system

Abstract

Provide a system. A means for a user to input meal information; A server means for receiving and analyzing the meal information; A means for comparing the analyzed nutrient data with a standard intake amount and calculating nutrient deficiency or excess; A means for recommending restaurants to supplement the nutrient deficiency and excess; means for notifying a user of the recommended restaurant information; A system including:

Description

[Technical Field]

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

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

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

[0004] In today's busy lifestyles, it is difficult to easily understand specific nutrient deficiencies and excesses from individual meals and maintain a healthy diet. In particular, when meals tend to be unbalanced in nutrition, there is a need for a system that suggests specific actions to correct this. [Means for solving the problem]

[0005] The present invention solves the above problem by providing a system that includes a means for a user to input meal information, a server means for receiving and analyzing the meal information, a means for comparing the analyzed nutrient data with standard intake amounts and calculating nutrient deficiencies or excesses, a means for recommending restaurants to compensate for the nutrient deficiencies or excesses, and a means for notifying the user of information about the recommended restaurants.

[0006] In particular, by using natural language processing technology to analyze dietary information, the system can extract nutrient data more accurately and, by taking into account the user's age and gender when comparing it with standard intake amounts, propose an individually optimized nutritional balance. The server also recommends restaurants suitable for relieving nutrient deficiencies and notifies the user of this information. This allows users to easily understand their own nutritional balance and take specific actions to supplement the necessary nutrients.

[0007] "User" refers to an individual who uses this system to input their own dietary information and receive nutrient analysis results and recommendation information.

[0008] "Meal information" refers to information input by the user regarding ingredients, dishes, meal contents, and amounts.

[0009] "Server" refers to a computer system that has the function of receiving and analyzing dietary information sent by users, calculating nutrient deficiencies and excesses, and recommending appropriate restaurants.

[0010] "Nutrient data" refers to information about the amounts of specific nutritional elements such as carbohydrates, proteins, and vitamins extracted by the server based on dietary information.

[0011] "Standard intake" refers to the amount of nutrients needed per day based on the user's age, gender, weight, etc.

[0012] "Excess / deficiency" refers to information that indicates the difference between the amount of nutrients taken by the user and the standard intake amount, and indicates whether there is a deficiency or excess.

[0013] "Natural language processing technology" refers to technology that allows the server to analyze text data entered by the user, understand its meaning, and extract appropriate nutrient data.

[0014] "Recommendation" refers to information that the server suggests to the user based on the analysis results to achieve a specific goal.

[0015] "Restaurant information" refers to information about the recommended restaurant, such as its name, location, and the food it serves.

[0016] "Notification" refers to the server sending recommendation information to the terminal and presenting that information to the user. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The system according to the present invention allows a user to input their own dietary information, analyzes the information, calculates nutrient deficiencies and excesses, and recommends appropriate restaurants. Specific embodiments are described in detail below.

[0039] First, the user inputs information about their most recent meal into the device. For example, the user enters specific details of their meal into a text box, such as "I had toast and eggs for breakfast, and salad and chicken for lunch." After inputting the details, the user presses the send button to send the meal information to the server.

[0040] The device then converts the user's input data into JSON format and sends it as an HTTP request to the server, which receives the request at an API endpoint, parses the data, and prepares it for analysis.

[0041] The server analyzes the received meal information and extracts key nutrient data. This is done using natural language processing technology. The server analyzes the meal contents and extracts key nutrients from each ingredient and dish. For example, carbohydrates and protein are extracted from "toast and eggs," and vitamin C and protein are extracted from "salad and chicken."

[0042] Once the analysis is complete, the server compares the extracted nutrient data with the standard intake amount to calculate whether there is a nutrient deficiency or excess. The standard intake amount is set based on the user's age, gender, weight, etc. The comparison results in a determination of which nutrients are deficient and which are in excess.

[0043] The server then recommends restaurants that can help fill any nutrient gaps. For example, if you're deficient in vitamin D, it will recommend restaurants that serve fish or mushroom dishes. The server also includes information such as the name and location of each restaurant, as well as the dishes they serve.

[0044] Finally, the server notifies the user of the recommended restaurant information. The server sends the recommended restaurant information to the terminal, which then displays the information to the user. This allows the user to easily know which restaurants they should visit to improve their nutritional balance.

[0045] For example, the display may say, "We recommend nearby seafood restaurant A to supplement your vitamin D." In this way, by using the system of the present invention, users can easily adjust the nutrients they need to maintain a healthy diet.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] The user enters meal information. The user enters meal details into the text box on the device, for example, "I had toast and eggs for breakfast, and salad and chicken for lunch," and presses the send button.

[0049] Step 2:

[0050] The terminal sends the input data to the server. The terminal converts the user's input data into JSON format and sends it to the server as an HTTP request.

[0051] Step 3:

[0052] The server receives the input data. The server receives the HTTP request at the API endpoint and parses the JSON data to prepare it for analysis.

[0053] Step 4:

[0054] The server analyzes the meal information. It uses natural language processing technology to extract key nutrient data from each part of the meal. For example, it extracts carbohydrates from "toast," proteins from "eggs," and vitamins from "salad."

[0055] Step 5:

[0056] The server compares the nutrient data with the standard intake amount. The server refers to a database of standard intake amounts based on the user's age, sex, and weight, and compares the extracted nutrient data to calculate whether there is a surplus or deficiency.

[0057] Step 6:

[0058] The server calculates the nutrient deficiency or excess, and determines whether each nutrient is deficient or excessive based on the comparison results.

[0059] Step 7:

[0060] The server recommends restaurants. Based on the nutrient deficiency data, the server extracts and lists restaurants from the database that can provide the nutrients you are lacking. For example, if you are deficient in vitamin D, it will find restaurants that serve fish dishes.

[0061] Step 8:

[0062] The server sends the recommendation information to the device. Information about the recommended restaurants is generated in JSON format and sent to the device as an HTTP response.

[0063] Step 9:

[0064] The device displays the recommended information to the user. The device receives the response from the server, parses it, and displays it on the screen. The user can refer to this information to choose an appropriate restaurant to eat at.

[0065] Through this series of processes, users can easily understand their own nutritional balance and obtain specific dietary options to supplement their necessary nutrients.

[0066] Example 1

[0067] 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."

[0068] In conventional systems, even if users input their dietary information, the information could not be analyzed efficiently and accurately, and sufficient advice on maintaining a proper nutritional balance could not be provided. As a result, users had difficulty understanding their own nutrient deficiencies and excesses, and were unable to make appropriate dietary choices. Furthermore, if a user was lacking in a particular nutrient, it was difficult to find an appropriate restaurant to supplement that nutrient.

[0069] 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.

[0070] In this invention, the server includes a means for a user to input dietary information, a means for converting the dietary information into JSON format and sending it to the server as an HTTP request, a server means for receiving the HTTP request and analyzing the data, a means for comparing the analyzed nutrient data with standard intake amounts and calculating nutrient deficiencies, a means for recommending restaurants that can compensate for the nutrient deficiencies, and a means for notifying the user of the recommended restaurants. This allows users to easily input their dietary information and accurately determine whether they are nutrient deficient or not based on that information. Furthermore, users can quickly find appropriate restaurants to compensate for nutrient deficiencies, allowing them to take specific actions to maintain a healthy diet.

[0071] A "user" is a person who uses the system to input dietary information and receives nutrient analysis results and recommendation information.

[0072] "Dietary information" is details of the meal the user has most recently eaten, and is entered into a text box and sent.

[0073] A "terminal" is a device used by a user to input meal information and communicate with the server, and includes smartphones, tablets, PCs, etc.

[0074] "JSON format" is a data format used to send meal information to a server as structured data.

[0075] An "HTTP request" is a communication protocol for sending data from a terminal to a server.

[0076] A "server" is a device that analyzes dietary information received from a user, extracts nutrient data, and returns recommended information to the user.

[0077] "Natural language processing technology" is a technology used to extract nutrient data from dietary information and analyzes text data.

[0078] "Nutrient data" is information on various nutritional components extracted from dietary content.

[0079] The "standard intake" is the amount of nutrients required daily, set based on the user's age, sex, weight, etc.

[0080] A "restaurant" is a place that serves food and drinks, and is a recommended store to help users meet their nutritional needs.

[0081] "Recommendation" refers to the act of recommending appropriate restaurants to help the user meet their nutritional needs.

[0082] "Recommendation information" is detailed information about suitable restaurants that can help users make up for nutrient deficiencies and excesses, sent from the server to the user.

[0083] "Notification" refers to the act of conveying important information, such as recommendation information, to the user via the device.

[0084] The system according to the present invention allows a user to input their own dietary information, analyzes the information, calculates nutrient deficiencies and excesses, and recommends appropriate restaurants. Specific embodiments are described in detail below.

[0085] First, the user inputs the most recent meal information into the device. For example, the user enters specific meal details such as "I had toast and eggs for breakfast, and salad and chicken for lunch" into the text box on the device, and then presses the send button to send the meal information to the server.

[0086] The terminal converts the input data into JSON format. For example, it converts the text data "I had toast and eggs for breakfast, and salad and chicken for lunch" into JSON data { "breakfast": "toast and eggs", "lunch": "salad and chicken"}. The converted data is sent to the server as an HTTP request.

[0087] The server receives HTTP requests at the API endpoint, parses the received JSON data, and prepares it for analysis. Natural language processing techniques (e.g., spaCy, NLTK, Transformers) are used to extract key nutrient data from the meal contents. For example, carbohydrates and protein are extracted from "toast and eggs," and vitamin C and protein are extracted from "salad and chicken."

[0088] The server then compares the extracted nutrient data with the standard intake based on the user's profile information, such as age, gender, and weight. This comparison calculates whether each nutrient is in a deficiency or excess. For example, a 30-year-old man may be found to have sufficient carbohydrates but a vitamin D deficiency.

[0089] The server then recommends appropriate restaurants based on the nutrient deficiency or excess. For example, if a person is deficient in vitamin D, it searches the database for restaurants that serve fish or mushroom dishes, and lists information such as the specific restaurant's name, location, and the dishes they serve.

[0090] Finally, the server sends the recommendation information to the device, which then displays the received information to the user, notifying them of the specific recommendation, "We recommend a nearby seafood restaurant to supplement your vitamin D intake." This allows the user to immediately take action to efficiently adjust their nutritional balance.

[0091] Specific examples

[0092] For example, a user enters the following prompt into the system:

[0093] "I had toast and eggs for breakfast and salad and chicken for lunch. Please calculate my nutritional surplus and deficiency and recommend restaurants that are good for me."

[0094] The system responds with the following:

[0095] "I recommend a nearby seafood restaurant to get some Vitamin D."

[0096] By using this system, users can easily manage their own dietary information and take quick action to maintain proper nutritional balance.

[0097] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0098] Step 1:

[0099] The user inputs meal information into the terminal.

[0100] Input: Specific meal details (e.g., "I had toast and eggs for breakfast and salad and chicken for lunch.")

[0101] Action: Enter this information into a text box in the terminal application.

[0102] Output: The input text data

[0103] Step 2:

[0104] The user presses the send button.

[0105] Input: Text data (meal information)

[0106] Processing: Detects that the submit button has been pressed and passes the entered data to the next processing step.

[0107] Output: Text data (prepared for transmission)

[0108] Step 3:

[0109] The device converts the meal information into JSON format.

[0110] Input: Text data (meal information)

[0111] Processing: Use a conversion function to convert text data into JSON format (e.g., {"breakfast": "toast and eggs", "lunch": "salad and chicken"}).

[0112] Output: JSON data

[0113] Step 4:

[0114] The device generates an HTTP request and sends it to the server.

[0115] Input: JSON data

[0116] Processing: Generate an HTTP request and send it to the server's API endpoint, including the JSON data.

[0117] Output: HTTP request (including JSON data)

[0118] Step 5:

[0119] The server receives the HTTP request and prepares to parse the data.

[0120] Input: HTTP request (including JSON data)

[0121] Processing: Receive the request and parse the JSON data.

[0122] Output: Parsed meal information data

[0123] Step 6:

[0124] The server uses natural language processing technology to analyze the dietary information and extract nutrient data.

[0125] Input: Parsed meal information data

[0126] Processing: Using natural language processing libraries (e.g., spaCy, NLTK), extract nutrients from meal descriptions (e.g., extract carbohydrates and protein from "toast and eggs," and vitamin C and protein from "salad and chicken").

[0127] Output: Extracted nutrient data (e.g. carbohydrates, protein, vitamin C)

[0128] Step 7:

[0129] The server compares the nutrient data with standard intakes and calculates nutrient surpluses and deficiencies.

[0130] Input: Extracted nutrient data, standard intake information (based on age, sex, and weight)

[0131] Processing: Nutrient data is compared to standard intakes based on user profile information to calculate deficiencies or excesses (e.g., enough carbohydrates but not enough vitamin D).

[0132] Output: Nutrient deficiency and excess data

[0133] Step 8:

[0134] The server will recommend restaurants that will help you make up for any nutrient deficiencies or excesses.

[0135] Input: Nutrient deficiency and excess data, restaurant information database

[0136] Processing: Search the database for appropriate restaurants based on the deficiency or surplus and create a list (e.g., if there is a vitamin D deficiency, recommend a seafood restaurant).

[0137] Output: Recommendation information (restaurant name, location, dishes served, etc.)

[0138] Step 9:

[0139] The server transmits the recommendation information to the terminal.

[0140] Input: Recommendation information

[0141] Processing: Generate data including recommendation information as an HTTP response and send it to the terminal.

[0142] Output: HTTP response (including recommendation information)

[0143] Step 10:

[0144] The device displays the recommended information to the user.

[0145] Input: HTTP response (including recommendation information)

[0146] Processing: Parse the received recommendation information and display it in a user-friendly format (e.g., "We recommend a nearby seafood restaurant to help you get your vitamin D.").

[0147] Output: Recommendation information displayed to the user (visual display)

[0148] (Application example 1)

[0149] 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."

[0150] Conventional nutrition management systems allow users to input their own dietary information and calculate nutrient deficiencies or excesses, but they lack the functionality to consistently support users, from specific meal suggestions based on the results to using food delivery services. This means that users have to go through the trouble of actually selecting and ordering meals, which reduces their ability to maintain a healthy diet.

[0151] 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.

[0152] In this invention, the server includes means for a user to input dietary information, means for receiving and analyzing the dietary information, means for comparing the analyzed nutrient data with standard intakes and calculating nutrient deficiencies and excesses, means for recommending restaurants that will compensate for the nutrient deficiencies and excesses, means for notifying the user of information on the recommended restaurants, means for placing an order with a food delivery service, and means for suggesting appropriate dishes to compensate for the nutrient deficiencies and excesses. This allows users to receive consistent support while receiving specific dietary suggestions for maintaining a healthy diet, and makes it easy to use food delivery services.

[0153] A "user" is a person who uses the system to input their own dietary information and receives analysis results and suggestions regarding nutrient deficiencies and excesses.

[0154] "Dietary information" is data in which the user specifically describes the contents of their own meals, including the names of ingredients and dishes and the amounts consumed.

[0155] The "server" is a computer system that receives and analyzes dietary information sent by a user and calculates deficiencies or excesses in nutrient data.

[0156] "Nutrient data" is information on the quantity and type of each nutrient extracted from dietary information.

[0157] The "standard intake amount" is a reference intake amount for a particular nutrient that is set based on the user's age, sex, weight, etc.

[0158] "Excess or deficiency" is the result of comparing the intake of each nutrient calculated based on the user's dietary information with the standard intake, and is information indicating whether there is an excess or deficiency.

[0159] "Restaurant" means an establishment established to provide meals, and the dishes offered therein are suitable for supplementing nutritional deficiencies or excesses.

[0160] "Recommendation" refers to the system selecting and suggesting appropriate restaurants and dishes based on the user's nutritional deficiencies or excesses.

[0161] A "food delivery service" is a service that allows users to order food from restaurants and have it delivered without having to move to another location.

[0162] An "appropriate meal" is a specific meal that is recommended to compensate for the user's nutritional deficiency or excess.

[0163] The present invention relates to a system that allows a user to input their own dietary information, analyzes the information, calculates nutrient deficiencies and excesses, and suggests appropriate restaurants and dishes.

[0164] System program generation

[0165] This system is realized by performing a complex process including the following means.

[0166] Hardware and Software

[0167] Hardware: Smartphone (iOS / ANDROID (registered trademark))

[0168] Software: A Python environment to run the application, an HTTP library (requests), a JSON library, and a natural language processing library (e.g., spaCy or NLTK).

[0169] Data processing and calculation

[0170] Data entry: The user enters meal information into the device in text format, for example, "toast and eggs for breakfast, salad and chicken for lunch."

[0171] Examples:

[0172] Enter your most recent meal (e.g., toast and eggs for breakfast, salad and chicken for lunch):

[0173] Data transmission: The device converts the entered meal information into JSON format and sends it to the server as an HTTP request. For example, it is sent to the server in the following format:

[0174] Sending example:

[0175] json

[0176] {

[0177] "meal_info": "Toast and eggs for breakfast, salad and chicken for lunch"

[0178] }

[0179] Data analysis: The server analyzes the received data and uses natural language processing techniques to extract key nutrient data, for example, carbohydrates and protein from "toast and eggs" and vitamin C and protein from "salad and chicken."

[0180] Nutrient deficiency / surplus calculation: The server compares the extracted nutrient data with the standard intake amount, which is set based on the user's age, gender, weight, etc. As a result of the comparison, the deficiency / surplus of each nutrient is calculated.

[0181] Recommendations: The server recommends restaurants and dishes to help you meet your nutritional needs. For example, if you are deficient in vitamin D, it will suggest restaurants that serve fish or mushroom dishes, or alternative dishes.

[0182] Notification and ordering: The server sends the recommendation results to the device and notifies the user, allowing the user to easily find out about the recommended restaurants and dishes, and also supporting the use of food delivery services.

[0183] Specific examples

[0184] For example, a user enters meal information as follows:

[0185] Enter your most recent meal (e.g., toast and eggs for breakfast, salad and chicken for lunch):

[0186] Once the input is complete, the device converts the dietary information into JSON format and sends it to the server. The server analyzes the data, calculates which nutrients the user is lacking, and suggests appropriate dishes based on the results. For example, if the user is deficient in vitamin D, the system:

[0187] To supplement your vitamin D intake, the recommended menu item at nearby seafood restaurant A is salmon steak.

[0188] Furthermore, by selecting the notification, you can easily use food delivery services.

[0189] In this way, users can receive consistent support, receive specific meal suggestions to maintain a healthy diet, and easily use food delivery services.

[0190] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0191] Step 1:

[0192] Users input meal information in text format using a device such as a smartphone. The input content is specific meal details such as "toast and eggs for breakfast, salad and chicken for lunch." This input information becomes the basis of the data.

[0193] input:

[0194] Toast and eggs for breakfast, salad and chicken for lunch

[0195] output:

[0196] Text-based meal information

[0197] Step 2:

[0198] The device converts the meal information entered by the user into JSON format and sends it to the server as an HTTP request. Specifically, the converted JSON data has the following format:

[0199] input:

[0200] Text-based meal information

[0201] Data processing:

[0202] {

[0203] "meal_info": "Toast and eggs for breakfast, salad and chicken for lunch"

[0204] }

[0205] output:

[0206] Meal information in JSON format

[0207] Step 3:

[0208] The server analyzes the received meal information. Specifically, it uses natural language processing technology to extract key nutrient data from the meal contents. For example, carbohydrates and protein are extracted from "toast and eggs," and vitamin C and protein are extracted from "salad and chicken."

[0209] input:

[0210] Meal information in JSON format

[0211] Data Calculation:

[0212] Libraries used: spaCy, NLTK

[0213] {

[0214] "carbohydrates": 30,

[0215] "protein": 20,

[0216] "vitaminC": 10

[0217] }

[0218] output:

[0219] Key Nutrient Data

[0220] Step 4:

[0221] The server compares the extracted nutrient data with the standard intake amount and calculates the nutrient deficiency or excess. The standard intake amount is set based on the user's age, gender, and weight information. The deficiency or excess is determined based on this data.

[0222] input:

[0223] Key Nutrient Data

[0224] Data Calculation:

[0225] Vitamin D: -5 (deficiency)

[0226] Protein: +10 (excess)

[0227] output:

[0228] Nutrient deficiency or excess

[0229] Step 5:

[0230] The server recommends restaurants and food delivery services that provide meals that can help fill nutrient gaps and deficiencies.

[0231] input:

[0232] Nutrient deficiency or excess

[0233] Data processing:

[0234] [

[0235] {

[0236] "restaurant_name": "Seafood Restaurant A",

[0237] "menu_item": "Salmon steak",

[0238] "nutrient": "vitamin D"

[0239] }

[0240] ]

[0241] output:

[0242] Recommended information

[0243] Step 6:

[0244] The server sends the recommendation information to the terminal, which then notifies the user. The user can then check the recommended restaurants and dishes and place an order using a food delivery service if necessary.

[0245] input:

[0246] Recommended information

[0247] Data processing:

[0248] To supplement your vitamin D intake, the recommended menu item at nearby seafood restaurant A is salmon steak.

[0249] output:

[0250] Recommendation information notified to the user

[0251] In this way, the entire system processes, providing users with consistent support and specific meal suggestions to maintain a healthy diet.

[0252] 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.

[0253] The system according to the present invention allows a user to input their own dietary information, analyzes the information to calculate nutrient deficiencies and excesses, and recommends suitable restaurants, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments are described in detail below.

[0254] First, the user inputs their most recent meal information into the device. For example, they enter specific details of their meal, such as "I had toast and eggs for breakfast, and salad and chicken for lunch," into the text box and press the send button. At that time, the emotion engine analyzes the user's facial expressions and tone of voice in real time to recognize their emotional state.

[0255] Next, the device converts the user's input data and the emotion data recognized by the emotion engine into JSON format and sends it as an HTTP request to the server. The server receives this request at an API endpoint, parses the data, and prepares it for analysis.

[0256] The server analyzes the received meal information and extracts key nutrient data. This is done using natural language processing technology. The server analyzes the meal contents and extracts key nutrients from each ingredient and dish. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[0257] Once the analysis is complete, the server compares the extracted nutrient data with the standard intake amount to calculate whether there is a nutrient deficiency or excess. The standard intake amount is set based on the user's age, gender, weight, etc. The comparison results in a determination of which nutrients are deficient and which are in excess.

[0258] The server then recommends restaurants that can help replenish the user's nutritional needs. This recommendation also takes into account the user's emotional data. For example, if the user is feeling stressed, the server will recommend restaurants with a relaxing environment.

[0259] The recommendation routine based on emotion data works as follows: The server creates a list of restaurant candidates based on nutrient deficiency data, and then selects the restaurant that best suits the user's emotional state. Specifically, it recommends restaurants that offer relaxing ingredients and restaurants with a calming atmosphere.

[0260] The recommendation results are generated in JSON format and sent to the device as an HTTP response. The device receives the response from the server, parses it, and displays it on the screen. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[0261] For example, the display might say, "To supplement your vitamin D, we recommend nearby seafood restaurant A." This restaurant is selected based on the user's emotional state. If the emotion engine recognizes that the user is feeling stressed, it will select a restaurant that offers a relaxing restaurant environment and a menu suitable for changing the mood.

[0262] In this way, by using the system of the present invention, users can easily understand their own nutritional balance and select an appropriate eating environment according to their emotional state.

[0263] The processing flow will be explained below.

[0264] Step 1:

[0265] The user inputs meal information. The user enters meal details into the device's text box, for example, "I had toast and eggs for breakfast, and salad and chicken for lunch," and presses the send button. The emotion engine also analyzes the user's facial expressions and tone of voice in real time to recognize the user's emotional state.

[0266] Step 2:

[0267] The device sends the input data and emotion data to the server. The device converts the user's meal information and the emotion data recognized by the emotion engine into JSON format and sends it to the server as an HTTP request.

[0268] Step 3:

[0269] The server receives the input data and emotion data. The server receives the HTTP request at the API endpoint, parses the JSON data, and prepares it for analysis.

[0270] Step 4:

[0271] The server analyzes the meal information. It uses natural language processing technology to extract key nutrient data from each part of the meal. For example, it extracts carbohydrates from "toast," proteins from "eggs," and vitamins from "salad."

[0272] Step 5:

[0273] The server compares the nutrient data with the standard intake amount. The server refers to a database of standard intake amounts based on the user's age, sex, and weight, and compares the extracted nutrient data to calculate whether there is a surplus or deficiency.

[0274] Step 6:

[0275] The server calculates the nutrient deficiency or excess, and determines whether each nutrient is deficient or excessive based on the comparison results.

[0276] Step 7:

[0277] The server recommends restaurants. Based on the nutrient deficiency data, the server extracts and lists restaurants from the database that can provide the missing nutrients. This recommendation also takes into account the user's recognized emotional data. For example, if the user is feeling stressed, the server will recommend restaurants with a relaxing environment.

[0278] Step 8:

[0279] The server sends the recommendation information to the device. Information about the recommended restaurants is generated in JSON format and sent to the device as an HTTP response.

[0280] Step 9:

[0281] The device displays the recommended information to the user. The device receives the response from the server, parses the data, and displays it on the screen. The user can refer to this information to choose an appropriate restaurant. For example, the device may display, "To supplement your vitamin D, we recommend nearby seafood restaurant A." This restaurant is selected based on the user's emotional state, offering a relaxing restaurant environment and a menu suitable for a change of pace.

[0282] Example 2

[0283] 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."

[0284] Conventional nutrient analysis and restaurant recommendation systems recommend restaurants simply based on nutrient data without taking the user's emotional state into consideration, which means that they are unable to make recommendations that are appropriate for the user's emotional state, and this does not lead to increased satisfaction or stress reduction.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0286] In this invention, the server includes means for receiving and analyzing input dietary information and user emotional information, means for comparing the analyzed nutrient data with standard intake amounts to calculate nutrient deficiencies and excesses, and means for recommending restaurants that will compensate for nutrient deficiencies and excesses, taking into account the user's emotional state. This makes it possible to recommend optimal restaurants that match the user's emotional state.

[0287] A "user" is a person who uses the system to input their own dietary information and receive the analysis results.

[0288] "Dietary information" is text data entered by a user about the contents of their meal, such as "I had toast and eggs for breakfast."

[0289] "Emotion information" is emotion data obtained from the user's facial expression and tone of voice, and indicates psychological states such as stress and happiness, for example.

[0290] The "server" is a computer system that receives dietary information and emotional information sent by users, analyzes it, calculates nutrient deficiencies and excesses, and recommends restaurants.

[0291] "Natural language processing technology" is a technology that allows computers to understand, interpret, and generate human language, and is used to extract nutritional data from dietary information.

[0292] "Nutrient data" refers to data on nutrients such as carbohydrates, proteins, and vitamins obtained by analyzing dietary information.

[0293] The "standard intake amount" is the appropriate daily intake amount of nutrients that is set based on the user's age, sex, weight, etc.

[0294] "Deficiency" refers to a state of deficiency or excess of a particular nutrient, determined when nutrient data is compared with standard intakes.

[0295] "Restaurant recommendation" refers to recommending restaurants suitable for the user, taking into consideration the user's nutritional deficiency and emotional state.

[0296] The "notification means" refers to a means for transmitting the recommendation results generated by the server to the user, and includes a method of displaying the results on the terminal.

[0297] MODE FOR CARRYING OUT THE INVENTION

[0298] The system according to the present invention allows a user to input their own dietary information, analyzes the information to calculate nutrient deficiencies and excesses, and recommends suitable restaurants, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments are described in detail below.

[0299] First, the user inputs information about their most recent meal into their device. For example, the user enters specific details of their meal into a text box, such as "I had toast and eggs for breakfast, and salad and chicken for lunch," and presses the send button. At this time, the emotion engine analyzes the user's facial expressions and tone of voice in real time to recognize the user's emotional state.

[0300] Next, the device converts the user's input data and the emotion data recognized by the emotion engine into JSON format and sends it as an HTTP request to the server. The server receives this request at an API endpoint, parses the data, and prepares it for analysis.

[0301] The server analyzes the received meal information and extracts major nutrient data. This analysis uses natural language processing technology. Specifically, it uses the Google® Cloud Natural Language API to analyze the meal contents and extract major nutrients from each ingredient and dish. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[0302] Once the analysis is complete, the server compares the extracted nutrient data with standard intakes based on the user's age, gender, and weight to determine whether the user is deficient in any nutrients. For example, the comparison may determine that the user is deficient in vitamin D.

[0303] The server then recommends restaurants that are suitable for replenishing the nutritional deficiency or excess. This recommendation also takes into account the user's emotional data. For example, if the user is feeling stressed, it will recommend restaurants with a relaxing environment. This recommendation routine lists restaurant candidates based on the nutrient deficiency or excess data, and selects from that list the restaurant that best suits the user's emotional state.

[0304] The recommendation results are generated in JSON format and sent to the device as an HTTP response. The device receives the response from the server, parses it, and displays it on the screen. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[0305] For example, if a user inputs "I had toast and eggs for breakfast and salad and chicken for lunch," and the emotion engine recognizes that the user is under stress, the server will present a recommendation such as "To supplement your vitamin D, we recommend nearby seafood restaurant A." Seafood restaurant A offers a relaxing restaurant environment and a menu suitable for reducing stress.

[0306] Below are some examples of specific prompts that are useful for using the system: "If a user has had toast and eggs for breakfast and salad and chicken for lunch and is feeling stressed, which restaurant would you recommend?" can be input into the generative AI model to obtain effective recommendations.

[0307] In this way, by using the system of the present invention, users can easily understand their own nutritional balance and select an appropriate eating environment according to their emotional state.

[0308] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0309] Step 1:

[0310] The user inputs his / her meal information into the terminal.

[0311] Input: A user enters a meal description into a text box, such as "I had toast and eggs for breakfast and salad and chicken for lunch."

[0312] Output: The terminal holds the input data.

[0313] Specific operation: The user enters meal information and presses the send button. The device collects the input data and begins processing.

[0314] Step 2:

[0315] The device analyzes the user's facial expressions and tone of voice in real time, and the emotion engine recognizes their emotional state.

[0316] Input: Data on the user's facial expressions and tone of voice from the device's camera and microphone.

[0317] Output: "Emotional state data" recognized by the emotion engine.

[0318] Specific operation: The device's camera captures the user's facial expressions, the microphone analyzes the tone of the voice, and sends them to the emotion engine to analyze the emotional state.

[0319] Step 3:

[0320] The device converts the meal information and emotional state data into JSON format and sends it to the server as an HTTP request.

[0321] Input: Food information text data and emotional state data.

[0322] Output: The HTTP request with the data converted to JSON format.

[0323] Specific operation: The device integrates the input data and emotion data, converts them into JSON format, generates an HTTP request, and sends it to the server.

[0324] Step 4:

[0325] The server receives the HTTP request and parses the JSON data, preparing it for analysis.

[0326] Input: The JSON data sent by the HTTP request.

[0327] Output: Data ready for analysis.

[0328] What happens: The server receives the HTTP request and converts the JSON data into a format that is easy to parse.

[0329] Step 5:

[0330] The server analyzes the dietary information using natural language processing technology and extracts key nutrient data.

[0331] Input: Parsed meal information data.

[0332] Output: Extracted macronutrient data.

[0333] How it works: The server uses natural language processing APIs to identify and extract nutrients from food information, for example, extracting carbohydrates from "toast" and protein from "eggs."

[0334] Step 6:

[0335] The server compares the nutrient data with standard intakes and calculates nutrient surpluses and deficiencies.

[0336] Input: Extracted nutrient data and standard intake data.

[0337] Output: Nutrient deficiency and excess data.

[0338] Specific operation: The server compares the nutrient data with the standard intake and determines whether there is a deficiency or excess, such as a vitamin D deficiency.

[0339] Step 7:

[0340] The server takes into account the user's emotional state and recommends appropriate restaurants to compensate for any nutrient deficiencies or excesses.

[0341] Input: Nutrient deficiency and excess data and emotional state data.

[0342] Output: Recommended restaurant information.

[0343] Specific operation: The server uses a recommendation algorithm to select restaurants that, for example, can help replenish vitamin D deficiency and reduce stress.

[0344] Step 8:

[0345] The server generates the recommendation results in JSON format and sends them to the terminal as an HTTP response.

[0346] Input: Recommended restaurant information.

[0347] Output: HTTP response in JSON format containing the recommendation results.

[0348] Specific operation: The server generates recommendation results in JSON format and sends them to the device as an HTTP response.

[0349] Step 9:

[0350] The device receives the HTTP response from the server, parses it, and displays it on the screen.

[0351] Input: HTTP response (JSON data) from the server.

[0352] Output: Recommendation results displayed on the screen.

[0353] Specific behavior: The device receives the HTTP response, parses the JSON data, and displays to the user, "To supplement your vitamin D, we recommend nearby seafood restaurant A."

[0354] Through these steps, users can receive restaurant recommendations that suit their nutritional balance and emotional state.

[0355] (Application example 2)

[0356] 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."

[0357] In modern society, it is important to consume a balanced diet to maintain good health. However, it is not easy to manage one's diet and consume the necessary nutrients in the right amounts in a busy daily life. Furthermore, it is difficult with conventional technologies to propose a meal plan that takes into account not only the deficiency or excess of individual nutrients but also the user's emotional state. The present invention aims to solve these problems and provide a system that allows users to enjoy meals that suit their emotional state while maintaining a healthy diet.

[0358] 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 the user to input dietary information, server means for receiving and analyzing the dietary information, means for comparing the analyzed nutrient data with standard intake amounts to calculate nutrient deficiency or excess, means for analyzing the user's emotional data, means for recommending restaurants based on the nutrient deficiency or excess and the emotional data, and means for notifying the user of the recommended restaurant information. This enables the user to easily manage their diet and find restaurants that provide an optimal dining environment that takes their emotional state into consideration.

[0359] "Dietary information" refers to information about ingredients and dishes consumed by the user, and is provided through text, voice, or other input means.

[0360] "Nutrient data" refers to information on major nutrients extracted from dietary information, and specifically includes carbohydrates, proteins, vitamins, etc. contained in each ingredient or dish.

[0361] "Emotion data" is information about the user's emotional state analyzed from facial expressions, tone of voice, etc., and includes states such as relaxation, stress, and anxiety.

[0362] "Recommendation" is the act of suggesting the most suitable restaurant based on the user's nutritional deficiency or excess and emotional data.

[0363] "Natural language processing technology" is a general term for technology that analyzes natural language data such as text and speech, and understands and extracts meaning.

[0364] A "standard intake" is a reference value that indicates the amount of each nutrient needed per day to maintain health, and is determined based on age, gender, weight, etc.

[0365] "Server means" refers to computer resources or programs for receiving and analyzing meal information and emotion data provided by the user.

[0366] The system embodying this invention allows users to input their own dietary information, analyzes it to calculate nutrient deficiencies and excesses, and recommends appropriate restaurants based on their emotional state, allowing users to maintain their health while enjoying meals that suit their emotional state.

[0367] First, the user inputs meal information using the smart glasses' voice recognition system. The voice recognition system converts the voice input into text data and sends the meal information to the device. For example, the user might say, "I had toast and eggs for breakfast, and salad and chicken for lunch," which is input as text data.

[0368] Next, emotion recognition is performed. The smart glasses' camera and microphone are used to analyze the user's facial expressions and tone of voice in real time to recognize their emotional state. For emotion recognition, the FER library is used to detect emotions such as joy, sadness, and stress from the user's facial expressions.

[0369] The obtained food information and emotion data are converted into JSON format and sent as an HTTP request to the server, which receives the request at its API endpoint, parses the data, and prepares it for analysis.

[0370] The server analyzes the received meal information and uses natural language processing (NLP) to extract key nutrient data. The analyzed nutrient data is compared with standard intakes based on the user's age, gender, and weight, and any nutrient surpluses or deficiencies are calculated. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[0371] After calculating the nutrient surplus / deficiency, the server recommends appropriate restaurants based on that information and emotional data. For example, if a user is feeling stressed, a recommendation algorithm based on emotional data will recommend restaurants with a relaxing environment. Specifically, the server creates a list of restaurant candidates based on the nutrient surplus / deficiency data, and then selects from that list the restaurant that best suits the user's emotional state.

[0372] The recommendation results are again generated in JSON format and sent to the device as an HTTP response. The device receives the response from the server, parses it, and displays it on the screen. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[0373] An example prompt is:

[0374] "Enter the user's dietary information, analyze the nutritional data, and output recommendations. The recommendations change depending on the user's emotional state."

[0375] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0376] Step 1:

[0377] The user inputs meal information using the smart glasses' voice recognition system. The voice input is converted into text data and sent to the device. For example, if the user says, "I had toast and eggs for breakfast, and salad and chicken for lunch," this information is converted into text using voice recognition technology. The input data is saved as "meal information."

[0378] Step 2:

[0379] The emotion recognition module uses the smart glasses' camera and microphone to analyze the user's facial expressions and tone of voice in real time to recognize their emotional state. The acquired emotional data is stored as "emotion data." For example, the FER library can be used to detect "stress" from the user's facial expressions.

[0380] Step 3:

[0381] The device converts the obtained food information and emotion data into JSON format and sends it to the server as an HTTP request. The input data is food information and emotion data, which are encoded as structured data.

[0382] Step 4:

[0383] The server receives HTTP requests at the API endpoint, parses the data, and prepares it for analysis. The server then sends the parsed data to the analysis module. The input data is food information and emotion data in JSON format, which is then converted into an analyzable format.

[0384] Step 5:

[0385] The server analyzes the meal information using natural language processing technology and extracts key nutrient data. The input data is the text of the meal information, and the output data is the nutrient data for each ingredient. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[0386] Step 6:

[0387] The server compares the extracted nutrient data with the standard intake based on the user's age, gender, and weight, and calculates whether a nutrient is insufficient or excessive. The input data is the nutrient data and the user's basic information, and the output data is information on whether a nutrient is insufficient or excessive. For example, it can be calculated that the user's protein intake is already above the standard amount, but that the user is deficient in vitamins.

[0388] Step 7:

[0389] The server recommends appropriate restaurants based on the nutrient deficiency and excess data and emotional data. The input data is nutrient deficiency and excess data and emotional data, and the output data is a list of recommended restaurants. For example, if the user is feeling "stressed," the server selects restaurants with a relaxing environment.

[0390] Step 8:

[0391] The server generates the recommendation results in JSON format and sends them to the terminal as an HTTP response. The input data is a list of recommended restaurants, and the output data is the recommendation information in JSON format.

[0392] Step 9:

[0393] The device receives the response from the server, parses it, and displays it on the screen. The input data is recommendation information in JSON format, and the output data is information that is visually displayed to the user. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[0394] 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.

[0395] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0396] 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.

[0397] [Second embodiment]

[0398] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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."

[0410] The system according to the present invention allows a user to input their own dietary information, analyzes the information, calculates nutrient deficiencies and excesses, and recommends appropriate restaurants. Specific embodiments are described in detail below.

[0411] First, the user inputs information about their most recent meal into the device. For example, the user enters specific details of their meal into a text box, such as "I had toast and eggs for breakfast, and salad and chicken for lunch." After inputting the details, the user presses the send button to send the meal information to the server.

[0412] The device then converts the user's input data into JSON format and sends it as an HTTP request to the server, which receives the request at an API endpoint, parses the data, and prepares it for analysis.

[0413] The server analyzes the received meal information and extracts key nutrient data. This is done using natural language processing technology. The server analyzes the meal contents and extracts key nutrients from each ingredient and dish. For example, carbohydrates and protein are extracted from "toast and eggs," and vitamin C and protein are extracted from "salad and chicken."

[0414] Once the analysis is complete, the server compares the extracted nutrient data with the standard intake amount to calculate whether there is a nutrient deficiency or excess. The standard intake amount is set based on the user's age, gender, weight, etc. The comparison results in a determination of which nutrients are deficient and which are in excess.

[0415] The server then recommends restaurants that can help fill any nutrient gaps. For example, if you're deficient in vitamin D, it will recommend restaurants that serve fish or mushroom dishes. The server also includes information such as the name and location of each restaurant, as well as the dishes they serve.

[0416] Finally, the server notifies the user of the recommended restaurant information. The server sends the recommended restaurant information to the terminal, which then displays the information to the user. This allows the user to easily know which restaurants they should visit to improve their nutritional balance.

[0417] For example, the display may say, "We recommend nearby seafood restaurant A to supplement your vitamin D." In this way, by using the system of the present invention, users can easily adjust the nutrients they need to maintain a healthy diet.

[0418] The processing flow will be explained below.

[0419] Step 1:

[0420] The user enters meal information. The user enters meal details into the text box on the device, for example, "I had toast and eggs for breakfast, and salad and chicken for lunch," and presses the send button.

[0421] Step 2:

[0422] The terminal sends the input data to the server. The terminal converts the user's input data into JSON format and sends it to the server as an HTTP request.

[0423] Step 3:

[0424] The server receives the input data. The server receives the HTTP request at the API endpoint and parses the JSON data to prepare it for analysis.

[0425] Step 4:

[0426] The server analyzes the meal information. It uses natural language processing technology to extract key nutrient data from each part of the meal. For example, it extracts carbohydrates from "toast," proteins from "eggs," and vitamins from "salad."

[0427] Step 5:

[0428] The server compares the nutrient data with the standard intake amount. The server refers to a database of standard intake amounts based on the user's age, sex, and weight, and compares the extracted nutrient data to calculate whether there is a surplus or deficiency.

[0429] Step 6:

[0430] The server calculates the nutrient deficiency or excess, and determines whether each nutrient is deficient or excessive based on the comparison results.

[0431] Step 7:

[0432] The server recommends restaurants. Based on the nutrient deficiency data, the server extracts and lists restaurants from the database that can provide the nutrients you are lacking. For example, if you are deficient in vitamin D, it will find restaurants that serve fish dishes.

[0433] Step 8:

[0434] The server sends the recommendation information to the device. Information about the recommended restaurants is generated in JSON format and sent to the device as an HTTP response.

[0435] Step 9:

[0436] The device displays the recommended information to the user. The device receives the response from the server, parses it, and displays it on the screen. The user can refer to this information to choose an appropriate restaurant to eat at.

[0437] Through this series of processes, users can easily understand their own nutritional balance and obtain specific dietary options to supplement their necessary nutrients.

[0438] Example 1

[0439] 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."

[0440] In conventional systems, even if users input their dietary information, the information could not be analyzed efficiently and accurately, and sufficient advice on maintaining a proper nutritional balance could not be provided. As a result, users had difficulty understanding their own nutrient deficiencies and excesses, and were unable to make appropriate dietary choices. Furthermore, if a user was lacking in a particular nutrient, it was difficult to find an appropriate restaurant to supplement that nutrient.

[0441] 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.

[0442] In this invention, the server includes a means for a user to input dietary information, a means for converting the dietary information into JSON format and sending it to the server as an HTTP request, a server means for receiving the HTTP request and analyzing the data, a means for comparing the analyzed nutrient data with standard intake amounts and calculating nutrient deficiencies, a means for recommending restaurants that can compensate for the nutrient deficiencies, and a means for notifying the user of the recommended restaurants. This allows users to easily input their dietary information and accurately determine whether they are nutrient deficient or not based on that information. Furthermore, users can quickly find appropriate restaurants to compensate for nutrient deficiencies, allowing them to take specific actions to maintain a healthy diet.

[0443] A "user" is a person who uses the system to input dietary information and receives nutrient analysis results and recommendation information.

[0444] "Dietary information" is details of the meal the user has most recently eaten, and is entered into a text box and sent.

[0445] A "terminal" is a device used by a user to input meal information and communicate with the server, and includes smartphones, tablets, PCs, etc.

[0446] "JSON format" is a data format used to send meal information to a server as structured data.

[0447] An "HTTP request" is a communication protocol for sending data from a terminal to a server.

[0448] A "server" is a device that analyzes dietary information received from a user, extracts nutrient data, and returns recommended information to the user.

[0449] "Natural language processing technology" is a technology used to extract nutrient data from dietary information and analyzes text data.

[0450] "Nutrient data" is information on various nutritional components extracted from dietary content.

[0451] The "standard intake" is the amount of nutrients required daily, set based on the user's age, sex, weight, etc.

[0452] A "restaurant" is a place that serves food and drinks, and is a recommended store to help users meet their nutritional needs.

[0453] "Recommendation" refers to the act of recommending appropriate restaurants to help the user meet their nutritional needs.

[0454] "Recommendation information" is detailed information about suitable restaurants that can help users make up for nutrient deficiencies and excesses, sent from the server to the user.

[0455] "Notification" refers to the act of conveying important information, such as recommendation information, to the user via the device.

[0456] The system according to the present invention allows a user to input their own dietary information, analyzes the information, calculates nutrient deficiencies and excesses, and recommends appropriate restaurants. Specific embodiments are described in detail below.

[0457] First, the user inputs the most recent meal information into the device. For example, the user enters specific meal details such as "I had toast and eggs for breakfast, and salad and chicken for lunch" into the text box on the device, and then presses the send button to send the meal information to the server.

[0458] The terminal converts the input data into JSON format. For example, it converts the text data "I had toast and eggs for breakfast, and salad and chicken for lunch" into JSON data { "breakfast": "toast and eggs", "lunch": "salad and chicken"}. The converted data is sent to the server as an HTTP request.

[0459] The server receives HTTP requests at the API endpoint, parses the received JSON data, and prepares it for analysis. Natural language processing techniques (e.g., spaCy, NLTK, Transformers) are used to extract key nutrient data from the meal contents. For example, carbohydrates and protein are extracted from "toast and eggs," and vitamin C and protein are extracted from "salad and chicken."

[0460] The server then compares the extracted nutrient data with the standard intake based on the user's profile information, such as age, gender, and weight. This comparison calculates whether each nutrient is in a deficiency or excess. For example, a 30-year-old man may be found to have sufficient carbohydrates but a vitamin D deficiency.

[0461] The server then recommends appropriate restaurants based on the nutrient deficiency or excess. For example, if a person is deficient in vitamin D, it searches the database for restaurants that serve fish or mushroom dishes, and lists information such as the specific restaurant's name, location, and the dishes they serve.

[0462] Finally, the server sends the recommendation information to the device, which then displays the received information to the user, notifying them of the specific recommendation, "We recommend a nearby seafood restaurant to supplement your vitamin D intake." This allows the user to immediately take action to efficiently adjust their nutritional balance.

[0463] Specific examples

[0464] For example, a user enters the following prompt into the system:

[0465] "I had toast and eggs for breakfast and salad and chicken for lunch. Please calculate my nutritional surplus and deficiency and recommend restaurants that are good for me."

[0466] The system responds with the following:

[0467] "I recommend a nearby seafood restaurant to get some Vitamin D."

[0468] By using this system, users can easily manage their own dietary information and take quick action to maintain proper nutritional balance.

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

[0470] Step 1:

[0471] The user inputs meal information into the terminal.

[0472] Input: Specific meal details (e.g., "I had toast and eggs for breakfast and salad and chicken for lunch.")

[0473] Action: Enter this information into a text box in the terminal application.

[0474] Output: The input text data

[0475] Step 2:

[0476] The user presses the send button.

[0477] Input: Text data (meal information)

[0478] Processing: Detects that the submit button has been pressed and passes the entered data to the next processing step.

[0479] Output: Text data (prepared for transmission)

[0480] Step 3:

[0481] The device converts the meal information into JSON format.

[0482] Input: Text data (meal information)

[0483] Processing: Use a conversion function to convert text data into JSON format (e.g., {"breakfast": "toast and eggs", "lunch": "salad and chicken"}).

[0484] Output: JSON data

[0485] Step 4:

[0486] The device generates an HTTP request and sends it to the server.

[0487] Input: JSON data

[0488] Processing: Generate an HTTP request and send it to the server's API endpoint, including the JSON data.

[0489] Output: HTTP request (including JSON data)

[0490] Step 5:

[0491] The server receives the HTTP request and prepares to parse the data.

[0492] Input: HTTP request (including JSON data)

[0493] Processing: Receive the request and parse the JSON data.

[0494] Output: Parsed meal information data

[0495] Step 6:

[0496] The server uses natural language processing technology to analyze the dietary information and extract nutrient data.

[0497] Input: Parsed meal information data

[0498] Processing: Using natural language processing libraries (e.g., spaCy, NLTK), extract nutrients from meal descriptions (e.g., extract carbohydrates and protein from "toast and eggs," and vitamin C and protein from "salad and chicken").

[0499] Output: Extracted nutrient data (e.g. carbohydrates, protein, vitamin C)

[0500] Step 7:

[0501] The server compares the nutrient data with standard intakes and calculates nutrient surpluses and deficiencies.

[0502] Input: Extracted nutrient data, standard intake information (based on age, sex, and weight)

[0503] Processing: Nutrient data is compared to standard intakes based on user profile information to calculate deficiencies or excesses (e.g., enough carbohydrates but not enough vitamin D).

[0504] Output: Nutrient deficiency and excess data

[0505] Step 8:

[0506] The server will recommend restaurants that will help you make up for any nutrient deficiencies or excesses.

[0507] Input: Nutrient deficiency and excess data, restaurant information database

[0508] Processing: Search the database for appropriate restaurants based on the deficiency or surplus and create a list (e.g., if there is a vitamin D deficiency, recommend a seafood restaurant).

[0509] Output: Recommendation information (restaurant name, location, dishes served, etc.)

[0510] Step 9:

[0511] The server transmits the recommendation information to the terminal.

[0512] Input: Recommendation information

[0513] Processing: Generate data including recommendation information as an HTTP response and send it to the terminal.

[0514] Output: HTTP response (including recommendation information)

[0515] Step 10:

[0516] The device displays the recommended information to the user.

[0517] Input: HTTP response (including recommendation information)

[0518] Processing: Parse the received recommendation information and display it in a user-friendly format (e.g., "We recommend a nearby seafood restaurant to help you get your vitamin D.").

[0519] Output: Recommendation information displayed to the user (visual display)

[0520] (Application example 1)

[0521] 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."

[0522] Conventional nutrition management systems allow users to input their own dietary information and calculate nutrient deficiencies or excesses, but they lack the functionality to consistently support users, from specific meal suggestions based on the results to using food delivery services. This means that users have to go through the trouble of actually selecting and ordering meals, which reduces their ability to maintain a healthy diet.

[0523] 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.

[0524] In this invention, the server includes means for a user to input dietary information, means for receiving and analyzing the dietary information, means for comparing the analyzed nutrient data with standard intakes and calculating nutrient deficiencies and excesses, means for recommending restaurants that will compensate for the nutrient deficiencies and excesses, means for notifying the user of information on the recommended restaurants, means for placing an order with a food delivery service, and means for suggesting appropriate dishes to compensate for the nutrient deficiencies and excesses. This allows users to receive consistent support while receiving specific dietary suggestions for maintaining a healthy diet, and makes it easy to use food delivery services.

[0525] A "user" is a person who uses the system to input their own dietary information and receives analysis results and suggestions regarding nutrient deficiencies and excesses.

[0526] "Dietary information" is data in which the user specifically describes the contents of their own meals, including the names of ingredients and dishes and the amounts consumed.

[0527] The "server" is a computer system that receives and analyzes dietary information sent by a user and calculates deficiencies or excesses in nutrient data.

[0528] "Nutrient data" is information on the quantity and type of each nutrient extracted from dietary information.

[0529] The "standard intake amount" is a reference intake amount for a particular nutrient that is set based on the user's age, sex, weight, etc.

[0530] "Excess or deficiency" is the result of comparing the intake of each nutrient calculated based on the user's dietary information with the standard intake, and is information indicating whether there is an excess or deficiency.

[0531] "Restaurant" means an establishment established to provide meals, and the dishes offered therein are suitable for supplementing nutritional deficiencies or excesses.

[0532] "Recommendation" refers to the system selecting and suggesting appropriate restaurants and dishes based on the user's nutritional deficiencies or excesses.

[0533] A "food delivery service" is a service that allows users to order food from restaurants and have it delivered without having to move to another location.

[0534] An "appropriate meal" is a specific meal that is recommended to compensate for the user's nutritional deficiency or excess.

[0535] The present invention relates to a system that allows a user to input their own dietary information, analyzes the information, calculates nutrient deficiencies and excesses, and suggests appropriate restaurants and dishes.

[0536] System program generation

[0537] This system is realized by performing a complex process including the following means.

[0538] Hardware and Software

[0539] Hardware: Smartphone (iOS / Android)

[0540] Software: A Python environment to run the application, an HTTP library (requests), a JSON library, and a natural language processing library (e.g., spaCy or NLTK).

[0541] Data processing and calculation

[0542] Data entry: The user enters meal information into the device in text format, for example, "toast and eggs for breakfast, salad and chicken for lunch."

[0543] Examples:

[0544] Enter your most recent meal (e.g., toast and eggs for breakfast, salad and chicken for lunch):

[0545] Data transmission: The device converts the entered meal information into JSON format and sends it to the server as an HTTP request. For example, it is sent to the server in the following format:

[0546] Sending example:

[0547] json

[0548] {

[0549] "meal_info": "Toast and eggs for breakfast, salad and chicken for lunch"

[0550] }

[0551] Data analysis: The server analyzes the received data and uses natural language processing techniques to extract key nutrient data, for example, carbohydrates and protein from "toast and eggs" and vitamin C and protein from "salad and chicken."

[0552] Nutrient deficiency / surplus calculation: The server compares the extracted nutrient data with the standard intake amount, which is set based on the user's age, gender, weight, etc. As a result of the comparison, the deficiency / surplus of each nutrient is calculated.

[0553] Recommendations: The server recommends restaurants and dishes to help you meet your nutritional needs. For example, if you are deficient in vitamin D, it will suggest restaurants that serve fish or mushroom dishes, or alternative dishes.

[0554] Notification and ordering: The server sends the recommendation results to the device and notifies the user, allowing the user to easily find out about the recommended restaurants and dishes, and also supporting the use of food delivery services.

[0555] Specific examples

[0556] For example, a user enters meal information as follows:

[0557] Enter your most recent meal (e.g., toast and eggs for breakfast, salad and chicken for lunch):

[0558] Once the input is complete, the device converts the dietary information into JSON format and sends it to the server. The server analyzes the data, calculates which nutrients the user is lacking, and suggests appropriate dishes based on the results. For example, if the user is deficient in vitamin D, the system:

[0559] To supplement your vitamin D intake, the recommended menu item at nearby seafood restaurant A is salmon steak.

[0560] Furthermore, by selecting the notification, you can easily use food delivery services.

[0561] In this way, users can receive consistent support, receive specific meal suggestions to maintain a healthy diet, and easily use food delivery services.

[0562] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0563] Step 1:

[0564] Users input meal information in text format using a device such as a smartphone. The input content is specific meal details such as "toast and eggs for breakfast, salad and chicken for lunch." This input information becomes the basis of the data.

[0565] input:

[0566] Toast and eggs for breakfast, salad and chicken for lunch

[0567] output:

[0568] Text-based meal information

[0569] Step 2:

[0570] The device converts the meal information entered by the user into JSON format and sends it to the server as an HTTP request. Specifically, the converted JSON data has the following format:

[0571] input:

[0572] Text-based meal information

[0573] Data processing:

[0574] {

[0575] "meal_info": "Toast and eggs for breakfast, salad and chicken for lunch"

[0576] }

[0577] output:

[0578] Meal information in JSON format

[0579] Step 3:

[0580] The server analyzes the received meal information. Specifically, it uses natural language processing technology to extract key nutrient data from the meal contents. For example, carbohydrates and protein are extracted from "toast and eggs," and vitamin C and protein are extracted from "salad and chicken."

[0581] input:

[0582] Meal information in JSON format

[0583] Data Calculation:

[0584] Libraries used: spaCy, NLTK

[0585] {

[0586] "carbohydrates": 30,

[0587] "protein": 20,

[0588] "vitaminC": 10

[0589] }

[0590] output:

[0591] Key Nutrient Data

[0592] Step 4:

[0593] The server compares the extracted nutrient data with the standard intake amount and calculates the nutrient deficiency or excess. The standard intake amount is set based on the user's age, gender, and weight information. The deficiency or excess is determined based on this data.

[0594] input:

[0595] Key Nutrient Data

[0596] Data Calculation:

[0597] Vitamin D: -5 (deficiency)

[0598] Protein: +10 (excess)

[0599] output:

[0600] Nutrient deficiency or excess

[0601] Step 5:

[0602] The server recommends restaurants and food delivery services that provide meals that can help fill nutrient gaps and deficiencies.

[0603] input:

[0604] Nutrient deficiency or excess

[0605] Data processing:

[0606] [

[0607] {

[0608] "restaurant_name": "Seafood Restaurant A",

[0609] "menu_item": "Salmon steak",

[0610] "nutrient": "vitamin D"

[0611] }

[0612] ]

[0613] output:

[0614] Recommended information

[0615] Step 6:

[0616] The server sends the recommendation information to the terminal, which then notifies the user. The user can then check the recommended restaurants and dishes and place an order using a food delivery service if necessary.

[0617] input:

[0618] Recommended information

[0619] Data processing:

[0620] To supplement your vitamin D intake, the recommended menu item at nearby seafood restaurant A is salmon steak.

[0621] output:

[0622] Recommendation information notified to the user

[0623] In this way, the entire system processes, providing users with consistent support and specific meal suggestions to maintain a healthy diet.

[0624] 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.

[0625] The system according to the present invention allows a user to input their own dietary information, analyzes the information to calculate nutrient deficiencies and excesses, and recommends suitable restaurants, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments are described in detail below.

[0626] First, the user inputs their most recent meal information into the device. For example, they enter specific details of their meal, such as "I had toast and eggs for breakfast, and salad and chicken for lunch," into the text box and press the send button. At that time, the emotion engine analyzes the user's facial expressions and tone of voice in real time to recognize their emotional state.

[0627] Next, the device converts the user's input data and the emotion data recognized by the emotion engine into JSON format and sends it as an HTTP request to the server. The server receives this request at an API endpoint, parses the data, and prepares it for analysis.

[0628] The server analyzes the received meal information and extracts key nutrient data. This is done using natural language processing technology. The server analyzes the meal contents and extracts key nutrients from each ingredient and dish. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[0629] Once the analysis is complete, the server compares the extracted nutrient data with the standard intake amount to calculate whether there is a nutrient deficiency or excess. The standard intake amount is set based on the user's age, gender, weight, etc. The comparison results in a determination of which nutrients are deficient and which are in excess.

[0630] The server then recommends restaurants that can help replenish the user's nutritional needs. This recommendation also takes into account the user's emotional data. For example, if the user is feeling stressed, the server will recommend restaurants with a relaxing environment.

[0631] The recommendation routine based on emotion data works as follows: The server creates a list of restaurant candidates based on nutrient deficiency data, and then selects the restaurant that best suits the user's emotional state. Specifically, it recommends restaurants that offer relaxing ingredients and restaurants with a calming atmosphere.

[0632] The recommendation results are generated in JSON format and sent to the device as an HTTP response. The device receives the response from the server, parses it, and displays it on the screen. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[0633] For example, the display might say, "To supplement your vitamin D, we recommend nearby seafood restaurant A." This restaurant is selected based on the user's emotional state. If the emotion engine recognizes that the user is feeling stressed, it will select a restaurant that offers a relaxing restaurant environment and a menu suitable for changing the mood.

[0634] In this way, by using the system of the present invention, users can easily understand their own nutritional balance and select an appropriate eating environment according to their emotional state.

[0635] The processing flow will be explained below.

[0636] Step 1:

[0637] The user inputs meal information. The user enters meal details into the device's text box, for example, "I had toast and eggs for breakfast, and salad and chicken for lunch," and presses the send button. The emotion engine also analyzes the user's facial expressions and tone of voice in real time to recognize the user's emotional state.

[0638] Step 2:

[0639] The device sends the input data and emotion data to the server. The device converts the user's meal information and the emotion data recognized by the emotion engine into JSON format and sends it to the server as an HTTP request.

[0640] Step 3:

[0641] The server receives the input data and emotion data. The server receives the HTTP request at the API endpoint, parses the JSON data, and prepares it for analysis.

[0642] Step 4:

[0643] The server analyzes the meal information. It uses natural language processing technology to extract key nutrient data from each part of the meal. For example, it extracts carbohydrates from "toast," proteins from "eggs," and vitamins from "salad."

[0644] Step 5:

[0645] The server compares the nutrient data with the standard intake amount. The server refers to a database of standard intake amounts based on the user's age, sex, and weight, and compares the extracted nutrient data to calculate whether there is a surplus or deficiency.

[0646] Step 6:

[0647] The server calculates the nutrient deficiency or excess, and determines whether each nutrient is deficient or excessive based on the comparison results.

[0648] Step 7:

[0649] The server recommends restaurants. Based on the nutrient deficiency data, the server extracts and lists restaurants from the database that can provide the missing nutrients. This recommendation also takes into account the user's recognized emotional data. For example, if the user is feeling stressed, the server will recommend restaurants with a relaxing environment.

[0650] Step 8:

[0651] The server sends the recommendation information to the device. Information about the recommended restaurants is generated in JSON format and sent to the device as an HTTP response.

[0652] Step 9:

[0653] The device displays the recommended information to the user. The device receives the response from the server, parses the data, and displays it on the screen. The user can refer to this information to choose an appropriate restaurant. For example, the device may display, "To supplement your vitamin D, we recommend nearby seafood restaurant A." This restaurant is selected based on the user's emotional state, offering a relaxing restaurant environment and a menu suitable for a change of pace.

[0654] Example 2

[0655] 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."

[0656] Conventional nutrient analysis and restaurant recommendation systems recommend restaurants simply based on nutrient data without taking the user's emotional state into consideration, which means that they are unable to make recommendations that are appropriate for the user's emotional state, and this does not lead to increased satisfaction or stress reduction.

[0657] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0658] In this invention, the server includes means for receiving and analyzing input dietary information and user emotional information, means for comparing the analyzed nutrient data with standard intake amounts to calculate nutrient deficiencies and excesses, and means for recommending restaurants that will compensate for nutrient deficiencies and excesses, taking into account the user's emotional state. This makes it possible to recommend optimal restaurants that match the user's emotional state.

[0659] A "user" is a person who uses the system to input their own dietary information and receive the analysis results.

[0660] "Dietary information" is text data entered by a user about the contents of their meal, such as "I had toast and eggs for breakfast."

[0661] "Emotion information" is emotion data obtained from the user's facial expression and tone of voice, and indicates psychological states such as stress and happiness, for example.

[0662] The "server" is a computer system that receives dietary information and emotional information sent by users, analyzes it, calculates nutrient deficiencies and excesses, and recommends restaurants.

[0663] "Natural language processing technology" is a technology that allows computers to understand, interpret, and generate human language, and is used to extract nutritional data from dietary information.

[0664] "Nutrient data" refers to data on nutrients such as carbohydrates, proteins, and vitamins obtained by analyzing dietary information.

[0665] The "standard intake amount" is the appropriate daily intake amount of nutrients that is set based on the user's age, sex, weight, etc.

[0666] "Deficiency" refers to a state of deficiency or excess of a particular nutrient, determined when nutrient data is compared with standard intakes.

[0667] "Restaurant recommendation" refers to recommending restaurants suitable for the user, taking into consideration the user's nutritional deficiency and emotional state.

[0668] The "notification means" refers to a means for transmitting the recommendation results generated by the server to the user, and includes a method of displaying the results on the terminal.

[0669] MODE FOR CARRYING OUT THE INVENTION

[0670] The system according to the present invention allows a user to input their own dietary information, analyzes the information to calculate nutrient deficiencies and excesses, and recommends suitable restaurants, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments are described in detail below.

[0671] First, the user inputs information about their most recent meal into their device. For example, the user enters specific details of their meal into a text box, such as "I had toast and eggs for breakfast, and salad and chicken for lunch," and presses the send button. At this time, the emotion engine analyzes the user's facial expressions and tone of voice in real time to recognize the user's emotional state.

[0672] Next, the device converts the user's input data and the emotion data recognized by the emotion engine into JSON format and sends it as an HTTP request to the server. The server receives this request at an API endpoint, parses the data, and prepares it for analysis.

[0673] The server analyzes the received meal information and extracts key nutrient data. This analysis uses natural language processing technology. Specifically, it uses the Google Cloud Natural Language API to analyze the meal contents and extract key nutrients from each ingredient and dish. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[0674] Once the analysis is complete, the server compares the extracted nutrient data with standard intakes based on the user's age, gender, and weight to determine whether the user is deficient in any nutrients. For example, the comparison may determine that the user is deficient in vitamin D.

[0675] The server then recommends restaurants that are suitable for replenishing the nutritional deficiency or excess. This recommendation also takes into account the user's emotional data. For example, if the user is feeling stressed, it will recommend restaurants with a relaxing environment. This recommendation routine lists restaurant candidates based on the nutrient deficiency or excess data, and selects from that list the restaurant that best suits the user's emotional state.

[0676] The recommendation results are generated in JSON format and sent to the device as an HTTP response. The device receives the response from the server, parses it, and displays it on the screen. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[0677] For example, if a user inputs "I had toast and eggs for breakfast and salad and chicken for lunch," and the emotion engine recognizes that the user is under stress, the server will present a recommendation such as "To supplement your vitamin D, we recommend nearby seafood restaurant A." Seafood restaurant A offers a relaxing restaurant environment and a menu suitable for reducing stress.

[0678] Below are some examples of specific prompts that are useful for using the system: "If a user has had toast and eggs for breakfast and salad and chicken for lunch and is feeling stressed, which restaurant would you recommend?" can be input into the generative AI model to obtain effective recommendations.

[0679] In this way, by using the system of the present invention, users can easily understand their own nutritional balance and select an appropriate eating environment according to their emotional state.

[0680] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0681] Step 1:

[0682] The user inputs his / her meal information into the terminal.

[0683] Input: A user enters a meal description into a text box, such as "I had toast and eggs for breakfast and salad and chicken for lunch."

[0684] Output: The terminal holds the input data.

[0685] Specific operation: The user enters meal information and presses the send button. The device collects the input data and begins processing.

[0686] Step 2:

[0687] The device analyzes the user's facial expressions and tone of voice in real time, and the emotion engine recognizes their emotional state.

[0688] Input: Data on the user's facial expressions and tone of voice from the device's camera and microphone.

[0689] Output: "Emotional state data" recognized by the emotion engine.

[0690] Specific operation: The device's camera captures the user's facial expressions, the microphone analyzes the tone of the voice, and sends them to the emotion engine to analyze the emotional state.

[0691] Step 3:

[0692] The device converts the meal information and emotional state data into JSON format and sends it to the server as an HTTP request.

[0693] Input: Food information text data and emotional state data.

[0694] Output: The HTTP request with the data converted to JSON format.

[0695] Specific operation: The device integrates the input data and emotion data, converts them into JSON format, generates an HTTP request, and sends it to the server.

[0696] Step 4:

[0697] The server receives the HTTP request and parses the JSON data, preparing it for analysis.

[0698] Input: The JSON data sent by the HTTP request.

[0699] Output: Data ready for analysis.

[0700] What happens: The server receives the HTTP request and converts the JSON data into a format that is easy to parse.

[0701] Step 5:

[0702] The server analyzes the dietary information using natural language processing technology and extracts key nutrient data.

[0703] Input: Parsed meal information data.

[0704] Output: Extracted macronutrient data.

[0705] How it works: The server uses natural language processing APIs to identify and extract nutrients from food information, for example, extracting carbohydrates from "toast" and protein from "eggs."

[0706] Step 6:

[0707] The server compares the nutrient data with standard intakes and calculates nutrient surpluses and deficiencies.

[0708] Input: Extracted nutrient data and standard intake data.

[0709] Output: Nutrient deficiency and excess data.

[0710] Specific operation: The server compares the nutrient data with the standard intake and determines whether there is a deficiency or excess, such as a vitamin D deficiency.

[0711] Step 7:

[0712] The server takes into account the user's emotional state and recommends appropriate restaurants to compensate for any nutrient deficiencies or excesses.

[0713] Input: Nutrient deficiency and excess data and emotional state data.

[0714] Output: Recommended restaurant information.

[0715] Specific operation: The server uses a recommendation algorithm to select restaurants that, for example, can help replenish vitamin D deficiency and reduce stress.

[0716] Step 8:

[0717] The server generates the recommendation results in JSON format and sends them to the terminal as an HTTP response.

[0718] Input: Recommended restaurant information.

[0719] Output: HTTP response in JSON format containing the recommendation results.

[0720] Specific operation: The server generates recommendation results in JSON format and sends them to the device as an HTTP response.

[0721] Step 9:

[0722] The device receives the HTTP response from the server, parses it, and displays it on the screen.

[0723] Input: HTTP response (JSON data) from the server.

[0724] Output: Recommendation results displayed on the screen.

[0725] Specific behavior: The device receives the HTTP response, parses the JSON data, and displays to the user, "To supplement your vitamin D, we recommend nearby seafood restaurant A."

[0726] Through these steps, users can receive restaurant recommendations that suit their nutritional balance and emotional state.

[0727] (Application example 2)

[0728] 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."

[0729] In modern society, it is important to consume a balanced diet to maintain good health. However, it is not easy to manage one's diet and consume the necessary nutrients in the right amounts in a busy daily life. Furthermore, it is difficult with conventional technologies to propose a meal plan that takes into account not only the deficiency or excess of individual nutrients but also the user's emotional state. The present invention aims to solve these problems and provide a system that allows users to enjoy meals that suit their emotional state while maintaining a healthy diet.

[0730] 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 the user to input dietary information, server means for receiving and analyzing the dietary information, means for comparing the analyzed nutrient data with standard intake amounts to calculate nutrient deficiency or excess, means for analyzing the user's emotional data, means for recommending restaurants based on the nutrient deficiency or excess and the emotional data, and means for notifying the user of the recommended restaurant information. This enables the user to easily manage their diet and find restaurants that provide an optimal dining environment that takes their emotional state into consideration.

[0731] "Dietary information" refers to information about ingredients and dishes consumed by the user, and is provided through text, voice, or other input means.

[0732] "Nutrient data" refers to information on major nutrients extracted from dietary information, and specifically includes carbohydrates, proteins, vitamins, etc. contained in each ingredient or dish.

[0733] "Emotion data" is information about the user's emotional state analyzed from facial expressions, tone of voice, etc., and includes states such as relaxation, stress, and anxiety.

[0734] "Recommendation" is the act of suggesting the most suitable restaurant based on the user's nutritional deficiency or excess and emotional data.

[0735] "Natural language processing technology" is a general term for technology that analyzes natural language data such as text and speech, and understands and extracts meaning.

[0736] A "standard intake" is a reference value that indicates the amount of each nutrient needed per day to maintain health, and is determined based on age, gender, weight, etc.

[0737] "Server means" refers to computer resources or programs for receiving and analyzing meal information and emotion data provided by the user.

[0738] The system embodying this invention allows users to input their own dietary information, analyzes it to calculate nutrient deficiencies and excesses, and recommends appropriate restaurants based on their emotional state, allowing users to maintain their health while enjoying meals that suit their emotional state.

[0739] First, the user inputs meal information using the smart glasses' voice recognition system. The voice recognition system converts the voice input into text data and sends the meal information to the device. For example, the user might say, "I had toast and eggs for breakfast, and salad and chicken for lunch," which is input as text data.

[0740] Next, emotion recognition is performed. The smart glasses' camera and microphone are used to analyze the user's facial expressions and tone of voice in real time to recognize their emotional state. For emotion recognition, the FER library is used to detect emotions such as joy, sadness, and stress from the user's facial expressions.

[0741] The obtained food information and emotion data are converted into JSON format and sent as an HTTP request to the server, which receives the request at its API endpoint, parses the data, and prepares it for analysis.

[0742] The server analyzes the received meal information and uses natural language processing (NLP) to extract key nutrient data. The analyzed nutrient data is compared with standard intakes based on the user's age, gender, and weight, and any nutrient surpluses or deficiencies are calculated. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[0743] After calculating the nutrient surplus / deficiency, the server recommends appropriate restaurants based on that information and emotional data. For example, if a user is feeling stressed, a recommendation algorithm based on emotional data will recommend restaurants with a relaxing environment. Specifically, the server creates a list of restaurant candidates based on the nutrient surplus / deficiency data, and then selects from that list the restaurant that best suits the user's emotional state.

[0744] The recommendation results are again generated in JSON format and sent to the device as an HTTP response. The device receives the response from the server, parses it, and displays it on the screen. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[0745] An example prompt is:

[0746] "Enter the user's dietary information, analyze the nutritional data, and output recommendations. The recommendations change depending on the user's emotional state."

[0747] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0748] Step 1:

[0749] The user inputs meal information using the smart glasses' voice recognition system. The voice input is converted into text data and sent to the device. For example, if the user says, "I had toast and eggs for breakfast, and salad and chicken for lunch," this information is converted into text using voice recognition technology. The input data is saved as "meal information."

[0750] Step 2:

[0751] The emotion recognition module uses the smart glasses' camera and microphone to analyze the user's facial expressions and tone of voice in real time to recognize their emotional state. The acquired emotional data is stored as "emotion data." For example, the FER library can be used to detect "stress" from the user's facial expressions.

[0752] Step 3:

[0753] The device converts the obtained food information and emotion data into JSON format and sends it to the server as an HTTP request. The input data is food information and emotion data, which are encoded as structured data.

[0754] Step 4:

[0755] The server receives HTTP requests at the API endpoint, parses the data, and prepares it for analysis. The server then sends the parsed data to the analysis module. The input data is food information and emotion data in JSON format, which is then converted into an analyzable format.

[0756] Step 5:

[0757] The server analyzes the meal information using natural language processing technology and extracts key nutrient data. The input data is the text of the meal information, and the output data is the nutrient data for each ingredient. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[0758] Step 6:

[0759] The server compares the extracted nutrient data with the standard intake based on the user's age, gender, and weight, and calculates whether a nutrient is insufficient or excessive. The input data is the nutrient data and the user's basic information, and the output data is information on whether a nutrient is insufficient or excessive. For example, it can be calculated that the user's protein intake is already above the standard amount, but that the user is deficient in vitamins.

[0760] Step 7:

[0761] The server recommends appropriate restaurants based on the nutrient deficiency and excess data and emotional data. The input data is nutrient deficiency and excess data and emotional data, and the output data is a list of recommended restaurants. For example, if the user is feeling "stressed," the server selects restaurants with a relaxing environment.

[0762] Step 8:

[0763] The server generates the recommendation results in JSON format and sends them to the terminal as an HTTP response. The input data is a list of recommended restaurants, and the output data is the recommendation information in JSON format.

[0764] Step 9:

[0765] The device receives the response from the server, parses it, and displays it on the screen. The input data is recommendation information in JSON format, and the output data is information that is visually displayed to the user. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] [Third embodiment]

[0770] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0771] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0772] 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).

[0773] 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.

[0774] 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.

[0775] 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).

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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."

[0782] The system according to the present invention allows a user to input their own dietary information, analyzes the information, calculates nutrient deficiencies and excesses, and recommends appropriate restaurants. Specific embodiments are described in detail below.

[0783] First, the user inputs information about their most recent meal into the device. For example, the user enters specific details of their meal into a text box, such as "I had toast and eggs for breakfast, and salad and chicken for lunch." After inputting the details, the user presses the send button to send the meal information to the server.

[0784] The device then converts the user's input data into JSON format and sends it as an HTTP request to the server, which receives the request at an API endpoint, parses the data, and prepares it for analysis.

[0785] The server analyzes the received meal information and extracts key nutrient data. This is done using natural language processing technology. The server analyzes the meal contents and extracts key nutrients from each ingredient and dish. For example, carbohydrates and protein are extracted from "toast and eggs," and vitamin C and protein are extracted from "salad and chicken."

[0786] Once the analysis is complete, the server compares the extracted nutrient data with the standard intake amount to calculate whether there is a nutrient deficiency or excess. The standard intake amount is set based on the user's age, gender, weight, etc. The comparison results in a determination of which nutrients are deficient and which are in excess.

[0787] The server then recommends restaurants that can help fill any nutrient gaps. For example, if you're deficient in vitamin D, it will recommend restaurants that serve fish or mushroom dishes. The server also includes information such as the name and location of each restaurant, as well as the dishes they serve.

[0788] Finally, the server notifies the user of the recommended restaurant information. The server sends the recommended restaurant information to the terminal, which then displays the information to the user. This allows the user to easily know which restaurants they should visit to improve their nutritional balance.

[0789] For example, the display may say, "We recommend nearby seafood restaurant A to supplement your vitamin D." In this way, by using the system of the present invention, users can easily adjust the nutrients they need to maintain a healthy diet.

[0790] The processing flow will be explained below.

[0791] Step 1:

[0792] The user enters meal information. The user enters meal details into the text box on the device, for example, "I had toast and eggs for breakfast, and salad and chicken for lunch," and presses the send button.

[0793] Step 2:

[0794] The terminal sends the input data to the server. The terminal converts the user's input data into JSON format and sends it to the server as an HTTP request.

[0795] Step 3:

[0796] The server receives the input data. The server receives the HTTP request at the API endpoint and parses the JSON data to prepare it for analysis.

[0797] Step 4:

[0798] The server analyzes the meal information. It uses natural language processing technology to extract key nutrient data from each part of the meal. For example, it extracts carbohydrates from "toast," proteins from "eggs," and vitamins from "salad."

[0799] Step 5:

[0800] The server compares the nutrient data with the standard intake amount. The server refers to a database of standard intake amounts based on the user's age, sex, and weight, and compares the extracted nutrient data to calculate whether there is a surplus or deficiency.

[0801] Step 6:

[0802] The server calculates the nutrient deficiency or excess, and determines whether each nutrient is deficient or excessive based on the comparison results.

[0803] Step 7:

[0804] The server recommends restaurants. Based on the nutrient deficiency data, the server extracts and lists restaurants from the database that can provide the nutrients you are lacking. For example, if you are deficient in vitamin D, it will find restaurants that serve fish dishes.

[0805] Step 8:

[0806] The server sends the recommendation information to the device. Information about the recommended restaurants is generated in JSON format and sent to the device as an HTTP response.

[0807] Step 9:

[0808] The device displays the recommended information to the user. The device receives the response from the server, parses it, and displays it on the screen. The user can refer to this information to choose an appropriate restaurant to eat at.

[0809] Through this series of processes, users can easily understand their own nutritional balance and obtain specific dietary options to supplement their necessary nutrients.

[0810] Example 1

[0811] 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."

[0812] In conventional systems, even if users input their dietary information, the information could not be analyzed efficiently and accurately, and sufficient advice on maintaining a proper nutritional balance could not be provided. As a result, users had difficulty understanding their own nutrient deficiencies and excesses, and were unable to make appropriate dietary choices. Furthermore, if a user was lacking in a particular nutrient, it was difficult to find an appropriate restaurant to supplement that nutrient.

[0813] 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.

[0814] In this invention, the server includes a means for a user to input dietary information, a means for converting the dietary information into JSON format and sending it to the server as an HTTP request, a server means for receiving the HTTP request and analyzing the data, a means for comparing the analyzed nutrient data with standard intake amounts and calculating nutrient deficiencies, a means for recommending restaurants that can compensate for the nutrient deficiencies, and a means for notifying the user of the recommended restaurants. This allows users to easily input their dietary information and accurately determine whether they are nutrient deficient or not based on that information. Furthermore, users can quickly find appropriate restaurants to compensate for nutrient deficiencies, allowing them to take specific actions to maintain a healthy diet.

[0815] A "user" is a person who uses the system to input dietary information and receives nutrient analysis results and recommendation information.

[0816] "Dietary information" is details of the meal the user has most recently eaten, and is entered into a text box and sent.

[0817] A "terminal" is a device used by a user to input meal information and communicate with the server, and includes smartphones, tablets, PCs, etc.

[0818] "JSON format" is a data format used to send meal information to a server as structured data.

[0819] An "HTTP request" is a communication protocol for sending data from a terminal to a server.

[0820] A "server" is a device that analyzes dietary information received from a user, extracts nutrient data, and returns recommended information to the user.

[0821] "Natural language processing technology" is a technology used to extract nutrient data from dietary information and analyzes text data.

[0822] "Nutrient data" is information on various nutritional components extracted from dietary content.

[0823] The "standard intake" is the amount of nutrients required daily, set based on the user's age, sex, weight, etc.

[0824] A "restaurant" is a place that serves food and drinks, and is a recommended store to help users meet their nutritional needs.

[0825] "Recommendation" refers to the act of recommending appropriate restaurants to help the user meet their nutritional needs.

[0826] "Recommendation information" is detailed information about suitable restaurants that can help users make up for nutrient deficiencies and excesses, sent from the server to the user.

[0827] "Notification" refers to the act of conveying important information, such as recommendation information, to the user via the device.

[0828] The system according to the present invention allows a user to input their own dietary information, analyzes the information, calculates nutrient deficiencies and excesses, and recommends appropriate restaurants. Specific embodiments are described in detail below.

[0829] First, the user inputs the most recent meal information into the device. For example, the user enters specific meal details such as "I had toast and eggs for breakfast, and salad and chicken for lunch" into the text box on the device, and then presses the send button to send the meal information to the server.

[0830] The terminal converts the input data into JSON format. For example, it converts the text data "I had toast and eggs for breakfast, and salad and chicken for lunch" into JSON data { "breakfast": "toast and eggs", "lunch": "salad and chicken"}. The converted data is sent to the server as an HTTP request.

[0831] The server receives HTTP requests at the API endpoint, parses the received JSON data, and prepares it for analysis. Natural language processing techniques (e.g., spaCy, NLTK, Transformers) are used to extract key nutrient data from the meal contents. For example, carbohydrates and protein are extracted from "toast and eggs," and vitamin C and protein are extracted from "salad and chicken."

[0832] The server then compares the extracted nutrient data with the standard intake based on the user's profile information, such as age, gender, and weight. This comparison calculates whether each nutrient is in a deficiency or excess. For example, a 30-year-old man may be found to have sufficient carbohydrates but a vitamin D deficiency.

[0833] The server then recommends appropriate restaurants based on the nutrient deficiency or excess. For example, if a person is deficient in vitamin D, it searches the database for restaurants that serve fish or mushroom dishes, and lists information such as the specific restaurant's name, location, and the dishes they serve.

[0834] Finally, the server sends the recommendation information to the device, which then displays the received information to the user, notifying them of the specific recommendation, "We recommend a nearby seafood restaurant to supplement your vitamin D intake." This allows the user to immediately take action to efficiently adjust their nutritional balance.

[0835] Specific examples

[0836] For example, a user enters the following prompt into the system:

[0837] "I had toast and eggs for breakfast and salad and chicken for lunch. Please calculate my nutritional surplus and deficiency and recommend restaurants that are good for me."

[0838] The system responds with the following:

[0839] "I recommend a nearby seafood restaurant to get some Vitamin D."

[0840] By using this system, users can easily manage their own dietary information and take quick action to maintain proper nutritional balance.

[0841] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0842] Step 1:

[0843] The user inputs meal information into the terminal.

[0844] Input: Specific meal details (e.g., "I had toast and eggs for breakfast and salad and chicken for lunch.")

[0845] Action: Enter this information into a text box in the terminal application.

[0846] Output: The input text data

[0847] Step 2:

[0848] The user presses the send button.

[0849] Input: Text data (meal information)

[0850] Processing: Detects that the submit button has been pressed and passes the entered data to the next processing step.

[0851] Output: Text data (prepared for transmission)

[0852] Step 3:

[0853] The device converts the meal information into JSON format.

[0854] Input: Text data (meal information)

[0855] Processing: Use a conversion function to convert text data into JSON format (e.g., {"breakfast": "toast and eggs", "lunch": "salad and chicken"}).

[0856] Output: JSON data

[0857] Step 4:

[0858] The device generates an HTTP request and sends it to the server.

[0859] Input: JSON data

[0860] Processing: Generate an HTTP request and send it to the server's API endpoint, including the JSON data.

[0861] Output: HTTP request (including JSON data)

[0862] Step 5:

[0863] The server receives the HTTP request and prepares to parse the data.

[0864] Input: HTTP request (including JSON data)

[0865] Processing: Receive the request and parse the JSON data.

[0866] Output: Parsed meal information data

[0867] Step 6:

[0868] The server uses natural language processing technology to analyze the dietary information and extract nutrient data.

[0869] Input: Parsed meal information data

[0870] Processing: Using natural language processing libraries (e.g., spaCy, NLTK), extract nutrients from meal descriptions (e.g., extract carbohydrates and protein from "toast and eggs," and vitamin C and protein from "salad and chicken").

[0871] Output: Extracted nutrient data (e.g. carbohydrates, protein, vitamin C)

[0872] Step 7:

[0873] The server compares the nutrient data with standard intakes and calculates nutrient surpluses and deficiencies.

[0874] Input: Extracted nutrient data, standard intake information (based on age, sex, and weight)

[0875] Processing: Nutrient data is compared to standard intakes based on user profile information to calculate deficiencies or excesses (e.g., enough carbohydrates but not enough vitamin D).

[0876] Output: Nutrient deficiency and excess data

[0877] Step 8:

[0878] The server will recommend restaurants that will help you make up for any nutrient deficiencies or excesses.

[0879] Input: Nutrient deficiency and excess data, restaurant information database

[0880] Processing: Search the database for appropriate restaurants based on the deficiency or surplus and create a list (e.g., if there is a vitamin D deficiency, recommend a seafood restaurant).

[0881] Output: Recommendation information (restaurant name, location, dishes served, etc.)

[0882] Step 9:

[0883] The server transmits the recommendation information to the terminal.

[0884] Input: Recommendation information

[0885] Processing: Generate data including recommendation information as an HTTP response and send it to the terminal.

[0886] Output: HTTP response (including recommendation information)

[0887] Step 10:

[0888] The device displays the recommended information to the user.

[0889] Input: HTTP response (including recommendation information)

[0890] Processing: Parse the received recommendation information and display it in a user-friendly format (e.g., "We recommend a nearby seafood restaurant to help you get your vitamin D.").

[0891] Output: Recommendation information displayed to the user (visual display)

[0892] (Application example 1)

[0893] 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."

[0894] Conventional nutrition management systems allow users to input their own dietary information and calculate nutrient deficiencies or excesses, but they lack the functionality to consistently support users, from specific meal suggestions based on the results to using food delivery services. This means that users have to go through the trouble of actually selecting and ordering meals, which reduces their ability to maintain a healthy diet.

[0895] 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.

[0896] In this invention, the server includes means for a user to input dietary information, means for receiving and analyzing the dietary information, means for comparing the analyzed nutrient data with standard intakes and calculating nutrient deficiencies and excesses, means for recommending restaurants that will compensate for the nutrient deficiencies and excesses, means for notifying the user of information on the recommended restaurants, means for placing an order with a food delivery service, and means for suggesting appropriate dishes to compensate for the nutrient deficiencies and excesses. This allows users to receive consistent support while receiving specific dietary suggestions for maintaining a healthy diet, and makes it easy to use food delivery services.

[0897] A "user" is a person who uses the system to input their own dietary information and receives analysis results and suggestions regarding nutrient deficiencies and excesses.

[0898] "Dietary information" is data in which the user specifically describes the contents of their own meals, including the names of ingredients and dishes and the amounts consumed.

[0899] The "server" is a computer system that receives and analyzes dietary information sent by a user and calculates deficiencies or excesses in nutrient data.

[0900] "Nutrient data" is information on the quantity and type of each nutrient extracted from dietary information.

[0901] The "standard intake amount" is a reference intake amount for a particular nutrient that is set based on the user's age, sex, weight, etc.

[0902] "Excess or deficiency" is the result of comparing the intake of each nutrient calculated based on the user's dietary information with the standard intake, and is information indicating whether there is an excess or deficiency.

[0903] "Restaurant" means an establishment established to provide meals, and the dishes offered therein are suitable for supplementing nutritional deficiencies or excesses.

[0904] "Recommendation" refers to the system selecting and suggesting appropriate restaurants and dishes based on the user's nutritional deficiencies or excesses.

[0905] A "food delivery service" is a service that allows users to order food from restaurants and have it delivered without having to move to another location.

[0906] An "appropriate meal" is a specific meal that is recommended to compensate for the user's nutritional deficiency or excess.

[0907] The present invention relates to a system that allows a user to input their own dietary information, analyzes the information, calculates nutrient deficiencies and excesses, and suggests appropriate restaurants and dishes.

[0908] System program generation

[0909] This system is realized by performing a complex process including the following means.

[0910] Hardware and Software

[0911] Hardware: Smartphone (iOS / Android)

[0912] Software: A Python environment to run the application, an HTTP library (requests), a JSON library, and a natural language processing library (e.g., spaCy or NLTK).

[0913] Data processing and calculation

[0914] Data entry: The user enters meal information into the device in text format, for example, "toast and eggs for breakfast, salad and chicken for lunch."

[0915] Examples:

[0916] Enter your most recent meal (e.g., toast and eggs for breakfast, salad and chicken for lunch):

[0917] Data transmission: The device converts the entered meal information into JSON format and sends it to the server as an HTTP request. For example, it is sent to the server in the following format:

[0918] Sending example:

[0919] json

[0920] {

[0921] "meal_info": "Toast and eggs for breakfast, salad and chicken for lunch"

[0922] }

[0923] Data analysis: The server analyzes the received data and uses natural language processing techniques to extract key nutrient data, for example, carbohydrates and protein from "toast and eggs" and vitamin C and protein from "salad and chicken."

[0924] Nutrient deficiency / surplus calculation: The server compares the extracted nutrient data with the standard intake amount, which is set based on the user's age, gender, weight, etc. As a result of the comparison, the deficiency / surplus of each nutrient is calculated.

[0925] Recommendations: The server recommends restaurants and dishes to help you meet your nutritional needs. For example, if you are deficient in vitamin D, it will suggest restaurants that serve fish or mushroom dishes, or alternative dishes.

[0926] Notification and ordering: The server sends the recommendation results to the device and notifies the user, allowing the user to easily find out about the recommended restaurants and dishes, and also supporting the use of food delivery services.

[0927] Specific examples

[0928] For example, a user enters meal information as follows:

[0929] Enter your most recent meal (e.g., toast and eggs for breakfast, salad and chicken for lunch):

[0930] Once the input is complete, the device converts the dietary information into JSON format and sends it to the server. The server analyzes the data, calculates which nutrients the user is lacking, and suggests appropriate dishes based on the results. For example, if the user is deficient in vitamin D, the system:

[0931] To supplement your vitamin D intake, the recommended menu item at nearby seafood restaurant A is salmon steak.

[0932] Furthermore, by selecting the notification, you can easily use food delivery services.

[0933] In this way, users can receive consistent support, receive specific meal suggestions to maintain a healthy diet, and easily use food delivery services.

[0934] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0935] Step 1:

[0936] Users input meal information in text format using a device such as a smartphone. The input content is specific meal details such as "toast and eggs for breakfast, salad and chicken for lunch." This input information becomes the basis of the data.

[0937] input:

[0938] Toast and eggs for breakfast, salad and chicken for lunch

[0939] output:

[0940] Text-based meal information

[0941] Step 2:

[0942] The device converts the meal information entered by the user into JSON format and sends it to the server as an HTTP request. Specifically, the converted JSON data has the following format:

[0943] input:

[0944] Text-based meal information

[0945] Data processing:

[0946] {

[0947] "meal_info": "Toast and eggs for breakfast, salad and chicken for lunch"

[0948] }

[0949] output:

[0950] Meal information in JSON format

[0951] Step 3:

[0952] The server analyzes the received meal information. Specifically, it uses natural language processing technology to extract key nutrient data from the meal contents. For example, carbohydrates and protein are extracted from "toast and eggs," and vitamin C and protein are extracted from "salad and chicken."

[0953] input:

[0954] Meal information in JSON format

[0955] Data Calculation:

[0956] Libraries used: spaCy, NLTK

[0957] {

[0958] "carbohydrates": 30,

[0959] "protein": 20,

[0960] "vitaminC": 10

[0961] }

[0962] output:

[0963] Key Nutrient Data

[0964] Step 4:

[0965] The server compares the extracted nutrient data with the standard intake amount and calculates the nutrient deficiency or excess. The standard intake amount is set based on the user's age, gender, and weight information. The deficiency or excess is determined based on this data.

[0966] input:

[0967] Key Nutrient Data

[0968] Data Calculation:

[0969] Vitamin D: -5 (deficiency)

[0970] Protein: +10 (excess)

[0971] output:

[0972] Nutrient deficiency or excess

[0973] Step 5:

[0974] The server recommends restaurants and food delivery services that provide meals that can help fill nutrient gaps and deficiencies.

[0975] input:

[0976] Nutrient deficiency or excess

[0977] Data processing:

[0978] [

[0979] {

[0980] "restaurant_name": "Seafood Restaurant A",

[0981] "menu_item": "Salmon steak",

[0982] "nutrient": "vitamin D"

[0983] }

[0984] ]

[0985] output:

[0986] Recommended information

[0987] Step 6:

[0988] The server sends the recommendation information to the terminal, which then notifies the user. The user can then check the recommended restaurants and dishes and place an order using a food delivery service if necessary.

[0989] input:

[0990] Recommended information

[0991] Data processing:

[0992] To supplement your vitamin D intake, the recommended menu item at nearby seafood restaurant A is salmon steak.

[0993] output:

[0994] Recommendation information notified to the user

[0995] In this way, the entire system processes, providing users with consistent support and specific meal suggestions to maintain a healthy diet.

[0996] 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.

[0997] The system according to the present invention allows a user to input their own dietary information, analyzes the information to calculate nutrient deficiencies and excesses, and recommends suitable restaurants, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments are described in detail below.

[0998] First, the user inputs their most recent meal information into the device. For example, they enter specific details of their meal, such as "I had toast and eggs for breakfast, and salad and chicken for lunch," into the text box and press the send button. At that time, the emotion engine analyzes the user's facial expressions and tone of voice in real time to recognize their emotional state.

[0999] Next, the device converts the user's input data and the emotion data recognized by the emotion engine into JSON format and sends it as an HTTP request to the server. The server receives this request at an API endpoint, parses the data, and prepares it for analysis.

[1000] The server analyzes the received meal information and extracts key nutrient data. This is done using natural language processing technology. The server analyzes the meal contents and extracts key nutrients from each ingredient and dish. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[1001] Once the analysis is complete, the server compares the extracted nutrient data with the standard intake amount to calculate whether there is a nutrient deficiency or excess. The standard intake amount is set based on the user's age, gender, weight, etc. The comparison results in a determination of which nutrients are deficient and which are in excess.

[1002] The server then recommends restaurants that can help replenish the user's nutritional needs. This recommendation also takes into account the user's emotional data. For example, if the user is feeling stressed, the server will recommend restaurants with a relaxing environment.

[1003] The recommendation routine based on emotion data works as follows: The server creates a list of restaurant candidates based on nutrient deficiency data, and then selects the restaurant that best suits the user's emotional state. Specifically, it recommends restaurants that offer relaxing ingredients and restaurants with a calming atmosphere.

[1004] The recommendation results are generated in JSON format and sent to the device as an HTTP response. The device receives the response from the server, parses it, and displays it on the screen. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[1005] For example, the display might say, "To supplement your vitamin D, we recommend nearby seafood restaurant A." This restaurant is selected based on the user's emotional state. If the emotion engine recognizes that the user is feeling stressed, it will select a restaurant that offers a relaxing restaurant environment and a menu suitable for changing the mood.

[1006] In this way, by using the system of the present invention, users can easily understand their own nutritional balance and select an appropriate eating environment according to their emotional state.

[1007] The processing flow will be explained below.

[1008] Step 1:

[1009] The user inputs meal information. The user enters meal details into the device's text box, for example, "I had toast and eggs for breakfast, and salad and chicken for lunch," and presses the send button. The emotion engine also analyzes the user's facial expressions and tone of voice in real time to recognize the user's emotional state.

[1010] Step 2:

[1011] The device sends the input data and emotion data to the server. The device converts the user's meal information and the emotion data recognized by the emotion engine into JSON format and sends it to the server as an HTTP request.

[1012] Step 3:

[1013] The server receives the input data and emotion data. The server receives the HTTP request at the API endpoint, parses the JSON data, and prepares it for analysis.

[1014] Step 4:

[1015] The server analyzes the meal information. It uses natural language processing technology to extract key nutrient data from each part of the meal. For example, it extracts carbohydrates from "toast," proteins from "eggs," and vitamins from "salad."

[1016] Step 5:

[1017] The server compares the nutrient data with the standard intake amount. The server refers to a database of standard intake amounts based on the user's age, sex, and weight, and compares the extracted nutrient data to calculate whether there is a surplus or deficiency.

[1018] Step 6:

[1019] The server calculates the nutrient deficiency or excess, and determines whether each nutrient is deficient or excessive based on the comparison results.

[1020] Step 7:

[1021] The server recommends restaurants. Based on the nutrient deficiency data, the server extracts and lists restaurants from the database that can provide the missing nutrients. This recommendation also takes into account the user's recognized emotional data. For example, if the user is feeling stressed, the server will recommend restaurants with a relaxing environment.

[1022] Step 8:

[1023] The server sends the recommendation information to the device. Information about the recommended restaurants is generated in JSON format and sent to the device as an HTTP response.

[1024] Step 9:

[1025] The device displays the recommended information to the user. The device receives the response from the server, parses the data, and displays it on the screen. The user can refer to this information to choose an appropriate restaurant. For example, the device may display, "To supplement your vitamin D, we recommend nearby seafood restaurant A." This restaurant is selected based on the user's emotional state, offering a relaxing restaurant environment and a menu suitable for a change of pace.

[1026] Example 2

[1027] 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."

[1028] Conventional nutrient analysis and restaurant recommendation systems recommend restaurants simply based on nutrient data without taking the user's emotional state into consideration, which means that they are unable to make recommendations that are appropriate for the user's emotional state, and this does not lead to increased satisfaction or stress reduction.

[1029] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1030] In this invention, the server includes means for receiving and analyzing input dietary information and user emotional information, means for comparing the analyzed nutrient data with standard intake amounts to calculate nutrient deficiencies and excesses, and means for recommending restaurants that will compensate for nutrient deficiencies and excesses, taking into account the user's emotional state. This makes it possible to recommend optimal restaurants that match the user's emotional state.

[1031] A "user" is a person who uses the system to input their own dietary information and receive the analysis results.

[1032] "Dietary information" is text data entered by a user about the contents of their meal, such as "I had toast and eggs for breakfast."

[1033] "Emotion information" is emotion data obtained from the user's facial expression and tone of voice, and indicates psychological states such as stress and happiness, for example.

[1034] The "server" is a computer system that receives dietary information and emotional information sent by users, analyzes it, calculates nutrient deficiencies and excesses, and recommends restaurants.

[1035] "Natural language processing technology" is a technology that allows computers to understand, interpret, and generate human language, and is used to extract nutritional data from dietary information.

[1036] "Nutrient data" refers to data on nutrients such as carbohydrates, proteins, and vitamins obtained by analyzing dietary information.

[1037] The "standard intake amount" is the appropriate daily intake amount of nutrients that is set based on the user's age, sex, weight, etc.

[1038] "Deficiency" refers to a state of deficiency or excess of a particular nutrient, determined when nutrient data is compared with standard intakes.

[1039] "Restaurant recommendation" refers to recommending restaurants suitable for the user, taking into consideration the user's nutritional deficiency and emotional state.

[1040] The "notification means" refers to a means for transmitting the recommendation results generated by the server to the user, and includes a method of displaying the results on the terminal.

[1041] MODE FOR CARRYING OUT THE INVENTION

[1042] The system according to the present invention allows a user to input their own dietary information, analyzes the information to calculate nutrient deficiencies and excesses, and recommends suitable restaurants, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments are described in detail below.

[1043] First, the user inputs information about their most recent meal into their device. For example, the user enters specific details of their meal into a text box, such as "I had toast and eggs for breakfast, and salad and chicken for lunch," and presses the send button. At this time, the emotion engine analyzes the user's facial expressions and tone of voice in real time to recognize the user's emotional state.

[1044] Next, the device converts the user's input data and the emotion data recognized by the emotion engine into JSON format and sends it as an HTTP request to the server. The server receives this request at an API endpoint, parses the data, and prepares it for analysis.

[1045] The server analyzes the received meal information and extracts key nutrient data. This analysis uses natural language processing technology. Specifically, it uses the Google Cloud Natural Language API to analyze the meal contents and extract key nutrients from each ingredient and dish. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[1046] Once the analysis is complete, the server compares the extracted nutrient data with standard intakes based on the user's age, gender, and weight to determine whether the user is deficient in any nutrients. For example, the comparison may determine that the user is deficient in vitamin D.

[1047] The server then recommends restaurants that are suitable for replenishing the nutritional deficiency or excess. This recommendation also takes into account the user's emotional data. For example, if the user is feeling stressed, it will recommend restaurants with a relaxing environment. This recommendation routine lists restaurant candidates based on the nutrient deficiency or excess data, and selects from that list the restaurant that best suits the user's emotional state.

[1048] The recommendation results are generated in JSON format and sent to the device as an HTTP response. The device receives the response from the server, parses it, and displays it on the screen. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[1049] For example, if a user inputs "I had toast and eggs for breakfast and salad and chicken for lunch," and the emotion engine recognizes that the user is under stress, the server will present a recommendation such as "To supplement your vitamin D, we recommend nearby seafood restaurant A." Seafood restaurant A offers a relaxing restaurant environment and a menu suitable for reducing stress.

[1050] Below are some examples of specific prompts that are useful for using the system: "If a user has had toast and eggs for breakfast and salad and chicken for lunch and is feeling stressed, which restaurant would you recommend?" can be input into the generative AI model to obtain effective recommendations.

[1051] In this way, by using the system of the present invention, users can easily understand their own nutritional balance and select an appropriate eating environment according to their emotional state.

[1052] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1053] Step 1:

[1054] The user inputs his / her meal information into the terminal.

[1055] Input: A user enters a meal description into a text box, such as "I had toast and eggs for breakfast and salad and chicken for lunch."

[1056] Output: The terminal holds the input data.

[1057] Specific operation: The user enters meal information and presses the send button. The device collects the input data and begins processing.

[1058] Step 2:

[1059] The device analyzes the user's facial expressions and tone of voice in real time, and the emotion engine recognizes their emotional state.

[1060] Input: Data on the user's facial expressions and tone of voice from the device's camera and microphone.

[1061] Output: "Emotional state data" recognized by the emotion engine.

[1062] Specific operation: The device's camera captures the user's facial expressions, the microphone analyzes the tone of the voice, and sends them to the emotion engine to analyze the emotional state.

[1063] Step 3:

[1064] The device converts the meal information and emotional state data into JSON format and sends it to the server as an HTTP request.

[1065] Input: Food information text data and emotional state data.

[1066] Output: The HTTP request with the data converted to JSON format.

[1067] Specific operation: The device integrates the input data and emotion data, converts them into JSON format, generates an HTTP request, and sends it to the server.

[1068] Step 4:

[1069] The server receives the HTTP request and parses the JSON data, preparing it for analysis.

[1070] Input: The JSON data sent by the HTTP request.

[1071] Output: Data ready for analysis.

[1072] What happens: The server receives the HTTP request and converts the JSON data into a format that is easy to parse.

[1073] Step 5:

[1074] The server analyzes the dietary information using natural language processing technology and extracts key nutrient data.

[1075] Input: Parsed meal information data.

[1076] Output: Extracted macronutrient data.

[1077] How it works: The server uses natural language processing APIs to identify and extract nutrients from food information, for example, extracting carbohydrates from "toast" and protein from "eggs."

[1078] Step 6:

[1079] The server compares the nutrient data with standard intakes and calculates nutrient surpluses and deficiencies.

[1080] Input: Extracted nutrient data and standard intake data.

[1081] Output: Nutrient deficiency and excess data.

[1082] Specific operation: The server compares the nutrient data with the standard intake and determines whether there is a deficiency or excess, such as a vitamin D deficiency.

[1083] Step 7:

[1084] The server takes into account the user's emotional state and recommends appropriate restaurants to compensate for any nutrient deficiencies or excesses.

[1085] Input: Nutrient deficiency and excess data and emotional state data.

[1086] Output: Recommended restaurant information.

[1087] Specific operation: The server uses a recommendation algorithm to select restaurants that, for example, can help replenish vitamin D deficiency and reduce stress.

[1088] Step 8:

[1089] The server generates the recommendation results in JSON format and sends them to the terminal as an HTTP response.

[1090] Input: Recommended restaurant information.

[1091] Output: HTTP response in JSON format containing the recommendation results.

[1092] Specific operation: The server generates recommendation results in JSON format and sends them to the device as an HTTP response.

[1093] Step 9:

[1094] The device receives the HTTP response from the server, parses it, and displays it on the screen.

[1095] Input: HTTP response (JSON data) from the server.

[1096] Output: Recommendation results displayed on the screen.

[1097] Specific behavior: The device receives the HTTP response, parses the JSON data, and displays to the user, "To supplement your vitamin D, we recommend nearby seafood restaurant A."

[1098] Through these steps, users can receive restaurant recommendations that suit their nutritional balance and emotional state.

[1099] (Application example 2)

[1100] 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."

[1101] In modern society, it is important to consume a balanced diet to maintain good health. However, it is not easy to manage one's diet and consume the necessary nutrients in the right amounts in a busy daily life. Furthermore, it is difficult with conventional technologies to propose a meal plan that takes into account not only the deficiency or excess of individual nutrients but also the user's emotional state. The present invention aims to solve these problems and provide a system that allows users to enjoy meals that suit their emotional state while maintaining a healthy diet.

[1102] 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 the user to input dietary information, server means for receiving and analyzing the dietary information, means for comparing the analyzed nutrient data with standard intake amounts to calculate nutrient deficiency or excess, means for analyzing the user's emotional data, means for recommending restaurants based on the nutrient deficiency or excess and the emotional data, and means for notifying the user of the recommended restaurant information. This enables the user to easily manage their diet and find restaurants that provide an optimal dining environment that takes their emotional state into consideration.

[1103] "Dietary information" refers to information about ingredients and dishes consumed by the user, and is provided through text, voice, or other input means.

[1104] "Nutrient data" refers to information on major nutrients extracted from dietary information, and specifically includes carbohydrates, proteins, vitamins, etc. contained in each ingredient or dish.

[1105] "Emotion data" is information about the user's emotional state analyzed from facial expressions, tone of voice, etc., and includes states such as relaxation, stress, and anxiety.

[1106] "Recommendation" is the act of suggesting the most suitable restaurant based on the user's nutritional deficiency or excess and emotional data.

[1107] "Natural language processing technology" is a general term for technology that analyzes natural language data such as text and speech, and understands and extracts meaning.

[1108] A "standard intake" is a reference value that indicates the amount of each nutrient needed per day to maintain health, and is determined based on age, gender, weight, etc.

[1109] "Server means" refers to computer resources or programs for receiving and analyzing meal information and emotion data provided by the user.

[1110] The system embodying this invention allows users to input their own dietary information, analyzes it to calculate nutrient deficiencies and excesses, and recommends appropriate restaurants based on their emotional state, allowing users to maintain their health while enjoying meals that suit their emotional state.

[1111] First, the user inputs meal information using the smart glasses' voice recognition system. The voice recognition system converts the voice input into text data and sends the meal information to the device. For example, the user might say, "I had toast and eggs for breakfast, and salad and chicken for lunch," which is input as text data.

[1112] Next, emotion recognition is performed. The smart glasses' camera and microphone are used to analyze the user's facial expressions and tone of voice in real time to recognize their emotional state. For emotion recognition, the FER library is used to detect emotions such as joy, sadness, and stress from the user's facial expressions.

[1113] The obtained food information and emotion data are converted into JSON format and sent as an HTTP request to the server, which receives the request at its API endpoint, parses the data, and prepares it for analysis.

[1114] The server analyzes the received meal information and uses natural language processing (NLP) to extract key nutrient data. The analyzed nutrient data is compared with standard intakes based on the user's age, gender, and weight, and any nutrient surpluses or deficiencies are calculated. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[1115] After calculating the nutrient surplus / deficiency, the server recommends appropriate restaurants based on that information and emotional data. For example, if a user is feeling stressed, a recommendation algorithm based on emotional data will recommend restaurants with a relaxing environment. Specifically, the server creates a list of restaurant candidates based on the nutrient surplus / deficiency data, and then selects from that list the restaurant that best suits the user's emotional state.

[1116] The recommendation results are again generated in JSON format and sent to the device as an HTTP response. The device receives the response from the server, parses it, and displays it on the screen. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[1117] An example prompt is:

[1118] "Enter the user's dietary information, analyze the nutritional data, and output recommendations. The recommendations change depending on the user's emotional state."

[1119] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1120] Step 1:

[1121] The user inputs meal information using the smart glasses' voice recognition system. The voice input is converted into text data and sent to the device. For example, if the user says, "I had toast and eggs for breakfast, and salad and chicken for lunch," this information is converted into text using voice recognition technology. The input data is saved as "meal information."

[1122] Step 2:

[1123] The emotion recognition module uses the smart glasses' camera and microphone to analyze the user's facial expressions and tone of voice in real time to recognize their emotional state. The acquired emotional data is stored as "emotion data." For example, the FER library can be used to detect "stress" from the user's facial expressions.

[1124] Step 3:

[1125] The device converts the obtained food information and emotion data into JSON format and sends it to the server as an HTTP request. The input data is food information and emotion data, which are encoded as structured data.

[1126] Step 4:

[1127] The server receives HTTP requests at the API endpoint, parses the data, and prepares it for analysis. The server then sends the parsed data to the analysis module. The input data is food information and emotion data in JSON format, which is then converted into an analyzable format.

[1128] Step 5:

[1129] The server analyzes the meal information using natural language processing technology and extracts key nutrient data. The input data is the text of the meal information, and the output data is the nutrient data for each ingredient. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[1130] Step 6:

[1131] The server compares the extracted nutrient data with the standard intake based on the user's age, gender, and weight, and calculates whether a nutrient is insufficient or excessive. The input data is the nutrient data and the user's basic information, and the output data is information on whether a nutrient is insufficient or excessive. For example, it can be calculated that the user's protein intake is already above the standard amount, but that the user is deficient in vitamins.

[1132] Step 7:

[1133] The server recommends appropriate restaurants based on the nutrient deficiency and excess data and emotional data. The input data is nutrient deficiency and excess data and emotional data, and the output data is a list of recommended restaurants. For example, if the user is feeling "stressed," the server selects restaurants with a relaxing environment.

[1134] Step 8:

[1135] The server generates the recommendation results in JSON format and sends them to the terminal as an HTTP response. The input data is a list of recommended restaurants, and the output data is the recommendation information in JSON format.

[1136] Step 9:

[1137] The device receives the response from the server, parses it, and displays it on the screen. The input data is recommendation information in JSON format, and the output data is information that is visually displayed to the user. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[1138] 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.

[1139] 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.

[1140] 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.

[1141] [Fourth embodiment]

[1142] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1143] 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.

[1144] 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).

[1145] 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.

[1146] 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.

[1147] 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).

[1148] 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.

[1149] 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.

[1150] 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.

[1151] 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.

[1152] 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.

[1153] 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.

[1154] 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."

[1155] The system according to the present invention allows a user to input their own dietary information, analyzes the information, calculates nutrient deficiencies and excesses, and recommends appropriate restaurants. Specific embodiments are described in detail below.

[1156] First, the user inputs information about their most recent meal into the device. For example, the user enters specific details of their meal into a text box, such as "I had toast and eggs for breakfast, and salad and chicken for lunch." After inputting the details, the user presses the send button to send the meal information to the server.

[1157] The device then converts the user's input data into JSON format and sends it as an HTTP request to the server, which receives the request at an API endpoint, parses the data, and prepares it for analysis.

[1158] The server analyzes the received meal information and extracts key nutrient data. This is done using natural language processing technology. The server analyzes the meal contents and extracts key nutrients from each ingredient and dish. For example, carbohydrates and protein are extracted from "toast and eggs," and vitamin C and protein are extracted from "salad and chicken."

[1159] Once the analysis is complete, the server compares the extracted nutrient data with the standard intake amount to calculate whether there is a nutrient deficiency or excess. The standard intake amount is set based on the user's age, gender, weight, etc. The comparison results in a determination of which nutrients are deficient and which are in excess.

[1160] The server then recommends restaurants that can help fill any nutrient gaps. For example, if you're deficient in vitamin D, it will recommend restaurants that serve fish or mushroom dishes. The server also includes information such as the name and location of each restaurant, as well as the dishes they serve.

[1161] Finally, the server notifies the user of the recommended restaurant information. The server sends the recommended restaurant information to the terminal, which then displays the information to the user. This allows the user to easily know which restaurants they should visit to improve their nutritional balance.

[1162] For example, the display may say, "We recommend nearby seafood restaurant A to supplement your vitamin D." In this way, by using the system of the present invention, users can easily adjust the nutrients they need to maintain a healthy diet.

[1163] The processing flow will be explained below.

[1164] Step 1:

[1165] The user enters meal information. The user enters meal details into the text box on the device, for example, "I had toast and eggs for breakfast, and salad and chicken for lunch," and presses the send button.

[1166] Step 2:

[1167] The terminal sends the input data to the server. The terminal converts the user's input data into JSON format and sends it to the server as an HTTP request.

[1168] Step 3:

[1169] The server receives the input data. The server receives the HTTP request at the API endpoint and parses the JSON data to prepare it for analysis.

[1170] Step 4:

[1171] The server analyzes the meal information. It uses natural language processing technology to extract key nutrient data from each part of the meal. For example, it extracts carbohydrates from "toast," proteins from "eggs," and vitamins from "salad."

[1172] Step 5:

[1173] The server compares the nutrient data with the standard intake amount. The server refers to a database of standard intake amounts based on the user's age, sex, and weight, and compares the extracted nutrient data to calculate whether there is a surplus or deficiency.

[1174] Step 6:

[1175] The server calculates the nutrient deficiency or excess, and determines whether each nutrient is deficient or excessive based on the comparison results.

[1176] Step 7:

[1177] The server recommends restaurants. Based on the nutrient deficiency data, the server extracts and lists restaurants from the database that can provide the nutrients you are lacking. For example, if you are deficient in vitamin D, it will find restaurants that serve fish dishes.

[1178] Step 8:

[1179] The server sends the recommendation information to the device. Information about the recommended restaurants is generated in JSON format and sent to the device as an HTTP response.

[1180] Step 9:

[1181] The device displays the recommended information to the user. The device receives the response from the server, parses it, and displays it on the screen. The user can refer to this information to choose an appropriate restaurant to eat at.

[1182] Through this series of processes, users can easily understand their own nutritional balance and obtain specific dietary options to supplement their necessary nutrients.

[1183] Example 1

[1184] 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."

[1185] In conventional systems, even if users input their dietary information, the information could not be analyzed efficiently and accurately, and sufficient advice on maintaining a proper nutritional balance could not be provided. As a result, users had difficulty understanding their own nutrient deficiencies and excesses, and were unable to make appropriate dietary choices. Furthermore, if a user was lacking in a particular nutrient, it was difficult to find an appropriate restaurant to supplement that nutrient.

[1186] 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.

[1187] In this invention, the server includes a means for a user to input dietary information, a means for converting the dietary information into JSON format and sending it to the server as an HTTP request, a server means for receiving the HTTP request and analyzing the data, a means for comparing the analyzed nutrient data with standard intake amounts and calculating nutrient deficiencies, a means for recommending restaurants that can compensate for the nutrient deficiencies, and a means for notifying the user of the recommended restaurants. This allows users to easily input their dietary information and accurately determine whether they are nutrient deficient or not based on that information. Furthermore, users can quickly find appropriate restaurants to compensate for nutrient deficiencies, allowing them to take specific actions to maintain a healthy diet.

[1188] A "user" is a person who uses the system to input dietary information and receives nutrient analysis results and recommendation information.

[1189] "Dietary information" is details of the meal the user has most recently eaten, and is entered into a text box and sent.

[1190] A "terminal" is a device used by a user to input meal information and communicate with the server, and includes smartphones, tablets, PCs, etc.

[1191] "JSON format" is a data format used to send meal information to a server as structured data.

[1192] An "HTTP request" is a communication protocol for sending data from a terminal to a server.

[1193] A "server" is a device that analyzes dietary information received from a user, extracts nutrient data, and returns recommended information to the user.

[1194] "Natural language processing technology" is a technology used to extract nutrient data from dietary information and analyzes text data.

[1195] "Nutrient data" is information on various nutritional components extracted from dietary content.

[1196] The "standard intake" is the amount of nutrients required daily, set based on the user's age, sex, weight, etc.

[1197] A "restaurant" is a place that serves food and drinks, and is a recommended store to help users meet their nutritional needs.

[1198] "Recommendation" refers to the act of recommending appropriate restaurants to help the user meet their nutritional needs.

[1199] "Recommendation information" is detailed information about suitable restaurants that can help users make up for nutrient deficiencies and excesses, sent from the server to the user.

[1200] "Notification" refers to the act of conveying important information, such as recommendation information, to the user via the device.

[1201] The system according to the present invention allows a user to input their own dietary information, analyzes the information, calculates nutrient deficiencies and excesses, and recommends appropriate restaurants. Specific embodiments are described in detail below.

[1202] First, the user inputs the most recent meal information into the device. For example, the user enters specific meal details such as "I had toast and eggs for breakfast, and salad and chicken for lunch" into the text box on the device, and then presses the send button to send the meal information to the server.

[1203] The terminal converts the input data into JSON format. For example, it converts the text data "I had toast and eggs for breakfast, and salad and chicken for lunch" into JSON data { "breakfast": "toast and eggs", "lunch": "salad and chicken"}. The converted data is sent to the server as an HTTP request.

[1204] The server receives HTTP requests at the API endpoint, parses the received JSON data, and prepares it for analysis. Natural language processing techniques (e.g., spaCy, NLTK, Transformers) are used to extract key nutrient data from the meal contents. For example, carbohydrates and protein are extracted from "toast and eggs," and vitamin C and protein are extracted from "salad and chicken."

[1205] The server then compares the extracted nutrient data with the standard intake based on the user's profile information, such as age, gender, and weight. This comparison calculates whether each nutrient is in a deficiency or excess. For example, a 30-year-old man may be found to have sufficient carbohydrates but a vitamin D deficiency.

[1206] The server then recommends appropriate restaurants based on the nutrient deficiency or excess. For example, if a person is deficient in vitamin D, it searches the database for restaurants that serve fish or mushroom dishes, and lists information such as the specific restaurant's name, location, and the dishes they serve.

[1207] Finally, the server sends the recommendation information to the device, which then displays the received information to the user, notifying them of the specific recommendation, "We recommend a nearby seafood restaurant to supplement your vitamin D intake." This allows the user to immediately take action to efficiently adjust their nutritional balance.

[1208] Specific examples

[1209] For example, a user enters the following prompt into the system:

[1210] "I had toast and eggs for breakfast and salad and chicken for lunch. Please calculate my nutritional surplus and deficiency and recommend restaurants that are good for me."

[1211] The system responds with the following:

[1212] "I recommend a nearby seafood restaurant to get some Vitamin D."

[1213] By using this system, users can easily manage their own dietary information and take quick action to maintain proper nutritional balance.

[1214] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1215] Step 1:

[1216] The user inputs meal information into the terminal.

[1217] Input: Specific meal details (e.g., "I had toast and eggs for breakfast and salad and chicken for lunch.")

[1218] Action: Enter this information into a text box in the terminal application.

[1219] Output: The input text data

[1220] Step 2:

[1221] The user presses the send button.

[1222] Input: Text data (meal information)

[1223] Processing: Detects that the submit button has been pressed and passes the entered data to the next processing step.

[1224] Output: Text data (prepared for transmission)

[1225] Step 3:

[1226] The device converts the meal information into JSON format.

[1227] Input: Text data (meal information)

[1228] Processing: Use a conversion function to convert text data into JSON format (e.g., {"breakfast": "toast and eggs", "lunch": "salad and chicken"}).

[1229] Output: JSON data

[1230] Step 4:

[1231] The device generates an HTTP request and sends it to the server.

[1232] Input: JSON data

[1233] Processing: Generate an HTTP request and send it to the server's API endpoint, including the JSON data.

[1234] Output: HTTP request (including JSON data)

[1235] Step 5:

[1236] The server receives the HTTP request and prepares to parse the data.

[1237] Input: HTTP request (including JSON data)

[1238] Processing: Receive the request and parse the JSON data.

[1239] Output: Parsed meal information data

[1240] Step 6:

[1241] The server uses natural language processing technology to analyze the dietary information and extract nutrient data.

[1242] Input: Parsed meal information data

[1243] Processing: Using natural language processing libraries (e.g., spaCy, NLTK), extract nutrients from meal descriptions (e.g., extract carbohydrates and protein from "toast and eggs," and vitamin C and protein from "salad and chicken").

[1244] Output: Extracted nutrient data (e.g. carbohydrates, protein, vitamin C)

[1245] Step 7:

[1246] The server compares the nutrient data with standard intakes and calculates nutrient surpluses and deficiencies.

[1247] Input: Extracted nutrient data, standard intake information (based on age, sex, and weight)

[1248] Processing: Nutrient data is compared to standard intakes based on user profile information to calculate deficiencies or excesses (e.g., enough carbohydrates but not enough vitamin D).

[1249] Output: Nutrient deficiency and excess data

[1250] Step 8:

[1251] The server will recommend restaurants that will help you make up for any nutrient deficiencies or excesses.

[1252] Input: Nutrient deficiency and excess data, restaurant information database

[1253] Processing: Search the database for appropriate restaurants based on the deficiency or surplus and create a list (e.g., if there is a vitamin D deficiency, recommend a seafood restaurant).

[1254] Output: Recommendation information (restaurant name, location, dishes served, etc.)

[1255] Step 9:

[1256] The server transmits the recommendation information to the terminal.

[1257] Input: Recommendation information

[1258] Processing: Generate data including recommendation information as an HTTP response and send it to the terminal.

[1259] Output: HTTP response (including recommendation information)

[1260] Step 10:

[1261] The device displays the recommended information to the user.

[1262] Input: HTTP response (including recommendation information)

[1263] Processing: Parse the received recommendation information and display it in a user-friendly format (e.g., "We recommend a nearby seafood restaurant to help you get your vitamin D.").

[1264] Output: Recommendation information displayed to the user (visual display)

[1265] (Application example 1)

[1266] 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."

[1267] Conventional nutrition management systems allow users to input their own dietary information and calculate nutrient deficiencies or excesses, but they lack the functionality to consistently support users, from specific meal suggestions based on the results to using food delivery services. This means that users have to go through the trouble of actually selecting and ordering meals, which reduces their ability to maintain a healthy diet.

[1268] 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.

[1269] In this invention, the server includes means for a user to input dietary information, means for receiving and analyzing the dietary information, means for comparing the analyzed nutrient data with standard intakes and calculating nutrient deficiencies and excesses, means for recommending restaurants that will compensate for the nutrient deficiencies and excesses, means for notifying the user of information on the recommended restaurants, means for placing an order with a food delivery service, and means for suggesting appropriate dishes to compensate for the nutrient deficiencies and excesses. This allows users to receive consistent support while receiving specific dietary suggestions for maintaining a healthy diet, and makes it easy to use food delivery services.

[1270] A "user" is a person who uses the system to input their own dietary information and receives analysis results and suggestions regarding nutrient deficiencies and excesses.

[1271] "Dietary information" is data in which the user specifically describes the contents of their own meals, including the names of ingredients and dishes and the amounts consumed.

[1272] The "server" is a computer system that receives and analyzes dietary information sent by a user and calculates deficiencies or excesses in nutrient data.

[1273] "Nutrient data" is information on the quantity and type of each nutrient extracted from dietary information.

[1274] The "standard intake amount" is a reference intake amount for a particular nutrient that is set based on the user's age, sex, weight, etc.

[1275] "Excess or deficiency" is the result of comparing the intake of each nutrient calculated based on the user's dietary information with the standard intake, and is information indicating whether there is an excess or deficiency.

[1276] "Restaurant" means an establishment established to provide meals, and the dishes offered therein are suitable for supplementing nutritional deficiencies or excesses.

[1277] "Recommendation" refers to the system selecting and suggesting appropriate restaurants and dishes based on the user's nutritional deficiencies or excesses.

[1278] A "food delivery service" is a service that allows users to order food from restaurants and have it delivered without having to move to another location.

[1279] An "appropriate meal" is a specific meal that is recommended to compensate for the user's nutritional deficiency or excess.

[1280] The present invention relates to a system that allows a user to input their own dietary information, analyzes the information, calculates nutrient deficiencies and excesses, and suggests appropriate restaurants and dishes.

[1281] System program generation

[1282] This system is realized by performing a complex process including the following means.

[1283] Hardware and Software

[1284] Hardware: Smartphone (iOS / Android)

[1285] Software: A Python environment to run the application, an HTTP library (requests), a JSON library, and a natural language processing library (e.g., spaCy or NLTK).

[1286] Data processing and calculation

[1287] Data entry: The user enters meal information into the device in text format, for example, "toast and eggs for breakfast, salad and chicken for lunch."

[1288] Examples:

[1289] Enter your most recent meal (e.g., toast and eggs for breakfast, salad and chicken for lunch):

[1290] Data transmission: The device converts the entered meal information into JSON format and sends it to the server as an HTTP request. For example, it is sent to the server in the following format:

[1291] Sending example:

[1292] json

[1293] {

[1294] "meal_info": "Toast and eggs for breakfast, salad and chicken for lunch"

[1295] }

[1296] Data analysis: The server analyzes the received data and uses natural language processing techniques to extract key nutrient data, for example, carbohydrates and protein from "toast and eggs" and vitamin C and protein from "salad and chicken."

[1297] Nutrient deficiency / surplus calculation: The server compares the extracted nutrient data with the standard intake amount, which is set based on the user's age, gender, weight, etc. As a result of the comparison, the deficiency / surplus of each nutrient is calculated.

[1298] Recommendations: The server recommends restaurants and dishes to help you meet your nutritional needs. For example, if you are deficient in vitamin D, it will suggest restaurants that serve fish or mushroom dishes, or alternative dishes.

[1299] Notification and ordering: The server sends the recommendation results to the device and notifies the user, allowing the user to easily find out about the recommended restaurants and dishes, and also supporting the use of food delivery services.

[1300] Specific examples

[1301] For example, a user enters meal information as follows:

[1302] Enter your most recent meal (e.g., toast and eggs for breakfast, salad and chicken for lunch):

[1303] Once the input is complete, the device converts the dietary information into JSON format and sends it to the server. The server analyzes the data, calculates which nutrients the user is lacking, and suggests appropriate dishes based on the results. For example, if the user is deficient in vitamin D, the system:

[1304] To supplement your vitamin D intake, the recommended menu item at nearby seafood restaurant A is salmon steak.

[1305] Furthermore, by selecting the notification, you can easily use food delivery services.

[1306] In this way, users can receive consistent support, receive specific meal suggestions to maintain a healthy diet, and easily use food delivery services.

[1307] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1308] Step 1:

[1309] Users input meal information in text format using a device such as a smartphone. The input content is specific meal details such as "toast and eggs for breakfast, salad and chicken for lunch." This input information becomes the basis of the data.

[1310] input:

[1311] Toast and eggs for breakfast, salad and chicken for lunch

[1312] output:

[1313] Text-based meal information

[1314] Step 2:

[1315] The device converts the meal information entered by the user into JSON format and sends it to the server as an HTTP request. Specifically, the converted JSON data has the following format:

[1316] input:

[1317] Text-based meal information

[1318] Data processing:

[1319] {

[1320] "meal_info": "Toast and eggs for breakfast, salad and chicken for lunch"

[1321] }

[1322] output:

[1323] Meal information in JSON format

[1324] Step 3:

[1325] The server analyzes the received meal information. Specifically, it uses natural language processing technology to extract key nutrient data from the meal contents. For example, carbohydrates and protein are extracted from "toast and eggs," and vitamin C and protein are extracted from "salad and chicken."

[1326] input:

[1327] Meal information in JSON format

[1328] Data Calculation:

[1329] Libraries used: spaCy, NLTK

[1330] {

[1331] "carbohydrates": 30,

[1332] "protein": 20,

[1333] "vitaminC": 10

[1334] }

[1335] output:

[1336] Key Nutrient Data

[1337] Step 4:

[1338] The server compares the extracted nutrient data with the standard intake amount and calculates the nutrient deficiency or excess. The standard intake amount is set based on the user's age, gender, and weight information. The deficiency or excess is determined based on this data.

[1339] input:

[1340] Key Nutrient Data

[1341] Data Calculation:

[1342] Vitamin D: -5 (deficiency)

[1343] Protein: +10 (excess)

[1344] output:

[1345] Nutrient deficiency or excess

[1346] Step 5:

[1347] The server recommends restaurants and food delivery services that provide meals that can help fill nutrient gaps and deficiencies.

[1348] input:

[1349] Nutrient deficiency or excess

[1350] Data processing:

[1351] [

[1352] {

[1353] "restaurant_name": "Seafood Restaurant A",

[1354] "menu_item": "Salmon steak",

[1355] "nutrient": "vitamin D"

[1356] }

[1357] ]

[1358] output:

[1359] Recommended information

[1360] Step 6:

[1361] The server sends the recommendation information to the terminal, which then notifies the user. The user can then check the recommended restaurants and dishes and place an order using a food delivery service if necessary.

[1362] input:

[1363] Recommended information

[1364] Data processing:

[1365] To supplement your vitamin D intake, the recommended menu item at nearby seafood restaurant A is salmon steak.

[1366] output:

[1367] Recommendation information notified to the user

[1368] In this way, the entire system processes, providing users with consistent support and specific meal suggestions to maintain a healthy diet.

[1369] 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.

[1370] The system according to the present invention allows a user to input their own dietary information, analyzes the information to calculate nutrient deficiencies and excesses, and recommends suitable restaurants, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments are described in detail below.

[1371] First, the user inputs their most recent meal information into the device. For example, they enter specific details of their meal, such as "I had toast and eggs for breakfast, and salad and chicken for lunch," into the text box and press the send button. At that time, the emotion engine analyzes the user's facial expressions and tone of voice in real time to recognize their emotional state.

[1372] Next, the device converts the user's input data and the emotion data recognized by the emotion engine into JSON format and sends it as an HTTP request to the server. The server receives this request at an API endpoint, parses the data, and prepares it for analysis.

[1373] The server analyzes the received meal information and extracts key nutrient data. This is done using natural language processing technology. The server analyzes the meal contents and extracts key nutrients from each ingredient and dish. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[1374] Once the analysis is complete, the server compares the extracted nutrient data with the standard intake amount to calculate whether there is a nutrient deficiency or excess. The standard intake amount is set based on the user's age, gender, weight, etc. The comparison results in a determination of which nutrients are deficient and which are in excess.

[1375] The server then recommends restaurants that can help replenish the user's nutritional needs. This recommendation also takes into account the user's emotional data. For example, if the user is feeling stressed, the server will recommend restaurants with a relaxing environment.

[1376] The recommendation routine based on emotion data works as follows: The server creates a list of restaurant candidates based on nutrient deficiency data, and then selects the restaurant that best suits the user's emotional state. Specifically, it recommends restaurants that offer relaxing ingredients and restaurants with a calming atmosphere.

[1377] The recommendation results are generated in JSON format and sent to the device as an HTTP response. The device receives the response from the server, parses it, and displays it on the screen. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[1378] For example, the display might say, "To supplement your vitamin D, we recommend nearby seafood restaurant A." This restaurant is selected based on the user's emotional state. If the emotion engine recognizes that the user is feeling stressed, it will select a restaurant that offers a relaxing restaurant environment and a menu suitable for changing the mood.

[1379] In this way, by using the system of the present invention, users can easily understand their own nutritional balance and select an appropriate eating environment according to their emotional state.

[1380] The processing flow will be explained below.

[1381] Step 1:

[1382] The user inputs meal information. The user enters meal details into the device's text box, for example, "I had toast and eggs for breakfast, and salad and chicken for lunch," and presses the send button. The emotion engine also analyzes the user's facial expressions and tone of voice in real time to recognize the user's emotional state.

[1383] Step 2:

[1384] The device sends the input data and emotion data to the server. The device converts the user's meal information and the emotion data recognized by the emotion engine into JSON format and sends it to the server as an HTTP request.

[1385] Step 3:

[1386] The server receives the input data and emotion data. The server receives the HTTP request at the API endpoint, parses the JSON data, and prepares it for analysis.

[1387] Step 4:

[1388] The server analyzes the meal information. It uses natural language processing technology to extract key nutrient data from each part of the meal. For example, it extracts carbohydrates from "toast," proteins from "eggs," and vitamins from "salad."

[1389] Step 5:

[1390] The server compares the nutrient data with the standard intake amount. The server refers to a database of standard intake amounts based on the user's age, sex, and weight, and compares the extracted nutrient data to calculate whether there is a surplus or deficiency.

[1391] Step 6:

[1392] The server calculates the nutrient deficiency or excess, and determines whether each nutrient is deficient or excessive based on the comparison results.

[1393] Step 7:

[1394] The server recommends restaurants. Based on the nutrient deficiency data, the server extracts and lists restaurants from the database that can provide the missing nutrients. This recommendation also takes into account the user's recognized emotional data. For example, if the user is feeling stressed, the server will recommend restaurants with a relaxing environment.

[1395] Step 8:

[1396] The server sends the recommendation information to the device. Information about the recommended restaurants is generated in JSON format and sent to the device as an HTTP response.

[1397] Step 9:

[1398] The device displays the recommended information to the user. The device receives the response from the server, parses the data, and displays it on the screen. The user can refer to this information to choose an appropriate restaurant. For example, the device may display, "To supplement your vitamin D, we recommend nearby seafood restaurant A." This restaurant is selected based on the user's emotional state, offering a relaxing restaurant environment and a menu suitable for a change of pace.

[1399] Example 2

[1400] 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."

[1401] Conventional nutrient analysis and restaurant recommendation systems recommend restaurants simply based on nutrient data without taking the user's emotional state into consideration, which means that they are unable to make recommendations that are appropriate for the user's emotional state, and this does not lead to increased satisfaction or stress reduction.

[1402] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1403] In this invention, the server includes means for receiving and analyzing input dietary information and user emotional information, means for comparing the analyzed nutrient data with standard intake amounts to calculate nutrient deficiencies and excesses, and means for recommending restaurants that will compensate for nutrient deficiencies and excesses, taking into account the user's emotional state. This makes it possible to recommend optimal restaurants that match the user's emotional state.

[1404] A "user" is a person who uses the system to input their own dietary information and receive the analysis results.

[1405] "Dietary information" is text data entered by a user about the contents of their meal, such as "I had toast and eggs for breakfast."

[1406] "Emotion information" is emotion data obtained from the user's facial expression and tone of voice, and indicates psychological states such as stress and happiness, for example.

[1407] The "server" is a computer system that receives dietary information and emotional information sent by users, analyzes it, calculates nutrient deficiencies and excesses, and recommends restaurants.

[1408] "Natural language processing technology" is a technology that allows computers to understand, interpret, and generate human language, and is used to extract nutritional data from dietary information.

[1409] "Nutrient data" refers to data on nutrients such as carbohydrates, proteins, and vitamins obtained by analyzing dietary information.

[1410] The "standard intake amount" is the appropriate daily intake amount of nutrients that is set based on the user's age, sex, weight, etc.

[1411] "Deficiency" refers to a state of deficiency or excess of a particular nutrient, determined when nutrient data is compared with standard intakes.

[1412] "Restaurant recommendation" refers to recommending restaurants suitable for the user, taking into consideration the user's nutritional deficiency and emotional state.

[1413] The "notification means" refers to a means for transmitting the recommendation results generated by the server to the user, and includes a method of displaying the results on the terminal.

[1414] MODE FOR CARRYING OUT THE INVENTION

[1415] The system according to the present invention allows a user to input their own dietary information, analyzes the information to calculate nutrient deficiencies and excesses, and recommends suitable restaurants, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments are described in detail below.

[1416] First, the user inputs information about their most recent meal into their device. For example, the user enters specific details of their meal into a text box, such as "I had toast and eggs for breakfast, and salad and chicken for lunch," and presses the send button. At this time, the emotion engine analyzes the user's facial expressions and tone of voice in real time to recognize the user's emotional state.

[1417] Next, the device converts the user's input data and the emotion data recognized by the emotion engine into JSON format and sends it as an HTTP request to the server. The server receives this request at an API endpoint, parses the data, and prepares it for analysis.

[1418] The server analyzes the received meal information and extracts key nutrient data. This analysis uses natural language processing technology. Specifically, it uses the Google Cloud Natural Language API to analyze the meal contents and extract key nutrients from each ingredient and dish. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[1419] Once the analysis is complete, the server compares the extracted nutrient data with standard intakes based on the user's age, gender, and weight to determine whether the user is deficient in any nutrients. For example, the comparison may determine that the user is deficient in vitamin D.

[1420] The server then recommends restaurants that are suitable for replenishing the nutritional deficiency or excess. This recommendation also takes into account the user's emotional data. For example, if the user is feeling stressed, it will recommend restaurants with a relaxing environment. This recommendation routine lists restaurant candidates based on the nutrient deficiency or excess data, and selects from that list the restaurant that best suits the user's emotional state.

[1421] The recommendation results are generated in JSON format and sent to the device as an HTTP response. The device receives the response from the server, parses it, and displays it on the screen. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[1422] For example, if a user inputs "I had toast and eggs for breakfast and salad and chicken for lunch," and the emotion engine recognizes that the user is under stress, the server will present a recommendation such as "To supplement your vitamin D, we recommend nearby seafood restaurant A." Seafood restaurant A offers a relaxing restaurant environment and a menu suitable for reducing stress.

[1423] Below are some examples of specific prompts that are useful for using the system: "If a user has had toast and eggs for breakfast and salad and chicken for lunch and is feeling stressed, which restaurant would you recommend?" can be input into the generative AI model to obtain effective recommendations.

[1424] In this way, by using the system of the present invention, users can easily understand their own nutritional balance and select an appropriate eating environment according to their emotional state.

[1425] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1426] Step 1:

[1427] The user inputs his / her meal information into the terminal.

[1428] Input: A user enters a meal description into a text box, such as "I had toast and eggs for breakfast and salad and chicken for lunch."

[1429] Output: The terminal holds the input data.

[1430] Specific operation: The user enters meal information and presses the send button. The device collects the input data and begins processing.

[1431] Step 2:

[1432] The device analyzes the user's facial expressions and tone of voice in real time, and the emotion engine recognizes their emotional state.

[1433] Input: Data on the user's facial expressions and tone of voice from the device's camera and microphone.

[1434] Output: "Emotional state data" recognized by the emotion engine.

[1435] Specific operation: The device's camera captures the user's facial expressions, the microphone analyzes the tone of the voice, and sends them to the emotion engine to analyze the emotional state.

[1436] Step 3:

[1437] The device converts the meal information and emotional state data into JSON format and sends it to the server as an HTTP request.

[1438] Input: Food information text data and emotional state data.

[1439] Output: The HTTP request with the data converted to JSON format.

[1440] Specific operation: The device integrates the input data and emotion data, converts them into JSON format, generates an HTTP request, and sends it to the server.

[1441] Step 4:

[1442] The server receives the HTTP request and parses the JSON data, preparing it for analysis.

[1443] Input: The JSON data sent by the HTTP request.

[1444] Output: Data ready for analysis.

[1445] What happens: The server receives the HTTP request and converts the JSON data into a format that is easy to parse.

[1446] Step 5:

[1447] The server analyzes the dietary information using natural language processing technology and extracts key nutrient data.

[1448] Input: Parsed meal information data.

[1449] Output: Extracted macronutrient data.

[1450] How it works: The server uses natural language processing APIs to identify and extract nutrients from food information, for example, extracting carbohydrates from "toast" and protein from "eggs."

[1451] Step 6:

[1452] The server compares the nutrient data with standard intakes and calculates nutrient surpluses and deficiencies.

[1453] Input: Extracted nutrient data and standard intake data.

[1454] Output: Nutrient deficiency and excess data.

[1455] Specific operation: The server compares the nutrient data with the standard intake and determines whether there is a deficiency or excess, such as a vitamin D deficiency.

[1456] Step 7:

[1457] The server takes into account the user's emotional state and recommends appropriate restaurants to compensate for any nutrient deficiencies or excesses.

[1458] Input: Nutrient deficiency and excess data and emotional state data.

[1459] Output: Recommended restaurant information.

[1460] Specific operation: The server uses a recommendation algorithm to select restaurants that, for example, can help replenish vitamin D deficiency and reduce stress.

[1461] Step 8:

[1462] The server generates the recommendation results in JSON format and sends them to the terminal as an HTTP response.

[1463] Input: Recommended restaurant information.

[1464] Output: HTTP response in JSON format containing the recommendation results.

[1465] Specific operation: The server generates recommendation results in JSON format and sends them to the device as an HTTP response.

[1466] Step 9:

[1467] The device receives the HTTP response from the server, parses it, and displays it on the screen.

[1468] Input: HTTP response (JSON data) from the server.

[1469] Output: Recommendation results displayed on the screen.

[1470] Specific behavior: The device receives the HTTP response, parses the JSON data, and displays to the user, "To supplement your vitamin D, we recommend nearby seafood restaurant A."

[1471] Through these steps, users can receive restaurant recommendations that suit their nutritional balance and emotional state.

[1472] (Application example 2)

[1473] 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."

[1474] In modern society, it is important to consume a balanced diet to maintain good health. However, it is not easy to manage one's diet and consume the necessary nutrients in the right amounts in a busy daily life. Furthermore, it is difficult with conventional technologies to propose a meal plan that takes into account not only the deficiency or excess of individual nutrients but also the user's emotional state. The present invention aims to solve these problems and provide a system that allows users to enjoy meals that suit their emotional state while maintaining a healthy diet.

[1475] 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 the user to input dietary information, server means for receiving and analyzing the dietary information, means for comparing the analyzed nutrient data with standard intake amounts to calculate nutrient deficiency or excess, means for analyzing the user's emotional data, means for recommending restaurants based on the nutrient deficiency or excess and the emotional data, and means for notifying the user of the recommended restaurant information. This enables the user to easily manage their diet and find restaurants that provide an optimal dining environment that takes their emotional state into consideration.

[1476] "Dietary information" refers to information about ingredients and dishes consumed by the user, and is provided through text, voice, or other input means.

[1477] "Nutrient data" refers to information on major nutrients extracted from dietary information, and specifically includes carbohydrates, proteins, vitamins, etc. contained in each ingredient or dish.

[1478] "Emotion data" is information about the user's emotional state analyzed from facial expressions, tone of voice, etc., and includes states such as relaxation, stress, and anxiety.

[1479] "Recommendation" is the act of suggesting the most suitable restaurant based on the user's nutritional deficiency or excess and emotional data.

[1480] "Natural language processing technology" is a general term for technology that analyzes natural language data such as text and speech, and understands and extracts meaning.

[1481] A "standard intake" is a reference value that indicates the amount of each nutrient needed per day to maintain health, and is determined based on age, gender, weight, etc.

[1482] "Server means" refers to computer resources or programs for receiving and analyzing meal information and emotion data provided by the user.

[1483] The system embodying this invention allows users to input their own dietary information, analyzes it to calculate nutrient deficiencies and excesses, and recommends appropriate restaurants based on their emotional state, allowing users to maintain their health while enjoying meals that suit their emotional state.

[1484] First, the user inputs meal information using the smart glasses' voice recognition system. The voice recognition system converts the voice input into text data and sends the meal information to the device. For example, the user might say, "I had toast and eggs for breakfast, and salad and chicken for lunch," which is input as text data.

[1485] Next, emotion recognition is performed. The smart glasses' camera and microphone are used to analyze the user's facial expressions and tone of voice in real time to recognize their emotional state. For emotion recognition, the FER library is used to detect emotions such as joy, sadness, and stress from the user's facial expressions.

[1486] The obtained food information and emotion data are converted into JSON format and sent as an HTTP request to the server, which receives the request at its API endpoint, parses the data, and prepares it for analysis.

[1487] The server analyzes the received meal information and uses natural language processing (NLP) to extract key nutrient data. The analyzed nutrient data is compared with standard intakes based on the user's age, gender, and weight, and any nutrient surpluses or deficiencies are calculated. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[1488] After calculating the nutrient surplus / deficiency, the server recommends appropriate restaurants based on that information and emotional data. For example, if a user is feeling stressed, a recommendation algorithm based on emotional data will recommend restaurants with a relaxing environment. Specifically, the server creates a list of restaurant candidates based on the nutrient surplus / deficiency data, and then selects from that list the restaurant that best suits the user's emotional state.

[1489] The recommendation results are again generated in JSON format and sent to the device as an HTTP response. The device receives the response from the server, parses it, and displays it on the screen. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[1490] An example prompt is:

[1491] "Enter the user's dietary information, analyze the nutritional data, and output recommendations. The recommendations change depending on the user's emotional state."

[1492] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1493] Step 1:

[1494] The user inputs meal information using the smart glasses' voice recognition system. The voice input is converted into text data and sent to the device. For example, if the user says, "I had toast and eggs for breakfast, and salad and chicken for lunch," this information is converted into text using voice recognition technology. The input data is saved as "meal information."

[1495] Step 2:

[1496] The emotion recognition module uses the smart glasses' camera and microphone to analyze the user's facial expressions and tone of voice in real time to recognize their emotional state. The acquired emotional data is stored as "emotion data." For example, the FER library can be used to detect "stress" from the user's facial expressions.

[1497] Step 3:

[1498] The device converts the obtained food information and emotion data into JSON format and sends it to the server as an HTTP request. The input data is food information and emotion data, which are encoded as structured data.

[1499] Step 4:

[1500] The server receives HTTP requests at the API endpoint, parses the data, and prepares it for analysis. The server then sends the parsed data to the analysis module. The input data is food information and emotion data in JSON format, which is then converted into an analyzable format.

[1501] Step 5:

[1502] The server analyzes the meal information using natural language processing technology and extracts key nutrient data. The input data is the text of the meal information, and the output data is the nutrient data for each ingredient. For example, carbohydrates are extracted from "toast," proteins from "eggs," and vitamins from "salad."

[1503] Step 6:

[1504] The server compares the extracted nutrient data with the standard intake based on the user's age, gender, and weight, and calculates whether a nutrient is insufficient or excessive. The input data is the nutrient data and the user's basic information, and the output data is information on whether a nutrient is insufficient or excessive. For example, it can be calculated that the user's protein intake is already above the standard amount, but that the user is deficient in vitamins.

[1505] Step 7:

[1506] The server recommends appropriate restaurants based on the nutrient deficiency and excess data and emotional data. The input data is nutrient deficiency and excess data and emotional data, and the output data is a list of recommended restaurants. For example, if the user is feeling "stressed," the server selects restaurants with a relaxing environment.

[1507] Step 8:

[1508] The server generates the recommendation results in JSON format and sends them to the terminal as an HTTP response. The input data is a list of recommended restaurants, and the output data is the recommendation information in JSON format.

[1509] Step 9:

[1510] The device receives the response from the server, parses it, and displays it on the screen. The input data is recommendation information in JSON format, and the output data is information that is visually displayed to the user. This allows the user to enjoy a meal at a restaurant that matches their emotional state.

[1511] 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.

[1512] 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.

[1513] 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.

[1514] 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.

[1515] 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.

[1516] 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.

[1517] 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).

[1518] 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.

[1519] 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."

[1520] 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.

[1521] 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).

[1522] 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.

[1523] 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.

[1524] 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.

[1525] 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.

[1526] 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.

[1527] 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.

[1528] 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.

[1529] 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.

[1530] 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.

[1531] 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.

[1532] The following is further disclosed regarding the above embodiment.

[1533] (Claim 1)

[1534] a means for a user to input meal information;

[1535] A server means for receiving and analyzing the meal information;

[1536] A means for comparing the analyzed nutrient data with a standard intake amount and calculating nutrient deficiency or excess;

[1537] A means for recommending restaurants to supplement the nutrient deficiency and excess;

[1538] means for notifying a user of the recommended restaurant information;

[1539] A system including:

[1540] (Claim 2)

[1541] 2. The system according to claim 1, wherein the means for analyzing the dietary information is means for extracting nutrient data from the dietary information using natural language processing techniques.

[1542] (Claim 3)

[1543] 2. The system of claim 1, wherein the means for comparing the nutrient data with a standard intake and calculating a nutrient surplus or deficiency takes into account a standard intake based on the user's age and sex.

[1544] "Example 1"

[1545] (Claim 1)

[1546] a means for a user to input meal information;

[1547] means for converting the meal information into JSON format and transmitting it to a server as an HTTP request;

[1548] a server means for receiving the HTTP request and analyzing the data;

[1549] A means for comparing the analyzed nutrient data with a standard intake amount and calculating nutrient deficiency or excess;

[1550] A means for recommending restaurants to supplement the nutrient deficiency and excess;

[1551] means for notifying a user of the recommended restaurant information;

[1552] A system including:

[1553] (Claim 2)

[1554] 2. The system according to claim 1, wherein the means for analyzing the dietary information is means for extracting nutrient data from the dietary information using natural language processing techniques.

[1555] (Claim 3)

[1556] 2. The system of claim 1, wherein the means for comparing the nutrient data with a standard intake and calculating a nutrient surplus or deficiency takes into account a standard intake based on the user's age, sex, and weight.

[1557] "Application Example 1"

[1558] (Claim 1)

[1559] a means for a user to input meal information;

[1560] A server means for receiving and analyzing the meal information;

[1561] A means for comparing the analyzed nutrient data with a standard intake amount and calculating nutrient deficiency or excess;

[1562] A means for recommending restaurants to supplement the nutrient deficiency and excess;

[1563] means for notifying a user of the recommended restaurant information;

[1564] A means of placing an order with a food delivery service;

[1565] A means for suggesting appropriate dishes to compensate for the deficiency or excess of the nutrients;

[1566] A system including:

[1567] (Claim 2)

[1568] 2. The system according to claim 1, wherein the means for analyzing the dietary information is means for extracting nutrient data from the dietary information using natural language processing techniques.

[1569] (Claim 3)

[1570] 2. The system of claim 1, wherein the means for comparing the nutrient data with a standard intake and calculating a nutrient surplus or deficiency takes into account a standard intake based on the user's age and sex.

[1571] "Example 2: Combining Emotion Engines"

[1572] (Claim 1)

[1573] a means for a user to input meal information;

[1574] a server means for receiving and analyzing the input meal information and the user's emotion information;

[1575] A means for comparing the analyzed nutrient data with a standard intake amount and calculating nutrient deficiency or excess;

[1576] A means for recommending restaurants that can supplement the nutrient deficiency or excess, taking into consideration the emotional state of the user;

[1577] means for notifying a user of the recommended restaurant information;

[1578] A system including:

[1579] (Claim 2)

[1580] 2. The system according to claim 1, wherein the means for analyzing the dietary information is means for extracting nutrient data from the dietary information using natural language processing techniques.

[1581] (Claim 3)

[1582] 2. The system of claim 1, wherein the means for comparing the nutrient data with a standard intake and calculating a nutrient surplus or deficiency takes into account a standard intake based on the user's age and sex.

[1583] "Application example 2 when combining emotion engines"

[1584] (Claim 1)

[1585] a means for a user to input meal information;

[1586] A server means for receiving and analyzing the meal information;

[1587] A means for comparing the analyzed nutrient data with a standard intake amount and calculating nutrient deficiency or excess;

[1588] means for analyzing user emotion data;

[1589] A means for recommending restaurants based on the nutrient deficiency and excess data and emotion data;

[1590] means for notifying a user of the recommended restaurant information;

[1591] A system including:

[1592] (Claim 2)

[1593] 2. The system according to claim 1, wherein the means for analyzing the dietary information is means for extracting nutrient data from the dietary information using natural language processing techniques.

[1594] (Claim 3)

[1595] 2. The system of claim 1, wherein the means for comparing the nutrient data with a standard intake and calculating a nutrient surplus or deficiency takes into account a standard intake based on the user's age and sex. [Explanation of symbols]

[1596] 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. a means for a user to input meal information; A server means for receiving and analyzing the meal information; A means for comparing the analyzed nutrient data with a standard intake amount and calculating nutrient deficiency or excess; A means for recommending restaurants to supplement the nutrient deficiency and excess; means for notifying a user of the recommended restaurant information; A system including:

2. 2. The system according to claim 1, wherein the means for analyzing the dietary information is means for extracting nutrient data from the dietary information using natural language processing techniques.

3. The system of claim 1 , wherein the means for comparing the nutrient data with a standard intake and calculating a nutrient surplus or deficiency takes into account a standard intake based on the user's age and sex.

Images