System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving as input dietary restrictions and location information from a user; means for generating a search query based on the dietary restrictions and location information; means for sending the search query to a generative model and receiving relevant restaurant information; means for filtering the received restaurant information based on the dietary restrictions; and means for providing the filtered results to the user.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 modern society, there are many people who must avoid certain foods due to allergies, calorie restrictions, religious reasons, etc. These people face risks when eating out, making it difficult for them to enjoy meals with peace of mind. As a result, they tend to refrain from eating out or limit themselves to safe restaurants. There is a need for a system that addresses this situation and helps people with dietary restrictions enjoy eating out more freely. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means: a system including means for receiving dietary restrictions and location information as input from a user, means for generating a search query based on the dietary restrictions and location information, means for sending the search query to a generative model and receiving related restaurant information, means for filtering the received restaurant information based on the dietary restrictions, and means for providing the filtered results to the user.

[0006] Furthermore, the present invention includes a means for collecting feedback information provided by users and storing it in a database, and a means for updating the reliability ratings and dietary restriction compliance status of restaurants using the database, thereby enabling the system to improve the reliability of the information based on user evaluation data and ensure further suitability.

[0007] Finally, the system includes a means for displaying the received restaurant information on a map in a selectable format, and a means for displaying detailed information about the selected restaurant, which allows users to visually check the information and increases their sense of security when eating out.

[0008] "User" refers to an individual who uses the system to input dietary restrictions and location information to search for restaurant information.

[0009] "Dietary Restrictions" refers to information about dietary restrictions entered by a user, such as the need to avoid certain ingredients, calorie restrictions, or religious reasons.

[0010] "Location Information" means a User's current location or designated geographic information used when conducting a search based on dietary restrictions.

[0011] A "search query" refers to question-type data generated based on a user's dietary restrictions and location information to search for relevant restaurant information.

[0012] "Generative model" refers to an algorithm or system that uses artificial intelligence to search and generate relevant information based on a search query.

[0013] "Related restaurant information" refers to information such as the name, location, and service details of a restaurant obtained by the generative model based on the search query.

[0014] "Filtering" refers to the process of selecting relevant restaurant information that meets specific dietary restrictions.

[0015] "Display on a map" refers to visually displaying filtered restaurant information using a map drawing system.

[0016] "Feedback information" refers to data including users' evaluations of restaurants they have actually visited and their opinions regarding the availability of such restaurants for dietary restrictions.

[0017] A "database" refers to an information system that systematically stores information such as feedback information and manages it in a form that can be referenced later.

[0018] "Trustworthiness assessment" refers to the process of evaluating the accuracy and reliability of restaurant information based on feedback information. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] This invention is a support system that allows people who must avoid certain foods due to allergies, calorie restrictions, religious reasons, etc. to enjoy eating out with peace of mind. The system displays restaurant information that matches specific criteria on a map simply by the user entering the criteria.

[0041] System configuration

[0042] User

[0043] Users use an interface to input dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"). This interface is designed to be easy for users to operate.

[0044] Terminal

[0045] The device receives dietary restrictions and location information from the user and sends it to the server. It also displays the information received from the server on a map. Specifically, it sends the conditions entered in the form to the server as a POST request, analyzes the restaurant information returned from the server, and displays it.

[0046] server

[0047] The server analyzes the request received from the device and generates a search query based on the specified dietary restrictions and location information. It then sends this search query to a generative model (generative AI) and receives relevant restaurant information. It then filters the received information and returns the filtered restaurant list to the device. It also collects feedback information and stores it in a database to improve the reliability of the information.

[0048] Program processing

[0049] User operations

[0050] The user opens the application, enters their dietary restrictions (e.g., gluten-free, under 1500 kcal) and their current location (e.g., Tokyo), and then presses the search button.

[0051] Device behavior

[0052] When the search button is pressed, the device sends the entered search criteria to the server. The results returned from the server are displayed on a map, providing the user with a visually easy-to-understand format. Feedback information from the user is also sent to the server.

[0053] Server Operation

[0054] The server analyzes the request received from the device and generates a search query. Specifically, it generates a query such as "Find gluten-free restaurants and restaurants in Tokyo that offer meals under 1500 kcal" based on the input criteria. The query is sent to the generative model (GPT) and relevant restaurant information is received. The received restaurant information is then filtered to create a list of restaurants that meet the criteria. This list is returned to the device, and feedback provided to the user is stored in a database, updating the restaurant's reliability rating and dietary restrictions.

[0055] Specific examples

[0056] 1. The user opens the app and enters criteria such as "gluten-free," "under 1500kcal," and "Tokyo."

[0057] 2. The device sends these conditions to the server.

[0058] 3. The server generates a query to find restaurants in Tokyo that offer "gluten-free" and "under 1500 kcal" meals based on the conditions and sends it to the generative model (GPT).

[0059] 4. The generative model (GPT) returns the relevant restaurant information.

[0060] 5. The server filters this information and creates a list of restaurants that meet the criteria.

[0061] 6. The terminal displays the filtered restaurant information on a map and provides it to the user.

[0062] 7. The user selects a restaurant based on the displayed information and provides feedback after visiting.

[0063] 8. The terminal sends this feedback information to the server, which updates the database.

[0064] The above is a specific embodiment for implementing the system of the present invention, which supports people with dietary restrictions in enjoying eating out with peace of mind.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] The user opens the application and enters their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo") through the interface. These conditions are displayed as a form, designed to make it easy for the user to enter them.

[0068] Step 2:

[0069] The device receives the dietary restrictions and location information entered by the user. When the user presses the search button, the device sends these restrictions to the server as a POST request. The request is serialized in JSON format and prepared for parsing on the server side.

[0070] Step 3:

[0071] The server analyzes the request received from the device, extracts dietary restrictions and location information, and stores each value in variables. Based on this information, it generates a search query (e.g., "Find restaurants in Tokyo that serve gluten-free meals under 1500 kcal").

[0072] Step 4:

[0073] The server sends the generated search query to the generative model (GPT). The generative model searches for relevant restaurant information from websites, reviews, etc., and returns the results. This process is performed asynchronously via the generative AI's API.

[0074] Step 5:

[0075] The server receives the restaurant information returned from the generative model. The received information is analyzed and filtered based on the dietary restrictions entered by the user. Specifically, it selects restaurants from the returned list that perfectly match the dietary restrictions.

[0076] Step 6:

[0077] The server constructs a filtered list of restaurants in JSON format and sends it to the device, including the restaurant's name, location, and corresponding dietary restriction details.

[0078] Step 7:

[0079] The terminal decodes the list of restaurants received from the server and displays it on a map. The user can visually check the restaurants indicated by pins on the map. Clicking on each pin will display a pop-up with detailed information.

[0080] Step 8:

[0081] Users can choose a restaurant to visit based on the displayed information, and after visiting, they can provide feedback through the app about the restaurant's rating and whether it accommodates dietary restrictions.

[0082] Step 9:

[0083] The device receives feedback information from the user and sends it to the server in JSON format.

[0084] Step 10:

[0085] The server receives the feedback information and stores it in a database. It then updates the restaurant's credibility rating and dietary restrictions based on the collected feedback. The information stored in the database is used to improve the accuracy of search results the next time.

[0086] The above is a concrete explanation of each step of the program's processing. The operations of the server, terminal, and user at each step have been described in detail.

[0087] Example 1

[0088] 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."

[0089] Recently, an increasing number of people have to avoid certain foods due to dietary restrictions, allergies, religious reasons, etc. In order for these people to enjoy eating out with peace of mind, they need to be able to easily and quickly obtain information about restaurants that meet their requirements. However, with conventional methods, it has been difficult to collect this information, and there have been challenges in obtaining reliable information.

[0090] 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.

[0091] In this invention, the server includes means for receiving dietary restrictions and location information as input from a user, means for generating a search query based on the dietary restrictions and location information, means for transmitting the search query to a generation AI model that generates the search query and receiving related restaurant information, means for filtering the received restaurant information based on the dietary restrictions, and means for providing the filtered results to the user. This allows users to quickly obtain restaurant information that meets their specific dietary restrictions and enjoy eating out with peace of mind.

[0092] "User" refers to a person who uses the system to input dietary restrictions and location information to obtain appropriate restaurant information.

[0093] "Dietary restrictions" refers to conditions that require avoidance of certain ingredients or cooking methods, such as allergies, calorie restrictions, or religious beliefs.

[0094] "Location information" refers to information about the area or place a user wants to search for, such as city name or postal code.

[0095] A "search query" refers to instructions or commands to search for restaurants that meet the dietary restrictions and location information entered by the user.

[0096] "Generative AI model" refers to an artificial intelligence model that generates relevant information based on an input search query.

[0097] "Restaurant information" refers to detailed information that users need when eating out, such as the restaurant's name, address, contact information, menu, and information regarding dietary restrictions.

[0098] "Filtering" refers to the process of selecting only information that meets the user's dietary restrictions from the generated restaurant information.

[0099] A "database" refers to an electronic data collection in which collected information is stored.

[0100] "Trustworthiness evaluation" refers to the process of evaluating the quality and reliability of restaurants based on feedback information from customers.

[0101] "Dietary restriction accommodation status" refers to the extent to which a restaurant accommodates the dietary restrictions of customers.

[0102] "Display on a map" refers to showing filtered restaurant information on a map in a visually easy-to-understand format.

[0103] "Detailed Information" refers to deeper level information provided about the selected restaurant, such as menu, prices, opening hours, etc.

[0104] "Feedback information" refers to the evaluations and opinions provided by customers after visiting a restaurant.

[0105] This invention relates to a support system that enables people with dietary restrictions to enjoy eating out with peace of mind. This system is designed so that when a user simply inputs specific conditions, information about restaurants that meet those conditions is displayed on a map.

[0106] 1. Specific processing content of the program

[0107] User Input

[0108] Users start the application using a device such as a smartphone or PC, and enter their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"). Once the user has finished entering the information, they press the search button to begin the next process.

[0109] Device behavior

[0110] The device receives the conditions entered by the user and sends them to the server in the form of an HTTP POST request, which includes the dietary restrictions and location information in JSON format.

[0111] Server Operation

[0112] The server receives the request sent from the device and analyzes its contents. Specifically, it decodes the dietary restrictions and location information and generates a search query. This query is in the form of "Find restaurants in Tokyo that serve gluten-free meals under 1500 kcal." This query is used to send a prompt to a generative AI model (e.g., GPT).

[0113] Processing generative AI models

[0114] The generative AI model generates restaurant information that matches the search criteria based on the prompt received from the server, including the restaurant's name, address, menu information, and corresponding dietary restrictions.

[0115] Server Filtering

[0116] The server receives the restaurant information returned by the generative AI model and filters it. During the filtering process, it checks whether the received information meets the dietary restrictions specified by the user. Only matching information is selected, and finally, a filtered information list is created.

[0117] Providing information to devices

[0118] The server sends the filtered restaurant information to the terminal. The terminal displays the received information on a map, providing the user with a visually easy-to-understand format. Restaurants that meet the criteria are displayed as pins on the map, and users can click on the pins to view detailed information.

[0119] User Feedback

[0120] Users select a restaurant based on the displayed restaurant information and provide feedback through the app after visiting. The feedback includes rating points and comments, which are used for the next process.

[0121] Accumulation of feedback information

[0122] The terminal sends the feedback information entered by the user to the server, which stores the feedback information in a database and uses this information to update the restaurant's reliability rating and its ability to accommodate dietary restrictions.

[0123] 2. Hardware and Software Used

[0124] Devices used by users: computing devices such as smartphones, PCs, tablets, etc.

[0125] Application: Software that provides an interface for users to enter criteria

[0126] Server: Receives requests, parses them, filters them, and manages the database

[0127] Database: Managing reliability ratings and feedback information

[0128] Generative AI models (e.g., GPT): Artificial intelligence models that generate relevant information based on a search query.

[0129] Map software: Software for displaying received restaurant information on a map

[0130] 3. Examples of concrete examples and prompts

[0131] Specific examples

[0132] 1. The user opens the app and enters criteria such as "gluten-free," "under 1500kcal," and "Tokyo."

[0133] 2. The device sends these conditions to the server.

[0134] 3. The server generates a query based on the conditions: "Find restaurants in Tokyo that are gluten-free and under 1500 kcal" and sends it to the generative AI model.

[0135] 4. The generative AI model returns the relevant restaurant information.

[0136] 5. The server filters this information and creates a list of restaurants that meet the criteria.

[0137] 6. The terminal displays the filtered restaurant information on a map and provides it to the user.

[0138] 7. The user selects a restaurant based on the displayed information and provides feedback after visiting.

[0139] 8. The terminal sends this feedback information to the server, which updates the database.

[0140] Prompt Sentence Examples

[0141] "Please suggest restaurants in Tokyo that meet the specified criteria (e.g. gluten-free, under 1500kcal)."

[0142] The above is a specific embodiment of the system of the present invention, which allows users to easily find restaurants that meet their specific dietary restrictions and enjoy eating out with peace of mind.

[0143] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0144] Step 1:

[0145] User Input

[0146] The user starts the application, enters dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"), and then presses the search button.

[0147] Specific operation: Enter the conditions into the application interface.

[0148] Input: dietary restrictions, location information

[0149] Output: Conditions are sent to the terminal

[0150] Step 2:

[0151] Sending a request from the device

[0152] The device sends the user-entered conditions to the server as an HTTP POST request, which includes the dietary restrictions and location information in JSON format.

[0153] Specific operation: The data in the form where the conditions were entered is converted to JSON format and sent to the " / search" endpoint.

[0154] Input: User-entered conditions (JSON format)

[0155] Output: Server receives request

[0156] Step 3:

[0157] Server request analysis

[0158] The server analyzes the request received from the device and generates a search query based on the conditions. The query is a sentence such as "Find restaurants in Tokyo that are gluten-free and under 1500 kcal."

[0159] Specific operation: Parse the received JSON data and extract each condition. Then, construct a query statement.

[0160] Input: HTTP POST request (conditions in JSON format)

[0161] Output: Search query

[0162] Step 4:

[0163] Sending prompts to the server's generated AI model

[0164] The server sends a search query to the generative AI model, which generates relevant restaurant information based on the prompt.

[0165] Specific operation: The constructed query sentence is sent to the generative AI model as a prompt sentence.

[0166] Input: Discovery query

[0167] Output: Generative AI model returns restaurant information

[0168] Step 5:

[0169] Receiving and filtering restaurant information

[0170] The server receives the restaurant information returned by the generative AI model and filters it to select only restaurants that meet specific dietary restrictions.

[0171] Specific operation: Analyze the information returned from the generative AI model and extract information that meets the conditions.

[0172] Input: Restaurant information from a generative AI model

[0173] Output: Filtered list of restaurants

[0174] Step 6:

[0175] Sending filtering results to the device

[0176] The server sends the filtered restaurant list in JSON format to the terminal.

[0177] Specific operation: The filtering results are encoded in JSON format and sent to the terminal as an HTTP response.

[0178] Input: A filtered list of restaurants

[0179] Output: The device receives the list

[0180] Step 7:

[0181] Displaying information on the device's map

[0182] The device passes the filtering results received from the server to the map application and displays them on a map, with the location of each restaurant indicated by a pin and detailed information displayed.

[0183] Specific operation: Data is passed to the map application API, and pins are placed on the map. Clicking on a pin displays detailed store information.

[0184] Input: A filtered list of restaurants

[0185] Output: Restaurant information displayed on a map

[0186] Step 8:

[0187] User feedback

[0188] Users enter feedback (rating points, comments) about the restaurants they visit within the app.

[0189] Specific action: The user fills out the feedback form and presses the submit button.

[0190] Input: Restaurant rating points, comments

[0191] Output: Feedback information sent to the terminal

[0192] Step 9:

[0193] Send device feedback

[0194] The terminal transmits the feedback information input by the user to the server in the form of an HTTP POST request.

[0195] Specific operation: The feedback information is converted into JSON format and sent to the server.

[0196] Input: User feedback information (JSON format)

[0197] Output: The server receives the feedback information.

[0198] Step 10:

[0199] Server database update

[0200] The server stores the received feedback information in a database, which updates the restaurant's reliability rating and dietary restrictions.

[0201] Specific operation: Update the corresponding record in the database and accumulate the information.

[0202] Input: Feedback information

[0203] Output: Updated database

[0204] This concludes the detailed description of the program processing of this system. This system allows users to quickly find restaurants that meet specific dietary restrictions, allowing them to enjoy eating out with peace of mind.

[0205] (Application example 1)

[0206] 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."

[0207] Conventional restaurant search systems do not provide sufficient support for people with dietary restrictions when it comes to enjoying dining out. Specifically, they lack information on restaurants that cater to specific allergies, calorie restrictions, or religious dietary restrictions, making it difficult for users to choose meals with confidence. Another issue is the inefficient collection of orders and feedback from restaurants selected from search results, and the inefficient updating of the database. This makes it difficult for users with dietary restrictions to find suitable restaurants, reducing the convenience of dining out.

[0208] 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.

[0209] In this invention, the server includes a means for receiving dietary restrictions and location information from a user as input, a means for generating a search query based on the dietary restrictions and location information, and a means for sending the search query to a generative model and receiving related restaurant information. This enables efficient searching and provision of restaurant information that satisfies dietary restrictions. The server also includes a means for filtering the received restaurant information based on the dietary restrictions, providing the filtered results to the user, and placing an order with the selected restaurant. It also includes a means for collecting feedback information provided by the user and storing and updating the information in a database. This allows users to select and order from an appropriate restaurant with peace of mind, and keeps the restaurant's reliability and service status up to date based on the results.

[0210] "User" refers to a person who uses the system to input dietary restrictions and location information to obtain appropriate restaurant information.

[0211] "Dietary restrictions" refers to conditions where certain ingredients or ingredients must be avoided due to allergies, calorie restrictions, religious reasons, etc.

[0212] "Location Information" means information about a geographic location where you are currently located or plan to visit.

[0213] A "search query" refers to a search query that is generated based on dietary restrictions and location information.

[0214] "Generative model" refers to an artificial intelligence model that generates relevant restaurant information based on a search query.

[0215] "Restaurant information" refers to information such as the restaurant's name, address, menu contents, and dietary restrictions that can be accommodated.

[0216] "Filtering" refers to the process of selecting only the information from the received restaurant information that meets the user's dietary restrictions.

[0217] "Ordering" refers to the process of a user purchasing a meal from a restaurant selected on the system.

[0218] "Feedback information" refers to information such as evaluations, opinions, and areas for improvement provided by customers after using a restaurant.

[0219] "Database" refers to a system for storing and managing collected feedback information and restaurant information.

[0220] This invention is a system that allows people with specific dietary restrictions to find suitable restaurants, place orders, and provide feedback. The specific configuration and program of the system are described below.

[0221] 1. System Program

[0222] First, the user enters their dietary restrictions and location information on their smartphone. Using the app's interface, users can easily input conditions such as "gluten-free," "under 1500 kcal," and "Tokyo." The smartphone application was developed using React Native.

[0223] The server receives the input information from the user and generates a search query that reflects the entered dietary restrictions and location information. The server is built using Node.js and Express.js.

[0224] The search query is sent to a generative model (OpenAI GPT-4) that receives relevant restaurant information, including a list of restaurants that meet specific dietary restrictions. The generated restaurant information is then filtered on the server to select only restaurants that meet the user's criteria.

[0225] The filtered restaurant information is returned to the smartphone application, which displays this information on a map for the user to visually confirm. The user can also place an order directly with the selected restaurant. The order information is also sent to the server, which notifies the appropriate restaurant.

[0226] After eating and drinking, the user provides feedback information. The feedback is again entered through a smartphone application and sent to the server. The server stores this feedback information in a database and uses it to keep up-to-date restaurant reliability ratings and dietary restriction compliance status. MongoDB is used for the database.

[0227] 2. Program Processing

[0228] The following hardware and software are used to receive input information from a user and to process and calculate data to generate a search query.

[0229] Hardware:

[0230] Smartphone: Providing a user interface and receiving / sending input information

[0231] Server: Parsing and responding to requests, managing databases

[0232] software:

[0233] Frontend: React Native

[0234] Backend: Node.js, Express.js

[0235] Database: MongoDB

[0236] Generative AI model: OpenAI GPT-4

[0237] The server analyzes the information received from the user and sends an appropriate query to the generative model. Once the generated restaurant information is returned, it is filtered to create a list of restaurants that meet the user's criteria. Finally, the filtered information is sent to the smartphone application and presented to the user.

[0238] 3. Examples and prompts

[0239] Examples:

[0240] A user opens the app and enters the criteria "gluten-free," "under 1500kcal," and "Tokyo." The server processes the request, returns matching restaurant information, and displays it on a map. The user then selects a specific restaurant, places an order, and provides feedback after completing the order.

[0241] Example prompt sentence:

[0242] "Find restaurants in Tokyo that provide gluten-free meals under 1500 calories."

[0243] This will create a system that allows people with specific dietary restrictions to enjoy eating out with peace of mind.

[0244] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0245] Step 1:

[0246] The user enters dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo") through a smartphone application. The information entered by the user is sent from the smartphone to the server. Specifically, the data entered in the user interface is sent to the server as an HTTP POST request.

[0247] Step 2:

[0248] The server analyzes the received dietary restrictions and location information to generate a search query. Based on the analyzed data, the server creates a query to identify "gluten-free meals" and "restaurants that offer meals under 1500 kcal." This query is then sent to the generative AI model.

[0249] Step 3:

[0250] The server sends a search query to the generative AI model and receives relevant restaurant information. The generative AI model (OpenAI GPT-4) analyzes the query and provides a list of restaurants that meet the criteria. The received information includes the restaurant's name, address, and menu items with corresponding dietary restrictions.

[0251] Step 4:

[0252] The server filters the received restaurant information based on the user's dietary restrictions. In this filtering process, restaurant information that does not meet the restrictions is excluded. Finally, a filtered list of restaurant information is generated.

[0253] Step 5:

[0254] The server returns the filtered restaurant information to the smartphone application, which then visually displays the received restaurant information on a map, including pin locations and detailed information about the restaurants.

[0255] Step 6:

[0256] The user browses restaurant information on the map and places an order at the restaurant of their choice. The smartphone application then sends the order information back to the server. The order includes details such as menu selection and delivery address.

[0257] Step 7:

[0258] The server analyzes the order information and notifies the appropriate restaurant, and a response is returned to the smartphone application to confirm that the order was successfully received.

[0259] Step 8:

[0260] After eating or drinking, the user provides feedback information. The feedback entered through the smartphone application is sent to the server, which then stores the feedback information in a database.

[0261] Step 9:

[0262] The server uses the feedback information stored in the database to update the restaurant's trustworthiness rating and dietary restriction availability, thereby improving the reliability of the information provided the next time a search is performed. The database is also continually improved based on user feedback.

[0263] 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.

[0264] This invention is a support system that allows people who must avoid certain foods due to allergies, calorie restrictions, religious reasons, etc. to enjoy eating out with peace of mind, as well as a system that recognizes the user's emotions and provides optimal restaurant information based on those emotions.The system displays restaurant information that meets the user's conditions and matches their emotions on a map simply by the user inputting specific conditions and emotional state.

[0265] System configuration

[0266] User

[0267] The user inputs dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo") through the system interface. Furthermore, the emotion engine automatically recognizes the user's emotional state. This emotional state can be obtained, for example, from facial expressions captured by the user or from audio recordings.

[0268] Terminal

[0269] The device receives the dietary restrictions and location information entered by the user, as well as emotion data from the emotion engine, and transmits them to the server. The device displays the information received from the server on a map and provides it to the user.

[0270] server

[0271] The server analyzes the dietary restrictions, location information, and emotion data received from the device and generates a search query. It then sends this search query to a generative model (generative AI) and receives relevant restaurant information. It filters the received information, adjusts the optimal restaurant list based on the emotion data, and returns it to the device. It also collects feedback information and emotion data and stores it in a database to improve the reliability of the information.

[0272] Program processing

[0273] User operations

[0274] The user opens the application and inputs their dietary restrictions (e.g., gluten-free, under 1500 kcal) and their current location (e.g., Tokyo).The emotion engine then automatically acquires emotion data based on the captured facial expressions and voice.

[0275] Device behavior

[0276] The device sends the entered dietary restrictions, location information, and emotional data to the server. The results returned from the server are displayed on a map, providing the user with a visually easy-to-understand format. Feedback information and emotional data from the user are also sent to the server.

[0277] Server Operation

[0278] The server analyzes the request received from the device and generates a search query. Specifically, it generates a query such as "Find restaurants in Tokyo that offer gluten-free meals under 1500 kcal" based on the input conditions and emotion data. The query is sent to the generative model (GPT) and relevant restaurant information is received. The received restaurant information is then filtered and prioritized based on the emotion data. For example, if the user is feeling stressed, restaurants with a relaxing atmosphere are prioritized. The results are returned to the device and provided to the user.

[0279] Specific examples

[0280] 1. The user opens the app and enters criteria such as "gluten-free," "under 1500 kcal," and "Tokyo." At the same time, the emotion engine analyzes the user's facial photo and recognizes the emotion of "stress."

[0281] 2. The device sends these conditions and emotion data to the server.

[0282] 3. Based on the conditions and emotion data, the server generates a query such as "Find restaurants in Tokyo that are gluten-free, under 1500 kcal, and have a stress-reducing atmosphere," and sends it to the generative model (GPT).

[0283] 4. The generative model (GPT) returns the relevant restaurant information.

[0284] 5. After filtering the information, the server creates a list that prioritizes restaurants with high ratings for "stress-reducing atmosphere."

[0285] 6. The terminal displays the filtered restaurant information on a map and provides it to the user.

[0286] 7. The user selects a restaurant based on the displayed information and provides feedback after visiting.

[0287] 8. The device sends the feedback information and emotion data to the server, which updates the database.

[0288] The above is a specific embodiment for implementing the system of the present invention. By combining it with an emotion engine, it is possible to provide optimal restaurant information according to the user's emotional state, supporting a more satisfying dining out experience.

[0289] The processing flow will be explained below.

[0290] Step 1:

[0291] The user opens the application. The user inputs their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"). The emotion engine then automatically recognizes the user's emotional state. This emotional state is obtained from facial expressions and voice captured by the user.

[0292] Step 2:

[0293] The device receives the dietary restrictions and location information entered by the user. When the user presses the search button, the device sends these restrictions and the recognized emotion data to the server. The request is sent as a POST request, serialized in JSON format.

[0294] Step 3:

[0295] The server analyzes the request received from the device, extracting dietary restrictions, location information, and emotion data, and stores each value in variables. Based on this information, it generates a search query (e.g., "Find restaurants in Tokyo that serve gluten-free meals under 1500 kcal").

[0296] Step 4:

[0297] The server sends the generated search query to the generative model (GPT). The generative model searches for relevant restaurant information from websites and reviews on the Internet and returns the results. This process is performed asynchronously through the generative AI's API.

[0298] Step 5:

[0299] The server receives the restaurant information returned from the generative model. The information is analyzed and filtered based on the user's dietary restrictions. Specifically, it selects restaurants from the returned list that perfectly match the user's dietary restrictions.

[0300] Step 6:

[0301] The server further adjusts the filtered restaurant list based on the emotion data. For example, if the user's emotion is "stress," it prioritizes restaurants with a relaxing atmosphere. The final adjusted list is then compiled in JSON format and sent to the device.

[0302] Step 7:

[0303] The terminal decodes the list of restaurants received from the server and displays it on a map. The user can visually check the restaurants indicated by pins on the map. Clicking on each pin will display a pop-up with detailed information.

[0304] Step 8:

[0305] Users can choose a restaurant to visit based on the displayed information, and after visiting, they can provide feedback through the app about the restaurant's rating and whether it accommodates dietary restrictions.

[0306] Step 9:

[0307] The device receives feedback information from the user and sends it to the server in JSON format.

[0308] Step 10:

[0309] The server receives the feedback information and stores it in a database. It then updates the restaurant's trustworthiness rating and dietary restrictions based on the collected feedback and sentiment data. The information stored in the database is used to improve the accuracy of search results the next time.

[0310] The above is a detailed explanation of the steps involved in the program's processing, which combines emotion engines. The operations of the server, terminal, and user at each step are described in detail.

[0311] Example 2

[0312] 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."

[0313] In today's world, it is difficult for people with dietary restrictions to enjoy eating out with peace of mind. Furthermore, it is also difficult for them to easily find an appropriate restaurant that matches their emotional state. The present invention aims to solve this problem by providing optimal restaurant information based on dietary restrictions and emotional state, thereby improving users' dining out experiences.

[0314] 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 conditions and location information from a user as input, means for generating a search query based on the dietary restriction conditions and location information, means for sending the search query to a generative AI model and receiving related restaurant information, means for filtering the received restaurant information based on the dietary restriction conditions and the user's emotional state, means for providing the filtered results to the user, means including an emotion recognition engine for acquiring emotion data of the user, and means for adjusting restaurant information based on the acquired emotion data. This makes it possible to provide restaurant information optimized for the user's dietary restriction conditions and emotional state.

[0315] "Dietary restriction conditions" are conditions that serve as criteria when a user selects a particular restaurant, such as restrictions on specific ingredients or calorie restrictions.

[0316] "Location information" refers to geographical data of the user's current location or a specified area, and is information used to select restaurants.

[0317] A "search query" is a query generated based on data such as dietary restrictions, location information, and emotional state, and is used to search for restaurant information.

[0318] A "generative AI model" is an artificial intelligence model that generates and provides the most relevant restaurant information based on a given search query.

[0319] An "emotion recognition engine" is software or hardware that analyzes a user's facial photograph and voice data to determine the user's current emotional state.

[0320] "Filtering" is the process of sorting received restaurant information based on dietary restrictions and emotional state, and extracting the most suitable information.

[0321] A "database" is an information management system that stores collected information such as feedback information and emotional data, and uses it for future searches and analyses.

[0322] "Feedback information" refers to information such as impressions and evaluations provided by users after visiting a restaurant, and is used to improve the accuracy of the system.

[0323] "Adjustment" refers to a process of changing the priority of the received restaurant information based on the acquired emotion data to provide the user with the most suitable information.

[0324] This invention provides a system that allows users to easily obtain optimal restaurant information based on their specific dietary restrictions and emotional state. The system is primarily composed of a user terminal, a server, and a generative AI model.

[0325] User operations

[0326] Users launch the application using a device such as a smartphone or tablet. First, they enter their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and their current location (e.g., "Tokyo"). The emotion engine then automatically obtains the user's emotional state. This emotional state is determined by analyzing a facial photograph taken by the user and a recorded voice.

[0327] Device behavior

[0328] The device sends the dietary restrictions, location information, and acquired emotion data entered by the user to the server as a single request. The device displays the restaurant information received from the server on a map to provide a visual reference for the user. The device also sends feedback information provided by the user to the restaurants they visited to the server.

[0329] Server Operation

[0330] The server analyzes the dietary restrictions, location information, and emotion data received from the device and generates a search query. Specifically, it generates a query to search for "restaurants in Tokyo that are gluten-free, serve meals under 1500 kcal, and have a stress-reducing atmosphere." The server sends this query to a generative AI model (e.g., GPT) and receives relevant restaurant information.

[0331] The received restaurant information is filtered by the server. The filtering is performed based on dietary restrictions and emotional data. For example, if the user is feeling "stressed," restaurants with a relaxing atmosphere will be prioritized. The filtered restaurant information is returned to the terminal and provided to the user.

[0332] In addition, the server stores feedback information and emotional data provided by users in a database. This database is used to update restaurant reliability ratings and dietary restrictions, helping to improve recommendation accuracy in future visits.

[0333] Specific examples

[0334] Below are specific operating procedures and examples of prompts.

[0335] 1. User Actions:

[0336] Users open the app and enter dietary restrictions such as "gluten-free," "under 1500 kcal," and "Tokyo."

[0337] The emotion engine analyzes the user's facial photo and recognizes the emotion as "stress."

[0338] 2. Device behavior:

[0339] The device sends the condition and emotion data to the server.

[0340] 3. Server Operation:

[0341] The server generates a query such as "Find a restaurant in Tokyo that is gluten-free, under 1500 kcal, and has a stress-reducing atmosphere" and sends it to the generative AI model.

[0342] A generative AI model (e.g., GPT) returns the relevant restaurant information.

[0343] The server filters the information and sends it back to the device.

[0344] 4. Display and Feedback:

[0345] The terminal displays filtered restaurant information on a map and provides it to the user.

[0346] After the user visits, feedback information is sent from the terminal to the server.

[0347] Prompt Sentence Examples

[0348] "Please tell me restaurants in Tokyo that offer gluten-free meals under 1500 kcal in a stress-relieving atmosphere."

[0349] This invention efficiently provides restaurant information optimized for the user's dietary restrictions and emotional state, resulting in a more satisfying dining out experience.

[0350] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0351] Step 1:

[0352] User input:

[0353] The user opens the application on their smartphone and enters their current location and dietary restrictions, such as "gluten-free," "under 1500 kcal," and "Tokyo," into the application interface. They then press the "Emotion Input" button to capture a photo of their face and their voice.

[0354] Input: dietary restrictions, location information, face photo or voice

[0355] Output: User condition and emotion data

[0356] Step 2:

[0357] Obtaining emotion data:

[0358] The device sends the captured facial photo and voice data to an emotion recognition engine, which analyzes them and determines the user's emotional state (e.g., "stress").

[0359] Input: Face photo or voice data

[0360] Output: Emotion recognition result (e.g. "Stress")

[0361] Step 3:

[0362] Data transmission:

[0363] The device sends the dietary restriction conditions, location information, and emotion recognition results as a single request to the server.

[0364] Input: dietary restriction conditions, location information, emotion recognition results

[0365] Output: Request to server

[0366] Step 4:

[0367] Generating a search query:

[0368] The server analyzes the received data and generates a search query, specifically, a query to find "restaurants in Tokyo that serve gluten-free meals under 1500 kcal and have a stress-reducing atmosphere."

[0369] Input: dietary restriction conditions, location information, emotion recognition results

[0370] Output: The search query

[0371] Step 5:

[0372] Querying a generative AI model:

[0373] The server sends the generated query to a generative AI model (e.g., GPT), which generates relevant restaurant information based on the query and returns it to the server.

[0374] Input: Search query

[0375] Output: Related restaurant information

[0376] Step 6:

[0377] Filter restaurant information:

[0378] The server then filters the received restaurant information based on dietary restrictions and emotion recognition results. For example, it prioritizes restaurants with a high rating for "stress-reducing atmosphere."

[0379] Input: Related restaurant information, dietary restrictions, emotion recognition results

[0380] Output: Filtered restaurant information

[0381] Step 7:

[0382] Sending adjustment results:

[0383] The server sends the filtered restaurant information to the device, which then plots the received information on a map using a map API (e.g., Google Maps) and provides it to the user in a visually easy-to-understand format.

[0384] Input: Filtered restaurant information

[0385] Output: Response to the terminal

[0386] Step 8:

[0387] Enter your feedback:

[0388] After visiting a restaurant, users can enter their impressions and ratings on the feedback screen. For example, they can add comments such as "The food was delicious" or "The atmosphere was relaxing."

[0389] Input: Feedback information

[0390] Output: Feedback data

[0391] Step 9:

[0392] Send feedback information:

[0393] The device sends feedback information to the server, which stores it in a database and uses it to improve the accuracy of future query generation and filtering.

[0394] Input: Feedback data

[0395] Output: Stored in a database

[0396] (Application example 2)

[0397] 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."

[0398] Conventional restaurant search systems can provide restaurant information based on a user's dietary restrictions, but they cannot provide restaurant information that takes into account the user's emotional state. This makes it difficult for users to find the best restaurant when they are in a specific emotional state. In particular, for users who are feeling stressed or tired, the system cannot suggest restaurants with a high relaxation effect, which leads to a problem of reduced user satisfaction.

[0399] 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 conditions and location information from a user as input, means for generating a search query based on the dietary restriction conditions and location information, means for sending the search query to a generative model and receiving related restaurant information, means for filtering the received restaurant information based on the dietary restriction conditions, means for providing the filtered results to the user, means for recognizing the user's emotional state, and means for prioritizing and adjusting the received restaurant information based on the emotional state. This makes it possible to provide optimal restaurant information according to the user's emotional state.

[0400] "Dietary restrictions" refer to conditions that require avoiding certain ingredients or nutrients due to allergies, calorie restrictions, religious reasons, etc.

[0401] "Location information" refers to geographic data about a user's current location or a location they specify.

[0402] A "search query" is a search command generated based on criteria entered by the user.

[0403] A "generative model" is an artificial intelligence model that generates relevant information based on an input search query.

[0404] "Restaurant information" refers to data about the type of restaurant, its location, the menu it offers, etc.

[0405] "Filtering" is the process of selecting and extracting data based on specific conditions.

[0406] "User" refers to a person who uses this system to search for restaurant information that meets dietary restrictions.

[0407] "Emotional state" refers to the user's psychological and emotional state as recognized from facial expressions, voice, etc.

[0408] "Prioritization" is the process of assigning importance to information based on the user's emotional state.

[0409] "Delivery" refers to a service that delivers ordered food and drinks to a specified location.

[0410] The system for implementing this invention is mainly composed of a user terminal and a server. The user terminal and the server work together via a communication line to provide the information requested by the user. Each element of the system is described in detail below.

[0411] System Configuration

[0412] User Operation

[0413] Users operate the application using a user device such as a smartphone. After opening the application, the user enters dietary restrictions (e.g., "gluten-free") and location information (e.g., "Tokyo"). The application also has an emotion recognition function that can capture the user's emotional state using a camera and microphone. To analyze the user's emotional state from facial expressions and voice, the application uses emotion recognition services such as Microsoft's Azure Emotion API.

[0414] Device behavior

[0415] The user device receives the dietary restrictions, location information, and emotion data entered by the user. This data is sent to the server. The results returned from the server are displayed on a map, providing the user with a visually easy-to-understand format. The system also collects the user's feedback information and emotion data, which are sent to the server to update the database.

[0416] Server Operation

[0417] The server analyzes the dietary restrictions, location information, and emotional data received from the user device and generates an appropriate search query. This search query is sent to a generative AI model (e.g., GPT-4) to receive relevant restaurant information. The received restaurant information is filtered based on the dietary restrictions and further prioritized based on the user's emotional state. For example, if the user is feeling stressed, restaurants with a high relaxation effect will be prioritized. The final restaurant list is returned to the user device and displayed in the user's application.

[0418] The server periodically collects feedback information and emotional data and updates the database to improve restaurant reliability ratings and dietary restrictions.

[0419] Specific examples

[0420] The user opens the app and enters search criteria such as "gluten-free" and "Tokyo." At the same time, the emotion engine analyzes the user's facial photo and recognizes that the user is feeling "stressed." The device then sends these criteria and emotion data to the server. Based on the criteria and emotion data, the server generates a search query such as "Find restaurants in Tokyo that offer gluten-free menus and have a stress-reducing atmosphere," and sends it to a generative model (GPT-4). The generative model returns relevant restaurant information, and the server creates a list prioritizing restaurants with a high stress-reducing rating. Finally, the filtered results are displayed on the user's device.

[0421] Prompt Sentence Examples

[0422] "Please tell me restaurants in Tokyo that offer gluten-free menus and have a great relaxation effect."

[0423] In this way, the present invention provides optimal restaurant information based on dietary restrictions and emotional state, thereby realizing a system that can increase user satisfaction.

[0424] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0425] Step 1:

[0426] The user launches the application using a device such as a smartphone. A screen appears where the user can enter their dietary restrictions (e.g., "gluten-free") and current location (e.g., "Tokyo"). The entered information is temporarily stored in the device's internal memory.

[0427] Step 2:

[0428] The device uses camera and microphone sensors to recognize the user's emotional state. Specifically, it takes a photo of the user's face or records their voice, and sends this to Microsoft's Azure Emotion API. It then receives emotion data (e.g., "stress") returned from the API. The input is the face photo or voice data, and the output is emotion data.

[0429] Step 3:

[0430] The device sends the acquired dietary restriction conditions, current location information, and emotion data to the server. Specifically, it sends them as an HTTP request. The input is the dietary restriction conditions, current location information, and emotion data, and the output is the transmission of an HTTP request.

[0431] Step 4:

[0432] The server analyzes the dietary restrictions, current location information, and emotion data received from the device and generates a search query. The generated search query may be in the form of, for example, "Find restaurants in Tokyo that offer gluten-free menus and have stress-reducing effects." The inputs are dietary restrictions, current location information, and emotion data, and the output is the generated search query.

[0433] Step 5:

[0434] The server sends the generated search query to a generative AI model (e.g., GPT-4) and receives related restaurant information. The generative AI model returns restaurant information in response to the search query. The input is the search query, and the output is related restaurant information.

[0435] Step 6:

[0436] The server filters the received restaurant information based on the dietary restrictions. As a result of the filtering, only matching restaurant information is extracted. The input is restaurant information and dietary restrictions, and the output is the filtered restaurant information.

[0437] Step 7:

[0438] The server prioritizes and adjusts the filtered restaurant information based on the user's emotional state. For example, if the user is feeling stressed, restaurants with a high relaxation effect are prioritized. The input is the filtered restaurant information and emotional data, and the output is prioritized restaurant information.

[0439] Step 8:

[0440] The server returns the prioritized restaurant information to the terminal and provides it to the user. The terminal displays the received restaurant information on a map and provides it to the user in a visually easy-to-understand format. The input is the prioritized restaurant information, and the output is the restaurant information displayed on the map.

[0441] Step 9:

[0442] The user makes a selection based on the displayed restaurant information and provides feedback information after visiting. The feedback information is sent from the terminal to the server. The input is the feedback information, and the output is the transmission to the server.

[0443] Step 10:

[0444] The server stores the received feedback information and emotion data in a database. The server uses the feedback information to update the restaurant's trustworthiness rating and dietary restriction compliance status. The input is the feedback information and emotion data, and the output is the updated database.

[0445] In this way, the system can provide optimal restaurant information based on dietary restrictions and emotional state, increasing user satisfaction.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] [Second embodiment]

[0450] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0451] 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.

[0452] 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).

[0453] 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.

[0454] 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.

[0455] 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).

[0456] 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.

[0457] 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.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] 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."

[0462] This invention is a support system that allows people who must avoid certain foods due to allergies, calorie restrictions, religious reasons, etc. to enjoy eating out with peace of mind. The system displays restaurant information that matches specific criteria on a map simply by the user entering the criteria.

[0463] System configuration

[0464] User

[0465] Users use an interface to input dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"). This interface is designed to be easy for users to operate.

[0466] Terminal

[0467] The device receives dietary restrictions and location information from the user and sends it to the server. It also displays the information received from the server on a map. Specifically, it sends the conditions entered in the form to the server as a POST request, analyzes the restaurant information returned from the server, and displays it.

[0468] server

[0469] The server analyzes the request received from the device and generates a search query based on the specified dietary restrictions and location information. It then sends this search query to a generative model (generative AI) and receives relevant restaurant information. It then filters the received information and returns the filtered restaurant list to the device. It also collects feedback information and stores it in a database to improve the reliability of the information.

[0470] Program processing

[0471] User operations

[0472] The user opens the application, enters their dietary restrictions (e.g., gluten-free, under 1500 kcal) and their current location (e.g., Tokyo), and then presses the search button.

[0473] Device behavior

[0474] When the search button is pressed, the device sends the entered search criteria to the server. The results returned from the server are displayed on a map, providing the user with a visually easy-to-understand format. Feedback information from the user is also sent to the server.

[0475] Server Operation

[0476] The server analyzes the request received from the device and generates a search query. Specifically, it generates a query such as "Find gluten-free restaurants and restaurants in Tokyo that offer meals under 1500 kcal" based on the input criteria. The query is sent to the generative model (GPT) and relevant restaurant information is received. The received restaurant information is then filtered to create a list of restaurants that meet the criteria. This list is returned to the device, and feedback provided to the user is stored in a database, updating the restaurant's reliability rating and dietary restrictions.

[0477] Specific examples

[0478] 1. The user opens the app and enters criteria such as "gluten-free," "under 1500kcal," and "Tokyo."

[0479] 2. The device sends these conditions to the server.

[0480] 3. The server generates a query to find restaurants in Tokyo that offer "gluten-free" and "under 1500 kcal" meals based on the conditions and sends it to the generative model (GPT).

[0481] 4. The generative model (GPT) returns the relevant restaurant information.

[0482] 5. The server filters this information and creates a list of restaurants that meet the criteria.

[0483] 6. The terminal displays the filtered restaurant information on a map and provides it to the user.

[0484] 7. The user selects a restaurant based on the displayed information and provides feedback after visiting.

[0485] 8. The terminal sends this feedback information to the server, which updates the database.

[0486] The above is a specific embodiment for implementing the system of the present invention, which supports people with dietary restrictions in enjoying eating out with peace of mind.

[0487] The processing flow will be explained below.

[0488] Step 1:

[0489] The user opens the application and enters their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo") through the interface. These conditions are displayed as a form, designed to make it easy for the user to enter them.

[0490] Step 2:

[0491] The device receives the dietary restrictions and location information entered by the user. When the user presses the search button, the device sends these restrictions to the server as a POST request. The request is serialized in JSON format and prepared for parsing on the server side.

[0492] Step 3:

[0493] The server analyzes the request received from the device, extracts dietary restrictions and location information, and stores each value in variables. Based on this information, it generates a search query (e.g., "Find restaurants in Tokyo that serve gluten-free meals under 1500 kcal").

[0494] Step 4:

[0495] The server sends the generated search query to the generative model (GPT). The generative model searches for relevant restaurant information from websites, reviews, etc., and returns the results. This process is performed asynchronously via the generative AI's API.

[0496] Step 5:

[0497] The server receives the restaurant information returned from the generative model. The received information is analyzed and filtered based on the dietary restrictions entered by the user. Specifically, it selects restaurants from the returned list that perfectly match the dietary restrictions.

[0498] Step 6:

[0499] The server constructs a filtered list of restaurants in JSON format and sends it to the device, including the restaurant's name, location, and corresponding dietary restriction details.

[0500] Step 7:

[0501] The terminal decodes the list of restaurants received from the server and displays it on a map. The user can visually check the restaurants indicated by pins on the map. Clicking on each pin will display a pop-up with detailed information.

[0502] Step 8:

[0503] Users can choose a restaurant to visit based on the displayed information, and after visiting, they can provide feedback through the app about the restaurant's rating and whether it accommodates dietary restrictions.

[0504] Step 9:

[0505] The device receives feedback information from the user and sends it to the server in JSON format.

[0506] Step 10:

[0507] The server receives the feedback information and stores it in a database. It then updates the restaurant's credibility rating and dietary restrictions based on the collected feedback. The information stored in the database is used to improve the accuracy of search results the next time.

[0508] The above is a concrete explanation of each step of the program's processing. The operations of the server, terminal, and user at each step have been described in detail.

[0509] Example 1

[0510] 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."

[0511] Recently, an increasing number of people have to avoid certain foods due to dietary restrictions, allergies, religious reasons, etc. In order for these people to enjoy eating out with peace of mind, they need to be able to easily and quickly obtain information about restaurants that meet their requirements. However, with conventional methods, it has been difficult to collect this information, and there have been challenges in obtaining reliable information.

[0512] 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.

[0513] In this invention, the server includes means for receiving dietary restrictions and location information as input from a user, means for generating a search query based on the dietary restrictions and location information, means for transmitting the search query to a generation AI model that generates the search query and receiving related restaurant information, means for filtering the received restaurant information based on the dietary restrictions, and means for providing the filtered results to the user. This allows users to quickly obtain restaurant information that meets their specific dietary restrictions and enjoy eating out with peace of mind.

[0514] "User" refers to a person who uses the system to input dietary restrictions and location information to obtain appropriate restaurant information.

[0515] "Dietary restrictions" refers to conditions that require avoidance of certain ingredients or cooking methods, such as allergies, calorie restrictions, or religious beliefs.

[0516] "Location information" refers to information about the area or place a user wants to search for, such as city name or postal code.

[0517] A "search query" refers to instructions or commands to search for restaurants that meet the dietary restrictions and location information entered by the user.

[0518] "Generative AI model" refers to an artificial intelligence model that generates relevant information based on an input search query.

[0519] "Restaurant information" refers to detailed information that users need when eating out, such as the restaurant's name, address, contact information, menu, and information regarding dietary restrictions.

[0520] "Filtering" refers to the process of selecting only information that meets the user's dietary restrictions from the generated restaurant information.

[0521] A "database" refers to an electronic data collection in which collected information is stored.

[0522] "Trustworthiness evaluation" refers to the process of evaluating the quality and reliability of restaurants based on feedback information from customers.

[0523] "Dietary restriction accommodation status" refers to the extent to which a restaurant accommodates the dietary restrictions of customers.

[0524] "Display on a map" refers to showing filtered restaurant information on a map in a visually easy-to-understand format.

[0525] "Detailed Information" refers to deeper level information provided about the selected restaurant, such as menu, prices, opening hours, etc.

[0526] "Feedback information" refers to the evaluations and opinions provided by customers after visiting a restaurant.

[0527] This invention relates to a support system that enables people with dietary restrictions to enjoy eating out with peace of mind. This system is designed so that when a user simply inputs specific conditions, information about restaurants that meet those conditions is displayed on a map.

[0528] 1. Specific processing content of the program

[0529] User Input

[0530] Users start the application using a device such as a smartphone or PC, and enter their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"). Once the user has finished entering the information, they press the search button to begin the next process.

[0531] Device behavior

[0532] The device receives the conditions entered by the user and sends them to the server in the form of an HTTP POST request, which includes the dietary restrictions and location information in JSON format.

[0533] Server Operation

[0534] The server receives the request sent from the device and analyzes its contents. Specifically, it decodes the dietary restrictions and location information and generates a search query. This query is in the form of "Find restaurants in Tokyo that serve gluten-free meals under 1500 kcal." This query is used to send a prompt to a generative AI model (e.g., GPT).

[0535] Processing generative AI models

[0536] The generative AI model generates restaurant information that matches the search criteria based on the prompt received from the server, including the restaurant's name, address, menu information, and corresponding dietary restrictions.

[0537] Server Filtering

[0538] The server receives the restaurant information returned by the generative AI model and filters it. During the filtering process, it checks whether the received information meets the dietary restrictions specified by the user. Only matching information is selected, and finally, a filtered information list is created.

[0539] Providing information to devices

[0540] The server sends the filtered restaurant information to the terminal. The terminal displays the received information on a map, providing the user with a visually easy-to-understand format. Restaurants that meet the criteria are displayed as pins on the map, and users can click on the pins to view detailed information.

[0541] User Feedback

[0542] Users select a restaurant based on the displayed restaurant information and provide feedback through the app after visiting. The feedback includes rating points and comments, which are used for the next process.

[0543] Accumulation of feedback information

[0544] The terminal sends the feedback information entered by the user to the server, which stores the feedback information in a database and uses this information to update the restaurant's reliability rating and its ability to accommodate dietary restrictions.

[0545] 2. Hardware and Software Used

[0546] Devices used by users: computing devices such as smartphones, PCs, tablets, etc.

[0547] Application: Software that provides an interface for users to enter criteria

[0548] Server: Receives requests, parses them, filters them, and manages the database

[0549] Database: Managing reliability ratings and feedback information

[0550] Generative AI models (e.g., GPT): Artificial intelligence models that generate relevant information based on a search query.

[0551] Map software: Software for displaying received restaurant information on a map

[0552] 3. Examples of concrete examples and prompts

[0553] Specific examples

[0554] 1. The user opens the app and enters criteria such as "gluten-free," "under 1500kcal," and "Tokyo."

[0555] 2. The device sends these conditions to the server.

[0556] 3. The server generates a query based on the conditions: "Find restaurants in Tokyo that are gluten-free and under 1500 kcal" and sends it to the generative AI model.

[0557] 4. The generative AI model returns the relevant restaurant information.

[0558] 5. The server filters this information and creates a list of restaurants that meet the criteria.

[0559] 6. The terminal displays the filtered restaurant information on a map and provides it to the user.

[0560] 7. The user selects a restaurant based on the displayed information and provides feedback after visiting.

[0561] 8. The terminal sends this feedback information to the server, which updates the database.

[0562] Prompt Sentence Examples

[0563] "Please suggest restaurants in Tokyo that meet the specified criteria (e.g. gluten-free, under 1500kcal)."

[0564] The above is a specific embodiment of the system of the present invention, which allows users to easily find restaurants that meet their specific dietary restrictions and enjoy eating out with peace of mind.

[0565] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0566] Step 1:

[0567] User Input

[0568] The user starts the application, enters dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"), and then presses the search button.

[0569] Specific operation: Enter the conditions into the application interface.

[0570] Input: dietary restrictions, location information

[0571] Output: Conditions are sent to the terminal

[0572] Step 2:

[0573] Sending a request from the device

[0574] The device sends the user-entered conditions to the server as an HTTP POST request, which includes the dietary restrictions and location information in JSON format.

[0575] Specific operation: The data in the form where the conditions were entered is converted to JSON format and sent to the " / search" endpoint.

[0576] Input: User-entered conditions (JSON format)

[0577] Output: Server receives request

[0578] Step 3:

[0579] Server request analysis

[0580] The server analyzes the request received from the device and generates a search query based on the conditions. The query is a sentence such as "Find restaurants in Tokyo that are gluten-free and under 1500 kcal."

[0581] Specific operation: Parse the received JSON data and extract each condition. Then, construct a query statement.

[0582] Input: HTTP POST request (conditions in JSON format)

[0583] Output: Search query

[0584] Step 4:

[0585] Sending prompts to the server's generated AI model

[0586] The server sends a search query to the generative AI model, which generates relevant restaurant information based on the prompt.

[0587] Specific operation: The constructed query sentence is sent to the generative AI model as a prompt sentence.

[0588] Input: Discovery query

[0589] Output: Generative AI model returns restaurant information

[0590] Step 5:

[0591] Receiving and filtering restaurant information

[0592] The server receives the restaurant information returned by the generative AI model and filters it to select only restaurants that meet specific dietary restrictions.

[0593] Specific operation: Analyze the information returned from the generative AI model and extract information that meets the conditions.

[0594] Input: Restaurant information from a generative AI model

[0595] Output: Filtered list of restaurants

[0596] Step 6:

[0597] Sending filtering results to the device

[0598] The server sends the filtered restaurant list in JSON format to the terminal.

[0599] Specific operation: The filtering results are encoded in JSON format and sent to the terminal as an HTTP response.

[0600] Input: A filtered list of restaurants

[0601] Output: The device receives the list

[0602] Step 7:

[0603] Displaying information on the device's map

[0604] The device passes the filtering results received from the server to the map application and displays them on a map, with the location of each restaurant indicated by a pin and detailed information displayed.

[0605] Specific operation: Data is passed to the map application API, and pins are placed on the map. Clicking on a pin displays detailed store information.

[0606] Input: A filtered list of restaurants

[0607] Output: Restaurant information displayed on a map

[0608] Step 8:

[0609] User feedback

[0610] Users enter feedback (rating points, comments) about the restaurants they visit within the app.

[0611] Specific action: The user fills out the feedback form and presses the submit button.

[0612] Input: Restaurant rating points, comments

[0613] Output: Feedback information sent to the terminal

[0614] Step 9:

[0615] Send device feedback

[0616] The terminal transmits the feedback information input by the user to the server in the form of an HTTP POST request.

[0617] Specific operation: The feedback information is converted into JSON format and sent to the server.

[0618] Input: User feedback information (JSON format)

[0619] Output: The server receives the feedback information.

[0620] Step 10:

[0621] Server database update

[0622] The server stores the received feedback information in a database, which updates the restaurant's reliability rating and dietary restrictions.

[0623] Specific operation: Update the corresponding record in the database and accumulate the information.

[0624] Input: Feedback information

[0625] Output: Updated database

[0626] This concludes the detailed description of the program processing of this system. This system allows users to quickly find restaurants that meet specific dietary restrictions, allowing them to enjoy eating out with peace of mind.

[0627] (Application example 1)

[0628] 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."

[0629] Conventional restaurant search systems do not provide sufficient support for people with dietary restrictions when it comes to enjoying dining out. Specifically, they lack information on restaurants that cater to specific allergies, calorie restrictions, or religious dietary restrictions, making it difficult for users to choose meals with confidence. Another issue is the inefficient collection of orders and feedback from restaurants selected from search results, and the inefficient updating of the database. This makes it difficult for users with dietary restrictions to find suitable restaurants, reducing the convenience of dining out.

[0630] 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.

[0631] In this invention, the server includes a means for receiving dietary restrictions and location information from a user as input, a means for generating a search query based on the dietary restrictions and location information, and a means for sending the search query to a generative model and receiving related restaurant information. This enables efficient searching and provision of restaurant information that satisfies dietary restrictions. The server also includes a means for filtering the received restaurant information based on the dietary restrictions, providing the filtered results to the user, and placing an order with the selected restaurant. It also includes a means for collecting feedback information provided by the user and storing and updating the information in a database. This allows users to select and order from an appropriate restaurant with peace of mind, and keeps the restaurant's reliability and service status up to date based on the results.

[0632] "User" refers to a person who uses the system to input dietary restrictions and location information to obtain appropriate restaurant information.

[0633] "Dietary restrictions" refers to conditions where certain ingredients or ingredients must be avoided due to allergies, calorie restrictions, religious reasons, etc.

[0634] "Location Information" means information about a geographic location where you are currently located or plan to visit.

[0635] A "search query" refers to a search query that is generated based on dietary restrictions and location information.

[0636] "Generative model" refers to an artificial intelligence model that generates relevant restaurant information based on a search query.

[0637] "Restaurant information" refers to information such as the restaurant's name, address, menu contents, and dietary restrictions that can be accommodated.

[0638] "Filtering" refers to the process of selecting only the information from the received restaurant information that meets the user's dietary restrictions.

[0639] "Ordering" refers to the process of a user purchasing a meal from a restaurant selected on the system.

[0640] "Feedback information" refers to information such as evaluations, opinions, and areas for improvement provided by customers after using a restaurant.

[0641] "Database" refers to a system for storing and managing collected feedback information and restaurant information.

[0642] This invention is a system that allows people with specific dietary restrictions to find suitable restaurants, place orders, and provide feedback. The specific configuration and program of the system are described below.

[0643] 1. System Program

[0644] First, the user enters their dietary restrictions and location information on their smartphone. Using the app's interface, users can easily input conditions such as "gluten-free," "under 1500 kcal," and "Tokyo." The smartphone application was developed using React Native.

[0645] The server receives the input information from the user and generates a search query that reflects the entered dietary restrictions and location information. The server is built using Node.js and Express.js.

[0646] The search query is sent to a generative model (OpenAI GPT-4) that receives relevant restaurant information, including a list of restaurants that meet specific dietary restrictions. The generated restaurant information is then filtered on the server to select only restaurants that meet the user's criteria.

[0647] The filtered restaurant information is returned to the smartphone application, which displays this information on a map for the user to visually confirm. The user can also place an order directly with the selected restaurant. The order information is also sent to the server, which notifies the appropriate restaurant.

[0648] After eating and drinking, the user provides feedback information. The feedback is again entered through a smartphone application and sent to the server. The server stores this feedback information in a database and uses it to keep up-to-date restaurant reliability ratings and dietary restriction compliance status. MongoDB is used for the database.

[0649] 2. Program Processing

[0650] The following hardware and software are used to receive input information from a user and to process and calculate data to generate a search query.

[0651] Hardware:

[0652] Smartphone: Providing a user interface and receiving / sending input information

[0653] Server: Parsing and responding to requests, managing databases

[0654] software:

[0655] Frontend: React Native

[0656] Backend: Node.js, Express.js

[0657] Database: MongoDB

[0658] Generative AI model: OpenAI GPT-4

[0659] The server analyzes the information received from the user and sends an appropriate query to the generative model. Once the generated restaurant information is returned, it is filtered to create a list of restaurants that meet the user's criteria. Finally, the filtered information is sent to the smartphone application and presented to the user.

[0660] 3. Examples and prompts

[0661] Examples:

[0662] A user opens the app and enters the criteria "gluten-free," "under 1500kcal," and "Tokyo." The server processes the request, returns matching restaurant information, and displays it on a map. The user then selects a specific restaurant, places an order, and provides feedback after completing the order.

[0663] Example prompt sentence:

[0664] "Find restaurants in Tokyo that provide gluten-free meals under 1500 calories."

[0665] This will create a system that allows people with specific dietary restrictions to enjoy eating out with peace of mind.

[0666] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0667] Step 1:

[0668] The user enters dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo") through a smartphone application. The information entered by the user is sent from the smartphone to the server. Specifically, the data entered in the user interface is sent to the server as an HTTP POST request.

[0669] Step 2:

[0670] The server analyzes the received dietary restrictions and location information to generate a search query. Based on the analyzed data, the server creates a query to identify "gluten-free meals" and "restaurants that offer meals under 1500 kcal." This query is then sent to the generative AI model.

[0671] Step 3:

[0672] The server sends a search query to the generative AI model and receives relevant restaurant information. The generative AI model (OpenAI GPT-4) analyzes the query and provides a list of restaurants that meet the criteria. The received information includes the restaurant's name, address, and menu items with corresponding dietary restrictions.

[0673] Step 4:

[0674] The server filters the received restaurant information based on the user's dietary restrictions. In this filtering process, restaurant information that does not meet the restrictions is excluded. Finally, a filtered list of restaurant information is generated.

[0675] Step 5:

[0676] The server returns the filtered restaurant information to the smartphone application, which then visually displays the received restaurant information on a map, including pin locations and detailed information about the restaurants.

[0677] Step 6:

[0678] The user browses restaurant information on the map and places an order at the restaurant of their choice. The smartphone application then sends the order information back to the server. The order includes details such as menu selection and delivery address.

[0679] Step 7:

[0680] The server analyzes the order information and notifies the appropriate restaurant, and a response is returned to the smartphone application to confirm that the order was successfully received.

[0681] Step 8:

[0682] After eating or drinking, the user provides feedback information. The feedback entered through the smartphone application is sent to the server, which then stores the feedback information in a database.

[0683] Step 9:

[0684] The server uses the feedback information stored in the database to update the restaurant's trustworthiness rating and dietary restriction availability, thereby improving the reliability of the information provided the next time a search is performed. The database is also continually improved based on user feedback.

[0685] 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.

[0686] This invention is a support system that allows people who must avoid certain foods due to allergies, calorie restrictions, religious reasons, etc. to enjoy eating out with peace of mind, as well as a system that recognizes the user's emotions and provides optimal restaurant information based on those emotions.The system displays restaurant information that meets the user's conditions and matches their emotions on a map simply by the user inputting specific conditions and emotional state.

[0687] System configuration

[0688] User

[0689] The user inputs dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo") through the system interface. Furthermore, the emotion engine automatically recognizes the user's emotional state. This emotional state can be obtained, for example, from facial expressions captured by the user or from audio recordings.

[0690] Terminal

[0691] The device receives the dietary restrictions and location information entered by the user, as well as emotion data from the emotion engine, and transmits them to the server. The device displays the information received from the server on a map and provides it to the user.

[0692] server

[0693] The server analyzes the dietary restrictions, location information, and emotion data received from the device and generates a search query. It then sends this search query to a generative model (generative AI) and receives relevant restaurant information. It filters the received information, adjusts the optimal restaurant list based on the emotion data, and returns it to the device. It also collects feedback information and emotion data and stores it in a database to improve the reliability of the information.

[0694] Program processing

[0695] User operations

[0696] The user opens the application and inputs their dietary restrictions (e.g., gluten-free, under 1500 kcal) and their current location (e.g., Tokyo).The emotion engine then automatically acquires emotion data based on the captured facial expressions and voice.

[0697] Device behavior

[0698] The device sends the entered dietary restrictions, location information, and emotional data to the server. The results returned from the server are displayed on a map, providing the user with a visually easy-to-understand format. Feedback information and emotional data from the user are also sent to the server.

[0699] Server Operation

[0700] The server analyzes the request received from the device and generates a search query. Specifically, it generates a query such as "Find restaurants in Tokyo that offer gluten-free meals under 1500 kcal" based on the input conditions and emotion data. The query is sent to the generative model (GPT) and relevant restaurant information is received. The received restaurant information is then filtered and prioritized based on the emotion data. For example, if the user is feeling stressed, restaurants with a relaxing atmosphere are prioritized. The results are returned to the device and provided to the user.

[0701] Specific examples

[0702] 1. The user opens the app and enters criteria such as "gluten-free," "under 1500 kcal," and "Tokyo." At the same time, the emotion engine analyzes the user's facial photo and recognizes the emotion of "stress."

[0703] 2. The device sends these conditions and emotion data to the server.

[0704] 3. Based on the conditions and emotion data, the server generates a query such as "Find restaurants in Tokyo that are gluten-free, under 1500 kcal, and have a stress-reducing atmosphere," and sends it to the generative model (GPT).

[0705] 4. The generative model (GPT) returns the relevant restaurant information.

[0706] 5. After filtering the information, the server creates a list that prioritizes restaurants with high ratings for "stress-reducing atmosphere."

[0707] 6. The terminal displays the filtered restaurant information on a map and provides it to the user.

[0708] 7. The user selects a restaurant based on the displayed information and provides feedback after visiting.

[0709] 8. The device sends the feedback information and emotion data to the server, which updates the database.

[0710] The above is a specific embodiment for implementing the system of the present invention. By combining it with an emotion engine, it is possible to provide optimal restaurant information according to the user's emotional state, supporting a more satisfying dining out experience.

[0711] The processing flow will be explained below.

[0712] Step 1:

[0713] The user opens the application. The user inputs their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"). The emotion engine then automatically recognizes the user's emotional state. This emotional state is obtained from facial expressions and voice captured by the user.

[0714] Step 2:

[0715] The device receives the dietary restrictions and location information entered by the user. When the user presses the search button, the device sends these restrictions and the recognized emotion data to the server. The request is sent as a POST request, serialized in JSON format.

[0716] Step 3:

[0717] The server analyzes the request received from the device, extracting dietary restrictions, location information, and emotion data, and stores each value in variables. Based on this information, it generates a search query (e.g., "Find restaurants in Tokyo that serve gluten-free meals under 1500 kcal").

[0718] Step 4:

[0719] The server sends the generated search query to the generative model (GPT). The generative model searches for relevant restaurant information from websites and reviews on the Internet and returns the results. This process is performed asynchronously through the generative AI's API.

[0720] Step 5:

[0721] The server receives the restaurant information returned from the generative model. The information is analyzed and filtered based on the user's dietary restrictions. Specifically, it selects restaurants from the returned list that perfectly match the user's dietary restrictions.

[0722] Step 6:

[0723] The server further adjusts the filtered restaurant list based on the emotion data. For example, if the user's emotion is "stress," it prioritizes restaurants with a relaxing atmosphere. The final adjusted list is then compiled in JSON format and sent to the device.

[0724] Step 7:

[0725] The terminal decodes the list of restaurants received from the server and displays it on a map. The user can visually check the restaurants indicated by pins on the map. Clicking on each pin will display a pop-up with detailed information.

[0726] Step 8:

[0727] Users can choose a restaurant to visit based on the displayed information, and after visiting, they can provide feedback through the app about the restaurant's rating and whether it accommodates dietary restrictions.

[0728] Step 9:

[0729] The device receives feedback information from the user and sends it to the server in JSON format.

[0730] Step 10:

[0731] The server receives the feedback information and stores it in a database. It then updates the restaurant's trustworthiness rating and dietary restrictions based on the collected feedback and sentiment data. The information stored in the database is used to improve the accuracy of search results the next time.

[0732] The above is a detailed explanation of the steps involved in the program's processing, which combines emotion engines. The operations of the server, terminal, and user at each step are described in detail.

[0733] Example 2

[0734] 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."

[0735] In today's world, it is difficult for people with dietary restrictions to enjoy eating out with peace of mind. Furthermore, it is also difficult for them to easily find an appropriate restaurant that matches their emotional state. The present invention aims to solve this problem by providing optimal restaurant information based on dietary restrictions and emotional state, thereby improving users' dining out experiences.

[0736] 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 conditions and location information from a user as input, means for generating a search query based on the dietary restriction conditions and location information, means for sending the search query to a generative AI model and receiving related restaurant information, means for filtering the received restaurant information based on the dietary restriction conditions and the user's emotional state, means for providing the filtered results to the user, means including an emotion recognition engine for acquiring emotion data of the user, and means for adjusting restaurant information based on the acquired emotion data. This makes it possible to provide restaurant information optimized for the user's dietary restriction conditions and emotional state.

[0737] "Dietary restriction conditions" are conditions that serve as criteria when a user selects a particular restaurant, such as restrictions on specific ingredients or calorie restrictions.

[0738] "Location information" refers to geographical data of the user's current location or a specified area, and is information used to select restaurants.

[0739] A "search query" is a query generated based on data such as dietary restrictions, location information, and emotional state, and is used to search for restaurant information.

[0740] A "generative AI model" is an artificial intelligence model that generates and provides the most relevant restaurant information based on a given search query.

[0741] An "emotion recognition engine" is software or hardware that analyzes a user's facial photograph and voice data to determine the user's current emotional state.

[0742] "Filtering" is the process of sorting received restaurant information based on dietary restrictions and emotional state, and extracting the most suitable information.

[0743] A "database" is an information management system that stores collected information such as feedback information and emotional data, and uses it for future searches and analyses.

[0744] "Feedback information" refers to information such as impressions and evaluations provided by users after visiting a restaurant, and is used to improve the accuracy of the system.

[0745] "Adjustment" refers to a process of changing the priority of the received restaurant information based on the acquired emotion data to provide the user with the most suitable information.

[0746] This invention provides a system that allows users to easily obtain optimal restaurant information based on their specific dietary restrictions and emotional state. The system is primarily composed of a user terminal, a server, and a generative AI model.

[0747] User operations

[0748] Users launch the application using a device such as a smartphone or tablet. First, they enter their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and their current location (e.g., "Tokyo"). The emotion engine then automatically obtains the user's emotional state. This emotional state is determined by analyzing a facial photograph taken by the user and a recorded voice.

[0749] Device behavior

[0750] The device sends the dietary restrictions, location information, and acquired emotion data entered by the user to the server as a single request. The device displays the restaurant information received from the server on a map to provide a visual reference for the user. The device also sends feedback information provided by the user to the restaurants they visited to the server.

[0751] Server Operation

[0752] The server analyzes the dietary restrictions, location information, and emotion data received from the device and generates a search query. Specifically, it generates a query to search for "restaurants in Tokyo that are gluten-free, serve meals under 1500 kcal, and have a stress-reducing atmosphere." The server sends this query to a generative AI model (e.g., GPT) and receives relevant restaurant information.

[0753] The received restaurant information is filtered by the server. The filtering is performed based on dietary restrictions and emotional data. For example, if the user is feeling "stressed," restaurants with a relaxing atmosphere will be prioritized. The filtered restaurant information is returned to the terminal and provided to the user.

[0754] In addition, the server stores feedback information and emotional data provided by users in a database. This database is used to update restaurant reliability ratings and dietary restrictions, helping to improve recommendation accuracy in future visits.

[0755] Specific examples

[0756] Below are specific operating procedures and examples of prompts.

[0757] 1. User Actions:

[0758] Users open the app and enter dietary restrictions such as "gluten-free," "under 1500 kcal," and "Tokyo."

[0759] The emotion engine analyzes the user's facial photo and recognizes the emotion as "stress."

[0760] 2. Device behavior:

[0761] The device sends the condition and emotion data to the server.

[0762] 3. Server Operation:

[0763] The server generates a query such as "Find a restaurant in Tokyo that is gluten-free, under 1500 kcal, and has a stress-reducing atmosphere" and sends it to the generative AI model.

[0764] A generative AI model (e.g., GPT) returns the relevant restaurant information.

[0765] The server filters the information and sends it back to the device.

[0766] 4. Display and Feedback:

[0767] The terminal displays filtered restaurant information on a map and provides it to the user.

[0768] After the user visits, feedback information is sent from the terminal to the server.

[0769] Prompt Sentence Examples

[0770] "Please tell me restaurants in Tokyo that offer gluten-free meals under 1500 kcal in a stress-relieving atmosphere."

[0771] This invention efficiently provides restaurant information optimized for the user's dietary restrictions and emotional state, resulting in a more satisfying dining out experience.

[0772] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0773] Step 1:

[0774] User input:

[0775] The user opens the application on their smartphone and enters their current location and dietary restrictions, such as "gluten-free," "under 1500 kcal," and "Tokyo," into the application interface. They then press the "Emotion Input" button to capture a photo of their face and their voice.

[0776] Input: dietary restrictions, location information, face photo or voice

[0777] Output: User condition and emotion data

[0778] Step 2:

[0779] Obtaining emotion data:

[0780] The device sends the captured facial photo and voice data to an emotion recognition engine, which analyzes them and determines the user's emotional state (e.g., "stress").

[0781] Input: Face photo or voice data

[0782] Output: Emotion recognition result (e.g. "Stress")

[0783] Step 3:

[0784] Data transmission:

[0785] The device sends the dietary restriction conditions, location information, and emotion recognition results as a single request to the server.

[0786] Input: dietary restriction conditions, location information, emotion recognition results

[0787] Output: Request to server

[0788] Step 4:

[0789] Generating a search query:

[0790] The server analyzes the received data and generates a search query, specifically, a query to find "restaurants in Tokyo that serve gluten-free meals under 1500 kcal and have a stress-reducing atmosphere."

[0791] Input: dietary restriction conditions, location information, emotion recognition results

[0792] Output: The search query

[0793] Step 5:

[0794] Querying a generative AI model:

[0795] The server sends the generated query to a generative AI model (e.g., GPT), which generates relevant restaurant information based on the query and returns it to the server.

[0796] Input: Search query

[0797] Output: Related restaurant information

[0798] Step 6:

[0799] Filter restaurant information:

[0800] The server then filters the received restaurant information based on dietary restrictions and emotion recognition results. For example, it prioritizes restaurants with a high rating for "stress-reducing atmosphere."

[0801] Input: Related restaurant information, dietary restrictions, emotion recognition results

[0802] Output: Filtered restaurant information

[0803] Step 7:

[0804] Sending adjustment results:

[0805] The server sends the filtered restaurant information to the device, which then plots the received information on a map using a map API (e.g., Google Maps) and provides it to the user in a visually easy-to-understand format.

[0806] Input: Filtered restaurant information

[0807] Output: Response to the terminal

[0808] Step 8:

[0809] Enter your feedback:

[0810] After visiting a restaurant, users can enter their impressions and ratings on the feedback screen. For example, they can add comments such as "The food was delicious" or "The atmosphere was relaxing."

[0811] Input: Feedback information

[0812] Output: Feedback data

[0813] Step 9:

[0814] Send feedback information:

[0815] The device sends feedback information to the server, which stores it in a database and uses it to improve the accuracy of future query generation and filtering.

[0816] Input: Feedback data

[0817] Output: Stored in a database

[0818] (Application example 2)

[0819] 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."

[0820] Conventional restaurant search systems can provide restaurant information based on a user's dietary restrictions, but they cannot provide restaurant information that takes into account the user's emotional state. This makes it difficult for users to find the best restaurant when they are in a specific emotional state. In particular, for users who are feeling stressed or tired, the system cannot suggest restaurants with a high relaxation effect, which leads to a problem of reduced user satisfaction.

[0821] 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 conditions and location information from a user as input, means for generating a search query based on the dietary restriction conditions and location information, means for sending the search query to a generative model and receiving related restaurant information, means for filtering the received restaurant information based on the dietary restriction conditions, means for providing the filtered results to the user, means for recognizing the user's emotional state, and means for prioritizing and adjusting the received restaurant information based on the emotional state. This makes it possible to provide optimal restaurant information according to the user's emotional state.

[0822] "Dietary restrictions" refer to conditions that require avoiding certain ingredients or nutrients due to allergies, calorie restrictions, religious reasons, etc.

[0823] "Location information" refers to geographic data about a user's current location or a location they specify.

[0824] A "search query" is a search command generated based on criteria entered by the user.

[0825] A "generative model" is an artificial intelligence model that generates relevant information based on an input search query.

[0826] "Restaurant information" refers to data about the type of restaurant, its location, the menu it offers, etc.

[0827] "Filtering" is the process of selecting and extracting data based on specific conditions.

[0828] "User" refers to a person who uses this system to search for restaurant information that meets dietary restrictions.

[0829] "Emotional state" refers to the user's psychological and emotional state as recognized from facial expressions, voice, etc.

[0830] "Prioritization" is the process of assigning importance to information based on the user's emotional state.

[0831] "Delivery" refers to a service that delivers ordered food and drinks to a specified location.

[0832] The system for implementing this invention is mainly composed of a user terminal and a server. The user terminal and the server work together via a communication line to provide the information requested by the user. Each element of the system is described in detail below.

[0833] System Configuration

[0834] User Operation

[0835] Users operate the application using a user device such as a smartphone. After opening the application, the user enters dietary restrictions (e.g., "gluten-free") and location information (e.g., "Tokyo"). The application also has an emotion recognition function that can capture the user's emotional state using a camera and microphone. To analyze the user's emotional state from facial expressions and voice, the application uses emotion recognition services such as Microsoft's Azure Emotion API.

[0836] Device behavior

[0837] The user device receives the dietary restrictions, location information, and emotion data entered by the user. This data is sent to the server. The results returned from the server are displayed on a map, providing the user with a visually easy-to-understand format. The system also collects the user's feedback information and emotion data, which are sent to the server to update the database.

[0838] Server Operation

[0839] The server analyzes the dietary restrictions, location information, and emotional data received from the user device and generates an appropriate search query. This search query is sent to a generative AI model (e.g., GPT-4) to receive relevant restaurant information. The received restaurant information is filtered based on the dietary restrictions and further prioritized based on the user's emotional state. For example, if the user is feeling stressed, restaurants with a high relaxation effect will be prioritized. The final restaurant list is returned to the user device and displayed in the user's application.

[0840] The server periodically collects feedback information and emotional data and updates the database to improve restaurant reliability ratings and dietary restrictions.

[0841] Specific examples

[0842] The user opens the app and enters search criteria such as "gluten-free" and "Tokyo." At the same time, the emotion engine analyzes the user's facial photo and recognizes that the user is feeling "stressed." The device then sends these criteria and emotion data to the server. Based on the criteria and emotion data, the server generates a search query such as "Find restaurants in Tokyo that offer gluten-free menus and have a stress-reducing atmosphere," and sends it to a generative model (GPT-4). The generative model returns relevant restaurant information, and the server creates a list prioritizing restaurants with a high stress-reducing rating. Finally, the filtered results are displayed on the user's device.

[0843] Prompt Sentence Examples

[0844] "Please tell me restaurants in Tokyo that offer gluten-free menus and have a great relaxation effect."

[0845] In this way, the present invention provides optimal restaurant information based on dietary restrictions and emotional state, thereby realizing a system that can increase user satisfaction.

[0846] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0847] Step 1:

[0848] The user launches the application using a device such as a smartphone. A screen appears where the user can enter their dietary restrictions (e.g., "gluten-free") and current location (e.g., "Tokyo"). The entered information is temporarily stored in the device's internal memory.

[0849] Step 2:

[0850] The device uses camera and microphone sensors to recognize the user's emotional state. Specifically, it takes a photo of the user's face or records their voice, and sends this to Microsoft's Azure Emotion API. It then receives emotion data (e.g., "stress") returned from the API. The input is the face photo or voice data, and the output is emotion data.

[0851] Step 3:

[0852] The device sends the acquired dietary restriction conditions, current location information, and emotion data to the server. Specifically, it sends them as an HTTP request. The input is the dietary restriction conditions, current location information, and emotion data, and the output is the transmission of an HTTP request.

[0853] Step 4:

[0854] The server analyzes the dietary restrictions, current location information, and emotion data received from the device and generates a search query. The generated search query may be in the form of, for example, "Find restaurants in Tokyo that offer gluten-free menus and have stress-reducing effects." The inputs are dietary restrictions, current location information, and emotion data, and the output is the generated search query.

[0855] Step 5:

[0856] The server sends the generated search query to a generative AI model (e.g., GPT-4) and receives related restaurant information. The generative AI model returns restaurant information in response to the search query. The input is the search query, and the output is related restaurant information.

[0857] Step 6:

[0858] The server filters the received restaurant information based on the dietary restrictions. As a result of the filtering, only matching restaurant information is extracted. The input is restaurant information and dietary restrictions, and the output is the filtered restaurant information.

[0859] Step 7:

[0860] The server prioritizes and adjusts the filtered restaurant information based on the user's emotional state. For example, if the user is feeling stressed, restaurants with a high relaxation effect are prioritized. The input is the filtered restaurant information and emotional data, and the output is prioritized restaurant information.

[0861] Step 8:

[0862] The server returns the prioritized restaurant information to the terminal and provides it to the user. The terminal displays the received restaurant information on a map and provides it to the user in a visually easy-to-understand format. The input is the prioritized restaurant information, and the output is the restaurant information displayed on the map.

[0863] Step 9:

[0864] The user makes a selection based on the displayed restaurant information and provides feedback information after visiting. The feedback information is sent from the terminal to the server. The input is the feedback information, and the output is the transmission to the server.

[0865] Step 10:

[0866] The server stores the received feedback information and emotion data in a database. The server uses the feedback information to update the restaurant's trustworthiness rating and dietary restriction compliance status. The input is the feedback information and emotion data, and the output is the updated database.

[0867] In this way, the system can provide optimal restaurant information based on dietary restrictions and emotional state, increasing user satisfaction.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] [Third embodiment]

[0872] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0873] 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.

[0874] 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).

[0875] 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.

[0876] 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.

[0877] 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).

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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."

[0884] This invention is a support system that allows people who must avoid certain foods due to allergies, calorie restrictions, religious reasons, etc. to enjoy eating out with peace of mind. The system displays restaurant information that matches specific criteria on a map simply by the user entering the criteria.

[0885] System configuration

[0886] User

[0887] Users use an interface to input dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"). This interface is designed to be easy for users to operate.

[0888] Terminal

[0889] The device receives dietary restrictions and location information from the user and sends it to the server. It also displays the information received from the server on a map. Specifically, it sends the conditions entered in the form to the server as a POST request, analyzes the restaurant information returned from the server, and displays it.

[0890] server

[0891] The server analyzes the request received from the device and generates a search query based on the specified dietary restrictions and location information. It then sends this search query to a generative model (generative AI) and receives relevant restaurant information. It then filters the received information and returns the filtered restaurant list to the device. It also collects feedback information and stores it in a database to improve the reliability of the information.

[0892] Program processing

[0893] User operations

[0894] The user opens the application, enters their dietary restrictions (e.g., gluten-free, under 1500 kcal) and their current location (e.g., Tokyo), and then presses the search button.

[0895] Device behavior

[0896] When the search button is pressed, the device sends the entered search criteria to the server. The results returned from the server are displayed on a map, providing the user with a visually easy-to-understand format. Feedback information from the user is also sent to the server.

[0897] Server Operation

[0898] The server analyzes the request received from the device and generates a search query. Specifically, it generates a query such as "Find gluten-free restaurants and restaurants in Tokyo that offer meals under 1500 kcal" based on the input criteria. The query is sent to the generative model (GPT) and relevant restaurant information is received. The received restaurant information is then filtered to create a list of restaurants that meet the criteria. This list is returned to the device, and feedback provided to the user is stored in a database, updating the restaurant's reliability rating and dietary restrictions.

[0899] Specific examples

[0900] 1. The user opens the app and enters criteria such as "gluten-free," "under 1500kcal," and "Tokyo."

[0901] 2. The device sends these conditions to the server.

[0902] 3. The server generates a query to find restaurants in Tokyo that offer "gluten-free" and "under 1500 kcal" meals based on the conditions and sends it to the generative model (GPT).

[0903] 4. The generative model (GPT) returns the relevant restaurant information.

[0904] 5. The server filters this information and creates a list of restaurants that meet the criteria.

[0905] 6. The terminal displays the filtered restaurant information on a map and provides it to the user.

[0906] 7. The user selects a restaurant based on the displayed information and provides feedback after visiting.

[0907] 8. The terminal sends this feedback information to the server, which updates the database.

[0908] The above is a specific embodiment for implementing the system of the present invention, which supports people with dietary restrictions in enjoying eating out with peace of mind.

[0909] The processing flow will be explained below.

[0910] Step 1:

[0911] The user opens the application and enters their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo") through the interface. These conditions are displayed as a form, designed to make it easy for the user to enter them.

[0912] Step 2:

[0913] The device receives the dietary restrictions and location information entered by the user. When the user presses the search button, the device sends these restrictions to the server as a POST request. The request is serialized in JSON format and prepared for parsing on the server side.

[0914] Step 3:

[0915] The server analyzes the request received from the device, extracts dietary restrictions and location information, and stores each value in variables. Based on this information, it generates a search query (e.g., "Find restaurants in Tokyo that serve gluten-free meals under 1500 kcal").

[0916] Step 4:

[0917] The server sends the generated search query to the generative model (GPT). The generative model searches for relevant restaurant information from websites, reviews, etc., and returns the results. This process is performed asynchronously via the generative AI's API.

[0918] Step 5:

[0919] The server receives the restaurant information returned from the generative model. The received information is analyzed and filtered based on the dietary restrictions entered by the user. Specifically, it selects restaurants from the returned list that perfectly match the dietary restrictions.

[0920] Step 6:

[0921] The server constructs a filtered list of restaurants in JSON format and sends it to the device, including the restaurant's name, location, and corresponding dietary restriction details.

[0922] Step 7:

[0923] The terminal decodes the list of restaurants received from the server and displays it on a map. The user can visually check the restaurants indicated by pins on the map. Clicking on each pin will display a pop-up with detailed information.

[0924] Step 8:

[0925] Users can choose a restaurant to visit based on the displayed information, and after visiting, they can provide feedback through the app about the restaurant's rating and whether it accommodates dietary restrictions.

[0926] Step 9:

[0927] The device receives feedback information from the user and sends it to the server in JSON format.

[0928] Step 10:

[0929] The server receives the feedback information and stores it in a database. It then updates the restaurant's credibility rating and dietary restrictions based on the collected feedback. The information stored in the database is used to improve the accuracy of search results the next time.

[0930] The above is a concrete explanation of each step of the program's processing. The operations of the server, terminal, and user at each step have been described in detail.

[0931] Example 1

[0932] 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."

[0933] Recently, an increasing number of people have to avoid certain foods due to dietary restrictions, allergies, religious reasons, etc. In order for these people to enjoy eating out with peace of mind, they need to be able to easily and quickly obtain information about restaurants that meet their requirements. However, with conventional methods, it has been difficult to collect this information, and there have been challenges in obtaining reliable information.

[0934] 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.

[0935] In this invention, the server includes means for receiving dietary restrictions and location information as input from a user, means for generating a search query based on the dietary restrictions and location information, means for transmitting the search query to a generation AI model that generates the search query and receiving related restaurant information, means for filtering the received restaurant information based on the dietary restrictions, and means for providing the filtered results to the user. This allows users to quickly obtain restaurant information that meets their specific dietary restrictions and enjoy eating out with peace of mind.

[0936] "User" refers to a person who uses the system to input dietary restrictions and location information to obtain appropriate restaurant information.

[0937] "Dietary restrictions" refers to conditions that require avoidance of certain ingredients or cooking methods, such as allergies, calorie restrictions, or religious beliefs.

[0938] "Location information" refers to information about the area or place a user wants to search for, such as city name or postal code.

[0939] A "search query" refers to instructions or commands to search for restaurants that meet the dietary restrictions and location information entered by the user.

[0940] "Generative AI model" refers to an artificial intelligence model that generates relevant information based on an input search query.

[0941] "Restaurant information" refers to detailed information that users need when eating out, such as the restaurant's name, address, contact information, menu, and information regarding dietary restrictions.

[0942] "Filtering" refers to the process of selecting only information that meets the user's dietary restrictions from the generated restaurant information.

[0943] A "database" refers to an electronic data collection in which collected information is stored.

[0944] "Trustworthiness evaluation" refers to the process of evaluating the quality and reliability of restaurants based on feedback information from customers.

[0945] "Dietary restriction accommodation status" refers to the extent to which a restaurant accommodates the dietary restrictions of customers.

[0946] "Display on a map" refers to showing filtered restaurant information on a map in a visually easy-to-understand format.

[0947] "Detailed Information" refers to deeper level information provided about the selected restaurant, such as menu, prices, opening hours, etc.

[0948] "Feedback information" refers to the evaluations and opinions provided by customers after visiting a restaurant.

[0949] This invention relates to a support system that enables people with dietary restrictions to enjoy eating out with peace of mind. This system is designed so that when a user simply inputs specific conditions, information about restaurants that meet those conditions is displayed on a map.

[0950] 1. Specific processing content of the program

[0951] User Input

[0952] Users start the application using a device such as a smartphone or PC, and enter their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"). Once the user has finished entering the information, they press the search button to begin the next process.

[0953] Device behavior

[0954] The device receives the conditions entered by the user and sends them to the server in the form of an HTTP POST request, which includes the dietary restrictions and location information in JSON format.

[0955] Server Operation

[0956] The server receives the request sent from the device and analyzes its contents. Specifically, it decodes the dietary restrictions and location information and generates a search query. This query is in the form of "Find restaurants in Tokyo that serve gluten-free meals under 1500 kcal." This query is used to send a prompt to a generative AI model (e.g., GPT).

[0957] Processing generative AI models

[0958] The generative AI model generates restaurant information that matches the search criteria based on the prompt received from the server, including the restaurant's name, address, menu information, and corresponding dietary restrictions.

[0959] Server Filtering

[0960] The server receives the restaurant information returned by the generative AI model and filters it. During the filtering process, it checks whether the received information meets the dietary restrictions specified by the user. Only matching information is selected, and finally, a filtered information list is created.

[0961] Providing information to devices

[0962] The server sends the filtered restaurant information to the terminal. The terminal displays the received information on a map, providing the user with a visually easy-to-understand format. Restaurants that meet the criteria are displayed as pins on the map, and users can click on the pins to view detailed information.

[0963] User Feedback

[0964] Users select a restaurant based on the displayed restaurant information and provide feedback through the app after visiting. The feedback includes rating points and comments, which are used for the next process.

[0965] Accumulation of feedback information

[0966] The terminal sends the feedback information entered by the user to the server, which stores the feedback information in a database and uses this information to update the restaurant's reliability rating and its ability to accommodate dietary restrictions.

[0967] 2. Hardware and Software Used

[0968] Devices used by users: computing devices such as smartphones, PCs, tablets, etc.

[0969] Application: Software that provides an interface for users to enter criteria

[0970] Server: Receives requests, parses them, filters them, and manages the database

[0971] Database: Managing reliability ratings and feedback information

[0972] Generative AI models (e.g., GPT): Artificial intelligence models that generate relevant information based on a search query.

[0973] Map software: Software for displaying received restaurant information on a map

[0974] 3. Examples of concrete examples and prompts

[0975] Specific examples

[0976] 1. The user opens the app and enters criteria such as "gluten-free," "under 1500kcal," and "Tokyo."

[0977] 2. The device sends these conditions to the server.

[0978] 3. The server generates a query based on the conditions: "Find restaurants in Tokyo that are gluten-free and under 1500 kcal" and sends it to the generative AI model.

[0979] 4. The generative AI model returns the relevant restaurant information.

[0980] 5. The server filters this information and creates a list of restaurants that meet the criteria.

[0981] 6. The terminal displays the filtered restaurant information on a map and provides it to the user.

[0982] 7. The user selects a restaurant based on the displayed information and provides feedback after visiting.

[0983] 8. The terminal sends this feedback information to the server, which updates the database.

[0984] Prompt Sentence Examples

[0985] "Please suggest restaurants in Tokyo that meet the specified criteria (e.g. gluten-free, under 1500kcal)."

[0986] The above is a specific embodiment of the system of the present invention, which allows users to easily find restaurants that meet their specific dietary restrictions and enjoy eating out with peace of mind.

[0987] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0988] Step 1:

[0989] User Input

[0990] The user starts the application, enters dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"), and then presses the search button.

[0991] Specific operation: Enter the conditions into the application interface.

[0992] Input: dietary restrictions, location information

[0993] Output: Conditions are sent to the terminal

[0994] Step 2:

[0995] Sending a request from the device

[0996] The device sends the user-entered conditions to the server as an HTTP POST request, which includes the dietary restrictions and location information in JSON format.

[0997] Specific operation: The data in the form where the conditions were entered is converted to JSON format and sent to the " / search" endpoint.

[0998] Input: User-entered conditions (JSON format)

[0999] Output: Server receives request

[1000] Step 3:

[1001] Server request analysis

[1002] The server analyzes the request received from the device and generates a search query based on the conditions. The query is a sentence such as "Find restaurants in Tokyo that are gluten-free and under 1500 kcal."

[1003] Specific operation: Parse the received JSON data and extract each condition. Then, construct a query statement.

[1004] Input: HTTP POST request (conditions in JSON format)

[1005] Output: Search query

[1006] Step 4:

[1007] Sending prompts to the server's generated AI model

[1008] The server sends a search query to the generative AI model, which generates relevant restaurant information based on the prompt.

[1009] Specific operation: The constructed query sentence is sent to the generative AI model as a prompt sentence.

[1010] Input: Discovery query

[1011] Output: Generative AI model returns restaurant information

[1012] Step 5:

[1013] Receiving and filtering restaurant information

[1014] The server receives the restaurant information returned by the generative AI model and filters it to select only restaurants that meet specific dietary restrictions.

[1015] Specific operation: Analyze the information returned from the generative AI model and extract information that meets the conditions.

[1016] Input: Restaurant information from a generative AI model

[1017] Output: Filtered list of restaurants

[1018] Step 6:

[1019] Sending filtering results to the device

[1020] The server sends the filtered restaurant list in JSON format to the terminal.

[1021] Specific operation: The filtering results are encoded in JSON format and sent to the terminal as an HTTP response.

[1022] Input: A filtered list of restaurants

[1023] Output: The device receives the list

[1024] Step 7:

[1025] Displaying information on the device's map

[1026] The device passes the filtering results received from the server to the map application and displays them on a map, with the location of each restaurant indicated by a pin and detailed information displayed.

[1027] Specific operation: Data is passed to the map application API, and pins are placed on the map. Clicking on a pin displays detailed store information.

[1028] Input: A filtered list of restaurants

[1029] Output: Restaurant information displayed on a map

[1030] Step 8:

[1031] User feedback

[1032] Users enter feedback (rating points, comments) about the restaurants they visit within the app.

[1033] Specific action: The user fills out the feedback form and presses the submit button.

[1034] Input: Restaurant rating points, comments

[1035] Output: Feedback information sent to the terminal

[1036] Step 9:

[1037] Send device feedback

[1038] The terminal transmits the feedback information input by the user to the server in the form of an HTTP POST request.

[1039] Specific operation: The feedback information is converted into JSON format and sent to the server.

[1040] Input: User feedback information (JSON format)

[1041] Output: The server receives the feedback information.

[1042] Step 10:

[1043] Server database update

[1044] The server stores the received feedback information in a database, which updates the restaurant's reliability rating and dietary restrictions.

[1045] Specific operation: Update the corresponding record in the database and accumulate the information.

[1046] Input: Feedback information

[1047] Output: Updated database

[1048] This concludes the detailed description of the program processing of this system. This system allows users to quickly find restaurants that meet specific dietary restrictions, allowing them to enjoy eating out with peace of mind.

[1049] (Application example 1)

[1050] 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."

[1051] Conventional restaurant search systems do not provide sufficient support for people with dietary restrictions when it comes to enjoying dining out. Specifically, they lack information on restaurants that cater to specific allergies, calorie restrictions, or religious dietary restrictions, making it difficult for users to choose meals with confidence. Another issue is the inefficient collection of orders and feedback from restaurants selected from search results, and the inefficient updating of the database. This makes it difficult for users with dietary restrictions to find suitable restaurants, reducing the convenience of dining out.

[1052] 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.

[1053] In this invention, the server includes a means for receiving dietary restrictions and location information from a user as input, a means for generating a search query based on the dietary restrictions and location information, and a means for sending the search query to a generative model and receiving related restaurant information. This enables efficient searching and provision of restaurant information that satisfies dietary restrictions. The server also includes a means for filtering the received restaurant information based on the dietary restrictions, providing the filtered results to the user, and placing an order with the selected restaurant. It also includes a means for collecting feedback information provided by the user and storing and updating the information in a database. This allows users to select and order from an appropriate restaurant with peace of mind, and keeps the restaurant's reliability and service status up to date based on the results.

[1054] "User" refers to a person who uses the system to input dietary restrictions and location information to obtain appropriate restaurant information.

[1055] "Dietary restrictions" refers to conditions where certain ingredients or ingredients must be avoided due to allergies, calorie restrictions, religious reasons, etc.

[1056] "Location Information" means information about a geographic location where you are currently located or plan to visit.

[1057] A "search query" refers to a search query that is generated based on dietary restrictions and location information.

[1058] "Generative model" refers to an artificial intelligence model that generates relevant restaurant information based on a search query.

[1059] "Restaurant information" refers to information such as the restaurant's name, address, menu contents, and dietary restrictions that can be accommodated.

[1060] "Filtering" refers to the process of selecting only the information from the received restaurant information that meets the user's dietary restrictions.

[1061] "Ordering" refers to the process of a user purchasing a meal from a restaurant selected on the system.

[1062] "Feedback information" refers to information such as evaluations, opinions, and areas for improvement provided by customers after using a restaurant.

[1063] "Database" refers to a system for storing and managing collected feedback information and restaurant information.

[1064] This invention is a system that allows people with specific dietary restrictions to find suitable restaurants, place orders, and provide feedback. The specific configuration and program of the system are described below.

[1065] 1. System Program

[1066] First, the user enters their dietary restrictions and location information on their smartphone. Using the app's interface, users can easily input conditions such as "gluten-free," "under 1500 kcal," and "Tokyo." The smartphone application was developed using React Native.

[1067] The server receives the input information from the user and generates a search query that reflects the entered dietary restrictions and location information. The server is built using Node.js and Express.js.

[1068] The search query is sent to a generative model (OpenAI GPT-4) that receives relevant restaurant information, including a list of restaurants that meet specific dietary restrictions. The generated restaurant information is then filtered on the server to select only restaurants that meet the user's criteria.

[1069] The filtered restaurant information is returned to the smartphone application, which displays this information on a map for the user to visually confirm. The user can also place an order directly with the selected restaurant. The order information is also sent to the server, which notifies the appropriate restaurant.

[1070] After eating and drinking, the user provides feedback information. The feedback is again entered through a smartphone application and sent to the server. The server stores this feedback information in a database and uses it to keep up-to-date restaurant reliability ratings and dietary restriction compliance status. MongoDB is used for the database.

[1071] 2. Program Processing

[1072] The following hardware and software are used to receive input information from a user and to process and calculate data to generate a search query.

[1073] Hardware:

[1074] Smartphone: Providing a user interface and receiving / sending input information

[1075] Server: Parsing and responding to requests, managing databases

[1076] software:

[1077] Frontend: React Native

[1078] Backend: Node.js, Express.js

[1079] Database: MongoDB

[1080] Generative AI model: OpenAI GPT-4

[1081] The server analyzes the information received from the user and sends an appropriate query to the generative model. Once the generated restaurant information is returned, it is filtered to create a list of restaurants that meet the user's criteria. Finally, the filtered information is sent to the smartphone application and presented to the user.

[1082] 3. Examples and prompts

[1083] Examples:

[1084] A user opens the app and enters the criteria "gluten-free," "under 1500kcal," and "Tokyo." The server processes the request, returns matching restaurant information, and displays it on a map. The user then selects a specific restaurant, places an order, and provides feedback after completing the order.

[1085] Example prompt sentence:

[1086] "Find restaurants in Tokyo that provide gluten-free meals under 1500 calories."

[1087] This will create a system that allows people with specific dietary restrictions to enjoy eating out with peace of mind.

[1088] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1089] Step 1:

[1090] The user enters dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo") through a smartphone application. The information entered by the user is sent from the smartphone to the server. Specifically, the data entered in the user interface is sent to the server as an HTTP POST request.

[1091] Step 2:

[1092] The server analyzes the received dietary restrictions and location information to generate a search query. Based on the analyzed data, the server creates a query to identify "gluten-free meals" and "restaurants that offer meals under 1500 kcal." This query is then sent to the generative AI model.

[1093] Step 3:

[1094] The server sends a search query to the generative AI model and receives relevant restaurant information. The generative AI model (OpenAI GPT-4) analyzes the query and provides a list of restaurants that meet the criteria. The received information includes the restaurant's name, address, and menu items with corresponding dietary restrictions.

[1095] Step 4:

[1096] The server filters the received restaurant information based on the user's dietary restrictions. In this filtering process, restaurant information that does not meet the restrictions is excluded. Finally, a filtered list of restaurant information is generated.

[1097] Step 5:

[1098] The server returns the filtered restaurant information to the smartphone application, which then visually displays the received restaurant information on a map, including pin locations and detailed information about the restaurants.

[1099] Step 6:

[1100] The user browses restaurant information on the map and places an order at the restaurant of their choice. The smartphone application then sends the order information back to the server. The order includes details such as menu selection and delivery address.

[1101] Step 7:

[1102] The server analyzes the order information and notifies the appropriate restaurant, and a response is returned to the smartphone application to confirm that the order was successfully received.

[1103] Step 8:

[1104] After eating or drinking, the user provides feedback information. The feedback entered through the smartphone application is sent to the server, which then stores the feedback information in a database.

[1105] Step 9:

[1106] The server uses the feedback information stored in the database to update the restaurant's trustworthiness rating and dietary restriction availability, thereby improving the reliability of the information provided the next time a search is performed. The database is also continually improved based on user feedback.

[1107] 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.

[1108] This invention is a support system that allows people who must avoid certain foods due to allergies, calorie restrictions, religious reasons, etc. to enjoy eating out with peace of mind, as well as a system that recognizes the user's emotions and provides optimal restaurant information based on those emotions.The system displays restaurant information that meets the user's conditions and matches their emotions on a map simply by the user inputting specific conditions and emotional state.

[1109] System configuration

[1110] User

[1111] The user inputs dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo") through the system interface. Furthermore, the emotion engine automatically recognizes the user's emotional state. This emotional state can be obtained, for example, from facial expressions captured by the user or from audio recordings.

[1112] Terminal

[1113] The device receives the dietary restrictions and location information entered by the user, as well as emotion data from the emotion engine, and transmits them to the server. The device displays the information received from the server on a map and provides it to the user.

[1114] server

[1115] The server analyzes the dietary restrictions, location information, and emotion data received from the device and generates a search query. It then sends this search query to a generative model (generative AI) and receives relevant restaurant information. It filters the received information, adjusts the optimal restaurant list based on the emotion data, and returns it to the device. It also collects feedback information and emotion data and stores it in a database to improve the reliability of the information.

[1116] Program processing

[1117] User operations

[1118] The user opens the application and inputs their dietary restrictions (e.g., gluten-free, under 1500 kcal) and their current location (e.g., Tokyo).The emotion engine then automatically acquires emotion data based on the captured facial expressions and voice.

[1119] Device behavior

[1120] The device sends the entered dietary restrictions, location information, and emotional data to the server. The results returned from the server are displayed on a map, providing the user with a visually easy-to-understand format. Feedback information and emotional data from the user are also sent to the server.

[1121] Server Operation

[1122] The server analyzes the request received from the device and generates a search query. Specifically, it generates a query such as "Find restaurants in Tokyo that offer gluten-free meals under 1500 kcal" based on the input conditions and emotion data. The query is sent to the generative model (GPT) and relevant restaurant information is received. The received restaurant information is then filtered and prioritized based on the emotion data. For example, if the user is feeling stressed, restaurants with a relaxing atmosphere are prioritized. The results are returned to the device and provided to the user.

[1123] Specific examples

[1124] 1. The user opens the app and enters criteria such as "gluten-free," "under 1500 kcal," and "Tokyo." At the same time, the emotion engine analyzes the user's facial photo and recognizes the emotion of "stress."

[1125] 2. The device sends these conditions and emotion data to the server.

[1126] 3. Based on the conditions and emotion data, the server generates a query such as "Find restaurants in Tokyo that are gluten-free, under 1500 kcal, and have a stress-reducing atmosphere," and sends it to the generative model (GPT).

[1127] 4. The generative model (GPT) returns the relevant restaurant information.

[1128] 5. After filtering the information, the server creates a list that prioritizes restaurants with high ratings for "stress-reducing atmosphere."

[1129] 6. The terminal displays the filtered restaurant information on a map and provides it to the user.

[1130] 7. The user selects a restaurant based on the displayed information and provides feedback after visiting.

[1131] 8. The device sends the feedback information and emotion data to the server, which updates the database.

[1132] The above is a specific embodiment for implementing the system of the present invention. By combining it with an emotion engine, it is possible to provide optimal restaurant information according to the user's emotional state, supporting a more satisfying dining out experience.

[1133] The processing flow will be explained below.

[1134] Step 1:

[1135] The user opens the application. The user inputs their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"). The emotion engine then automatically recognizes the user's emotional state. This emotional state is obtained from facial expressions and voice captured by the user.

[1136] Step 2:

[1137] The device receives the dietary restrictions and location information entered by the user. When the user presses the search button, the device sends these restrictions and the recognized emotion data to the server. The request is sent as a POST request, serialized in JSON format.

[1138] Step 3:

[1139] The server analyzes the request received from the device, extracting dietary restrictions, location information, and emotion data, and stores each value in variables. Based on this information, it generates a search query (e.g., "Find restaurants in Tokyo that serve gluten-free meals under 1500 kcal").

[1140] Step 4:

[1141] The server sends the generated search query to the generative model (GPT). The generative model searches for relevant restaurant information from websites and reviews on the Internet and returns the results. This process is performed asynchronously through the generative AI's API.

[1142] Step 5:

[1143] The server receives the restaurant information returned from the generative model. The information is analyzed and filtered based on the user's dietary restrictions. Specifically, it selects restaurants from the returned list that perfectly match the user's dietary restrictions.

[1144] Step 6:

[1145] The server further adjusts the filtered restaurant list based on the emotion data. For example, if the user's emotion is "stress," it prioritizes restaurants with a relaxing atmosphere. The final adjusted list is then compiled in JSON format and sent to the device.

[1146] Step 7:

[1147] The terminal decodes the list of restaurants received from the server and displays it on a map. The user can visually check the restaurants indicated by pins on the map. Clicking on each pin will display a pop-up with detailed information.

[1148] Step 8:

[1149] Users can choose a restaurant to visit based on the displayed information, and after visiting, they can provide feedback through the app about the restaurant's rating and whether it accommodates dietary restrictions.

[1150] Step 9:

[1151] The device receives feedback information from the user and sends it to the server in JSON format.

[1152] Step 10:

[1153] The server receives the feedback information and stores it in a database. It then updates the restaurant's trustworthiness rating and dietary restrictions based on the collected feedback and sentiment data. The information stored in the database is used to improve the accuracy of search results the next time.

[1154] The above is a detailed explanation of the steps involved in the program's processing, which combines emotion engines. The operations of the server, terminal, and user at each step are described in detail.

[1155] Example 2

[1156] 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."

[1157] In today's world, it is difficult for people with dietary restrictions to enjoy eating out with peace of mind. Furthermore, it is also difficult for them to easily find an appropriate restaurant that matches their emotional state. The present invention aims to solve this problem by providing optimal restaurant information based on dietary restrictions and emotional state, thereby improving users' dining out experiences.

[1158] 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 conditions and location information from a user as input, means for generating a search query based on the dietary restriction conditions and location information, means for sending the search query to a generative AI model and receiving related restaurant information, means for filtering the received restaurant information based on the dietary restriction conditions and the user's emotional state, means for providing the filtered results to the user, means including an emotion recognition engine for acquiring emotion data of the user, and means for adjusting restaurant information based on the acquired emotion data. This makes it possible to provide restaurant information optimized for the user's dietary restriction conditions and emotional state.

[1159] "Dietary restriction conditions" are conditions that serve as criteria when a user selects a particular restaurant, such as restrictions on specific ingredients or calorie restrictions.

[1160] "Location information" refers to geographical data of the user's current location or a specified area, and is information used to select restaurants.

[1161] A "search query" is a query generated based on data such as dietary restrictions, location information, and emotional state, and is used to search for restaurant information.

[1162] A "generative AI model" is an artificial intelligence model that generates and provides the most relevant restaurant information based on a given search query.

[1163] An "emotion recognition engine" is software or hardware that analyzes a user's facial photograph and voice data to determine the user's current emotional state.

[1164] "Filtering" is the process of sorting received restaurant information based on dietary restrictions and emotional state, and extracting the most suitable information.

[1165] A "database" is an information management system that stores collected information such as feedback information and emotional data, and uses it for future searches and analyses.

[1166] "Feedback information" refers to information such as impressions and evaluations provided by users after visiting a restaurant, and is used to improve the accuracy of the system.

[1167] "Adjustment" refers to a process of changing the priority of the received restaurant information based on the acquired emotion data to provide the user with the most suitable information.

[1168] This invention provides a system that allows users to easily obtain optimal restaurant information based on their specific dietary restrictions and emotional state. The system is primarily composed of a user terminal, a server, and a generative AI model.

[1169] User operations

[1170] Users launch the application using a device such as a smartphone or tablet. First, they enter their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and their current location (e.g., "Tokyo"). The emotion engine then automatically obtains the user's emotional state. This emotional state is determined by analyzing a facial photograph taken by the user and a recorded voice.

[1171] Device behavior

[1172] The device sends the dietary restrictions, location information, and acquired emotion data entered by the user to the server as a single request. The device displays the restaurant information received from the server on a map to provide a visual reference for the user. The device also sends feedback information provided by the user to the restaurants they visited to the server.

[1173] Server Operation

[1174] The server analyzes the dietary restrictions, location information, and emotion data received from the device and generates a search query. Specifically, it generates a query to search for "restaurants in Tokyo that are gluten-free, serve meals under 1500 kcal, and have a stress-reducing atmosphere." The server sends this query to a generative AI model (e.g., GPT) and receives relevant restaurant information.

[1175] The received restaurant information is filtered by the server. The filtering is performed based on dietary restrictions and emotional data. For example, if the user is feeling "stressed," restaurants with a relaxing atmosphere will be prioritized. The filtered restaurant information is returned to the terminal and provided to the user.

[1176] In addition, the server stores feedback information and emotional data provided by users in a database. This database is used to update restaurant reliability ratings and dietary restrictions, helping to improve recommendation accuracy in future visits.

[1177] Specific examples

[1178] Below are specific operating procedures and examples of prompts.

[1179] 1. User Actions:

[1180] Users open the app and enter dietary restrictions such as "gluten-free," "under 1500 kcal," and "Tokyo."

[1181] The emotion engine analyzes the user's facial photo and recognizes the emotion as "stress."

[1182] 2. Device behavior:

[1183] The device sends the condition and emotion data to the server.

[1184] 3. Server Operation:

[1185] The server generates a query such as "Find a restaurant in Tokyo that is gluten-free, under 1500 kcal, and has a stress-reducing atmosphere" and sends it to the generative AI model.

[1186] A generative AI model (e.g., GPT) returns the relevant restaurant information.

[1187] The server filters the information and sends it back to the device.

[1188] 4. Display and Feedback:

[1189] The terminal displays filtered restaurant information on a map and provides it to the user.

[1190] After the user visits, feedback information is sent from the terminal to the server.

[1191] Prompt Sentence Examples

[1192] "Please tell me restaurants in Tokyo that offer gluten-free meals under 1500 kcal in a stress-relieving atmosphere."

[1193] This invention efficiently provides restaurant information optimized for the user's dietary restrictions and emotional state, resulting in a more satisfying dining out experience.

[1194] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1195] Step 1:

[1196] User input:

[1197] The user opens the application on their smartphone and enters their current location and dietary restrictions, such as "gluten-free," "under 1500 kcal," and "Tokyo," into the application interface. They then press the "Emotion Input" button to capture a photo of their face and their voice.

[1198] Input: dietary restrictions, location information, face photo or voice

[1199] Output: User condition and emotion data

[1200] Step 2:

[1201] Obtaining emotion data:

[1202] The device sends the captured facial photo and voice data to an emotion recognition engine, which analyzes them and determines the user's emotional state (e.g., "stress").

[1203] Input: Face photo or voice data

[1204] Output: Emotion recognition result (e.g. "Stress")

[1205] Step 3:

[1206] Data transmission:

[1207] The device sends the dietary restriction conditions, location information, and emotion recognition results as a single request to the server.

[1208] Input: dietary restriction conditions, location information, emotion recognition results

[1209] Output: Request to server

[1210] Step 4:

[1211] Generating a search query:

[1212] The server analyzes the received data and generates a search query, specifically, a query to find "restaurants in Tokyo that serve gluten-free meals under 1500 kcal and have a stress-reducing atmosphere."

[1213] Input: dietary restriction conditions, location information, emotion recognition results

[1214] Output: The search query

[1215] Step 5:

[1216] Querying a generative AI model:

[1217] The server sends the generated query to a generative AI model (e.g., GPT), which generates relevant restaurant information based on the query and returns it to the server.

[1218] Input: Search query

[1219] Output: Related restaurant information

[1220] Step 6:

[1221] Filter restaurant information:

[1222] The server then filters the received restaurant information based on dietary restrictions and emotion recognition results. For example, it prioritizes restaurants with a high rating for "stress-reducing atmosphere."

[1223] Input: Related restaurant information, dietary restrictions, emotion recognition results

[1224] Output: Filtered restaurant information

[1225] Step 7:

[1226] Sending adjustment results:

[1227] The server sends the filtered restaurant information to the device, which then plots the received information on a map using a map API (e.g., Google Maps) and provides it to the user in a visually easy-to-understand format.

[1228] Input: Filtered restaurant information

[1229] Output: Response to the terminal

[1230] Step 8:

[1231] Enter your feedback:

[1232] After visiting a restaurant, users can enter their impressions and ratings on the feedback screen. For example, they can add comments such as "The food was delicious" or "The atmosphere was relaxing."

[1233] Input: Feedback information

[1234] Output: Feedback data

[1235] Step 9:

[1236] Send feedback information:

[1237] The device sends feedback information to the server, which stores it in a database and uses it to improve the accuracy of future query generation and filtering.

[1238] Input: Feedback data

[1239] Output: Stored in a database

[1240] (Application example 2)

[1241] 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."

[1242] Conventional restaurant search systems can provide restaurant information based on a user's dietary restrictions, but they cannot provide restaurant information that takes into account the user's emotional state. This makes it difficult for users to find the best restaurant when they are in a specific emotional state. In particular, for users who are feeling stressed or tired, the system cannot suggest restaurants with a high relaxation effect, which leads to a problem of reduced user satisfaction.

[1243] 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 conditions and location information from a user as input, means for generating a search query based on the dietary restriction conditions and location information, means for sending the search query to a generative model and receiving related restaurant information, means for filtering the received restaurant information based on the dietary restriction conditions, means for providing the filtered results to the user, means for recognizing the user's emotional state, and means for prioritizing and adjusting the received restaurant information based on the emotional state. This makes it possible to provide optimal restaurant information according to the user's emotional state.

[1244] "Dietary restrictions" refer to conditions that require avoiding certain ingredients or nutrients due to allergies, calorie restrictions, religious reasons, etc.

[1245] "Location information" refers to geographic data about a user's current location or a location they specify.

[1246] A "search query" is a search command generated based on criteria entered by the user.

[1247] A "generative model" is an artificial intelligence model that generates relevant information based on an input search query.

[1248] "Restaurant information" refers to data about the type of restaurant, its location, the menu it offers, etc.

[1249] "Filtering" is the process of selecting and extracting data based on specific conditions.

[1250] "User" refers to a person who uses this system to search for restaurant information that meets dietary restrictions.

[1251] "Emotional state" refers to the user's psychological and emotional state as recognized from facial expressions, voice, etc.

[1252] "Prioritization" is the process of assigning importance to information based on the user's emotional state.

[1253] "Delivery" refers to a service that delivers ordered food and drinks to a specified location.

[1254] The system for implementing this invention is mainly composed of a user terminal and a server. The user terminal and the server work together via a communication line to provide the information requested by the user. Each element of the system is described in detail below.

[1255] System Configuration

[1256] User Operation

[1257] Users operate the application using a user device such as a smartphone. After opening the application, the user enters dietary restrictions (e.g., "gluten-free") and location information (e.g., "Tokyo"). The application also has an emotion recognition function that can capture the user's emotional state using a camera and microphone. To analyze the user's emotional state from facial expressions and voice, the application uses emotion recognition services such as Microsoft's Azure Emotion API.

[1258] Device behavior

[1259] The user device receives the dietary restrictions, location information, and emotion data entered by the user. This data is sent to the server. The results returned from the server are displayed on a map, providing the user with a visually easy-to-understand format. The system also collects the user's feedback information and emotion data, which are sent to the server to update the database.

[1260] Server Operation

[1261] The server analyzes the dietary restrictions, location information, and emotional data received from the user device and generates an appropriate search query. This search query is sent to a generative AI model (e.g., GPT-4) to receive relevant restaurant information. The received restaurant information is filtered based on the dietary restrictions and further prioritized based on the user's emotional state. For example, if the user is feeling stressed, restaurants with a high relaxation effect will be prioritized. The final restaurant list is returned to the user device and displayed in the user's application.

[1262] The server periodically collects feedback information and emotional data and updates the database to improve restaurant reliability ratings and dietary restrictions.

[1263] Specific examples

[1264] The user opens the app and enters search criteria such as "gluten-free" and "Tokyo." At the same time, the emotion engine analyzes the user's facial photo and recognizes that the user is feeling "stressed." The device then sends these criteria and emotion data to the server. Based on the criteria and emotion data, the server generates a search query such as "Find restaurants in Tokyo that offer gluten-free menus and have a stress-reducing atmosphere," and sends it to a generative model (GPT-4). The generative model returns relevant restaurant information, and the server creates a list prioritizing restaurants with a high stress-reducing rating. Finally, the filtered results are displayed on the user's device.

[1265] Prompt Sentence Examples

[1266] "Please tell me restaurants in Tokyo that offer gluten-free menus and have a great relaxation effect."

[1267] In this way, the present invention provides optimal restaurant information based on dietary restrictions and emotional state, thereby realizing a system that can increase user satisfaction.

[1268] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1269] Step 1:

[1270] The user launches the application using a device such as a smartphone. A screen appears where the user can enter their dietary restrictions (e.g., "gluten-free") and current location (e.g., "Tokyo"). The entered information is temporarily stored in the device's internal memory.

[1271] Step 2:

[1272] The device uses camera and microphone sensors to recognize the user's emotional state. Specifically, it takes a photo of the user's face or records their voice, and sends this to Microsoft's Azure Emotion API. It then receives emotion data (e.g., "stress") returned from the API. The input is the face photo or voice data, and the output is emotion data.

[1273] Step 3:

[1274] The device sends the acquired dietary restriction conditions, current location information, and emotion data to the server. Specifically, it sends them as an HTTP request. The input is the dietary restriction conditions, current location information, and emotion data, and the output is the transmission of an HTTP request.

[1275] Step 4:

[1276] The server analyzes the dietary restrictions, current location information, and emotion data received from the device and generates a search query. The generated search query may be in the form of, for example, "Find restaurants in Tokyo that offer gluten-free menus and have stress-reducing effects." The inputs are dietary restrictions, current location information, and emotion data, and the output is the generated search query.

[1277] Step 5:

[1278] The server sends the generated search query to a generative AI model (e.g., GPT-4) and receives related restaurant information. The generative AI model returns restaurant information in response to the search query. The input is the search query, and the output is related restaurant information.

[1279] Step 6:

[1280] The server filters the received restaurant information based on the dietary restrictions. As a result of the filtering, only matching restaurant information is extracted. The input is restaurant information and dietary restrictions, and the output is the filtered restaurant information.

[1281] Step 7:

[1282] The server prioritizes and adjusts the filtered restaurant information based on the user's emotional state. For example, if the user is feeling stressed, restaurants with a high relaxation effect are prioritized. The input is the filtered restaurant information and emotional data, and the output is prioritized restaurant information.

[1283] Step 8:

[1284] The server returns the prioritized restaurant information to the terminal and provides it to the user. The terminal displays the received restaurant information on a map and provides it to the user in a visually easy-to-understand format. The input is the prioritized restaurant information, and the output is the restaurant information displayed on the map.

[1285] Step 9:

[1286] The user makes a selection based on the displayed restaurant information and provides feedback information after visiting. The feedback information is sent from the terminal to the server. The input is the feedback information, and the output is the transmission to the server.

[1287] Step 10:

[1288] The server stores the received feedback information and emotion data in a database. The server uses the feedback information to update the restaurant's trustworthiness rating and dietary restriction compliance status. The input is the feedback information and emotion data, and the output is the updated database.

[1289] In this way, the system can provide optimal restaurant information based on dietary restrictions and emotional state, increasing user satisfaction.

[1290] 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.

[1291] 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.

[1292] 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.

[1293] [Fourth embodiment]

[1294] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1295] 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.

[1296] 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).

[1297] 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.

[1298] 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.

[1299] 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).

[1300] 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.

[1301] 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.

[1302] 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.

[1303] 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.

[1304] 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.

[1305] 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.

[1306] 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."

[1307] This invention is a support system that allows people who must avoid certain foods due to allergies, calorie restrictions, religious reasons, etc. to enjoy eating out with peace of mind. The system displays restaurant information that matches specific criteria on a map simply by the user entering the criteria.

[1308] System configuration

[1309] User

[1310] Users use an interface to input dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"). This interface is designed to be easy for users to operate.

[1311] Terminal

[1312] The device receives dietary restrictions and location information from the user and sends it to the server. It also displays the information received from the server on a map. Specifically, it sends the conditions entered in the form to the server as a POST request, analyzes the restaurant information returned from the server, and displays it.

[1313] server

[1314] The server analyzes the request received from the device and generates a search query based on the specified dietary restrictions and location information. It then sends this search query to a generative model (generative AI) and receives relevant restaurant information. It then filters the received information and returns the filtered restaurant list to the device. It also collects feedback information and stores it in a database to improve the reliability of the information.

[1315] Program processing

[1316] User operations

[1317] The user opens the application, enters their dietary restrictions (e.g., gluten-free, under 1500 kcal) and their current location (e.g., Tokyo), and then presses the search button.

[1318] Device behavior

[1319] When the search button is pressed, the device sends the entered search criteria to the server. The results returned from the server are displayed on a map, providing the user with a visually easy-to-understand format. Feedback information from the user is also sent to the server.

[1320] Server Operation

[1321] The server analyzes the request received from the device and generates a search query. Specifically, it generates a query such as "Find gluten-free restaurants and restaurants in Tokyo that offer meals under 1500 kcal" based on the input criteria. The query is sent to the generative model (GPT) and relevant restaurant information is received. The received restaurant information is then filtered to create a list of restaurants that meet the criteria. This list is returned to the device, and feedback provided to the user is stored in a database, updating the restaurant's reliability rating and dietary restrictions.

[1322] Specific examples

[1323] 1. The user opens the app and enters criteria such as "gluten-free," "under 1500kcal," and "Tokyo."

[1324] 2. The device sends these conditions to the server.

[1325] 3. The server generates a query to find restaurants in Tokyo that offer "gluten-free" and "under 1500 kcal" meals based on the conditions and sends it to the generative model (GPT).

[1326] 4. The generative model (GPT) returns the relevant restaurant information.

[1327] 5. The server filters this information and creates a list of restaurants that meet the criteria.

[1328] 6. The terminal displays the filtered restaurant information on a map and provides it to the user.

[1329] 7. The user selects a restaurant based on the displayed information and provides feedback after visiting.

[1330] 8. The terminal sends this feedback information to the server, which updates the database.

[1331] The above is a specific embodiment for implementing the system of the present invention, which supports people with dietary restrictions in enjoying eating out with peace of mind.

[1332] The processing flow will be explained below.

[1333] Step 1:

[1334] The user opens the application and enters their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo") through the interface. These conditions are displayed as a form, designed to make it easy for the user to enter them.

[1335] Step 2:

[1336] The device receives the dietary restrictions and location information entered by the user. When the user presses the search button, the device sends these restrictions to the server as a POST request. The request is serialized in JSON format and prepared for parsing on the server side.

[1337] Step 3:

[1338] The server analyzes the request received from the device, extracts dietary restrictions and location information, and stores each value in variables. Based on this information, it generates a search query (e.g., "Find restaurants in Tokyo that serve gluten-free meals under 1500 kcal").

[1339] Step 4:

[1340] The server sends the generated search query to the generative model (GPT). The generative model searches for relevant restaurant information from websites, reviews, etc., and returns the results. This process is performed asynchronously via the generative AI's API.

[1341] Step 5:

[1342] The server receives the restaurant information returned from the generative model. The received information is analyzed and filtered based on the dietary restrictions entered by the user. Specifically, it selects restaurants from the returned list that perfectly match the dietary restrictions.

[1343] Step 6:

[1344] The server constructs a filtered list of restaurants in JSON format and sends it to the device, including the restaurant's name, location, and corresponding dietary restriction details.

[1345] Step 7:

[1346] The terminal decodes the list of restaurants received from the server and displays it on a map. The user can visually check the restaurants indicated by pins on the map. Clicking on each pin will display a pop-up with detailed information.

[1347] Step 8:

[1348] Users can choose a restaurant to visit based on the displayed information, and after visiting, they can provide feedback through the app about the restaurant's rating and whether it accommodates dietary restrictions.

[1349] Step 9:

[1350] The device receives feedback information from the user and sends it to the server in JSON format.

[1351] Step 10:

[1352] The server receives the feedback information and stores it in a database. It then updates the restaurant's credibility rating and dietary restrictions based on the collected feedback. The information stored in the database is used to improve the accuracy of search results the next time.

[1353] The above is a concrete explanation of each step of the program's processing. The operations of the server, terminal, and user at each step have been described in detail.

[1354] Example 1

[1355] 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."

[1356] Recently, an increasing number of people have to avoid certain foods due to dietary restrictions, allergies, religious reasons, etc. In order for these people to enjoy eating out with peace of mind, they need to be able to easily and quickly obtain information about restaurants that meet their requirements. However, with conventional methods, it has been difficult to collect this information, and there have been challenges in obtaining reliable information.

[1357] 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.

[1358] In this invention, the server includes means for receiving dietary restrictions and location information as input from a user, means for generating a search query based on the dietary restrictions and location information, means for transmitting the search query to a generation AI model that generates the search query and receiving related restaurant information, means for filtering the received restaurant information based on the dietary restrictions, and means for providing the filtered results to the user. This allows users to quickly obtain restaurant information that meets their specific dietary restrictions and enjoy eating out with peace of mind.

[1359] "User" refers to a person who uses the system to input dietary restrictions and location information to obtain appropriate restaurant information.

[1360] "Dietary restrictions" refers to conditions that require avoidance of certain ingredients or cooking methods, such as allergies, calorie restrictions, or religious beliefs.

[1361] "Location information" refers to information about the area or place a user wants to search for, such as city name or postal code.

[1362] A "search query" refers to instructions or commands to search for restaurants that meet the dietary restrictions and location information entered by the user.

[1363] "Generative AI model" refers to an artificial intelligence model that generates relevant information based on an input search query.

[1364] "Restaurant information" refers to detailed information that users need when eating out, such as the restaurant's name, address, contact information, menu, and information regarding dietary restrictions.

[1365] "Filtering" refers to the process of selecting only information that meets the user's dietary restrictions from the generated restaurant information.

[1366] A "database" refers to an electronic data collection in which collected information is stored.

[1367] "Trustworthiness evaluation" refers to the process of evaluating the quality and reliability of restaurants based on feedback information from customers.

[1368] "Dietary restriction accommodation status" refers to the extent to which a restaurant accommodates the dietary restrictions of customers.

[1369] "Display on a map" refers to showing filtered restaurant information on a map in a visually easy-to-understand format.

[1370] "Detailed Information" refers to deeper level information provided about the selected restaurant, such as menu, prices, opening hours, etc.

[1371] "Feedback information" refers to the evaluations and opinions provided by customers after visiting a restaurant.

[1372] This invention relates to a support system that enables people with dietary restrictions to enjoy eating out with peace of mind. This system is designed so that when a user simply inputs specific conditions, information about restaurants that meet those conditions is displayed on a map.

[1373] 1. Specific processing content of the program

[1374] User Input

[1375] Users start the application using a device such as a smartphone or PC, and enter their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"). Once the user has finished entering the information, they press the search button to begin the next process.

[1376] Device behavior

[1377] The device receives the conditions entered by the user and sends them to the server in the form of an HTTP POST request, which includes the dietary restrictions and location information in JSON format.

[1378] Server Operation

[1379] The server receives the request sent from the device and analyzes its contents. Specifically, it decodes the dietary restrictions and location information and generates a search query. This query is in the form of "Find restaurants in Tokyo that serve gluten-free meals under 1500 kcal." This query is used to send a prompt to a generative AI model (e.g., GPT).

[1380] Processing generative AI models

[1381] The generative AI model generates restaurant information that matches the search criteria based on the prompt received from the server, including the restaurant's name, address, menu information, and corresponding dietary restrictions.

[1382] Server Filtering

[1383] The server receives the restaurant information returned by the generative AI model and filters it. During the filtering process, it checks whether the received information meets the dietary restrictions specified by the user. Only matching information is selected, and finally, a filtered information list is created.

[1384] Providing information to devices

[1385] The server sends the filtered restaurant information to the terminal. The terminal displays the received information on a map, providing the user with a visually easy-to-understand format. Restaurants that meet the criteria are displayed as pins on the map, and users can click on the pins to view detailed information.

[1386] User Feedback

[1387] Users select a restaurant based on the displayed restaurant information and provide feedback through the app after visiting. The feedback includes rating points and comments, which are used for the next process.

[1388] Accumulation of feedback information

[1389] The terminal sends the feedback information entered by the user to the server, which stores the feedback information in a database and uses this information to update the restaurant's reliability rating and its ability to accommodate dietary restrictions.

[1390] 2. Hardware and Software Used

[1391] Devices used by users: computing devices such as smartphones, PCs, tablets, etc.

[1392] Application: Software that provides an interface for users to enter criteria

[1393] Server: Receives requests, parses them, filters them, and manages the database

[1394] Database: Managing reliability ratings and feedback information

[1395] Generative AI models (e.g., GPT): Artificial intelligence models that generate relevant information based on a search query.

[1396] Map software: Software for displaying received restaurant information on a map

[1397] 3. Examples of concrete examples and prompts

[1398] Specific examples

[1399] 1. The user opens the app and enters criteria such as "gluten-free," "under 1500kcal," and "Tokyo."

[1400] 2. The device sends these conditions to the server.

[1401] 3. The server generates a query based on the conditions: "Find restaurants in Tokyo that are gluten-free and under 1500 kcal" and sends it to the generative AI model.

[1402] 4. The generative AI model returns the relevant restaurant information.

[1403] 5. The server filters this information and creates a list of restaurants that meet the criteria.

[1404] 6. The terminal displays the filtered restaurant information on a map and provides it to the user.

[1405] 7. The user selects a restaurant based on the displayed information and provides feedback after visiting.

[1406] 8. The terminal sends this feedback information to the server, which updates the database.

[1407] Prompt Sentence Examples

[1408] "Please suggest restaurants in Tokyo that meet the specified criteria (e.g. gluten-free, under 1500kcal)."

[1409] The above is a specific embodiment of the system of the present invention, which allows users to easily find restaurants that meet their specific dietary restrictions and enjoy eating out with peace of mind.

[1410] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1411] Step 1:

[1412] User Input

[1413] The user starts the application, enters dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"), and then presses the search button.

[1414] Specific operation: Enter the conditions into the application interface.

[1415] Input: dietary restrictions, location information

[1416] Output: Conditions are sent to the terminal

[1417] Step 2:

[1418] Sending a request from the device

[1419] The device sends the user-entered conditions to the server as an HTTP POST request, which includes the dietary restrictions and location information in JSON format.

[1420] Specific operation: The data in the form where the conditions were entered is converted to JSON format and sent to the " / search" endpoint.

[1421] Input: User-entered conditions (JSON format)

[1422] Output: Server receives request

[1423] Step 3:

[1424] Server request analysis

[1425] The server analyzes the request received from the device and generates a search query based on the conditions. The query is a sentence such as "Find restaurants in Tokyo that are gluten-free and under 1500 kcal."

[1426] Specific operation: Parse the received JSON data and extract each condition. Then, construct a query statement.

[1427] Input: HTTP POST request (conditions in JSON format)

[1428] Output: Search query

[1429] Step 4:

[1430] Sending prompts to the server's generated AI model

[1431] The server sends a search query to the generative AI model, which generates relevant restaurant information based on the prompt.

[1432] Specific operation: The constructed query sentence is sent to the generative AI model as a prompt sentence.

[1433] Input: Discovery query

[1434] Output: Generative AI model returns restaurant information

[1435] Step 5:

[1436] Receiving and filtering restaurant information

[1437] The server receives the restaurant information returned by the generative AI model and filters it to select only restaurants that meet specific dietary restrictions.

[1438] Specific operation: Analyze the information returned from the generative AI model and extract information that meets the conditions.

[1439] Input: Restaurant information from a generative AI model

[1440] Output: Filtered list of restaurants

[1441] Step 6:

[1442] Sending filtering results to the device

[1443] The server sends the filtered restaurant list in JSON format to the terminal.

[1444] Specific operation: The filtering results are encoded in JSON format and sent to the terminal as an HTTP response.

[1445] Input: A filtered list of restaurants

[1446] Output: The device receives the list

[1447] Step 7:

[1448] Displaying information on the device's map

[1449] The device passes the filtering results received from the server to the map application and displays them on a map, with the location of each restaurant indicated by a pin and detailed information displayed.

[1450] Specific operation: Data is passed to the map application API, and pins are placed on the map. Clicking on a pin displays detailed store information.

[1451] Input: A filtered list of restaurants

[1452] Output: Restaurant information displayed on a map

[1453] Step 8:

[1454] User feedback

[1455] Users enter feedback (rating points, comments) about the restaurants they visit within the app.

[1456] Specific action: The user fills out the feedback form and presses the submit button.

[1457] Input: Restaurant rating points, comments

[1458] Output: Feedback information sent to the terminal

[1459] Step 9:

[1460] Send device feedback

[1461] The terminal transmits the feedback information input by the user to the server in the form of an HTTP POST request.

[1462] Specific operation: The feedback information is converted into JSON format and sent to the server.

[1463] Input: User feedback information (JSON format)

[1464] Output: The server receives the feedback information.

[1465] Step 10:

[1466] Server database update

[1467] The server stores the received feedback information in a database, which updates the restaurant's reliability rating and dietary restrictions.

[1468] Specific operation: Update the corresponding record in the database and accumulate the information.

[1469] Input: Feedback information

[1470] Output: Updated database

[1471] This concludes the detailed description of the program processing of this system. This system allows users to quickly find restaurants that meet specific dietary restrictions, allowing them to enjoy eating out with peace of mind.

[1472] (Application example 1)

[1473] 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."

[1474] Conventional restaurant search systems do not provide sufficient support for people with dietary restrictions when it comes to enjoying dining out. Specifically, they lack information on restaurants that cater to specific allergies, calorie restrictions, or religious dietary restrictions, making it difficult for users to choose meals with confidence. Another issue is the inefficient collection of orders and feedback from restaurants selected from search results, and the inefficient updating of the database. This makes it difficult for users with dietary restrictions to find suitable restaurants, reducing the convenience of dining out.

[1475] 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.

[1476] In this invention, the server includes a means for receiving dietary restrictions and location information from a user as input, a means for generating a search query based on the dietary restrictions and location information, and a means for sending the search query to a generative model and receiving related restaurant information. This enables efficient searching and provision of restaurant information that satisfies dietary restrictions. The server also includes a means for filtering the received restaurant information based on the dietary restrictions, providing the filtered results to the user, and placing an order with the selected restaurant. It also includes a means for collecting feedback information provided by the user and storing and updating the information in a database. This allows users to select and order from an appropriate restaurant with peace of mind, and keeps the restaurant's reliability and service status up to date based on the results.

[1477] "User" refers to a person who uses the system to input dietary restrictions and location information to obtain appropriate restaurant information.

[1478] "Dietary restrictions" refers to conditions where certain ingredients or ingredients must be avoided due to allergies, calorie restrictions, religious reasons, etc.

[1479] "Location Information" means information about a geographic location where you are currently located or plan to visit.

[1480] A "search query" refers to a search query that is generated based on dietary restrictions and location information.

[1481] "Generative model" refers to an artificial intelligence model that generates relevant restaurant information based on a search query.

[1482] "Restaurant information" refers to information such as the restaurant's name, address, menu contents, and dietary restrictions that can be accommodated.

[1483] "Filtering" refers to the process of selecting only the information from the received restaurant information that meets the user's dietary restrictions.

[1484] "Ordering" refers to the process of a user purchasing a meal from a restaurant selected on the system.

[1485] "Feedback information" refers to information such as evaluations, opinions, and areas for improvement provided by customers after using a restaurant.

[1486] "Database" refers to a system for storing and managing collected feedback information and restaurant information.

[1487] This invention is a system that allows people with specific dietary restrictions to find suitable restaurants, place orders, and provide feedback. The specific configuration and program of the system are described below.

[1488] 1. System Program

[1489] First, the user enters their dietary restrictions and location information on their smartphone. Using the app's interface, users can easily input conditions such as "gluten-free," "under 1500 kcal," and "Tokyo." The smartphone application was developed using React Native.

[1490] The server receives the input information from the user and generates a search query that reflects the entered dietary restrictions and location information. The server is built using Node.js and Express.js.

[1491] The search query is sent to a generative model (OpenAI GPT-4) that receives relevant restaurant information, including a list of restaurants that meet specific dietary restrictions. The generated restaurant information is then filtered on the server to select only restaurants that meet the user's criteria.

[1492] The filtered restaurant information is returned to the smartphone application, which displays this information on a map for the user to visually confirm. The user can also place an order directly with the selected restaurant. The order information is also sent to the server, which notifies the appropriate restaurant.

[1493] After eating and drinking, the user provides feedback information. The feedback is again entered through a smartphone application and sent to the server. The server stores this feedback information in a database and uses it to keep up-to-date restaurant reliability ratings and dietary restriction compliance status. MongoDB is used for the database.

[1494] 2. Program Processing

[1495] The following hardware and software are used to receive input information from a user and to process and calculate data to generate a search query.

[1496] Hardware:

[1497] Smartphone: Providing a user interface and receiving / sending input information

[1498] Server: Parsing and responding to requests, managing databases

[1499] software:

[1500] Frontend: React Native

[1501] Backend: Node.js, Express.js

[1502] Database: MongoDB

[1503] Generative AI model: OpenAI GPT-4

[1504] The server analyzes the information received from the user and sends an appropriate query to the generative model. Once the generated restaurant information is returned, it is filtered to create a list of restaurants that meet the user's criteria. Finally, the filtered information is sent to the smartphone application and presented to the user.

[1505] 3. Examples and prompts

[1506] Examples:

[1507] A user opens the app and enters the criteria "gluten-free," "under 1500kcal," and "Tokyo." The server processes the request, returns matching restaurant information, and displays it on a map. The user then selects a specific restaurant, places an order, and provides feedback after completing the order.

[1508] Example prompt sentence:

[1509] "Find restaurants in Tokyo that provide gluten-free meals under 1500 calories."

[1510] This will create a system that allows people with specific dietary restrictions to enjoy eating out with peace of mind.

[1511] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1512] Step 1:

[1513] The user enters dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo") through a smartphone application. The information entered by the user is sent from the smartphone to the server. Specifically, the data entered in the user interface is sent to the server as an HTTP POST request.

[1514] Step 2:

[1515] The server analyzes the received dietary restrictions and location information to generate a search query. Based on the analyzed data, the server creates a query to identify "gluten-free meals" and "restaurants that offer meals under 1500 kcal." This query is then sent to the generative AI model.

[1516] Step 3:

[1517] The server sends a search query to the generative AI model and receives relevant restaurant information. The generative AI model (OpenAI GPT-4) analyzes the query and provides a list of restaurants that meet the criteria. The received information includes the restaurant's name, address, and menu items with corresponding dietary restrictions.

[1518] Step 4:

[1519] The server filters the received restaurant information based on the user's dietary restrictions. In this filtering process, restaurant information that does not meet the restrictions is excluded. Finally, a filtered list of restaurant information is generated.

[1520] Step 5:

[1521] The server returns the filtered restaurant information to the smartphone application, which then visually displays the received restaurant information on a map, including pin locations and detailed information about the restaurants.

[1522] Step 6:

[1523] The user browses restaurant information on the map and places an order at the restaurant of their choice. The smartphone application then sends the order information back to the server. The order includes details such as menu selection and delivery address.

[1524] Step 7:

[1525] The server analyzes the order information and notifies the appropriate restaurant, and a response is returned to the smartphone application to confirm that the order was successfully received.

[1526] Step 8:

[1527] After eating or drinking, the user provides feedback information. The feedback entered through the smartphone application is sent to the server, which then stores the feedback information in a database.

[1528] Step 9:

[1529] The server uses the feedback information stored in the database to update the restaurant's trustworthiness rating and dietary restriction availability, thereby improving the reliability of the information provided the next time a search is performed. The database is also continually improved based on user feedback.

[1530] 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.

[1531] This invention is a support system that allows people who must avoid certain foods due to allergies, calorie restrictions, religious reasons, etc. to enjoy eating out with peace of mind, as well as a system that recognizes the user's emotions and provides optimal restaurant information based on those emotions.The system displays restaurant information that meets the user's conditions and matches their emotions on a map simply by the user inputting specific conditions and emotional state.

[1532] System configuration

[1533] User

[1534] The user inputs dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo") through the system interface. Furthermore, the emotion engine automatically recognizes the user's emotional state. This emotional state can be obtained, for example, from facial expressions captured by the user or from audio recordings.

[1535] Terminal

[1536] The device receives the dietary restrictions and location information entered by the user, as well as emotion data from the emotion engine, and transmits them to the server. The device displays the information received from the server on a map and provides it to the user.

[1537] server

[1538] The server analyzes the dietary restrictions, location information, and emotion data received from the device and generates a search query. It then sends this search query to a generative model (generative AI) and receives relevant restaurant information. It filters the received information, adjusts the optimal restaurant list based on the emotion data, and returns it to the device. It also collects feedback information and emotion data and stores it in a database to improve the reliability of the information.

[1539] Program processing

[1540] User operations

[1541] The user opens the application and inputs their dietary restrictions (e.g., gluten-free, under 1500 kcal) and their current location (e.g., Tokyo).The emotion engine then automatically acquires emotion data based on the captured facial expressions and voice.

[1542] Device behavior

[1543] The device sends the entered dietary restrictions, location information, and emotional data to the server. The results returned from the server are displayed on a map, providing the user with a visually easy-to-understand format. Feedback information and emotional data from the user are also sent to the server.

[1544] Server Operation

[1545] The server analyzes the request received from the device and generates a search query. Specifically, it generates a query such as "Find restaurants in Tokyo that offer gluten-free meals under 1500 kcal" based on the input conditions and emotion data. The query is sent to the generative model (GPT) and relevant restaurant information is received. The received restaurant information is then filtered and prioritized based on the emotion data. For example, if the user is feeling stressed, restaurants with a relaxing atmosphere are prioritized. The results are returned to the device and provided to the user.

[1546] Specific examples

[1547] 1. The user opens the app and enters criteria such as "gluten-free," "under 1500 kcal," and "Tokyo." At the same time, the emotion engine analyzes the user's facial photo and recognizes the emotion of "stress."

[1548] 2. The device sends these conditions and emotion data to the server.

[1549] 3. Based on the conditions and emotion data, the server generates a query such as "Find restaurants in Tokyo that are gluten-free, under 1500 kcal, and have a stress-reducing atmosphere," and sends it to the generative model (GPT).

[1550] 4. The generative model (GPT) returns the relevant restaurant information.

[1551] 5. After filtering the information, the server creates a list that prioritizes restaurants with high ratings for "stress-reducing atmosphere."

[1552] 6. The terminal displays the filtered restaurant information on a map and provides it to the user.

[1553] 7. The user selects a restaurant based on the displayed information and provides feedback after visiting.

[1554] 8. The device sends the feedback information and emotion data to the server, which updates the database.

[1555] The above is a specific embodiment for implementing the system of the present invention. By combining it with an emotion engine, it is possible to provide optimal restaurant information according to the user's emotional state, supporting a more satisfying dining out experience.

[1556] The processing flow will be explained below.

[1557] Step 1:

[1558] The user opens the application. The user inputs their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and location information (e.g., "Tokyo"). The emotion engine then automatically recognizes the user's emotional state. This emotional state is obtained from facial expressions and voice captured by the user.

[1559] Step 2:

[1560] The device receives the dietary restrictions and location information entered by the user. When the user presses the search button, the device sends these restrictions and the recognized emotion data to the server. The request is sent as a POST request, serialized in JSON format.

[1561] Step 3:

[1562] The server analyzes the request received from the device, extracting dietary restrictions, location information, and emotion data, and stores each value in variables. Based on this information, it generates a search query (e.g., "Find restaurants in Tokyo that serve gluten-free meals under 1500 kcal").

[1563] Step 4:

[1564] The server sends the generated search query to the generative model (GPT). The generative model searches for relevant restaurant information from websites and reviews on the Internet and returns the results. This process is performed asynchronously through the generative AI's API.

[1565] Step 5:

[1566] The server receives the restaurant information returned from the generative model. The information is analyzed and filtered based on the user's dietary restrictions. Specifically, it selects restaurants from the returned list that perfectly match the user's dietary restrictions.

[1567] Step 6:

[1568] The server further adjusts the filtered restaurant list based on the emotion data. For example, if the user's emotion is "stress," it prioritizes restaurants with a relaxing atmosphere. The final adjusted list is then compiled in JSON format and sent to the device.

[1569] Step 7:

[1570] The terminal decodes the list of restaurants received from the server and displays it on a map. The user can visually check the restaurants indicated by pins on the map. Clicking on each pin will display a pop-up with detailed information.

[1571] Step 8:

[1572] Users can choose a restaurant to visit based on the displayed information, and after visiting, they can provide feedback through the app about the restaurant's rating and whether it accommodates dietary restrictions.

[1573] Step 9:

[1574] The device receives feedback information from the user and sends it to the server in JSON format.

[1575] Step 10:

[1576] The server receives the feedback information and stores it in a database. It then updates the restaurant's trustworthiness rating and dietary restrictions based on the collected feedback and sentiment data. The information stored in the database is used to improve the accuracy of search results the next time.

[1577] The above is a detailed explanation of the steps involved in the program's processing, which combines emotion engines. The operations of the server, terminal, and user at each step are described in detail.

[1578] Example 2

[1579] 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."

[1580] In today's world, it is difficult for people with dietary restrictions to enjoy eating out with peace of mind. Furthermore, it is also difficult for them to easily find an appropriate restaurant that matches their emotional state. The present invention aims to solve this problem by providing optimal restaurant information based on dietary restrictions and emotional state, thereby improving users' dining out experiences.

[1581] 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 conditions and location information from a user as input, means for generating a search query based on the dietary restriction conditions and location information, means for sending the search query to a generative AI model and receiving related restaurant information, means for filtering the received restaurant information based on the dietary restriction conditions and the user's emotional state, means for providing the filtered results to the user, means including an emotion recognition engine for acquiring emotion data of the user, and means for adjusting restaurant information based on the acquired emotion data. This makes it possible to provide restaurant information optimized for the user's dietary restriction conditions and emotional state.

[1582] "Dietary restriction conditions" are conditions that serve as criteria when a user selects a particular restaurant, such as restrictions on specific ingredients or calorie restrictions.

[1583] "Location information" refers to geographical data of the user's current location or a specified area, and is information used to select restaurants.

[1584] A "search query" is a query generated based on data such as dietary restrictions, location information, and emotional state, and is used to search for restaurant information.

[1585] A "generative AI model" is an artificial intelligence model that generates and provides the most relevant restaurant information based on a given search query.

[1586] An "emotion recognition engine" is software or hardware that analyzes a user's facial photograph and voice data to determine the user's current emotional state.

[1587] "Filtering" is the process of sorting received restaurant information based on dietary restrictions and emotional state, and extracting the most suitable information.

[1588] A "database" is an information management system that stores collected information such as feedback information and emotional data, and uses it for future searches and analyses.

[1589] "Feedback information" refers to information such as impressions and evaluations provided by users after visiting a restaurant, and is used to improve the accuracy of the system.

[1590] "Adjustment" refers to a process of changing the priority of the received restaurant information based on the acquired emotion data to provide the user with the most suitable information.

[1591] This invention provides a system that allows users to easily obtain optimal restaurant information based on their specific dietary restrictions and emotional state. The system is primarily composed of a user terminal, a server, and a generative AI model.

[1592] User operations

[1593] Users launch the application using a device such as a smartphone or tablet. First, they enter their dietary restrictions (e.g., "gluten-free" or "under 1500 kcal") and their current location (e.g., "Tokyo"). The emotion engine then automatically obtains the user's emotional state. This emotional state is determined by analyzing a facial photograph taken by the user and a recorded voice.

[1594] Device behavior

[1595] The device sends the dietary restrictions, location information, and acquired emotion data entered by the user to the server as a single request. The device displays the restaurant information received from the server on a map to provide a visual reference for the user. The device also sends feedback information provided by the user to the restaurants they visited to the server.

[1596] Server Operation

[1597] The server analyzes the dietary restrictions, location information, and emotion data received from the device and generates a search query. Specifically, it generates a query to search for "restaurants in Tokyo that are gluten-free, serve meals under 1500 kcal, and have a stress-reducing atmosphere." The server sends this query to a generative AI model (e.g., GPT) and receives relevant restaurant information.

[1598] The received restaurant information is filtered by the server. The filtering is performed based on dietary restrictions and emotional data. For example, if the user is feeling "stressed," restaurants with a relaxing atmosphere will be prioritized. The filtered restaurant information is returned to the terminal and provided to the user.

[1599] In addition, the server stores feedback information and emotional data provided by users in a database. This database is used to update restaurant reliability ratings and dietary restrictions, helping to improve recommendation accuracy in future visits.

[1600] Specific examples

[1601] Below are specific operating procedures and examples of prompts.

[1602] 1. User Actions:

[1603] Users open the app and enter dietary restrictions such as "gluten-free," "under 1500 kcal," and "Tokyo."

[1604] The emotion engine analyzes the user's facial photo and recognizes the emotion as "stress."

[1605] 2. Device behavior:

[1606] The device sends the condition and emotion data to the server.

[1607] 3. Server Operation:

[1608] The server generates a query such as "Find a restaurant in Tokyo that is gluten-free, under 1500 kcal, and has a stress-reducing atmosphere" and sends it to the generative AI model.

[1609] A generative AI model (e.g., GPT) returns the relevant restaurant information.

[1610] The server filters the information and sends it back to the device.

[1611] 4. Display and Feedback:

[1612] The terminal displays filtered restaurant information on a map and provides it to the user.

[1613] After the user visits, feedback information is sent from the terminal to the server.

[1614] Prompt Sentence Examples

[1615] "Please tell me restaurants in Tokyo that offer gluten-free meals under 1500 kcal in a stress-relieving atmosphere."

[1616] This invention efficiently provides restaurant information optimized for the user's dietary restrictions and emotional state, resulting in a more satisfying dining out experience.

[1617] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1618] Step 1:

[1619] User input:

[1620] The user opens the application on their smartphone and enters their current location and dietary restrictions, such as "gluten-free," "under 1500 kcal," and "Tokyo," into the application interface. They then press the "Emotion Input" button to capture a photo of their face and their voice.

[1621] Input: dietary restrictions, location information, face photo or voice

[1622] Output: User condition and emotion data

[1623] Step 2:

[1624] Obtaining emotion data:

[1625] The device sends the captured facial photo and voice data to an emotion recognition engine, which analyzes them and determines the user's emotional state (e.g., "stress").

[1626] Input: Face photo or voice data

[1627] Output: Emotion recognition result (e.g. "Stress")

[1628] Step 3:

[1629] Data transmission:

[1630] The device sends the dietary restriction conditions, location information, and emotion recognition results as a single request to the server.

[1631] Input: dietary restriction conditions, location information, emotion recognition results

[1632] Output: Request to server

[1633] Step 4:

[1634] Generating a search query:

[1635] The server analyzes the received data and generates a search query, specifically, a query to find "restaurants in Tokyo that serve gluten-free meals under 1500 kcal and have a stress-reducing atmosphere."

[1636] Input: dietary restriction conditions, location information, emotion recognition results

[1637] Output: The search query

[1638] Step 5:

[1639] Querying a generative AI model:

[1640] The server sends the generated query to a generative AI model (e.g., GPT), which generates relevant restaurant information based on the query and returns it to the server.

[1641] Input: Search query

[1642] Output: Related restaurant information

[1643] Step 6:

[1644] Filter restaurant information:

[1645] The server then filters the received restaurant information based on dietary restrictions and emotion recognition results. For example, it prioritizes restaurants with a high rating for "stress-reducing atmosphere."

[1646] Input: Related restaurant information, dietary restrictions, emotion recognition results

[1647] Output: Filtered restaurant information

[1648] Step 7:

[1649] Sending adjustment results:

[1650] The server sends the filtered restaurant information to the device, which then plots the received information on a map using a map API (e.g., Google Maps) and provides it to the user in a visually easy-to-understand format.

[1651] Input: Filtered restaurant information

[1652] Output: Response to the terminal

[1653] Step 8:

[1654] Enter your feedback:

[1655] After visiting a restaurant, users can enter their impressions and ratings on the feedback screen. For example, they can add comments such as "The food was delicious" or "The atmosphere was relaxing."

[1656] Input: Feedback information

[1657] Output: Feedback data

[1658] Step 9:

[1659] Send feedback information:

[1660] The device sends feedback information to the server, which stores it in a database and uses it to improve the accuracy of future query generation and filtering.

[1661] Input: Feedback data

[1662] Output: Stored in a database

[1663] (Application example 2)

[1664] 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."

[1665] Conventional restaurant search systems can provide restaurant information based on a user's dietary restrictions, but they cannot provide restaurant information that takes into account the user's emotional state. This makes it difficult for users to find the best restaurant when they are in a specific emotional state. In particular, for users who are feeling stressed or tired, the system cannot suggest restaurants with a high relaxation effect, which leads to a problem of reduced user satisfaction.

[1666] 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 conditions and location information from a user as input, means for generating a search query based on the dietary restriction conditions and location information, means for sending the search query to a generative model and receiving related restaurant information, means for filtering the received restaurant information based on the dietary restriction conditions, means for providing the filtered results to the user, means for recognizing the user's emotional state, and means for prioritizing and adjusting the received restaurant information based on the emotional state. This makes it possible to provide optimal restaurant information according to the user's emotional state.

[1667] "Dietary restrictions" refer to conditions that require avoiding certain ingredients or nutrients due to allergies, calorie restrictions, religious reasons, etc.

[1668] "Location information" refers to geographic data about a user's current location or a location they specify.

[1669] A "search query" is a search command generated based on criteria entered by the user.

[1670] A "generative model" is an artificial intelligence model that generates relevant information based on an input search query.

[1671] "Restaurant information" refers to data about the type of restaurant, its location, the menu it offers, etc.

[1672] "Filtering" is the process of selecting and extracting data based on specific conditions.

[1673] "User" refers to a person who uses this system to search for restaurant information that meets dietary restrictions.

[1674] "Emotional state" refers to the user's psychological and emotional state as recognized from facial expressions, voice, etc.

[1675] "Prioritization" is the process of assigning importance to information based on the user's emotional state.

[1676] "Delivery" refers to a service that delivers ordered food and drinks to a specified location.

[1677] The system for implementing this invention is mainly composed of a user terminal and a server. The user terminal and the server work together via a communication line to provide the information requested by the user. Each element of the system is described in detail below.

[1678] System Configuration

[1679] User Operation

[1680] Users operate the application using a user device such as a smartphone. After opening the application, the user enters dietary restrictions (e.g., "gluten-free") and location information (e.g., "Tokyo"). The application also has an emotion recognition function that can capture the user's emotional state using a camera and microphone. To analyze the user's emotional state from facial expressions and voice, the application uses emotion recognition services such as Microsoft's Azure Emotion API.

[1681] Device behavior

[1682] The user device receives the dietary restrictions, location information, and emotion data entered by the user. This data is sent to the server. The results returned from the server are displayed on a map, providing the user with a visually easy-to-understand format. The system also collects the user's feedback information and emotion data, which are sent to the server to update the database.

[1683] Server Operation

[1684] The server analyzes the dietary restrictions, location information, and emotional data received from the user device and generates an appropriate search query. This search query is sent to a generative AI model (e.g., GPT-4) to receive relevant restaurant information. The received restaurant information is filtered based on the dietary restrictions and further prioritized based on the user's emotional state. For example, if the user is feeling stressed, restaurants with a high relaxation effect will be prioritized. The final restaurant list is returned to the user device and displayed in the user's application.

[1685] The server periodically collects feedback information and emotional data and updates the database to improve restaurant reliability ratings and dietary restrictions.

[1686] Specific examples

[1687] The user opens the app and enters search criteria such as "gluten-free" and "Tokyo." At the same time, the emotion engine analyzes the user's facial photo and recognizes that the user is feeling "stressed." The device then sends these criteria and emotion data to the server. Based on the criteria and emotion data, the server generates a search query such as "Find restaurants in Tokyo that offer gluten-free menus and have a stress-reducing atmosphere," and sends it to a generative model (GPT-4). The generative model returns relevant restaurant information, and the server creates a list prioritizing restaurants with a high stress-reducing rating. Finally, the filtered results are displayed on the user's device.

[1688] Prompt Sentence Examples

[1689] "Please tell me restaurants in Tokyo that offer gluten-free menus and have a great relaxation effect."

[1690] In this way, the present invention provides optimal restaurant information based on dietary restrictions and emotional state, thereby realizing a system that can increase user satisfaction.

[1691] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1692] Step 1:

[1693] The user launches the application using a device such as a smartphone. A screen appears where the user can enter their dietary restrictions (e.g., "gluten-free") and current location (e.g., "Tokyo"). The entered information is temporarily stored in the device's internal memory.

[1694] Step 2:

[1695] The device uses camera and microphone sensors to recognize the user's emotional state. Specifically, it takes a photo of the user's face or records their voice, and sends this to Microsoft's Azure Emotion API. It then receives emotion data (e.g., "stress") returned from the API. The input is the face photo or voice data, and the output is emotion data.

[1696] Step 3:

[1697] The device sends the acquired dietary restriction conditions, current location information, and emotion data to the server. Specifically, it sends them as an HTTP request. The input is the dietary restriction conditions, current location information, and emotion data, and the output is the transmission of an HTTP request.

[1698] Step 4:

[1699] The server analyzes the dietary restrictions, current location information, and emotion data received from the device and generates a search query. The generated search query may be in the form of, for example, "Find restaurants in Tokyo that offer gluten-free menus and have stress-reducing effects." The inputs are dietary restrictions, current location information, and emotion data, and the output is the generated search query.

[1700] Step 5:

[1701] The server sends the generated search query to a generative AI model (e.g., GPT-4) and receives related restaurant information. The generative AI model returns restaurant information in response to the search query. The input is the search query, and the output is related restaurant information.

[1702] Step 6:

[1703] The server filters the received restaurant information based on the dietary restrictions. As a result of the filtering, only matching restaurant information is extracted. The input is restaurant information and dietary restrictions, and the output is the filtered restaurant information.

[1704] Step 7:

[1705] The server prioritizes and adjusts the filtered restaurant information based on the user's emotional state. For example, if the user is feeling stressed, restaurants with a high relaxation effect are prioritized. The input is the filtered restaurant information and emotional data, and the output is prioritized restaurant information.

[1706] Step 8:

[1707] The server returns the prioritized restaurant information to the terminal and provides it to the user. The terminal displays the received restaurant information on a map and provides it to the user in a visually easy-to-understand format. The input is the prioritized restaurant information, and the output is the restaurant information displayed on the map.

[1708] Step 9:

[1709] The user makes a selection based on the displayed restaurant information and provides feedback information after visiting. The feedback information is sent from the terminal to the server. The input is the feedback information, and the output is the transmission to the server.

[1710] Step 10:

[1711] The server stores the received feedback information and emotion data in a database. The server uses the feedback information to update the restaurant's trustworthiness rating and dietary restriction compliance status. The input is the feedback information and emotion data, and the output is the updated database.

[1712] In this way, the system can provide optimal restaurant information based on dietary restrictions and emotional state, increasing user satisfaction.

[1713] 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.

[1714] 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.

[1715] 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.

[1716] 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.

[1717] 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.

[1718] 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.

[1719] 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).

[1720] 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.

[1721] 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."

[1722] 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.

[1723] 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).

[1724] 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.

[1725] 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.

[1726] 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.

[1727] 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.

[1728] 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.

[1729] 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.

[1730] 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.

[1731] 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.

[1732] 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.

[1733] 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.

[1734] The following is further disclosed regarding the above embodiment.

[1735] (Claim 1)

[1736] means for receiving dietary restriction conditions and location information as input from a user;

[1737] means for generating a search query based on the dietary restrictions and location information;

[1738] means for transmitting the search query to a generative model and receiving related restaurant information;

[1739] a means for filtering the received restaurant information based on the dietary restriction conditions;

[1740] means for providing the filtered results to a user;

[1741] A system including:

[1742] (Claim 2)

[1743] A means for collecting feedback information provided by users and storing it in a database;

[1744] a means for updating the reliability evaluation and dietary restriction compliance status of restaurants using the database;

[1745] The system of claim 1 further comprising:

[1746] (Claim 3)

[1747] a means for displaying the received restaurant information on a map and providing it in a selectable form;

[1748] a means for displaying detailed information about the selected restaurant;

[1749] The system of claim 1 further comprising:

[1750] "Example 1"

[1751] (Claim 1)

[1752] means for receiving dietary restriction conditions and location information as input from a user;

[1753] means for generating a search query based on the dietary restrictions and location information;

[1754] A means for transmitting the search query to a generation AI model for generating the search query and receiving related restaurant information;

[1755] a means for filtering the received restaurant information based on the dietary restriction conditions;

[1756] means for providing the filtered results to a user;

[1757] A system including:

[1758] (Claim 2)

[1759] A means for collecting feedback information provided by users and storing it in a database;

[1760] a means for updating the reliability evaluation and dietary restriction compliance status of restaurants using the database;

[1761] The system of claim 1 further comprising:

[1762] (Claim 3)

[1763] a means for displaying the received restaurant information on a map and providing it in a selectable form;

[1764] a means for displaying detailed information about the selected restaurant;

[1765] The system of claim 1 further comprising:

[1766] "Application Example 1"

[1767] (Claim 1)

[1768] means for receiving dietary restriction conditions and location information as input from a user;

[1769] means for generating a search query based on the dietary restrictions and location information;

[1770] means for transmitting the search query to a generative model and receiving related restaurant information;

[1771] a means for filtering the received restaurant information based on the dietary restriction conditions;

[1772] a means for providing the filtered results to a user and placing an order with the selected restaurant;

[1773] A system including:

[1774] (Claim 2)

[1775] A means for collecting feedback information provided by users and storing and updating the information in a database;

[1776] a means for updating the reliability evaluation and dietary restriction compliance status of restaurants using the database;

[1777] 10. The system of claim 1, comprising:

[1778] (Claim 3)

[1779] a means for displaying the received restaurant information on a map;

[1780] means for providing detailed information about and placing an order for the selected restaurant;

[1781] 10. The system of claim 1, comprising:

[1782] "Example 2: Combining Emotion Engines"

[1783] (Claim 1)

[1784] means for receiving dietary restriction conditions and location information as input from a user;

[1785] means for generating a search query based on the dietary restrictions and location information;

[1786] A means for transmitting the search query to a generative AI model and receiving related restaurant information;

[1787] a means for filtering the received restaurant information based on the dietary restriction conditions and the emotional state of the user;

[1788] means for providing the filtered results to a user;

[1789] means including an emotion recognition engine for acquiring emotion data of the user;

[1790] a means for adjusting restaurant information based on the acquired emotion data;

[1791] A system including:

[1792] (Claim 2)

[1793] a means for collecting feedback information and emotion data provided by users and storing them in a database;

[1794] a means for updating the reliability evaluation and dietary restriction compliance status of restaurants using the database;

[1795] A means for improving the accuracy of restaurant recommendations from next time onwards based on the database;

[1796] The system of claim 1 further comprising:

[1797] (Claim 3)

[1798] a means for displaying the received restaurant information on a map and providing it in a selectable form;

[1799] a means for displaying detailed information about the selected restaurant;

[1800] a means for displaying restaurant recommendation results based on the emotion data;

[1801] The system of claim 1 further comprising:

[1802] "Application example 2 when combining emotion engines"

[1803] (Claim 1)

[1804] means for receiving dietary restriction conditions and location information as input from a user;

[1805] means for generating a search query based on the dietary restrictions and location information;

[1806] means for transmitting the search query to a generative model and receiving related restaurant information;

[1807] a means for filtering the received restaurant information based on the dietary restriction conditions;

[1808] means for providing the filtered results to a user;

[1809] a means for recognizing the emotional state of a user;

[1810] A means for prioritizing and adjusting the received restaurant information based on the emotional state;

[1811] A system including:

[1812] (Claim 2)

[1813] A means for collecting feedback information provided by users and storing it in a database;

[1814] a means for updating the reliability evaluation and dietary restriction compliance status of restaurants using the database;

[1815] The system of claim 1 further comprising:

[1816] (Claim 3)

[1817] a means for displaying the received restaurant information on a map and providing it in a selectable form;

[1818] a means for displaying detailed information about the selected restaurant;

[1819] means for displaying a menu reflecting dietary restrictions and emotional state;

[1820] The system of claim 1 further comprising: [Explanation of symbols]

[1821] 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 conditions and location information as input from a user; means for generating a search query based on the dietary restrictions and location information; means for transmitting the search query to a generative model and receiving related restaurant information; a means for filtering the received restaurant information based on the dietary restriction conditions; means for providing the filtered results to a user; A system including:

2. A means for collecting feedback information provided by users and storing it in a database; a means for updating the reliability evaluation and dietary restriction compliance status of restaurants using the database; The system of claim 1 further comprising:

3. a means for displaying the received restaurant information on a map and providing it in a selectable form; a means for displaying detailed information about the selected restaurant; The system of claim 1 further comprising:

Images