a system, including, for example, application screens and buttons.

[1093] "Feedback information" refers to information such as ratings and comments provided by users after they have actually used a service or product.

[1094] The present invention relates to a system for suggesting suitable restaurants based on a user's dietary restriction information and allergy information. Hereinafter, an embodiment of the present invention will be described in detail.

[1095] Hardware and software used

[1096] Hardware

[1097] User terminal: A device such as a smartphone or PC that allows a user to input information and receive output from the system.

[1098] Server: A device that manages the entire system, processes and analyzes data, and manages databases.

[1099] software

[1100] Food app: An application installed on a user's device that allows them to enter information about dietary restrictions and allergies and display suggested restaurant information.

[1101] API: An interface for exchanging information between a user terminal and a server.

[1102] Database management system: A system for storing and managing restaurant information and user information.

[1103] AI analysis engine: A system that uses generative AI models to analyze data and evaluate restaurant safety.

[1104] Explanation of program processing

[1105] User terminal processing

[1106] First, the user launches the food app on their smartphone or PC and enters information about dietary restrictions and allergies. For example, they enter information such as "nut allergy," "gluten-free," or "vegan" into the input form. The device then sends the entered information to the server via an API. The sent information is in JSON format, and includes information about dietary restrictions and allergies.

[1107] Server Processing

[1108] The server receives the user's dietary restriction and allergy information via the API and stores it in a database. It then searches the database for appropriate restaurant information based on the stored information. The server then uses a generative AI model to analyze the menu trends and past reviews of the searched restaurant information and evaluates its safety. Specifically, for a user with a nut allergy, the server rates restaurants that offer nut-free menus highly as safe. Based on the evaluation results, it generates a list of restaurants suitable for the user and sends this list to the user's device.

[1109] User terminal processing (display)

[1110] The user device displays the restaurant list received from the server on the user interface (UI). The user can select the restaurant they want from the displayed list and make a reservation within the app or visit the restaurant in person.

[1111] User feedback

[1112] After a user visits a restaurant and finishes their meal, they provide feedback within the app. This feedback includes their satisfaction with the meal and an evaluation of whether the restaurant handled allergies. The server collects the feedback information provided by the user and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[1113] Examples of specific examples and prompts

[1114] As a concrete example, consider a case where a user with a nut allergy uses a food app to search for a suitable restaurant. The user enters "nut allergy" and the device sends this information to the server. The server searches for restaurants that offer nut-free menus and evaluates their safety. Based on the evaluation results, a list of appropriate restaurants is generated and sent to the user's device. The user then selects the desired restaurant from the displayed list and makes a reservation.

[1115] Example prompt sentence:

[1116] "Please suggest restaurants that are suitable for users with nut allergies."

[1117] "Search for and list vegan-friendly restaurants."

[1118] The above is an embodiment of the present invention. Taking into account the user's dietary restrictions and allergy information, it is possible to easily find a restaurant that is safe to use. Furthermore, by utilizing feedback from users, the reliability and evaluation accuracy of the entire system can be continuously improved.

[1119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1120] Step 1:

[1121] Enter information

[1122] Users launch the food app on their smartphone or PC and enter information about dietary restrictions and allergies.

[1123] Input: Nut allergy, gluten-free, vegan, etc. information.

[1124] How it works: A user fills out an application form and clicks the "Submit" button.

[1125] Output: The entered dietary restriction information and allergy information is saved on the device.

[1126] Step 2:

[1127] Information transmission

[1128] The device sends the entered dietary restriction and allergy information to the server via API.

[1129] Input: User-entered dietary restrictions and allergy information.

[1130] How it works: The device sends information to the server as a JSON-formatted API request.

[1131] Output: Dietary restrictions and allergy information sent to the server.

[1132] Step 3:

[1133] Receiving information

[1134] The server stores the dietary restriction and allergy information received via the API in a database.

[1135] Input: Dietary restriction and allergy information sent from your device.

[1136] How it works: The server parses the API request and stores the received information in a database.

[1137] Output: User's dietary restrictions and allergies stored in a database.

[1138] Step 4:

[1139] Database search

[1140] The server searches the database for appropriate restaurant information based on the stored user information.

[1141] Input: User's dietary restrictions and allergies stored in the database.

[1142] How it works: The server uses an SQL query to extract restaurant information from a database that matches the criteria.

[1143] Output: A list of restaurants that match the user's criteria.

[1144] Step 5:

[1145] Safety Rating

[1146] The server uses an AI analysis engine to analyze the menu trends and past reviews of the searched restaurant information and evaluate its safety.

[1147] Input: Restaurant information extracted from the database, menu trends, and past reviews.

[1148] How it works: Using a generative AI model, we analyze and evaluate the safety of restaurants. For example, we can evaluate a restaurant that offers nut-free menu items as being safe for a user with a nut allergy.

[1149] Output: A list of restaurant information with safety rating results.

[1150] Step 6:

[1151] Recommendation Generation

[1152] The server generates a list of restaurants suitable for the user based on the evaluated safety level.

[1153] Input: A list of restaurant information with safety rating results.

[1154] How it works: The server generates a list of restaurants based on the rating results and adds a safety rating for each restaurant to the list.

[1155] Output: The generated restaurant list.

[1156] Step 7:

[1157] Sending Recommendations

[1158] The server sends the generated restaurant list to the terminal via API.

[1159] Input: The generated restaurant list.

[1160] How it works: The server sends a list of restaurants to the device as a JSON-formatted API response.

[1161] Output: The restaurant list sent to the device.

[1162] Step 8:

[1163] Information reception and display

[1164] The terminal displays the restaurant list received from the server on a user interface (UI).

[1165] Input: A list of restaurants sent by the server.

[1166] Operation: The device analyzes the received information and displays it in a list format on the user interface. The user can then select a restaurant from the displayed list.

[1167] Output: The restaurant list displayed in a user interface.

[1168] Step 9:

[1169] Restaurant selection and reservations

[1170] Users can select the restaurant they want from the displayed list and make a reservation within the app, or visit the restaurant in person.

[1171] Input: A list of restaurants displayed in a user interface.

[1172] How it works: The user selects the restaurant they want, then uses the reservation feature to enter the date, time, and number of people to confirm the reservation, or visits the selected restaurant in person.

[1173] Output: The reservation is confirmed or information to visit the restaurant is displayed.

[1174] Step 10:

[1175] Providing Feedback

[1176] Users visit the restaurant in person, eat there and then provide feedback within the app.

[1177] Input: User's impressions and ratings after their visit. For example, this includes satisfaction with the food and ratings of allergy-related issues.

[1178] Action: A user fills in the feedback form and clicks the "Submit" button.

[1179] Output: The user's feedback information is saved on the device.

[1180] Step 11:

[1181] Collecting and using feedback

[1182] The server collects feedback information provided by users and stores it in a database. This feedback information is then used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[1183] Input: User feedback information sent from the device.

[1184] How it works: The server receives feedback information, stores it in a database, analyzes the stored feedback information, and provides feedback to the AI ​​analysis engine to improve the accuracy of the evaluation.

[1185] Output: An AI analysis engine with improved evaluation accuracy and an updated database.

[1186] (Application example 1)

[1187] 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."

[1188] Previously, it was difficult for users with dietary restrictions or allergies to find suitable restaurants, which posed a risk of accidents and problems. Furthermore, there was a lack of a mechanism for improving the system based on feedback from users after they had actually visited the restaurant, making it difficult to recommend restaurants with high accuracy. Another issue was how smoothly users could make reservations at recommended restaurants.

[1189] 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.

[1190] In this invention, the server includes means for receiving dietary restriction information and allergy information input from a user terminal, means for searching for appropriate dining facility information from a database based on the dietary restriction information and allergy information, means for analyzing menu trends and past reviews of the appropriate dining facility information and evaluating its safety, means for making reservations on the user terminal based on the evaluated safety, means for collecting feedback information from users and using it to improve the accuracy of the evaluated safety, and means for displaying the appropriate dining facility information through a user interface. This allows users with dietary restrictions or allergies to easily and safely find suitable dining facilities and make reservations smoothly. Furthermore, the accuracy of the system can be constantly improved through feedback.

[1191] "User terminal" refers to electronic devices used by users in general, including smartphones, tablets, personal computers, etc.

[1192] "Dining establishment information" refers to information necessary for users, such as the name of the dining establishment, its location, the menu items offered, and allergen information.

[1193] "Dietary restriction information" refers to a user's individual requirements for restricting certain ingredients or nutrients, and includes, for example, information such as gluten-free or low-carb.

[1194] "Allergy Information" refers to information about specific foods or ingredients to which a user has an allergic reaction.

[1195] "Search means" refers to software or a system that searches a database for appropriate restaurant information based on the user's dietary restrictions and allergy information.

[1196] "Means of analysis" refers to software and algorithms that evaluate the menu trends and past ratings of restaurant information and determine the safety level for users.

[1197] "Safety assessment method" refers to the process or system used to determine how safe a restaurant is in relation to a user's dietary restrictions or allergy information.

[1198] "Means for presenting in list format" refers to a user interface or display method for displaying a list of suitable dining establishments on a user's terminal.

[1199] "Means for making a reservation" refers to functionality or software that allows a user to make a reservation at a dining establishment selected by the user.

[1200] "Feedback information" refers to information such as ratings, comments, and satisfaction levels of restaurants and bars that users have actually visited.

[1201] "Means for displaying through a user interface" refers to a screen or interface for visually displaying dining establishment information on a user terminal.

[1202] This invention is a system that allows users to input information about dietary restrictions and allergies using a user terminal, searches for and suggests appropriate dining facilities via a server, and then makes reservations.

[1203] System Configuration

[1204] User terminal

[1205] The user device refers to an electronic device such as a smartphone, tablet, or personal computer, on which a mobile app using React Native is installed. This application allows users to input information about dietary restrictions and allergies and send it to the server.

[1206] server

[1207] The server receives the information sent from the user's device, searches the database, and provides appropriate restaurant information using AI analysis engines such as Google Cloud Machine Learning and Azure Machine Learning.

[1208] Program Overview

[1209] 1. Enter and submit information

[1210] Users open the smartphone app and enter their dietary restrictions (e.g., gluten-free or vegan) and allergy information (e.g., nut allergy) into a form. Once the information is complete, the user's device sends this information to the server using Axious.

[1211] 2. Database Search and Analysis

[1212] The server searches the database for appropriate restaurant information based on the received information. It uses an AI analysis engine to analyze menu trends and past reviews and evaluate safety. The safety evaluation criteria are based on whether the information meets the user's dietary restrictions and allergies.

[1213] 3. Generate and display a restaurant list

[1214] Based on the analysis results, the server generates a list of restaurants suitable for the user and sends it back to the user's device as an HTTP response. The user's device then displays the received list in list format within the app.

[1215] 4. Booking and Feedback

[1216] Users can select a restaurant from the list and make a reservation within the app. After visiting, users can provide feedback within the app. The collected feedback information is sent to the server and used to improve the accuracy of the system.

[1217] Specific examples

[1218] For example, if a user has a nut allergy and a vegan diet, they would enter the following information:

[1219] plaintext

[1220] Allergy Information: Nut allergy

[1221] Dietary Restrictions:Vegan

[1222] Based on this information, the server searches the database for restaurants that meet the user's requirements and generates a prompt like the following:

[1223] plaintext

[1224] Please suggest safe dining options based on the allergy information and dietary restrictions below:

[1225] Allergy Information: Nut allergy

[1226] Dietary Restrictions:Vegan

[1227] Proposed dining establishments should include the following information:

[1228] Name of restaurant

[1229] location

[1230] Menu Information

[1231] Safety level

[1232] Based on this prompt, the AI ​​analysis engine evaluates and selects suitable dining options and presents them to the user in a list format. The user can then select one from the list, make a reservation, and provide feedback after the visit.

[1233] This system allows users to easily find safe restaurants that meet their dietary restrictions and allergies, allowing them to enjoy meals safely. Furthermore, by improving the system's accuracy based on collected feedback, more reliable recommendations can be achieved.

[1234] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1235] Step 1:

[1236] The user opens the smartphone app. On the app interface, the user enters their dietary restrictions (e.g., gluten-free) and allergy information (e.g., nut allergy). After entering the information, the user presses the "Submit" button to proceed to the next step. This prepares the input data.

[1237] Step 2:

[1238] The user device sends the entered dietary restriction and allergy information to the server as an HTTP POST request using Axious. The server analyzes the received data and prepares a database search. The input is the user's dietary restriction and allergy information, and the output is JSON format data received by the server.

[1239] Step 3:

[1240] The server searches the database based on the received dietary restriction and allergy information. Specifically, it compares the menus of each restaurant in the database with the user's requirements and narrows down the list to restaurants that meet all the requirements. The input is the database stored on the server, and the output is a list of restaurant information that matches the requirements.

[1241] Step 4:

[1242] The server then uses an AI analysis engine to further analyze the narrowed-down restaurant information. During the analysis process, it evaluates the restaurant's menu trends and past reviews and calculates the safety rating of each restaurant. The input is restaurant information, and the output is a list of restaurants with a safety rating.

[1243] Step 5:

[1244] The server generates a list of restaurants that are most suitable for the user based on the safety assessment and sends it to the user's device as a list in an HTTP response. The output is a JSON-formatted list of restaurants that is sent to the user's device.

[1245] Step 6:

[1246] The user device receives the list of restaurants and displays it in list format within the app. The user selects the restaurant they are interested in from the displayed list. The input is the restaurant list data from the server, and the output is the restaurant information displayed in list format.

[1247] Step 7:

[1248] The user makes a reservation for the selected restaurant within the app. The reservation information is sent to the server using Axious. The server receives the reservation information and sends a reservation request to the restaurant. The input is the reservation information, and the output is the reservation confirmation data.

[1249] Step 8:

[1250] After a user visits a restaurant and finishes their meal, they provide feedback within the app. The feedback information is then sent to the server using Axious. The server stores the received feedback information in a database and uses it to improve the evaluation accuracy of the AI ​​analysis engine. The input is the feedback information, and the output is learning data for improving accuracy.

[1251] By going through the above steps, users can easily find and safely use restaurants that meet their dietary restrictions and allergies. The collected feedback information improves the system's evaluation accuracy, resulting in more reliable recommendations.

[1252] 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.

[1253] The present invention is a system that suggests appropriate restaurants based on a user's dietary restrictions and allergies, and also combines it with an emotion engine that recognizes the user's emotions to improve the accuracy of restaurant suggestions and the user experience. The program processing of this system is described in detail below.

[1254] User terminal processing

[1255] 1. Enter information

[1256] A user opens a food app on a device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information like "nut allergy" or "dairy-free."

[1257] 2. Emotion recognition

[1258] The emotion engine installed in the device acquires emotion data from the user's input, operations, facial expressions, tone of voice, etc. This emotion data indicates the user's current emotional state.

[1259] 3. Information Transmission

[1260] The device sends the dietary restriction information, allergy information, and emotional data entered by the user to the server via the API. During the sending process, the entered information and emotional data are structured in JSON format and sent as an HTTP request.

[1261] Server Processing

[1262] 4. Receiving Information

[1263] The server receives information about dietary restrictions, allergies, and emotional data sent by the user, and stores the received information in a database.

[1264] 5. Database Search

[1265] Based on the received information, the server searches for restaurant information in a database that includes restaurant names, locations, menu information, allergen information, etc., and filters restaurants that match the user's criteria.

[1266] 6. Safety Assessment

[1267] The server uses an AI analysis engine to evaluate the safety of the listed restaurants, analyzing menu items, past reviews, ingredient information, and other factors to calculate an overall safety score.

[1268] 7. Utilizing Emotional Data

[1269] The server analyzes the emotion data acquired by the emotion engine and makes suggestions according to the user's emotional state, such as suggesting restaurants with a more relaxing environment if the user is feeling stressed.

[1270] 8. Recommendation Generation

[1271] The server generates a list of restaurants suitable for the user based on the safety rating and emotion data. The list includes the restaurant's name, safety score, location, menu summary, and emotional response suggestions.

[1272] 9. Sending Recommendations

[1273] The server generates a list of restaurants and sends it to the terminal via the API. The response data is structured in JSON format.

[1274] User terminal processing (display)

[1275] 10. Receiving and Displaying Information

[1276] The device displays the restaurant list received from the server in a user interface (UI). The UI is organized in a list format, allowing users to easily view detailed information, safety scores, and emotional response suggestions for each restaurant.

[1277] User Action

[1278] 11. Restaurant Selection and Reservations

[1279] The user selects the desired restaurant from the presented restaurant list and makes a reservation within the app or visits the restaurant in person.

[1280] feedback

[1281] 12. Providing Feedback

[1282] After users visit a restaurant and finish their meal, they provide in-app feedback, including satisfaction with the meal, a rating of allergy accommodations, and emotional reactions to the suggested restaurant.

[1283] Server processing (feedback)

[1284] 13. Collect and use feedback

[1285] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine and emotion engine.

[1286] In this way, the present invention allows users to easily find safe restaurants that take into account their emotional state as well as their dietary restrictions and allergies. Furthermore, by utilizing feedback, the reliability and accuracy of the overall system can be continuously improved.

[1287] The processing flow will be explained below.

[1288] Step 1:

[1289] A user opens a food app on a device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information like "nut allergy" or "dairy-free."

[1290] Step 2:

[1291] The device acquires emotional data from the user's input, operations, facial expressions, tone of voice, etc. At this time, the emotion engine analyzes the user's emotions in real time and determines their emotional state, such as stress, satisfaction, or joy.

[1292] Step 3:

[1293] The device converts the dietary restriction information, allergy information, and emotional data entered by the user into JSON format and sends it to the server via an API.

[1294] Step 4:

[1295] The server receives information on dietary restrictions, allergies, and emotional data from the user, associates each piece of information, and stores it in a database. The stored information is linked to the user ID.

[1296] Step 5:

[1297] The server retrieves all restaurant information from the database and filters it based on dietary restrictions and allergies. This filtering involves checking the ingredients and components contained in restaurant menus and listing restaurants that meet the user's criteria.

[1298] Step 6:

[1299] The server uses an AI analysis engine to evaluate the safety of the listed restaurants, calculating an overall safety score based on the restaurant's menu items, past reviews, and ingredient information.

[1300] Step 7:

[1301] The server then uses the emotion data to suggest restaurants that correspond to the user's emotional state. For example, if the user is feeling stressed, it will prioritize restaurants that offer a high level of relaxation.

[1302] Step 8:

[1303] The server generates a list of restaurants suitable for the user based on the safety rating and emotion data. The list includes the restaurant's name, safety score, location, menu summary, and emotional response suggestions.

[1304] Step 9:

[1305] The server generates a list of restaurants and sends it to the device via API. The data is structured in JSON format.

[1306] Step 10:

[1307] The device displays the restaurant list received from the server in a user interface (UI). The UI is organized in a list format, allowing users to easily view detailed information, safety scores, and emotional response suggestions for each restaurant.

[1308] Step 11:

[1309] The user selects the restaurant they want from the presented list, makes a reservation within the app, or visits the restaurant in person.

[1310] Step 12:

[1311] After users visit a restaurant and finish their meal, they provide feedback within the app, including their satisfaction with the meal, their rating of allergy accommodations, and their emotional reaction to the suggested restaurant.

[1312] Step 13:

[1313] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine and emotion engine. This will improve the accuracy and reliability of future suggestions.

[1314] Example 2

[1315] 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."

[1316] Conventional restaurant search systems were able to suggest appropriate restaurants based on a user's dietary restrictions and allergies. However, they did not take into account the user's emotional state, limiting the improvement of the user experience. Furthermore, there was no mechanism in place to fully utilize feedback information when rating the safety of the suggested restaurants, leaving challenges in improving the accuracy of the ratings.

[1317] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving dietary restriction information and allergy information input from a user terminal; means for searching for appropriate facility information from a database based on the dietary restriction information and allergy information; means for analyzing menu trends and past reviews of the appropriate facility information and evaluating safety; means for presenting a list of facilities suitable for the user based on the evaluated safety level and the user's emotional data; means for analyzing the user's input content and facial expressions using an emotion recognition engine installed in the user terminal and acquiring emotional data; and means for analyzing the acquired emotional data and preferentially suggesting facilities with a relaxing environment. This allows the user to easily find safe facilities that take into account not only their dietary restriction and allergy information but also their emotional state. Furthermore, the reliability and evaluation accuracy of the entire system can be continuously improved based on feedback information.

[1318] A "user terminal" is an electronic device used by a user, including a smartphone, a PC, etc.

[1319] "Dietary restriction information" is information about foods and ingredients that the user wants to avoid consuming.

[1320] "Allergy information" is information about foods or ingredients to which the user is allergic.

[1321] An "emotion recognition engine" is software that includes technology for acquiring emotional data from a user's facial expressions, tone of voice, etc.

[1322] A "server" is a central computer system responsible for processing and storing data.

[1323] A "database" is a system that stores information systematically and enables efficient searching and access.

[1324] "Appropriate facility information" is information about facilities (restaurants, etc.) that have been filtered based on the user's dietary restriction information and allergy information.

[1325] "Safety level" is a score that evaluates the safety of dietary restriction information and allergy information for the user.

[1326] The "means for presenting in list form" is a method for displaying the evaluated information to the user as a list.

[1327] "Feedback information" refers to evaluations and impressions based on actual experiences provided by users.

[1328] "Emotion data" is data that indicates the user's emotional state, and is obtained from the user's facial expression and tone of voice.

[1329] The present invention is a system that proposes appropriate facilities based on a user's dietary restriction information and allergy information, and also combines it with an emotion engine that recognizes the user's emotions to improve the accuracy of proposals and the user experience. An embodiment of the system of the present invention will be described in detail below.

[1330] System Overview

[1331] This system consists of a user terminal, a server, and a database. The user terminal is an electronic device such as a smartphone or PC, and is the device through which the user enters information about their dietary restrictions and allergies. The server is a central computer system responsible for processing and storing data, and the database is a system that systematically stores information and enables efficient search and access.

[1332] Hardware and software used

[1333] 1. User Device

[1334] A device such as a smartphone or PC that allows users to enter information about dietary restrictions and allergies.

[1335] Equipped with an emotion recognition engine (such as Microsoft Azure's Emotion API or Google Cloud's Vision AI).

[1336] 2. Server

[1337] A central computer system that processes and stores data.

[1338] Connect to a database (such as MySQL or PostgreSQL) to manage your data.

[1339] 3. Software and APIs

[1340] Data communication between user devices and servers is achieved through RESTful API.

[1341] Safety is evaluated using an AI analysis engine (a model using TensorFlow and PyTorch).

[1342] Data processing and calculation

[1343] 1. Enter information

[1344] The user opens a food app on their device and enters their dietary restrictions and allergies, such as "nut allergy" or "dairy-free."

[1345] 2. Emotion recognition

[1346] The device uses an emotion recognition engine to analyze the user's facial expressions and tone of voice to obtain emotional data, and measures the user's emotional state in real time through the camera and microphone.

[1347] 3. Information Transmission

[1348] The device structures the entered dietary restriction information and acquired emotional data into JSON format and sends it to the server via a RESTful API.

[1349] 4. Receiving Information

[1350] The server receives the data sent from the terminal in JSON format and stores it in a database.

[1351] 5. Database Search

[1352] The server searches a database based on the received dietary restriction and allergy information and extracts appropriate restaurant information.

[1353] 6. Safety Assessment

[1354] The server uses an AI analysis engine to evaluate safety, analyzing restaurant menu information and past reviews to calculate an overall safety score.

[1355] 7. Emotion Data Analysis

[1356] The server analyzes the acquired emotional data and gives priority to suggesting restaurants with a relaxing environment for the user.

[1357] 8. Recommendation Generation

[1358] The server generates a list of restaurants suitable for the user based on the safety score and sentiment data.

[1359] 9. Information Transmission and Display

[1360] The server structures the generated restaurant list in JSON format and sends it to the device via a RESTful API. The device then displays the received list on the user interface.

[1361] Specific examples

[1362] Suppose a user enters "nut allergy" and "dairy-free" into a food app, and the emotion recognition engine detects high stress levels. Based on this information, the server suggests restaurants with a high safety rating and a relaxing environment. For example, the server presents the user with a list of two restaurants: "Relax Bistro" and "Healthy Eats."

[1363] Prompt Sentence Examples

[1364] "When a user enters nut allergies and dairy-free diets and the emotion engine detects a stressed state, what type of restaurant should be suggested? Please explain, including the specific restaurant names and the reason for the suggestions."

[1365] In this way, users can easily find restaurants that fit their dietary restrictions and emotional state, and continuous feedback can be collected and utilized to improve the reliability and accuracy of the entire system.

[1366] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1367] Step 1:

[1368] The user enters the information.

[1369] Specific operation: A user opens a food app and enters their dietary restrictions and allergies into the device. For example, they enter "nut allergy" or "dairy-free" into the form.

[1370] Input: User's dietary restrictions and allergy information.

[1371] Output: Dietary restriction information and allergy information are saved on the device.

[1372] Step 2:

[1373] The device recognizes emotions.

[1374] How it works: The device uses an emotion recognition engine (such as Microsoft Azure's Emotion API) to analyze the user's facial expressions and tone of voice to obtain emotional data. The analysis is carried out in real time via the camera and microphone.

[1375] Input: User facial and voice data.

[1376] Output: The user's emotional data (e.g., stress level) is obtained.

[1377] Step 3:

[1378] The terminal transmits the information.

[1379] Specific operation: The device structures the acquired dietary restriction information, allergy information, and emotion data into JSON format and sends it to the server via a RESTful API.

[1380] Input: dietary restriction information, allergy information, emotional data.

[1381] Output: Data structured in JSON format is sent to the server.

[1382] Step 4:

[1383] The server receives the information.

[1384] Specific operation: The server receives the JSON data sent from the terminal, parses it, and saves it in the database.

[1385] Input: JSON formatted data from the terminal.

[1386] Output: Parsed data stored in a database.

[1387] Step 5:

[1388] The server searches the database.

[1389] What it does: The server searches for restaurant information in its database based on the dietary restrictions and allergies received, and uses an SQL query to find the appropriate restaurant.

[1390] Input: Facility information, dietary restrictions, and allergy information in the database.

[1391] Output: A list of restaurants that match the criteria.

[1392] Step 6:

[1393] The server evaluates the security level.

[1394] How it works: The server uses an AI analysis engine (e.g., a TensorFlow model) to evaluate the safety of the listed restaurants. It analyzes menu information, past reviews, ingredient lists, etc. to calculate a safety score.

[1395] Input: Listed restaurant information, menu information, past reviews, ingredient list.

[1396] Output: Safety score for each restaurant.

[1397] Step 7:

[1398] The server utilizes the emotion data.

[1399] Specific operation: The server analyzes the user's emotional state based on the acquired emotional data. For example, if the user is feeling stressed, it will prioritize and suggest restaurants with a relaxing environment.

[1400] Input: Sentiment data, safety score.

[1401] Output: A list of restaurants that match the user's emotional state.

[1402] Step 8:

[1403] The server generates the recommendations.

[1404] Specific operation: The server generates a list of restaurants suitable for the user based on the safety score and emotion data. The list includes the restaurant name, safety score, location, and menu summary.

[1405] Input: Safety score, sentiment data.

[1406] Output: A recommendation list.

[1407] Step 9:

[1408] The server sends the recommendations.

[1409] Specific operation: The server structures the generated recommendation list in JSON format and sends it to the terminal via a RESTful API.

[1410] Input: A recommendation list.

[1411] Output: Data structured in JSON format is sent to the terminal.

[1412] Step 10:

[1413] The terminal receives and displays the information.

[1414] Specific operation: The device receives the recommendation list sent from the server and displays it on the user interface (UI). The user can view detailed information about each restaurant, its safety score, and emotional response suggestions.

[1415] Input: Recommendation data in JSON format from the server.

[1416] Output: The recommendation list displayed in the user interface.

[1417] Step 11:

[1418] The user selects a restaurant and makes a reservation.

[1419] Specific behavior: The user selects the desired restaurant from the presented restaurant list and makes a reservation within the app or visits the restaurant in person.

[1420] Input: User selection.

[1421] Output: Booking completed or visit.

[1422] Step 12:

[1423] The user provides feedback.

[1424] Specific operation: The user actually visits a restaurant and, after finishing their meal, provides feedback within the app, including their satisfaction with the meal, their evaluation of allergy-related responses, and their emotional reactions to the suggested restaurant.

[1425] Input: User feedback.

[1426] Output: The feedback data is sent to the server.

[1427] Step 13:

[1428] The server collects and uses the feedback.

[1429] Specific operation: The server collects feedback information provided by users and stores it in a database. This feedback information is used to improve the evaluation accuracy of the AI ​​analysis engine and emotion engine.

[1430] Input: User feedback.

[1431] Output: Improved model and estimated accuracy.

[1432] (Application example 2)

[1433] 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."

[1434] Conventional restaurant recommendation systems primarily select restaurants based on dietary restrictions and allergies, but this approach fails to fully consider the user's emotional state and fails to provide an optimal user experience. In particular, for food delivery services, where a user's emotions have a significant impact on meal satisfaction, restaurant recommendation systems that take emotional data into account are needed.

[1435] The identification process by the identification 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 dietary restriction information and allergy information input from a user terminal, means for receiving emotion data, means for searching for appropriate restaurant information from a database based on the dietary restriction information, allergy information, and emotion data, means for analyzing menu trends and past reviews of the appropriate restaurant information and evaluating safety, and means for presenting a list of restaurants suitable for the user based on the evaluated safety and emotion data. This makes it possible to provide optimal restaurants and dishes tailored to the user's emotional state in addition to their dietary restriction and allergy information.

[1436] A "user terminal" is a device that a user operates to input information, and specifically refers to a smartphone, personal computer, etc.

[1437] "Dietary restriction information" is information about foods and ingredients that a user should avoid, such as vegetarians, vegans, or certain religious dietary restrictions.

[1438] "Allergy information" refers to information about foods or ingredients that may cause a user an allergic reaction, such as peanut allergies or dairy allergies.

[1439] "Emotion data" is information that indicates the user's current emotional state, and is data obtained from the user's facial expression, tone of voice, input content, and the like.

[1440] A "database" refers to a data structure that stores data such as restaurant information, menu items, and reviews, and can be used for searching and analysis.

[1441] "Appropriate restaurant information" is information about restaurants selected based on the user's dietary restriction information, allergy information, and emotional data, and specifically includes the restaurant name, location, menu information, and the like.

[1442] "Menu trends" refers to the general characteristics or patterns of food served at a particular restaurant.

[1443] "Past reviews" are ratings and comments provided by users who have previously visited the restaurant, and are important information for evaluating the quality of the restaurant and the user experience.

[1444] "Safety level" is an index that indicates the degree to which a particular restaurant or dish meets the user's dietary restriction information and allergy information.

[1445] "List format" refers to a format in which search results are organized and displayed so that they are easy for users to view, and usually refers to a list format in which the results are divided into categories.

[1446] A system for carrying out the present invention is realized by the cooperation of a user terminal, a server, and a database.

[1447] 1. User terminal processing

[1448] The user terminal can be a smartphone, tablet, or personal computer. The user inputs information about dietary restrictions and allergies, as well as emotional data into the application. Emotional data is obtained from the user's facial expressions, tone of voice, and input content. This information is structured in JSON format and sent to the server via an API.

[1449] 2. Server Processing

[1450] The server receives dietary restriction information, allergy information, and emotional data sent by the user. This data is stored in a database on the server. The server then searches the database for appropriate restaurant information and evaluates safety by analyzing menu trends and past reviews. In addition, based on the emotional data, it suggests restaurants that suit the user's emotions. These suggestions are generated in list form and sent to the user's device via API.

[1451] 3. Display on the user's device

[1452] The user device displays the restaurant list received from the server on the user interface. The list includes the name of each restaurant, its safety score, a menu summary, and emotional response suggestions. The user can select and reserve a restaurant based on this information.

[1453] Software and hardware used

[1454] Hardware: Smartphones, tablets, personal computers

[1455] Software: Python, RESTful API, requests library, emotion recognition engine

[1456] Specific examples of processing

[1457] For example, if User A inputs the dietary restrictions "vegan" and "nut allergy" and the emotional state "happy," the system will search for vegan-friendly restaurants that do not use nuts and suggest restaurants with the "fun" feeling that matches the emotional state. Similarly, if User B inputs the information "gluten-free" and "dairy allergy" and the feeling of "stress," the system will prioritize suggesting restaurants with a relaxing atmosphere.

[1458] Example prompts for generative AI models

[1459] Enter your emotional state, dietary restrictions, and allergy information. For example, "Emotional state: happy, dietary restrictions: vegan, allergy information: nuts." The system will then use this information to suggest the best restaurants and dishes.

[1460] In this way, the present invention can provide a more personalized restaurant recommendation and food delivery experience by taking into account not only a user's dietary restrictions and allergy information, but also their emotional state.

[1461] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1462] Step 1:

[1463] The user enters information about dietary restrictions, allergies, and emotional state from their device. Specifically, they open the application and enter information such as "vegan," "nut allergy," or "happy." The entered data is then properly formatted (JSON format) within the app.

[1464] Input: Dietary restriction information, allergy information, emotional state

[1465] Processing: Data entry and formatting

[1466] Output: User data in JSON format

[1467] Step 2:

[1468] The device sends the data formatted in step 1 to the server. At this time, it uses an HTTP request to send JSON formatted data via the API. After sending, it checks whether the request was processed correctly.

[1469] Input: User data in JSON format

[1470] Processing: Sending data via HTTP request

[1471] Output: A confirmation response for data transfer to the server

[1472] Step 3:

[1473] The server receives the user data sent from the device. The received data is first analyzed and then saved in a database. The database records user information associated with the user ID.

[1474] Input: User data in JSON format

[1475] Processing: Receiving and analyzing data, storing it in a database

[1476] Output: User information stored in the database

[1477] Step 4:

[1478] The server searches the database for appropriate restaurant information. The restaurant information is filtered based on dietary restrictions, allergies, and emotional state. Filtering is done using SQL queries, etc.

[1479] Input: User information stored in the database

[1480] Processing: Searching and filtering restaurant information using SQL queries, etc.

[1481] Output: A list of restaurants suitable for the user

[1482] Step 5:

[1483] The server performs AI analysis on the filtered restaurant information to evaluate its safety, analyzing past reviews and menu trends, and scoring the level of allergy-friendliness.

[1484] Input: Filtered restaurant information

[1485] Processing: Safety assessment using AI analysis

[1486] Output: Restaurant information with safety scores

[1487] Step 6:

[1488] The server evaluates which restaurant best suits the user's emotional state based on the emotional data, for example, choosing a restaurant with a relaxing atmosphere for a stressed user, or a restaurant with adventurous cuisine for a happy user.

[1489] Input: Restaurant information with safety scores and sentiment data

[1490] Processing: Selecting the best restaurant based on sentiment data

[1491] Output: Final restaurant list with sentiment-based suggestions

[1492] Step 7:

[1493] The server sends the final restaurant list to the device via the API, again using an HTTP request to transfer the data and returning it in the appropriate structure (JSON format).

[1494] Input: Final restaurant list with sentiment-based suggestions

[1495] Processing: Sending data via HTTP request

[1496] Output: Confirmation response of data transfer to the device

[1497] Step 8:

[1498] The device displays the restaurant list received from the server on a user interface, organized in a list format, and allows users to view detailed information about each restaurant, its safety score, and emotional response suggestions.

[1499] Input: The final restaurant list received from the server

[1500] Processing: Displaying data in the user interface

[1501] Output: The list of restaurants displayed to the user

[1502] In this way, users can receive restaurant and food recommendations that take into account their dietary restrictions, allergy information, and emotional state.

[1503] 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.

[1504] 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.

[1505] 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.

[1506] [Fourth embodiment]

[1507] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1508] 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.

[1509] 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).

[1510] 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.

[1511] 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.

[1512] 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).

[1513] 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.

[1514] 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.

[1515] 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.

[1516] 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.

[1517] 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.

[1518] 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.

[1519] 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."

[1520] The present invention is a system that suggests appropriate restaurants based on a user's dietary restrictions and allergy information. The program processing of this system will be described in detail below.

[1521] User terminal processing

[1522] 1. Enter information

[1523] A user opens a food app on their device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information such as nut allergies, gluten-free diets, or vegan diets into a form.

[1524] 2. Information Transmission

[1525] The device sends the information entered by the user to the server via API, including information on dietary restrictions and allergies.

[1526] Server Processing

[1527] 3. Receiving Information

[1528] The server receives the dietary restriction and allergy information sent by the user, and stores the received information in a database.

[1529] 4. Database Search

[1530] Based on the received information, the server searches for restaurant information in a database that includes restaurant names, locations, menu information, allergen information, etc.

[1531] 5. Safety Assessment

[1532] The server uses an AI analysis engine to analyze restaurant information suitable for the user. During the analysis process, the safety of the restaurant is evaluated based on the restaurant's menu trends and past reviews. For example, for a user with a nut allergy, a restaurant that offers nut-free menu items will be given a high safety rating.

[1533] 6. Recommendation Generation

[1534] The server generates a list of restaurants suitable for the user based on the safety rating. The generated restaurant list also includes the safety rating of each restaurant.

[1535] 7. Sending Recommendations

[1536] The restaurant list generated by the server is sent to the terminal via API.

[1537] User terminal processing (display)

[1538] 8. Receiving and Displaying Information

[1539] The device displays the restaurant list received from the server on the user interface (UI). The user can check the list to see which restaurants are safe for them.

[1540] User Action

[1541] 9. Restaurant Selection and Reservations

[1542] The user selects the restaurant they want from the list of restaurants presented, then makes a reservation within the app or visits the restaurant in person.

[1543] feedback

[1544] 10. Providing Feedback

[1545] After a user visits a restaurant and finishes their meal, they provide feedback within the app, including their satisfaction with the meal and their rating of allergy-related issues.

[1546] Server processing (feedback)

[1547] 11. Collect and use feedback

[1548] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[1549] In this way, the present invention allows users to easily find safe restaurants that take into account their dietary restrictions and allergies. Furthermore, by utilizing feedback, the reliability and accuracy of the overall system can be continuously improved.

[1550] The processing flow will be explained below.

[1551] Step 1:

[1552] A user opens a food app on a device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information like "nut allergy" or "dairy-free."

[1553] Step 2:

[1554] The device sends the dietary restriction and allergy information entered by the user to the server via the API. During the sending process, the entered information is structured in JSON format and sent as an HTTP request.

[1555] Step 3:

[1556] The server stores the received dietary restriction and allergy information in a database. This information is stored in association with the user's ID.

[1557] Step 4:

[1558] The server retrieves all restaurant information from the database and filters it based on the received dietary restrictions and allergy information. This filtering checks the ingredients and components contained in the restaurant menu and lists restaurants that meet the user's criteria.

[1559] Step 5:

[1560] The server uses an AI analysis engine to evaluate the safety of the listed restaurants, analyzing menu items, past reviews, ingredient information, and other factors to calculate an overall safety score.

[1561] Step 6:

[1562] The server generates a list of restaurants suitable for the user based on the safety rating, including the restaurant's name, safety score, location, and menu summary.

[1563] Step 7:

[1564] The server generates a list of restaurants and sends it to the terminal via the API. The response data is structured in JSON format.

[1565] Step 8:

[1566] The device displays the restaurant list received from the server on a user interface (UI). The UI is organized in a list format, allowing users to easily view detailed information and safety scores for each restaurant.

[1567] Step 9:

[1568] The user selects the restaurant they want from the list of restaurants presented, then makes a reservation within the app or visits the restaurant in person.

[1569] Step 10:

[1570] After a user visits a restaurant and finishes their meal, they provide feedback within the app, including their satisfaction with the meal and their rating of allergy-related issues.

[1571] Step 11:

[1572] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[1573] Example 1

[1574] 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."

[1575] Conventional restaurant search systems do not adequately consider users' dietary restrictions or allergies when suggesting restaurants, making it difficult for users to find restaurants they can trust. Furthermore, the reliability of the safety of the suggested restaurants is low, necessitating improvements to increase user satisfaction. Furthermore, there is a lack of a way to effectively utilize user feedback to improve the system's accuracy.

[1576] 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.

[1577] In this invention, the server includes: means for receiving dietary restriction information and allergy information input from a user terminal; means for searching for appropriate restaurant information from a database based on the dietary restriction information and allergy information; means for analyzing the menu trends and past reviews of the appropriate restaurant information using a generative AI model to evaluate safety; means for presenting a list of restaurants suitable for the user based on the evaluated safety; means for transmitting the list to the user terminal; and means for displaying the list through a user interface of the user terminal. This allows the system to present restaurants with a high safety rating based on the user's dietary restriction information and allergy information, enabling the user to easily find a restaurant they can use with confidence. Furthermore, the system can collect user feedback and use it to improve the accuracy of the evaluation, thereby continuously improving the reliability of the system and user satisfaction.

[1578] "User terminal" refers to a device such as a smartphone or PC used by a user, and is a device for inputting information and receiving output from a system.

[1579] "Dietary restriction information" refers to information that prevents a user from consuming certain foods or ingredients, including, for example, vegan or low-calorie restrictions.

[1580] "Allergy information" refers to information about foods that a user should avoid because they react to certain allergens, such as nut allergies or milk allergies.

[1581] A "database" is a system that refers to a collection of accumulated data that stores restaurant information, menu information, allergen information, etc.

[1582] A "generative AI model" refers to an analytical engine that uses artificial intelligence to analyze, predict, and classify data.

[1583] "Menu trends" refers to statistical trends regarding the types, frequency, and ingredients of meals served at a particular restaurant.

[1584] "Past Reviews" refers to a record of ratings and comments provided by a User in the past, including User's reactions to a restaurant or its services.

[1585] "Safety level" is an evaluation index that indicates whether a particular restaurant is safe for the user, taking into consideration the user's dietary restrictions and allergy information.

[1586] "List format" refers to the method of presenting restaurant information in bulleted or tabular form, in a way that is easy for users to visually check.

[1587] "User interface (UI)" refers to the screens and operating means that allow a user to interact with a system, including, for example, application screens and buttons.

[1588] "Feedback information" refers to information such as ratings and comments provided by users after they have actually used a service or product.

[1589] The present invention relates to a system for suggesting suitable restaurants based on a user's dietary restriction information and allergy information. Hereinafter, an embodiment of the present invention will be described in detail.

[1590] Hardware and software used

[1591] Hardware

[1592] User terminal: A device such as a smartphone or PC that allows a user to input information and receive output from the system.

[1593] Server: A device that manages the entire system, processes and analyzes data, and manages databases.

[1594] software

[1595] Food app: An application installed on a user's device that allows them to enter information about dietary restrictions and allergies and display suggested restaurant information.

[1596] API: An interface for exchanging information between a user terminal and a server.

[1597] Database management system: A system for storing and managing restaurant information and user information.

[1598] AI analysis engine: A system that uses generative AI models to analyze data and evaluate restaurant safety.

[1599] Explanation of program processing

[1600] User terminal processing

[1601] First, the user launches the food app on their smartphone or PC and enters information about dietary restrictions and allergies. For example, they enter information such as "nut allergy," "gluten-free," or "vegan" into the input form. The device then sends the entered information to the server via an API. The sent information is in JSON format, and includes information about dietary restrictions and allergies.

[1602] Server Processing

[1603] The server receives the user's dietary restriction and allergy information via the API and stores it in a database. It then searches the database for appropriate restaurant information based on the stored information. The server then uses a generative AI model to analyze the menu trends and past reviews of the searched restaurant information and evaluates its safety. Specifically, for a user with a nut allergy, the server rates restaurants that offer nut-free menus highly as safe. Based on the evaluation results, it generates a list of restaurants suitable for the user and sends this list to the user's device.

[1604] User terminal processing (display)

[1605] The user device displays the restaurant list received from the server on the user interface (UI). The user can select the restaurant they want from the displayed list and make a reservation within the app or visit the restaurant in person.

[1606] User feedback

[1607] After a user visits a restaurant and finishes their meal, they provide feedback within the app. This feedback includes their satisfaction with the meal and an evaluation of whether the restaurant handled allergies. The server collects the feedback information provided by the user and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[1608] Examples of specific examples and prompts

[1609] As a concrete example, consider a case where a user with a nut allergy uses a food app to search for a suitable restaurant. The user enters "nut allergy" and the device sends this information to the server. The server searches for restaurants that offer nut-free menus and evaluates their safety. Based on the evaluation results, a list of appropriate restaurants is generated and sent to the user's device. The user then selects the desired restaurant from the displayed list and makes a reservation.

[1610] Example prompt sentence:

[1611] "Please suggest restaurants that are suitable for users with nut allergies."

[1612] "Search for and list vegan-friendly restaurants."

[1613] The above is an embodiment of the present invention. Taking into account the user's dietary restrictions and allergy information, it is possible to easily find a restaurant that is safe to use. Furthermore, by utilizing feedback from users, the reliability and evaluation accuracy of the entire system can be continuously improved.

[1614] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1615] Step 1:

[1616] Enter information

[1617] Users launch the food app on their smartphone or PC and enter information about dietary restrictions and allergies.

[1618] Input: Nut allergy, gluten-free, vegan, etc. information.

[1619] How it works: A user fills out an application form and clicks the "Submit" button.

[1620] Output: The entered dietary restriction information and allergy information is saved on the device.

[1621] Step 2:

[1622] Information transmission

[1623] The device sends the entered dietary restriction and allergy information to the server via API.

[1624] Input: User-entered dietary restrictions and allergy information.

[1625] How it works: The device sends information to the server as a JSON-formatted API request.

[1626] Output: Dietary restrictions and allergy information sent to the server.

[1627] Step 3:

[1628] Receiving information

[1629] The server stores the dietary restriction and allergy information received via the API in a database.

[1630] Input: Dietary restriction and allergy information sent from your device.

[1631] How it works: The server parses the API request and stores the received information in a database.

[1632] Output: User's dietary restrictions and allergies stored in a database.

[1633] Step 4:

[1634] Database search

[1635] The server searches the database for appropriate restaurant information based on the stored user information.

[1636] Input: User's dietary restrictions and allergies stored in the database.

[1637] How it works: The server uses an SQL query to extract restaurant information from a database that matches the criteria.

[1638] Output: A list of restaurants that match the user's criteria.

[1639] Step 5:

[1640] Safety Rating

[1641] The server uses an AI analysis engine to analyze the menu trends and past reviews of the searched restaurant information and evaluate its safety.

[1642] Input: Restaurant information extracted from the database, menu trends, and past reviews.

[1643] How it works: Using a generative AI model, we analyze and evaluate the safety of restaurants. For example, we can evaluate a restaurant that offers nut-free menu items as being safe for a user with a nut allergy.

[1644] Output: A list of restaurant information with safety rating results.

[1645] Step 6:

[1646] Recommendation Generation

[1647] The server generates a list of restaurants suitable for the user based on the evaluated safety level.

[1648] Input: A list of restaurant information with safety rating results.

[1649] How it works: The server generates a list of restaurants based on the rating results and adds a safety rating for each restaurant to the list.

[1650] Output: The generated restaurant list.

[1651] Step 7:

[1652] Sending Recommendations

[1653] The server sends the generated restaurant list to the terminal via API.

[1654] Input: The generated restaurant list.

[1655] How it works: The server sends a list of restaurants to the device as a JSON-formatted API response.

[1656] Output: The restaurant list sent to the device.

[1657] Step 8:

[1658] Information reception and display

[1659] The terminal displays the restaurant list received from the server on a user interface (UI).

[1660] Input: A list of restaurants sent by the server.

[1661] Operation: The device analyzes the received information and displays it in a list format on the user interface. The user can then select a restaurant from the displayed list.

[1662] Output: The restaurant list displayed in a user interface.

[1663] Step 9:

[1664] Restaurant selection and reservations

[1665] Users can select the restaurant they want from the displayed list and make a reservation within the app, or visit the restaurant in person.

[1666] Input: A list of restaurants displayed in a user interface.

[1667] How it works: The user selects the restaurant they want, then uses the reservation feature to enter the date, time, and number of people to confirm the reservation, or visits the selected restaurant in person.

[1668] Output: The reservation is confirmed or information to visit the restaurant is displayed.

[1669] Step 10:

[1670] Providing Feedback

[1671] Users visit the restaurant in person, eat there and then provide feedback within the app.

[1672] Input: User's impressions and ratings after their visit. For example, this includes satisfaction with the food and ratings of allergy-related issues.

[1673] Action: A user fills in the feedback form and clicks the "Submit" button.

[1674] Output: The user's feedback information is saved on the device.

[1675] Step 11:

[1676] Collecting and using feedback

[1677] The server collects feedback information provided by users and stores it in a database. This feedback information is then used as learning data to improve the evaluation accuracy of the AI ​​analysis engine.

[1678] Input: User feedback information sent from the device.

[1679] How it works: The server receives feedback information, stores it in a database, analyzes the stored feedback information, and provides feedback to the AI ​​analysis engine to improve the accuracy of the evaluation.

[1680] Output: An AI analysis engine with improved evaluation accuracy and an updated database.

[1681] (Application example 1)

[1682] 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."

[1683] Previously, it was difficult for users with dietary restrictions or allergies to find suitable restaurants, which posed a risk of accidents and problems. Furthermore, there was a lack of a mechanism for improving the system based on feedback from users after they had actually visited the restaurant, making it difficult to recommend restaurants with high accuracy. Another issue was how smoothly users could make reservations at recommended restaurants.

[1684] 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.

[1685] In this invention, the server includes means for receiving dietary restriction information and allergy information input from a user terminal, means for searching for appropriate dining facility information from a database based on the dietary restriction information and allergy information, means for analyzing menu trends and past reviews of the appropriate dining facility information and evaluating its safety, means for making reservations on the user terminal based on the evaluated safety, means for collecting feedback information from users and using it to improve the accuracy of the evaluated safety, and means for displaying the appropriate dining facility information through a user interface. This allows users with dietary restrictions or allergies to easily and safely find suitable dining facilities and make reservations smoothly. Furthermore, the accuracy of the system can be constantly improved through feedback.

[1686] "User terminal" refers to electronic devices used by users in general, including smartphones, tablets, personal computers, etc.

[1687] "Dining establishment information" refers to information necessary for users, such as the name of the dining establishment, its location, the menu items offered, and allergen information.

[1688] "Dietary restriction information" refers to a user's individual requirements for restricting certain ingredients or nutrients, and includes, for example, information such as gluten-free or low-carb.

[1689] "Allergy Information" refers to information about specific foods or ingredients to which a user has an allergic reaction.

[1690] "Search means" refers to software or a system that searches a database for appropriate restaurant information based on the user's dietary restrictions and allergy information.

[1691] "Means of analysis" refers to software and algorithms that evaluate the menu trends and past ratings of restaurant information and determine the safety level for users.

[1692] "Safety assessment method" refers to the process or system used to determine how safe a restaurant is in relation to a user's dietary restrictions or allergy information.

[1693] "Means for presenting in list format" refers to a user interface or display method for displaying a list of suitable dining establishments on a user's terminal.

[1694] "Means for making a reservation" refers to functionality or software that allows a user to make a reservation at a dining establishment selected by the user.

[1695] "Feedback information" refers to information such as ratings, comments, and satisfaction levels of restaurants and bars that users have actually visited.

[1696] "Means for displaying through a user interface" refers to a screen or interface for visually displaying dining establishment information on a user terminal.

[1697] This invention is a system that allows users to input information about dietary restrictions and allergies using a user terminal, searches for and suggests appropriate dining facilities via a server, and then makes reservations.

[1698] System Configuration

[1699] User terminal

[1700] The user device refers to an electronic device such as a smartphone, tablet, or personal computer, on which a mobile app using React Native is installed. This application allows users to input information about dietary restrictions and allergies and send it to the server.

[1701] server

[1702] The server receives the information sent from the user's device, searches the database, and provides appropriate restaurant information using AI analysis engines such as Google Cloud Machine Learning and Azure Machine Learning.

[1703] Program Overview

[1704] 1. Enter and submit information

[1705] Users open the smartphone app and enter their dietary restrictions (e.g., gluten-free or vegan) and allergy information (e.g., nut allergy) into a form. Once the information is complete, the user's device sends this information to the server using Axious.

[1706] 2. Database Search and Analysis

[1707] The server searches the database for appropriate restaurant information based on the received information. It uses an AI analysis engine to analyze menu trends and past reviews and evaluate safety. The safety evaluation criteria are based on whether the information meets the user's dietary restrictions and allergies.

[1708] 3. Generate and display a restaurant list

[1709] Based on the analysis results, the server generates a list of restaurants suitable for the user and sends it back to the user's device as an HTTP response. The user's device then displays the received list in list format within the app.

[1710] 4. Booking and Feedback

[1711] Users can select a restaurant from the list and make a reservation within the app. After visiting, users can provide feedback within the app. The collected feedback information is sent to the server and used to improve the accuracy of the system.

[1712] Specific examples

[1713] For example, if a user has a nut allergy and a vegan diet, they would enter the following information:

[1714] plaintext

[1715] Allergy Information: Nut allergy

[1716] Dietary Restrictions:Vegan

[1717] Based on this information, the server searches the database for restaurants that meet the user's requirements and generates a prompt like the following:

[1718] plaintext

[1719] Please suggest safe dining options based on the allergy information and dietary restrictions below:

[1720] Allergy Information: Nut allergy

[1721] Dietary Restrictions:Vegan

[1722] Proposed dining establishments should include the following information:

[1723] Name of restaurant

[1724] location

[1725] Menu Information

[1726] Safety level

[1727] Based on this prompt, the AI ​​analysis engine evaluates and selects suitable dining options and presents them to the user in a list format. The user can then select one from the list, make a reservation, and provide feedback after the visit.

[1728] This system allows users to easily find safe restaurants that meet their dietary restrictions and allergies, allowing them to enjoy meals safely. Furthermore, by improving the system's accuracy based on collected feedback, more reliable recommendations can be achieved.

[1729] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1730] Step 1:

[1731] The user opens the smartphone app. On the app interface, the user enters their dietary restrictions (e.g., gluten-free) and allergy information (e.g., nut allergy). After entering the information, the user presses the "Submit" button to proceed to the next step. This prepares the input data.

[1732] Step 2:

[1733] The user device sends the entered dietary restriction and allergy information to the server as an HTTP POST request using Axious. The server analyzes the received data and prepares a database search. The input is the user's dietary restriction and allergy information, and the output is JSON format data received by the server.

[1734] Step 3:

[1735] The server searches the database based on the received dietary restriction and allergy information. Specifically, it compares the menus of each restaurant in the database with the user's requirements and narrows down the list to restaurants that meet all the requirements. The input is the database stored on the server, and the output is a list of restaurant information that matches the requirements.

[1736] Step 4:

[1737] The server then uses an AI analysis engine to further analyze the narrowed-down restaurant information. During the analysis process, it evaluates the restaurant's menu trends and past reviews and calculates the safety rating of each restaurant. The input is restaurant information, and the output is a list of restaurants with a safety rating.

[1738] Step 5:

[1739] The server generates a list of restaurants that are most suitable for the user based on the safety assessment and sends it to the user's device as a list in an HTTP response. The output is a JSON-formatted list of restaurants that is sent to the user's device.

[1740] Step 6:

[1741] The user device receives the list of restaurants and displays it in list format within the app. The user selects the restaurant they are interested in from the displayed list. The input is the restaurant list data from the server, and the output is the restaurant information displayed in list format.

[1742] Step 7:

[1743] The user makes a reservation for the selected restaurant within the app. The reservation information is sent to the server using Axious. The server receives the reservation information and sends a reservation request to the restaurant. The input is the reservation information, and the output is the reservation confirmation data.

[1744] Step 8:

[1745] After a user visits a restaurant and finishes their meal, they provide feedback within the app. The feedback information is then sent to the server using Axious. The server stores the received feedback information in a database and uses it to improve the evaluation accuracy of the AI ​​analysis engine. The input is the feedback information, and the output is learning data for improving accuracy.

[1746] By going through the above steps, users can easily find and safely use restaurants that meet their dietary restrictions and allergies. The collected feedback information improves the system's evaluation accuracy, resulting in more reliable recommendations.

[1747] 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.

[1748] The present invention is a system that suggests appropriate restaurants based on a user's dietary restrictions and allergies, and also combines it with an emotion engine that recognizes the user's emotions to improve the accuracy of restaurant suggestions and the user experience. The program processing of this system is described in detail below.

[1749] User terminal processing

[1750] 1. Enter information

[1751] A user opens a food app on a device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information like "nut allergy" or "dairy-free."

[1752] 2. Emotion recognition

[1753] The emotion engine installed in the device acquires emotion data from the user's input, operations, facial expressions, tone of voice, etc. This emotion data indicates the user's current emotional state.

[1754] 3. Information Transmission

[1755] The device sends the dietary restriction information, allergy information, and emotional data entered by the user to the server via the API. During the sending process, the entered information and emotional data are structured in JSON format and sent as an HTTP request.

[1756] Server Processing

[1757] 4. Receiving Information

[1758] The server receives information about dietary restrictions, allergies, and emotional data sent by the user, and stores the received information in a database.

[1759] 5. Database Search

[1760] Based on the received information, the server searches for restaurant information in a database that includes restaurant names, locations, menu information, allergen information, etc., and filters restaurants that match the user's criteria.

[1761] 6. Safety Assessment

[1762] The server uses an AI analysis engine to evaluate the safety of the listed restaurants, analyzing menu items, past reviews, ingredient information, and other factors to calculate an overall safety score.

[1763] 7. Utilizing Emotional Data

[1764] The server analyzes the emotion data acquired by the emotion engine and makes suggestions according to the user's emotional state, such as suggesting restaurants with a more relaxing environment if the user is feeling stressed.

[1765] 8. Recommendation Generation

[1766] The server generates a list of restaurants suitable for the user based on the safety rating and emotion data. The list includes the restaurant's name, safety score, location, menu summary, and emotional response suggestions.

[1767] 9. Sending Recommendations

[1768] The server generates a list of restaurants and sends it to the terminal via the API. The response data is structured in JSON format.

[1769] User terminal processing (display)

[1770] 10. Receiving and Displaying Information

[1771] The device displays the restaurant list received from the server in a user interface (UI). The UI is organized in a list format, allowing users to easily view detailed information, safety scores, and emotional response suggestions for each restaurant.

[1772] User Action

[1773] 11. Restaurant Selection and Reservations

[1774] The user selects the desired restaurant from the presented restaurant list and makes a reservation within the app or visits the restaurant in person.

[1775] feedback

[1776] 12. Providing Feedback

[1777] After users visit a restaurant and finish their meal, they provide in-app feedback, including satisfaction with the meal, a rating of allergy accommodations, and emotional reactions to the suggested restaurant.

[1778] Server processing (feedback)

[1779] 13. Collect and use feedback

[1780] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine and emotion engine.

[1781] In this way, the present invention allows users to easily find safe restaurants that take into account their emotional state as well as their dietary restrictions and allergies. Furthermore, by utilizing feedback, the reliability and accuracy of the overall system can be continuously improved.

[1782] The processing flow will be explained below.

[1783] Step 1:

[1784] A user opens a food app on a device (such as a smartphone or PC) and enters information about dietary restrictions and allergies. For example, they enter information like "nut allergy" or "dairy-free."

[1785] Step 2:

[1786] The device acquires emotional data from the user's input, operations, facial expressions, tone of voice, etc. At this time, the emotion engine analyzes the user's emotions in real time and determines their emotional state, such as stress, satisfaction, or joy.

[1787] Step 3:

[1788] The device converts the dietary restriction information, allergy information, and emotional data entered by the user into JSON format and sends it to the server via an API.

[1789] Step 4:

[1790] The server receives information on dietary restrictions, allergies, and emotional data from the user, associates each piece of information, and stores it in a database. The stored information is linked to the user ID.

[1791] Step 5:

[1792] The server retrieves all restaurant information from the database and filters it based on dietary restrictions and allergies. This filtering involves checking the ingredients and components contained in restaurant menus and listing restaurants that meet the user's criteria.

[1793] Step 6:

[1794] The server uses an AI analysis engine to evaluate the safety of the listed restaurants, calculating an overall safety score based on the restaurant's menu items, past reviews, and ingredient information.

[1795] Step 7:

[1796] The server then uses the emotion data to suggest restaurants that correspond to the user's emotional state. For example, if the user is feeling stressed, it will prioritize restaurants that offer a high level of relaxation.

[1797] Step 8:

[1798] The server generates a list of restaurants suitable for the user based on the safety rating and emotion data. The list includes the restaurant's name, safety score, location, menu summary, and emotional response suggestions.

[1799] Step 9:

[1800] The server generates a list of restaurants and sends it to the device via API. The data is structured in JSON format.

[1801] Step 10:

[1802] The device displays the restaurant list received from the server in a user interface (UI). The UI is organized in a list format, allowing users to easily view detailed information, safety scores, and emotional response suggestions for each restaurant.

[1803] Step 11:

[1804] The user selects the restaurant they want from the presented list, makes a reservation within the app, or visits the restaurant in person.

[1805] Step 12:

[1806] After users visit a restaurant and finish their meal, they provide feedback within the app, including their satisfaction with the meal, their rating of allergy accommodations, and their emotional reaction to the suggested restaurant.

[1807] Step 13:

[1808] The server collects feedback information provided by users and stores it in a database. This feedback information is used as learning data to improve the evaluation accuracy of the AI ​​analysis engine and emotion engine. This will improve the accuracy and reliability of future suggestions.

[1809] Example 2

[1810] 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."

[1811] Conventional restaurant search systems were able to suggest appropriate restaurants based on a user's dietary restrictions and allergies. However, they did not take into account the user's emotional state, limiting the improvement of the user experience. Furthermore, there was no mechanism in place to fully utilize feedback information when rating the safety of the suggested restaurants, leaving challenges in improving the accuracy of the ratings.

[1812] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving dietary restriction information and allergy information input from a user terminal; means for searching for appropriate facility information from a database based on the dietary restriction information and allergy information; means for analyzing menu trends and past reviews of the appropriate facility information and evaluating safety; means for presenting a list of facilities suitable for the user based on the evaluated safety level and the user's emotional data; means for analyzing the user's input content and facial expressions using an emotion recognition engine installed in the user terminal and acquiring emotional data; and means for analyzing the acquired emotional data and preferentially suggesting facilities with a relaxing environment. This allows the user to easily find safe facilities that take into account not only their dietary restriction and allergy information but also their emotional state. Furthermore, the reliability and evaluation accuracy of the entire system can be continuously improved based on feedback information.

[1813] A "user terminal" is an electronic device used by a user, including a smartphone, a PC, etc.

[1814] "Dietary restriction information" is information about foods and ingredients that the user wants to avoid consuming.

[1815] "Allergy information" is information about foods or ingredients to which the user is allergic.

[1816] An "emotion recognition engine" is software that includes technology for acquiring emotional data from a user's facial expressions, tone of voice, etc.

[1817] A "server" is a central computer system responsible for processing and storing data.

[1818] A "database" is a system that stores information systematically and enables efficient searching and access.

[1819] "Appropriate facility information" is information about facilities (restaurants, etc.) that have been filtered based on the user's dietary restriction information and allergy information.

[1820] "Safety level" is a score that evaluates the safety of dietary restriction information and allergy information for the user.

[1821] The "means for presenting in list form" is a method for displaying the evaluated information to the user as a list.

[1822] "Feedback information" refers to evaluations and impressions based on actual experiences provided by users.

[1823] "Emotion data" is data that indicates the user's emotional state, and is obtained from the user's facial expression and tone of voice.

[1824] The present invention is a system that proposes appropriate facilities based on a user's dietary restriction information and allergy information, and also combines it with an emotion engine that recognizes the user's emotions to improve the accuracy of proposals and the user experience. An embodiment of the system of the present invention will be described in detail below.

[1825] System Overview

[1826] This system consists of a user terminal, a server, and a database. The user terminal is an electronic device such as a smartphone or PC, and is the device through which the user enters information about their dietary restrictions and allergies. The server is a central computer system responsible for processing and storing data, and the database is a system that systematically stores information and enables efficient search and access.

[1827] Hardware and software used

[1828] 1. User Device

[1829] A device such as a smartphone or PC that allows users to enter information about dietary restrictions and allergies.

[1830] Equipped with an emotion recognition engine (such as Microsoft Azure's Emotion API or Google Cloud's Vision AI).

[1831] 2. Server

[1832] A central computer system that processes and stores data.

[1833] Connect to a database (such as MySQL or PostgreSQL) to manage your data.

[1834] 3. Software and APIs

[1835] Data communication between user devices and servers is achieved through RESTful API.

[1836] Safety is evaluated using an AI analysis engine (a model using TensorFlow and PyTorch).

[1837] Data processing and calculation

[1838] 1. Enter information

[1839] The user opens a food app on their device and enters their dietary restrictions and allergies, such as "nut allergy" or "dairy-free."

[1840] 2. Emotion recognition

[1841] The device uses an emotion recognition engine to analyze the user's facial expressions and tone of voice to obtain emotional data, and measures the user's emotional state in real time through the camera and microphone.

[1842] 3. Information Transmission

[1843] The device structures the entered dietary restriction information and acquired emotional data into JSON format and sends it to the server via a RESTful API.

[1844] 4. Receiving Information

[1845] The server receives the data sent from the terminal in JSON format and stores it in a database.

[1846] 5. Database Search

[1847] The server searches a database based on the received dietary restriction and allergy information and extracts appropriate restaurant information.

[1848] 6. Safety Assessment

[1849] The server uses an AI analysis engine to evaluate safety, analyzing restaurant menu information and past reviews to calculate an overall safety score.

[1850] 7. Emotion Data Analysis

[1851] The server analyzes the acquired emotional data and gives priority to suggesting restaurants with a relaxing environment for the user.

[1852] 8. Recommendation Generation

[1853] The server generates a list of restaurants suitable for the user based on the safety score and sentiment data.

[1854] 9. Information Transmission and Display

[1855] The server structures the generated restaurant list in JSON format and sends it to the device via a RESTful API. The device then displays the received list on the user interface.

[1856] Specific examples

[1857] Suppose a user enters "nut allergy" and "dairy-free" into a food app, and the emotion recognition engine detects high stress levels. Based on this information, the server suggests restaurants with a high safety rating and a relaxing environment. For example, the server presents the user with a list of two restaurants: "Relax Bistro" and "Healthy Eats."

[1858] Prompt Sentence Examples

[1859] "When a user enters nut allergies and dairy-free diets and the emotion engine detects a stressed state, what type of restaurant should be suggested? Please explain, including the specific restaurant names and the reason for the suggestions."

[1860] In this way, users can easily find restaurants that fit their dietary restrictions and emotional state, and continuous feedback can be collected and utilized to improve the reliability and accuracy of the entire system.

[1861] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1862] Step 1:

[1863] The user enters the information.

[1864] Specific operation: A user opens a food app and enters their dietary restrictions and allergies into the device. For example, they enter "nut allergy" or "dairy-free" into the form.

[1865] Input: User's dietary restrictions and allergy information.

[1866] Output: Dietary restriction information and allergy information are saved on the device.

[1867] Step 2:

[1868] The device recognizes emotions.

[1869] How it works: The device uses an emotion recognition engine (such as Microsoft Azure's Emotion API) to analyze the user's facial expressions and tone of voice to obtain emotional data. The analysis is carried out in real time via the camera and microphone.

[1870] Input: User facial and voice data.

[1871] Output: The user's emotional data (e.g., stress level) is obtained.

[1872] Step 3:

[1873] The terminal transmits the information.

[1874] Specific operation: The device structures the acquired dietary restriction information, allergy information, and emotion data into JSON format and sends it to the server via a RESTful API.

[1875] Input: dietary restriction information, allergy information, emotional data.

[1876] Output: Data structured in JSON format is sent to the server.

[1877] Step 4:

[1878] The server receives the information.

[1879] Specific operation: The server receives the JSON data sent from the terminal, parses it, and saves it in the database.

[1880] Input: JSON formatted data from the terminal.

[1881] Output: Parsed data stored in a database.

[1882] Step 5:

[1883] The server searches the database.

[1884] What it does: The server searches for restaurant information in its database based on the dietary restrictions and allergies received, and uses an SQL query to find the appropriate restaurant.

[1885] Input: Facility information, dietary restrictions, and allergy information in the database.

[1886] Output: A list of restaurants that match the criteria.

[1887] Step 6:

[1888] The server evaluates the security level.

[1889] How it works: The server uses an AI analysis engine (e.g., a TensorFlow model) to evaluate the safety of the listed restaurants. It analyzes menu information, past reviews, ingredient lists, etc. to calculate a safety score.

[1890] Input: Listed restaurant information, menu information, past reviews, ingredient list.

[1891] Output: Safety score for each restaurant.

[1892] Step 7:

[1893] The server utilizes the emotion data.

[1894] Specific operation: The server analyzes the user's emotional state based on the acquired emotional data. For example, if the user is feeling stressed, it will prioritize and suggest restaurants with a relaxing environment.

[1895] Input: Sentiment data, safety score.

[1896] Output: A list of restaurants that match the user's emotional state.

[1897] Step 8:

[1898] The server generates the recommendations.

[1899] Specific operation: The server generates a list of restaurants suitable for the user based on the safety score and emotion data. The list includes the restaurant name, safety score, location, and menu summary.

[1900] Input: Safety score, sentiment data.

[1901] Output: A recommendation list.

[1902] Step 9:

[1903] The server sends the recommendations.

[1904] Specific operation: The server structures the generated recommendation list in JSON format and sends it to the terminal via a RESTful API.

[1905] Input: A recommendation list.

[1906] Output: Data structured in JSON format is sent to the terminal.

[1907] Step 10:

[1908] The terminal receives and displays the information.

[1909] Specific operation: The device receives the recommendation list sent from the server and displays it on the user interface (UI). The user can view detailed information about each restaurant, its safety score, and emotional response suggestions.

[1910] Input: Recommendation data in JSON format from the server.

[1911] Output: The recommendation list displayed in the user interface.

[1912] Step 11:

[1913] The user selects a restaurant and makes a reservation.

[1914] Specific behavior: The user selects the desired restaurant from the presented restaurant list and makes a reservation within the app or visits the restaurant in person.

[1915] Input: User selection.

[1916] Output: Booking completed or visit.

[1917] Step 12:

[1918] The user provides feedback.

[1919] Specific operation: The user actually visits a restaurant and, after finishing their meal, provides feedback within the app, including their satisfaction with the meal, their evaluation of allergy-related responses, and their emotional reactions to the suggested restaurant.

[1920] Input: User feedback.

[1921] Output: The feedback data is sent to the server.

[1922] Step 13:

[1923] The server collects and uses the feedback.

[1924] Specific operation: The server collects feedback information provided by users and stores it in a database. This feedback information is used to improve the evaluation accuracy of the AI ​​analysis engine and emotion engine.

[1925] Input: User feedback.

[1926] Output: Improved model and estimated accuracy.

[1927] (Application example 2)

[1928] 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."

[1929] Conventional restaurant recommendation systems primarily select restaurants based on dietary restrictions and allergies, but this approach fails to fully consider the user's emotional state and fails to provide an optimal user experience. In particular, for food delivery services, where a user's emotions have a significant impact on meal satisfaction, restaurant recommendation systems that take emotional data into account are needed.

[1930] The identification process by the identification 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 dietary restriction information and allergy information input from a user terminal, means for receiving emotion data, means for searching for appropriate restaurant information from a database based on the dietary restriction information, allergy information, and emotion data, means for analyzing menu trends and past reviews of the appropriate restaurant information and evaluating safety, and means for presenting a list of restaurants suitable for the user based on the evaluated safety and emotion data. This makes it possible to provide optimal restaurants and dishes tailored to the user's emotional state in addition to their dietary restriction and allergy information.

[1931] A "user terminal" is a device that a user operates to input information, and specifically refers to a smartphone, personal computer, etc.

[1932] "Dietary restriction information" is information about foods and ingredients that a user should avoid, such as vegetarians, vegans, or certain religious dietary restrictions.

[1933] "Allergy information" refers to information about foods or ingredients that may cause a user an allergic reaction, such as peanut allergies or dairy allergies.

[1934] "Emotion data" is information that indicates the user's current emotional state, and is data obtained from the user's facial expression, tone of voice, input content, and the like.

[1935] A "database" refers to a data structure that stores data such as restaurant information, menu items, and reviews, and can be used for searching and analysis.

[1936] "Appropriate restaurant information" is information about restaurants selected based on the user's dietary restriction information, allergy information, and emotional data, and specifically includes the restaurant name, location, menu information, and the like.

[1937] "Menu trends" refers to the general characteristics or patterns of food served at a particular restaurant.

[1938] "Past reviews" are ratings and comments provided by users who have previously visited the restaurant, and are important information for evaluating the quality of the restaurant and the user experience.

[1939] "Safety level" is an index that indicates the degree to which a particular restaurant or dish meets the user's dietary restriction information and allergy information.

[1940] "List format" refers to a format in which search results are organized and displayed so that they are easy for users to view, and usually refers to a list format in which the results are divided into categories.

[1941] A system for carrying out the present invention is realized by the cooperation of a user terminal, a server, and a database.

[1942] 1. User terminal processing

[1943] The user terminal can be a smartphone, tablet, or personal computer. The user inputs information about dietary restrictions and allergies, as well as emotional data into the application. Emotional data is obtained from the user's facial expressions, tone of voice, and input content. This information is structured in JSON format and sent to the server via an API.

[1944] 2. Server Processing

[1945] The server receives dietary restriction information, allergy information, and emotional data sent by the user. This data is stored in a database on the server. The server then searches the database for appropriate restaurant information and evaluates safety by analyzing menu trends and past reviews. In addition, based on the emotional data, it suggests restaurants that suit the user's emotions. These suggestions are generated in list form and sent to the user's device via API.

[1946] 3. Display on the user's device

[1947] The user device displays the restaurant list received from the server on the user interface. The list includes the name of each restaurant, its safety score, a menu summary, and emotional response suggestions. The user can select and reserve a restaurant based on this information.

[1948] Software and hardware used

[1949] Hardware: Smartphones, tablets, personal computers

[1950] Software: Python, RESTful API, requests library, emotion recognition engine

[1951] Specific examples of processing

[1952] For example, if User A inputs the dietary restrictions "vegan" and "nut allergy" and the emotional state "happy," the system will search for vegan-friendly restaurants that do not use nuts and suggest restaurants with the "fun" feeling that matches the emotional state. Similarly, if User B inputs the information "gluten-free" and "dairy allergy" and the feeling of "stress," the system will prioritize suggesting restaurants with a relaxing atmosphere.

[1953] Example prompts for generative AI models

[1954] Enter your emotional state, dietary restrictions, and allergy information. For example, "Emotional state: happy, dietary restrictions: vegan, allergy information: nuts." The system will then use this information to suggest the best restaurants and dishes.

[1955] In this way, the present invention can provide a more personalized restaurant recommendation and food delivery experience by taking into account not only a user's dietary restrictions and allergy information, but also their emotional state.

[1956] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1957] Step 1:

[1958] The user enters information about dietary restrictions, allergies, and emotional state from their device. Specifically, they open the application and enter information such as "vegan," "nut allergy," or "happy." The entered data is then properly formatted (JSON format) within the app.

[1959] Input: Dietary restriction information, allergy information, emotional state

[1960] Processing: Data entry and formatting

[1961] Output: User data in JSON format

[1962] Step 2:

[1963] The device sends the data formatted in step 1 to the server. At this time, it uses an HTTP request to send JSON formatted data via the API. After sending, it checks whether the request was processed correctly.

[1964] Input: User data in JSON format

[1965] Processing: Sending data via HTTP request

[1966] Output: A confirmation response for data transfer to the server

[1967] Step 3:

[1968] The server receives the user data sent from the device. The received data is first analyzed and then saved in a database. The database records user information associated with the user ID.

[1969] Input: User data in JSON format

[1970] Processing: Receiving and analyzing data, storing it in a database

[1971] Output: User information stored in the database

[1972] Step 4:

[1973] The server searches the database for appropriate restaurant information. The restaurant information is filtered based on dietary restrictions, allergies, and emotional state. Filtering is done using SQL queries, etc.

[1974] Input: User information stored in the database

[1975] Processing: Searching and filtering restaurant information using SQL queries, etc.

[1976] Output: A list of restaurants suitable for the user

[1977] Step 5:

[1978] The server performs AI analysis on the filtered restaurant information to evaluate its safety, analyzing past reviews and menu trends, and scoring the level of allergy-friendliness.

[1979] Input: Filtered restaurant information

[1980] Processing: Safety assessment using AI analysis

[1981] Output: Restaurant information with safety scores

[1982] Step 6:

[1983] The server evaluates which restaurant best suits the user's emotional state based on the emotional data, for example, choosing a restaurant with a relaxing atmosphere for a stressed user, or a restaurant with adventurous cuisine for a happy user.

[1984] Input: Restaurant information with safety scores and sentiment data

[1985] Processing: Selecting the best restaurant based on sentiment data

[1986] Output: Final restaurant list with sentiment-based suggestions

[1987] Step 7:

[1988] The server sends the final restaurant list to the device via the API, again using an HTTP request to transfer the data and returning it in the appropriate structure (JSON format).

[1989] Input: Final restaurant list with sentiment-based suggestions

[1990] Processing: Sending data via HTTP request

[1991] Output: Confirmation response of data transfer to the device

[1992] Step 8:

[1993] The device displays the restaurant list received from the server on a user interface, organized in a list format, and allows users to view detailed information about each restaurant, its safety score, and emotional response suggestions.

[1994] Input: The final restaurant list received from the server

[1995] Processing: Displaying data in the user interface

[1996] Output: The list of restaurants displayed to the user

[1997] In this way, users can receive restaurant and food recommendations that take into account their dietary restrictions, allergy information, and emotional state.

[1998] 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.

[1999] 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.

[2000] 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.

[2001] 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.

[2002] 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.

[2003] 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.

[2004] 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).

[2005] 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.

[2006] 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."

[2007] 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.

[2008] 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).

[2009] 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.

[2010] 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.

[2011] 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.

[2012] 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.

[2013] 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.

[2014] 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.

[2015] 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.

[2016] 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.

[2017] 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.

[2018] 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.

[2019] The following is further disclosed regarding the above embodiment.

[2020] (Claim 1)

[2021] means for receiving dietary restriction information and allergy information input from a user terminal;

[2022] A means for searching for appropriate restaurant information from a database based on the dietary restriction information and allergy information;

[2023] A means for analyzing the menu trends and past reviews of the appropriate restaurant information and evaluating the safety level;

[2024] A means for presenting a list of restaurants suitable for the user based on the evaluated safety level;

[2025] A system including:

[2026] (Claim 2)

[2027] 10. The system of claim 1, further comprising means for collecting feedback information from users to help improve the accuracy of the safety assessment.

[2028] (Claim 3)

[2029] The system of claim 1 , further comprising: means for displaying the suitable restaurant information through a user interface.

[2030] "Example 1"

[2031] (Claim 1)

[2032] means for receiving dietary restriction information and allergy information input from a user terminal;

[2033] A means for searching for appropriate restaurant information from a database based on the dietary restriction information and allergy information;

[2034] A means for analyzing the menu trends and past reviews of the appropriate restaurant information using a generation AI model and evaluating safety;

[2035] A means for presenting a list of restaurants suitable for the user based on the evaluated safety level;

[2036] means for transmitting the list to a user terminal;

[2037] means for displaying said list through a user interface of a user terminal;

[2038] A system including:

[2039] (Claim 2)

[2040] 10. The system of claim 1, further comprising means for collecting feedback information from users to help improve the accuracy of the safety assessment.

[2041] (Claim 3)

[2042] The system of claim 1 , further comprising: means for displaying the suitable restaurant information through a user interface.

[2043] "Application Example 1"

[2044] (Claim 1)

[2045] means for receiving dietary restriction information and allergy information input from a user terminal;

[2046] A means for searching for appropriate dining facility information from a database based on the dietary restriction information and allergy information;

[2047] A means for analyzing the menu trends and past evaluations of the appropriate dining facility information and evaluating safety;

[2048] means for presenting a list of dining facilities suitable for the user based on the evaluated safety level;

[2049] The system further includes means for executing the reservation on the user terminal.

[2050] (Claim 2)

[2051] 10. The system of claim 1, further comprising means for collecting feedback information from users to help improve the accuracy of the safety assessment.

[2052] (Claim 3)

[2053] 10. The system of claim 1, further comprising means for displaying the appropriate dining establishment information through a user interface.

[2054] "Example 2: Combining Emotion Engines"

[2055] (Claim 1)

[2056] means for receiving dietary restriction information and allergy information input from a user terminal;

[2057] A means for searching for appropriate facility information from a database based on the dietary restriction information and allergy information;

[2058] A means for analyzing menu trends and past reviews of the appropriate facility information and evaluating safety;

[2059] means for presenting a list of facilities suitable for the user based on the evaluated safety level and the user's emotion data;

[2060] A means for analyzing the input contents and facial expressions of a user using an emotion recognition engine installed in the user terminal and acquiring emotion data;

[2061] means for analyzing the acquired emotion data and preferentially suggesting facilities with relaxing environments;

[2062] A system including...

[2063] (Claim 2)

[2064] 2. The system according to claim 1, further comprising means for collecting feedback information from users and using the collected feedback information to improve the accuracy of the safety evaluation and the accuracy of the emotion data analysis.

[2065] (Claim 3)

[2066] The system of claim 1, further comprising means for displaying the appropriate facility information through a user interface to allow a user to easily view and select the appropriate facility information.

[2067] "Application example 2 when combining emotion engines"

[2068] (Claim 1)

[2069] means for receiving dietary restriction information and allergy information input from a user terminal;

[2070] means for receiving emotion data in addition to the dietary restriction information and allergy information;

[2071] a means for searching a database for appropriate restaurant information based on the dietary restriction information, allergy information, and emotion data;

[2072] A means for analyzing the menu trends and past reviews of the appropriate restaurant information and evaluating the safety level;

[2073] A means for presenting a list of restaurants suitable for the user based on the evaluated safety level and emotion data;

[2074] ...

[2075] A system including:

[2076] (Claim 2)

[2077] 10. The system of claim 1, further comprising means for collecting feedback information from users to help improve the accuracy of the safety assessment.

[2078] (Claim 3)

[2079] The system of claim 1 , further comprising: means for displaying the suitable restaurant information through a user interface. [Explanation of symbols]

[2080] 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 dietary restriction information and allergy information input from a user terminal; A means for searching for appropriate restaurant information from a database based on the dietary restriction information and allergy information; A means for analyzing the menu trends and past reviews of the appropriate restaurant information and evaluating the safety level; and means for presenting to the user in the form of a list of restaurants suitable for the user based on the evaluated safety level.

2. The system of claim 1 further comprising means for collecting feedback information from users to help improve the accuracy of the safety assessment.

3. The system of claim 1 further comprising means for displaying the appropriate restaurant information through a user interface.

Images