System

Abstract

A system is provided.SOLUTION: A system including means for receiving a comment or a photograph posted by a user and storing data of the comment or the photograph in a database, means for analyzing the stored comment or photograph using an artificial intelligence model and classifying and tagging the comment or the photograph on the basis of a preference of the user, means for proposing a nearby recommended restaurant on the basis of position information of the user on the basis of the analyzed data, means for providing a privilege for a post when the user posts the comment or the photograph, and means for collecting a congestion situation of the restaurant in real time and providing the congestion situation to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Current restaurant search services, while offering multiple review sites, lack the ability to perform detailed searches based on a user's specific preferences. Another problem is that it is difficult for consumers to find restaurants and meals that suit their preferences. Furthermore, restaurants are also required to have effective advertising methods. The objective of this invention is to solve these problems and provide a system that allows consumers to more conveniently find restaurants. [Means for solving the problem]

[0005] The present invention is a system that includes a means for receiving comments and photos posted by users and storing the data in a database, and a means for analyzing the stored comments and photos using an artificial intelligence model and categorizing and tagging them based on the user's preferences. It also includes a means for suggesting recommended nearby restaurants based on the user's location information based on the analyzed data, a means for providing rewards for comments and photos posted by users, and a means for collecting restaurant congestion information in real time and providing the information to users. This allows users to easily find restaurants based on their specific preferences, and the rewards increase their motivation to post. It also enables restaurants to advertise more effectively.

[0006] "User" refers to a user who uses the system to search for and post about restaurants.

[0007] "Terminal" refers to a device operated by a user, such as a smartphone or personal computer.

[0008] "Comments" refer to opinions and evaluations in text format written by users about restaurants and food.

[0009] "Photos" refer to image data that users take of restaurants and food and upload.

[0010] "Server" refers to a computer system that centrally manages the entire system and stores, analyzes, and provides information.

[0011] "Database" refers to a storage device that the server uses to store and manage data such as comments and photos.

[0012] An "artificial intelligence model" refers to an algorithm or program that uses AI technology to analyze and classify data.

[0013] "Classification and tagging" refers to the process of assigning categories and characteristics to analyzed data.

[0014] "Location information" refers to data indicating a user's current location, usually obtained using GPS.

[0015] "Benefits" refers to rewards, such as coupons or discounts, that are provided when a user meets the system's conditions.

[0016] A "coupon" is an electronic or paper certificate that allows you to receive discounts or other benefits when paying at a specific restaurant.

[0017] A "discount" refers to a benefit that reduces the total amount paid at a restaurant.

[0018] "Real-time" refers to immediate availability with little or no delay.

[0019] "Crowd situation" refers to the current number of customers in a restaurant and the degree of congestion. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] The system of the present invention includes the following components to enable users to easily and specifically search for restaurants.

[0042] 1. Collecting comments and photos

[0043] Users use the app to post comments and photos about restaurants. The device then sends these posts to the server, which then stores the received comments and photos in a database. This process creates a system in which user experiences are accumulated as information.

[0044] 2. Data Analysis and Classification

[0045] The server periodically scans the comments and photos stored in the database to extract new data. The server then analyzes the data using an artificial intelligence model and assigns categories and tags based on the user's preferences. This analysis process extracts characteristics such as ingredients, atmosphere, and price range. The analysis results are reflected in the user's profile and used for future recommendations.

[0046] 3. Recommended Suggestions

[0047] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preferred characteristics to the server. Based on the received information, the server lists the most suitable restaurants from its database. This makes it possible to make personalized recommendations based on the user's current location and preferences. The restaurant information listed by the server is sent to the device and displayed to the user.

[0048] 4. Posting comments and offering rewards

[0049] When a user posts a new comment or photo about a restaurant, the server records that action. If the reward conditions are met, the server issues a coupon or discount. This coupon information is sent to the terminal and notified to the user, allowing the user to use the reward for their next meal.

[0050] 5. Real-time congestion information

[0051] The restaurant's terminals and Wi-Fi devices periodically send their current occupancy status to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when choosing a restaurant.

[0052] Specific examples

[0053] For example, if a user wants to eat "yakiniku" (grilled meat), they search for "yakiniku" in the app, and the device sends their current location and preference data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. The server then sends this list to the device and presents it to the user. When the user visits a specific restaurant and posts new comments or photos there, the server records the action and issues a coupon. This allows the user to receive a discount and increase their motivation to return. Real-time congestion information is also provided, allowing users to avoid waiting times and choose a restaurant efficiently.

[0054] This process allows users to easily find restaurants that perfectly suit their tastes and also receive special benefits, resulting in a system that encourages increased usage.

[0055] The processing flow will be explained below.

[0056] 1. Comment and photo collection

[0057] Step 1:

[0058] The user launches the app and enters or takes a photo or comments about the restaurant.

[0059] Step 2:

[0060] The device sends the comments and photo data entered by the user to the server.

[0061] Step 3:

[0062] The server stores the received comments and photo data in a database.

[0063] 2. Analysis and Classification

[0064] Step 4:

[0065] The server periodically scans the database for new comments and photos.

[0066] Step 5:

[0067] The server uses an artificial intelligence model to analyze the acquired data, specifically extracting characteristics such as ingredients, atmosphere, and price range from the comments.

[0068] Step 6:

[0069] Based on the analysis results, the server assigns categories and tags to each comment and photo.

[0070] Step 7:

[0071] The server reflects the analysis results in the user profile and updates the user's preference data.

[0072] 3. Recommended Suggestions

[0073] Step 8:

[0074] The user presses the "Search for recommended restaurants" button on the app.

[0075] Step 9:

[0076] The device sends the user's location information and data about the user's preferences to the server.

[0077] Step 10:

[0078] Based on the location information and preference data received by the server, the server searches the database for the most suitable restaurant.

[0079] Step 11:

[0080] The server ranks and lists the search results.

[0081] Step 12:

[0082] The server sends the listed restaurant information to the terminal.

[0083] Step 13:

[0084] The terminal displays the recommended restaurant information to the user.

[0085] 4. Posting comments and offering rewards

[0086] Step 14:

[0087] A user posts a new comment or photo.

[0088] Step 15:

[0089] The terminal transmits the posting data to the server.

[0090] Step 16:

[0091] The server analyzes the post and checks whether it meets the conditions for the reward.

[0092] Step 17:

[0093] The server issues coupons and discounts when certain conditions are met.

[0094] Step 18:

[0095] The server transmits the issued coupon information to the terminal and notifies the user.

[0096] Step 19:

[0097] The terminal displays the coupon information to the user.

[0098] 5. Real-time congestion information

[0099] Step 20:

[0100] The restaurant's terminals and WiFi devices send the store's congestion status to the server.

[0101] Step 21:

[0102] The server analyzes the congestion information received.

[0103] Step 22:

[0104] When a user requests congestion information through the app, the server sends the latest congestion information to the device.

[0105] Step 23:

[0106] The terminal displays real-time congestion status to the user.

[0107] Through the above process, users can easily find restaurants that suit their tastes. In addition, they can receive rewards, which motivates them to post, and they can also check the real-time congestion status, which helps them avoid crowded restaurants.

[0108] Example 1

[0109] 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."

[0110] Conventional restaurant search systems make it difficult for users to quickly find suitable restaurants, and they lack real-time information about restaurant congestion and suggestions based on user preferences. This results in a limited user experience and the inconvenience of having to use multiple applications. Furthermore, they lack incentives for users to post information.

[0111] 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.

[0112] In this invention, the server includes: means for receiving comments and photos posted by users and storing the data in a database; means for analyzing the stored comments and photos using an artificial intelligence model and categorizing and tagging them based on the user's preferences; means for suggesting nearby recommended restaurants based on the user's location information based on the analyzed data; means for providing rewards for comments and photos posted by users; and means for receiving congestion status data transmitted by the restaurant's communication terminal or wireless communication device and providing the data to the user in real time. This allows users to easily find restaurants that perfectly match their preferences and makes appropriate choices based on real-time information. Furthermore, providing rewards for user posts increases user engagement.

[0113] "User" means an individual who uses the Application to post comments and photos of restaurants and obtain information.

[0114] A "terminal" refers to an electronic device on which an application is installed, such as a smartphone or tablet used by a user.

[0115] "Server" means a computer system that receives, stores, and processes data from users, analyzes comments and photos, and provides information to users.

[0116] A "database" is a system for organizing and managing data such as comments and photos stored on a server.

[0117] "Artificial Intelligence Model" means a machine learning or deep learning algorithm used to analyze User-Submitted Data and categorize and tag it based on preferences.

[0118] "Location information" refers to information that indicates the user's current geographical data.

[0119] "Rewards" means rewards, coupons, or discounts offered to users for using the Application or posting comments or photos.

[0120] "Occupancy data" refers to information about the current number of customers and how crowded a restaurant is.

[0121] A "communication terminal" refers to an electronic device used by a restaurant to transmit congestion status data to a server.

[0122] A "wireless communication device" is a device that communicates data using wireless technology such as Wi-Fi.

[0123] "Analysis" refers to the process of processing received comments and photo data to extract user preferences and store characteristics.

[0124] The system of the present invention allows users to search for and use restaurants, and includes the following components:

[0125] 1. User comments and photo posting

[0126] Users use the application to post comments and photos about restaurants. At this time, the device sends the user's posted data to the server. The server stores the received comments and photos in a database. This allows the user's experiences to be accumulated as information.

[0127] 2. Analysis and classification of comments and photos

[0128] The server periodically scans the comments and photos stored in the database to extract new data. The server then analyzes this data using an artificial intelligence model (e.g., TensorFlow) to assign categories and tags based on the user's preferences. This analysis process extracts characteristics such as ingredients, atmosphere, and price range. The analysis results are reflected in the user's profile and used to make future recommendations.

[0129] 3. Recommended Suggestions

[0130] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preference data to the server. Based on the received information, the server queries and lists the most suitable restaurants from its database. This enables personalized recommendations based on the user's current location and preferences. The restaurant information listed by the server is sent to the device and displayed to the user.

[0131] 4. Posting comments and offering rewards

[0132] When a user posts a new comment or photo, the server logs the action. If the reward conditions are met, the server generates coupons or discount information, sends it to the user's device, and notifies the user, allowing them to use the reward for their next meal.

[0133] 5. Real-time congestion information

[0134] The restaurant's terminal or wireless communication device (e.g., WiFi device) sends current occupancy data to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when the user chooses a restaurant.

[0135] Specific examples

[0136] For example, if a user wants to eat "yakiniku" (grilled meat), they search for "yakiniku" in the app, and the device sends their current location and preference data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. The server then sends this list to the device and presents it to the user. When the user visits a specific restaurant and posts new comments or photos there, the server records the action and issues a coupon if the conditions for the offer are met. This allows the user to receive a discount, increasing their motivation to return. In addition, the server provides real-time information on the restaurant's congestion status, allowing users to avoid waiting times and choose a restaurant efficiently.

[0137] Prompt Sentence Examples

[0138] An example of a prompt sentence to input into a generative AI model is, "If the user wants to eat yakiniku, list related restaurant recommendations and suggest personalized restaurant recommendations based on the user's current location."

[0139] This process allows users to easily find restaurants that perfectly suit their tastes and also receive special benefits, resulting in a system that encourages increased usage.

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Program processing flow

[0142] Step 1: User posts comments and photos

[0143] Users open the application and enter comments and photos about restaurants by entering comments in the text box and uploading photos. Once the posting is complete, the device sends the data in JSON format to the server.

[0144] Input: User comments and photos

[0145] Output: Post data sent to the server (JSON format)

[0146] Specific behavior: The user presses the "New Post" button to post the entered text and selected photo.

[0147] Step 2: Receiving and storing comments and photos

[0148] The server receives the posted data sent from the terminal and stores it in a database.

[0149] Input: Post data sent from the device

[0150] Output: Post data stored in the database

[0151] Specific behavior: The server receives the POST request and inserts the received data into an SQL database.

[0152] Step 3: Analyze and classify comments and photos

[0153] The server periodically scans the database to extract new data, which is then analyzed using an artificial intelligence model (e.g., TensorFlow) to assign categories and tags, such as ingredients, atmosphere, and price range.

[0154] Input: New comments and photos extracted from the database

[0155] Output: Classified and tagged data

[0156] What it does: The server runs a Python script, analyzes comments using an NLP model, and classifies photos using an image recognition model.

[0157] Step 4: Recommendations

[0158] When a user presses the "Search for recommended restaurants" button on the application, the device sends the user's location information and preference data to the server, which then queries the database for the most suitable restaurants and creates a list.

[0159] Input: User location and preference data

[0160] Output: A list of the best restaurants

[0161] Specific operation: The server uses GPS data to search for store information near the current location and filters it based on preference data.

[0162] Step 5: Post a comment and receive a reward

[0163] When a user posts a new comment or photo, the server logs the action. If the conditions for the reward are met, the server generates coupons or discount information and sends it to the device.

[0164] Input: New comment and photo post data

[0165] Output: Issued coupons and discount information

[0166] Specific operation: The server checks the conditions, and if the conditions are met, generates a coupon code, sends it to the terminal, and notifies the user.

[0167] Step 6: Providing real-time congestion information

[0168] The restaurant's terminals and wireless communication devices (e.g., WiFi devices) periodically transmit current occupancy data to the server, which analyzes this data and provides it to users in real time.

[0169] Input: Occupancy data sent from restaurants

[0170] Output: Real-time congestion information displayed to the user

[0171] Specific operation: The restaurant's WiFi device sends data such as the number of connections to the server, which then analyzes the information, calculates the level of congestion, and displays it to the user.

[0172] Through these steps, users can easily find restaurants that suit their tastes and get real-time information on how busy they are. In addition, rewards can be offered to increase users' motivation to post.

[0173] (Application example 1)

[0174] 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."

[0175] Today's consumers strongly desire to smoothly find products that match their preferences while shopping in physical stores, to make product selections based on reviews and comments from others, and to act efficiently based on real-time information. However, conventional systems have had difficulty meeting these demands. Specifically, they lack the ability to make personalized suggestions that reflect users' preferences, provide real-time congestion information, and do not smoothly trigger comment and photo posts linked to special offers.

[0176] 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.

[0177] In this invention, the server

[0178] A means for receiving comments and photos posted by users and storing such data in a database;

[0179] A means for analyzing stored comments and photos using an artificial intelligence model and categorizing and tagging them based on user preferences;

[0180] Based on the analyzed data, the system will suggest nearby restaurants and products based on the user's location information.

[0181] A means to provide rewards for posts when users post comments or photos;

[0182] A means for collecting information on the congestion status of a physical store in real time and providing it to users;

[0183] A means for functioning as an application installed on a smartphone, smart glasses, or robot;

[0184] This allows consumers to receive personalized product and restaurant recommendations based on their preferences, and allows them to act efficiently while keeping track of real-time congestion. In addition, the provision of rewards encourages users to take action, leading to further information accumulation and improved user satisfaction.

[0185] A "comment" is information in which a user writes their opinion or impression about a particular restaurant or product.

[0186] A "photo" is image data taken by a user to provide visual information about a particular restaurant or product.

[0187] A "database" is a system for organizing and storing various data in one place, and is used to store user-generated content such as comments and photos.

[0188] An "artificial intelligence model" is a software model that uses machine learning and deep learning techniques to analyze data and identify patterns and features.

[0189] "Classification and tagging" is the process of using artificial intelligence models to analyze data and assign it specific categories or labels.

[0190] "Location information" is information that indicates the user's current geographical location, and is obtained using technology such as GPS.

[0191] "Recommendation suggestions" is the process of recommending the most suitable restaurants and products based on the user's past behavior, preferences, and location information.

[0192] A "benefit" is an incentive such as a coupon or discount that is provided when a user meets certain conditions.

[0193] A "physical store" refers to a physical retail store or restaurant where real-time services are provided.

[0194] "Crowd situation" refers to information about the number of people and their movements in a particular location or store, and is useful for responding to customers in real time.

[0195] A "smartphone" is a mobile phone terminal that can connect to the Internet and run a variety of applications.

[0196] "Smart glasses" are wearable devices that integrate visual and digital information and provide it to users.

[0197] A "robot" is an automated mechanical device that is programmed to perform designated tasks.

[0198] An "application" is a software program that performs a specific function and runs on a smartphone, smart glasses, or robot.

[0199] The system of the present invention is designed to enhance users' shopping experience in physical stores by enabling them to receive personalized services through the posting and analysis of comments and photos, recommendations based on the user's location and preferences, real-time congestion information, and incentives.

[0200] 1. Collecting comments and photos

[0201] Users can use their smartphones, smart glasses, or robots to post comments and photos about products in physical stores. This data is then sent to a server via the device and stored in a database. This process accumulates real-time user feedback.

[0202] 2. Data Analysis and Classification

[0203] The server periodically scans the comments and photos stored in the database and analyzes them using an artificial intelligence model. During this analysis process, categories and tags are assigned based on the product's characteristics and the user's preferences. The analysis results are reflected in the user's profile and used to make future recommendations. The artificial intelligence models used include TensorFlow and PyTorch.

[0204] 3. Recommended Suggestions

[0205] When a user presses the "Search for recommended products" button, the device sends the user's location information and preferred characteristics to the server. Based on the received information, the server selects the most suitable products and nearby restaurants from its database and provides them as detailed information. During this process, a geocoding library (e.g., geopy) is used to obtain accurate location information.

[0206] 4. Posting comments and offering rewards

[0207] When a user posts a new comment or photo, the server records that action and issues a coupon or discount if the conditions for the reward are met. This reward information is sent to the user's device and notified, encouraging them to make their next purchase.

[0208] 5. Real-time congestion information

[0209] Wi-Fi devices and sensors installed in physical stores periodically send current congestion status to a server. The server analyzes this information and provides it to users in real time. Based on this information, users can efficiently choose stores.

[0210] Specific examples

[0211] For example, when a user approaches a particular shelf, the smart glasses will display past comments and reviews related to that shelf. They will also display items on sale and recommended items in the same category. When a user uses their smartphone to "search for recommended items," the server will generate an optimal product list based on their current location and preference data and provide it to the user.

[0212] Example of input prompt for generative AI model

[0213] Prompt: Based on the user's location and preferences, list the best stores and sales information:

[0214] Location: Latitude: 35.6895, Longitude: 139.6917

[0215] Interest data: ["Fashion", "Electronics", "Sports equipment"]

[0216] The system of the present invention allows users to shop efficiently in physical stores based on their preferences and receive optimal service based on real-time information.

[0217] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0218] Step 1:

[0219] A user posts comments and photos about products in a physical store using a smartphone, smart glasses, or a robot. This posted data is sent to the server by the terminal. The input is the comments and photos posted by the user, and the output is the posted data stored on the server. In this step, the comments and photos are accumulated in a database.

[0220] Step 2:

[0221] The server periodically scans the comments and photos stored in the database and analyzes them using an AI model. The input is the comments and photos in the database, and the output is the analyzed data. The AI ​​model analyzes the data using TensorFlow and PyTorch, and assigns categories and tags based on product characteristics and user preferences.

[0222] Step 3:

[0223] When a user presses the "Search for Recommended Products" button, the device sends the user's location information and preferred characteristics to the server. The input is the user's location information and preference data, and the output is a list of the best products and nearby restaurants generated by the server. The server uses the Geopy library to analyze the location information and list the best recommendations from the database.

[0224] Step 4:

[0225] When a user posts a new comment or photo, the server records that action and issues a coupon or discount if the conditions for the reward are met. The input is the newly posted comment or photo, and the output is the coupon information sent to the user's device. In this step, the content of the post is evaluated and a reward is issued.

[0226] Step 5:

[0227] WiFi devices and sensors installed in physical stores periodically send current congestion status to a server. The input is the congestion information of the physical store, and the output is analyzed real-time congestion status data. The server analyzes this information and notifies the user.

[0228] Step 6:

[0229] When a user approaches a specific product shelf in a physical store using smart glasses or a smartphone, related past comments and reviews are displayed on the device. The input is the user's current location information and a product database, and the output is product information and reviews displayed on the device. Specifically, the server obtains relevant data based on the user's location information and sends it to the device in real time.

[0230] Step 7:

[0231] When a user behaves in a way that meets the conditions for a reward, the server checks the conditions and issues a coupon or discount. The input is the user's behavioral data and the conditions for the reward, and the output is the coupon or discount data. The server uses an algorithm to check the behavioral data and issues a reward if the conditions are met. In this step, the process of providing incentives to the user is executed.

[0232] 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.

[0233] The system of the present invention includes the following components to enable users to easily and specifically search for restaurants.

[0234] 1. Collecting comments and photos

[0235] Users use the app to input and take comments and photos about restaurants. The device then sends these posts to the server, which then stores the received comments and photos in a database. This process creates a system in which user experiences are accumulated as information.

[0236] 2. Data Analysis and Classification

[0237] The server periodically scans the comments and photos stored in the database to extract new data. The server then analyzes the data using an artificial intelligence model and assigns categories and tags based on the user's preferences. This analysis process extracts characteristics such as ingredients, atmosphere, and price range. The analysis results are reflected in the user's profile and used for future recommendations.

[0238] 3. Recommended Suggestions

[0239] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preferred characteristics to the server. Based on the received information, the server lists the most suitable restaurants from its database. This makes it possible to make personalized recommendations based on the user's current location and preferences. The restaurant information listed by the server is sent to the device and displayed to the user.

[0240] 4. Posting comments and offering rewards

[0241] When a user posts a new comment or photo about a restaurant, the server records that action. If the reward conditions are met, the server issues a coupon or discount. This coupon information is sent to the terminal and notified to the user, allowing the user to use the reward for their next meal.

[0242] 5. Real-time congestion information

[0243] The restaurant's terminals and Wi-Fi devices periodically send their current occupancy status to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when choosing a restaurant.

[0244] 6. Emotion Recognition by Emotion Engine

[0245] When analyzing comments and photos posted by users, the server also uses an emotion engine to recognize the user's emotions. This emotion data is used for more detailed analysis of user preferences and is reflected in restaurant recommendation results and the provision of special offers.

[0246] Specific examples

[0247] For example, if a user wants to eat "yakiniku" (grilled meat), they search for "yakiniku" in the app, and the device sends their current location and preference data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. At this time, it also uses an emotion engine to reference the user's emotional data and prioritizes restaurants that the user felt happy or satisfied with. The server then sends this list to the device and presents it to the user.

[0248] Furthermore, when a user visits a specific store and posts new comments or photos there, the server analyzes the posts and issues coupons. If the user expresses positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to receive a discount and increase their motivation to visit again. In addition, real-time congestion information is provided, allowing users to avoid waiting times and efficiently choose a store.

[0249] This process allows users to easily find restaurants that perfectly match their preferences and also receive rewards, resulting in a system that encourages frequent use. Furthermore, the use of an emotion engine builds more detailed user profiles, improving recommendation accuracy.

[0250] The processing flow will be explained below.

[0251] 1. Comment and photo collection

[0252] Step 1:

[0253] The user launches the app and enters or takes a photo or comments about the restaurant.

[0254] Step 2:

[0255] The device sends the comments and photo data entered by the user to the server.

[0256] Step 3:

[0257] The server stores the received comments and photo data in a database.

[0258] 2. Data Analysis and Classification

[0259] Step 4:

[0260] The server periodically scans the database for new comments and photos.

[0261] Step 5:

[0262] The server uses an artificial intelligence model to analyze the acquired data, specifically extracting characteristics such as ingredients, atmosphere, and price range from the comments.

[0263] Step 6:

[0264] Based on the analysis results, the server assigns categories and tags to each comment and photo.

[0265] Step 7:

[0266] The server reflects the analysis results in the user profile and updates the user's preference data.

[0267] 3. Recommended Suggestions

[0268] Step 8:

[0269] The user presses the "Search for recommended restaurants" button on the app.

[0270] Step 9:

[0271] The device sends the user's location information and data about the user's preferences to the server.

[0272] Step 10:

[0273] Based on the location information and preference data received by the server, the server searches the database for the most suitable restaurant.

[0274] Step 11:

[0275] The server ranks and lists the search results.

[0276] Step 12:

[0277] The server sends the listed restaurant information to the terminal.

[0278] Step 13:

[0279] The terminal displays the recommended restaurant information to the user.

[0280] 4. Posting comments and offering rewards

[0281] Step 14:

[0282] A user posts a new comment or photo.

[0283] Step 15:

[0284] The terminal transmits the posting data to the server.

[0285] Step 16:

[0286] The server analyzes the post and checks whether it meets the conditions for the reward.

[0287] Step 17:

[0288] The server issues coupons and discounts when certain conditions are met.

[0289] Step 18:

[0290] The server transmits the issued coupon information to the terminal and notifies the user.

[0291] Step 19:

[0292] The terminal displays the coupon information to the user.

[0293] 5. Real-time congestion information

[0294] Step 20:

[0295] The restaurant's terminals and WiFi devices send the store's congestion status to the server.

[0296] Step 21:

[0297] The server analyzes the congestion information received.

[0298] Step 22:

[0299] When a user requests congestion information through the app, the server sends the latest congestion information to the device.

[0300] Step 23:

[0301] The terminal displays real-time congestion status to the user.

[0302] 6. Emotion Recognition by Emotion Engine

[0303] Step 24:

[0304] The server inputs the user's posted data into an emotion engine and analyzes the user's emotions.

[0305] Step 25:

[0306] The server adds the emotion data obtained from the emotion engine to the user profile.

[0307] Step 26:

[0308] The server reflects the user's emotional data in the analysis data and reflects it as a restaurant recommendation result.

[0309] Step 27:

[0310] The server issues a coupon with a higher discount rate based on the emotion data if certain conditions are met.

[0311] Specific examples

[0312] For example, if a user wants to eat "yakiniku" (grilled meat), they can search for "yakiniku" in the app, and the device will send their current location and preference data to the server. The server will then analyze past comments and photos related to "yakiniku" and use an emotion engine to obtain the user's emotional data. The server will prioritize restaurants that the user has positive feelings about, such as being happy or satisfied, and send the list to the device to present to the user.

[0313] Next, when a user visits a specific store and posts new comments or photos, the server analyzes the posts and issues coupons. If the user expresses positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to receive a discount and increase their motivation to visit again. In addition, real-time congestion information is provided, allowing users to avoid waiting times and choose a store efficiently.

[0314] This process allows users to easily find restaurants that perfectly match their preferences and also receive rewards, resulting in a system that encourages frequent use. Furthermore, the use of an emotion engine builds more detailed user profiles, improving recommendation accuracy.

[0315] Example 2

[0316] 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."

[0317] Today's consumers desire diverse dining experiences and want to efficiently find restaurants that suit their preferences. Information reflecting the user's emotions and the actual congestion status of restaurants visited are also important factors in their decision-making. However, conventional systems struggle to provide recommendations that take into account the user's detailed preferences and emotions, and they do not adequately provide real-time congestion status or special offers. Furthermore, they lack the functionality to quickly suggest restaurants that match the user's preferences using the user's location information. This has made it difficult for users to efficiently find restaurants that suit their preferences.

[0318] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving comments and photos posted by users and storing the data in a database, means for analyzing the stored comments and photos using an artificial intelligence model and classifying and tagging them based on the user's preferences, means for suggesting recommended nearby facilities based on the user's location information based on the analyzed data, means for providing rewards for posts made by users when the users post comments and photos, means for collecting information on facility congestion status in real time and providing the information to the users, and means for analyzing user posts and using an emotion engine that recognizes emotions. This improves convenience by allowing users to easily find recommended restaurants that suit their preferences, understand congestion status in real time, and receive rewards for posting.

[0319] "User" refers to an individual who uses the system to post comments and photos, search for restaurants, receive recommendations, and receive special offers.

[0320] "Comments" refer to posted data in which users express their impressions and opinions about restaurants in writing.

[0321] "Photos" refer to image data of restaurants and food taken by users.

[0322] "Database" refers to an information management system that allows the server to store user posted data and analysis results.

[0323] "Artificial intelligence model" refers to technology that uses machine learning algorithms to analyze and classify data.

[0324] "Preferences" refers to personal preferences such as the ingredients, cuisine, atmosphere, and price range that the user prefers.

[0325] "Classification and tagging" refers to the process by which an artificial intelligence model analyzes data and assigns it specific categories or attributes.

[0326] "Location Information" refers to data that indicates a user's current geographic location.

[0327] "Facility" refers to a service providing location that a user visits, including a restaurant.

[0328] "Benefits" refers to rewards such as coupons and discounts that users receive when they post comments or photos.

[0329] "Crowd situation" refers to information showing the current number of customers at a restaurant and waiting times.

[0330] "Real-time" refers to information being updated or provided almost instantly.

[0331] "Emotion engine" refers to technology that analyzes and recognizes emotions from user posted data.

[0332] The system of the present invention includes the following components to enable users to easily and specifically search for restaurants.

[0333] First, users must install an application on their device to post comments and photos. Using this application, users can input and take photos of the food and their impressions after eating. The device used for this is a smartphone, tablet, or other device with an internet connection.

[0334] The device then sends the comments and photos entered or taken by the user to a server, which then receives the posted data and stores it in a database, such as a cloud-based data storage system (the general term used here is "database management system").

[0335] The server then periodically scans the database to extract newly stored data. The extracted data is analyzed using an artificial intelligence model (e.g., a machine learning algorithm like TensorFlow or PyTorch). Based on the analysis results, comments and photos are assigned specific categories and tags (e.g., ingredients, atmosphere, price range). These analysis results are reflected in the user profile and used for future recommendations.

[0336] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and profile data to the server. The server uses this information to create a list of the most suitable restaurants from a database. This process may involve the use of a search engine such as Elasticsearch. The listed restaurant information is then sent to the device and displayed to the user.

[0337] Furthermore, when a user posts a new comment or photo, the post is sent again to the server and stored in the database. The server analyzes the posted data and issues coupons or discounts if the conditions are met. This special offer information is sent to the device and notified to the user. The server uses, for example, a REST API or push notification service to provide these special offers.

[0338] In addition, restaurant terminals and Wi-Fi devices periodically send occupancy data to a server. The server analyzes this data and provides it to users in real time. This analysis is sometimes performed using a real-time analysis engine (e.g., Apache Kafka).

[0339] The emotion engine also runs on the server, analyzing user posted data to recognize emotions. The recognized emotion data is used for more detailed preference analysis and is reflected in recommendation results and reward offers.

[0340] Examples and prompts

[0341] As a concrete example, if a user wants to eat "yakiniku," the following steps are executed: The user searches for "yakiniku" in the app, and the device sends its current location and profile data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. At this time, it also uses an emotion engine to prioritize the list of restaurants for which the user expressed positive emotions (such as joy or satisfaction). The server then sends this list to the device and presents it to the user.

[0342] Furthermore, when a user visits a specific restaurant and posts new comments or photos, the server analyzes the posts and issues coupons. If the user shows positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to use the rewards for their next meal, increasing frequency of use. In addition, real-time congestion information is provided, allowing users to avoid waiting times and efficiently choose a restaurant.

[0343] Prompt Sentence Examples

[0344] "If I want to eat yakiniku, how do I search for restaurants? Also, what kind of benefits do I get for posting comments and photos?"

[0345] Through this process, the present invention realizes a system that allows users to easily find restaurants that suit their preferences and also receive rewards, which increases the frequency of use. In addition, the use of an emotion engine will build more detailed user profiles, improving recommendation accuracy.

[0346] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0347] Step 1:

[0348] The user launches the app, enters comments about the restaurant, and takes a photo if necessary.

[0349] Input: User comments and photos

[0350] Specific operation: The user enters a comment in the text field and takes a photo using the camera function. The device temporarily stores this data in memory.

[0351] Step 2:

[0352] The terminal transmits comments and photos entered or taken by the user to the server.

[0353] Input: User comments and photos (output of step 1)

[0354] Output: Notification that transmission to the server was successful

[0355] How it works: The device generates an HTTP POST request to the server over the Internet, attaches the user's comments and photos, and sends them. If the transmission is successful, the device receives a confirmation response from the server.

[0356] Step 3:

[0357] The server stores the received comments and photos in a database.

[0358] Input: Comments and photos sent from the device (output of Step 2)

[0359] Output: Data ID stored in the database or notification of successful storage

[0360] Specific operation: The server stores the received data in the target database management system. If the storage is successful, it generates an ID for the stored data and notifies the terminal or internal process.

[0361] Step 4:

[0362] The server periodically scans the database and extracts new data.

[0363] Input: All data stored in the database

[0364] Output: A list of the new data

[0365] Specific operation: The server sets up a scheduled job to periodically query the database to extract and list new data.

[0366] Step 5:

[0367] The server inputs the extracted data into an artificial intelligence model for analysis.

[0368] Input: List of new data (output of Step 4)

[0369] Output: Analysis results (categories, tags, sentiment analysis results, etc.)

[0370] How it works: The server analyzes new data using artificial intelligence models (e.g., TensorFlow, PyTorch). The analysis uses text and image analysis algorithms to extract attributes such as ingredients, atmosphere, price range, and sentiment.

[0371] Step 6:

[0372] The server assigns categories and tags to the data based on the analysis results.

[0373] Input: Analysis results (output from Step 5)

[0374] Output: Classified and tagged data

[0375] Specific operation: The server assigns categories and tags (e.g., yakiniku, relaxed atmosphere, high price range, etc.) to the analyzed data and stores it in a database.

[0376] Step 7:

[0377] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preference data to the server.

[0378] Input: User location and preference data

[0379] Output: Notification that transmission to the server was successful

[0380] Specific operation: The device uses the GPS function to obtain its current location and transmits it along with the user profile data to the server. If the transmission is successful, the device receives a confirmation response.

[0381] Step 8:

[0382] The server creates a list of the most suitable restaurants based on the user's location information and preference data.

[0383] Input: User location and preference data (output of step 7)

[0384] Output: List of restaurants

[0385] What it does: The server uses a search engine like Elasticsearch to query the database and return a list of restaurants that fit the criteria, taking into account analytics results and data from the user profile.

[0386] Step 9:

[0387] The server sends the listed restaurant information to the terminal and displays it to the user.

[0388] Input: List of restaurants (output of Step 8)

[0389] Output: List of restaurants sent to the terminal

[0390] Specific operation: The server encodes the listed information in JSON format and sends it to the device as an HTTP response. The device receives this and displays it as a list on the app screen.

[0391] Step 10:

[0392] When a user posts new comments or photos, the device sends them back to the server and stores them in the database.

[0393] Input: New comment and new photo for the user

[0394] Output: Notification of successful transmission to the server and notification of completion of database storage

[0395] Specific operation: Similar to steps 1 to 3, the terminal sends new data to the server, and the server stores it in the database.

[0396] Step 11:

[0397] The server analyzes new posts and issues coupons or discounts if the conditions are met.

[0398] Input: New comment and new photo (input from step 10)

[0399] Output: Issued benefits (coupons and discounts) information

[0400] Specific operation: The server analyzes the new data and generates coupons and discounts for posts that meet the conditions. The generated reward information is sent to the terminal and notified to the user.

[0401] Step 12:

[0402] The restaurant's terminal or Wi-Fi device sends the current congestion status to the server.

[0403] Input: Restaurant congestion data

[0404] Output: Notification of successful transmission to the server

[0405] Specific operation: Restaurant terminals and Wi-Fi devices periodically send congestion status data such as the number of connections and bandwidth usage to the server. The server receives this data and returns an acknowledgement.

[0406] Step 13:

[0407] The server analyzes the congestion data and provides it to users in real time.

[0408] Input: Restaurant congestion data (output of Step 12)

[0409] Output: Real-time provision of analyzed congestion information

[0410] Specific operation: The server uses a real-time analysis engine (e.g., Apache Kafka) to analyze the congestion data and provide the analysis results to the user in real time.

[0411] Step 14:

[0412] The server analyzes the user's posted data using an emotion engine to recognize emotions.

[0413] Input: User comments and photos

[0414] Output: User emotion data

[0415] Specific operation: The server inputs the posted data (text and images) into the emotion engine, and recognizes the user's emotions through natural language processing and image analysis. The output emotion data is saved in the user profile.

[0416] Step 15:

[0417] The server uses the emotional data to make recommendations and provide rewards.

[0418] Input: User emotion data

[0419] Output: Improved recommendations and rewards information

[0420] Specific operation: The server reflects the emotional data in the user profile and uses it to improve the accuracy of the next restaurant recommendation and reward offer, thereby providing services that are more suited to the user's preferences.

[0421] (Application example 2)

[0422] 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."

[0423] In food delivery services, it is not easy for users to efficiently search and select restaurants that suit their preferences. In particular, there is a demand for personalized recommendations that take into account a variety of information, such as users' past ratings and real-time congestion status. It is also important to properly analyze comments and photos posted by users and provide rewards based on them, but there is no centralized system for this.

[0424] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving comments and photos posted by users and storing the data in a database, means for analyzing the stored comments and photos using an artificial intelligence model and classifying and tagging them based on the user's preferences, means for suggesting recommended nearby restaurants based on the user's location information based on the analyzed data, means for providing rewards for comments and photos posted by users, means for collecting restaurant congestion information in real time and providing the information to the user, means for understanding the comments and photos stored in the database using TF-IDF-based analysis and calculating similarity, and means for listing and providing food delivery services that best suit the user's preferences based on the similarity analysis. This allows users to easily find restaurants and food delivery services that best suit their preferences and also enjoy rewards.

[0425] "User" refers to an individual user who uses the system to search for restaurants, rate them, and post comments and photos.

[0426] "Comments" refer to text-based evaluations and opinions posted by users about restaurants.

[0427] "Photos" refer to image data that users take of restaurants and food and post.

[0428] "Database" refers to a storage system managed on a server for storing comments and photos collected from users.

[0429] "Artificial intelligence model" refers to a program that uses machine learning technology to analyze user comments and photos and categorize and tag them based on preferences.

[0430] "Preferences" refers to a user's likes, dislikes, and interests, and includes factors such as ingredients, atmosphere, and price range.

[0431] "Classification" refers to the process of sorting analyzed data into specific categories.

[0432] "Tagging" refers to the process of assigning appropriate labels to analyzed data.

[0433] "Location information" refers to geographical data about a user's current location.

[0434] "Suggestion" refers to the act of recommending restaurants suitable for the user based on the analysis results.

[0435] "Benefits" refer to rewards such as coupons and discount vouchers that are beneficial to users.

[0436] "Crowd situation" refers to information such as the current number of customers at a restaurant and waiting times.

[0437] "Real-time" refers to providing nearly instantaneous, up-to-date information.

[0438] "TF-IDF-based analysis" refers to the process of analyzing data using a technique that calculates significant words in a sentence.

[0439] "Similarity" refers to an index that calculates how similar different comments or photos are.

[0440] "Food delivery service" refers to a service that delivers meals ordered online by users to their homes or designated locations.

[0441] The system of this invention provides a series of processes that enable users to efficiently search for and select restaurants and food delivery services that suit their preferences. The system is composed of the following components and processes.

[0442] 1. Collecting comments and photos

[0443] Users use devices such as smartphones and tablets to input and take photos and comments about restaurants, and then send them to the server. A mobile application is installed on the user's device as an interface. Through this application, users can easily input comments and upload photos. The server receives these posts and stores them in a database.

[0444] 2. Data Analysis and Classification

[0445] The server periodically analyzes the comments and photos stored in the database using an artificial intelligence model. Specifically, it uses TF-IDF-based analysis to extract important words in sentences and calculate similarity. This data analysis then categorizes and tags each post based on the user's preferences. For example, categories such as ingredients, atmosphere, and price range are generated.

[0446] 3. Recommended Suggestions

[0447] When a user presses the "Search for recommended food delivery services" button, the device sends the user's location information and previous preference data to the server. Based on the received information, the server selects the most suitable food delivery services from its database. The server provides the list to the user, taking into account real-time congestion and available delivery times.

[0448] 4. Posting comments and offering rewards

[0449] When a user posts a new comment or photo about a food delivery service or restaurant, the server records the action. If the conditions for the reward are met, the server issues a coupon or discount and notifies the user's device.

[0450] 5. Real-time congestion information

[0451] The terminals and installed devices of the food delivery service periodically send information about current congestion and available delivery times to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when users choose a food delivery service.

[0452] Specific examples

[0453] For example, if a user wants to eat "sushi," they search for "sushi" in the app, and their location information and preference data are sent to the server. The server then analyzes past comments and photos related to "sushi" and lists recommended food delivery services in the vicinity. It also uses an emotion engine to prioritize restaurants and services that the user has positive feelings about, such as being happy or satisfied with. The server then sends this list to the user's device and presents it to the user.

[0454] Furthermore, when a user uses a specific food delivery service and posts new comments or photos, the server analyzes the posts and issues coupons. If the user expresses positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to receive a discount and increase their motivation to use the service again. Real-time congestion information is also provided, allowing users to avoid waiting times and use the service efficiently.

[0455] Prompt Sentence Examples

[0456] "Can you recommend any restaurants near my location that serve good sushi? Also, can you show me any coupons or special offers I can use?"

[0457] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0458] Step 1:

[0459] Users use a smartphone or tablet application to input and take comments and photos about restaurants. The input comments (text data) and photos (image data) are collected as data. This data is saved on the device via an interface and sent to a server. Input is performed manually by the user, and output is the transfer of data to the server.

[0460] Step 2:

[0461] The server receives comments and photos sent from the devices and stores them in a database. This database serves as a repository of information to be used for future data analysis and searches. The input is the comments and photos received from the devices, and the output is storage in the database. The stored data is used in subsequent analysis processes.

[0462] Step 3:

[0463] The server periodically scans the comments and photos stored in the database and extracts the latest data. The extracted data is then analyzed using an artificial intelligence model. Specifically, TF-IDF-based analysis is used to extract important words in the text and calculate their similarity. The input is the extracted comments and photos, and the output is classified and tagged data as the analysis results.

[0464] Step 4:

[0465] The server updates the user profile based on the analyzed data. The updated profile is classified into categories such as ingredients, atmosphere, and price range. This profile will be used in a future recommendation system. The input is the analysis results, and the output is the updated user profile.

[0466] Step 5:

[0467] When a user presses the "Search for recommended food delivery services" button in the application, the device sends its current location and past preference data to the server. Location information is obtained via GPS, and preference data is extracted from the user profile. The input is location information and preference data, and the output is a request sent to the server.

[0468] Step 6:

[0469] The server uses the received location information and preference data to create a list of optimal food delivery services from a database. The list also takes into account real-time congestion and available delivery times. The listed services are generated as an analysis result and provided to the user. The input is location information and preference data, and the output is the listed service information.

[0470] Step 7:

[0471] The server checks the analysis results and the conditions for the rewards, and issues a coupon or discount if the user meets the conditions. The issued reward information is sent to the terminal and notified to the user. The input is the reward conditions and the analysis results, and the output is the coupon or discount information.

[0472] Step 8:

[0473] Users use the provided food delivery service and post new comments and photos about the service. These posts are also sent to the server, stored in a database, and analyzed. This allows new feedback to be continuously collected, contributing to improving the accuracy of the system. The input is newly posted data, and the output is data transfer and storage to the server.

[0474] Step 9:

[0475] Users can check the congestion status provided in real time and efficiently select a food delivery service. This information is collected from the restaurant's terminal or installed device, analyzed by the server, and then provided to the user. The input is data from the restaurant, and the output is real-time congestion status information.

[0476] This series of processing steps allows users to easily find restaurants and food delivery services that suit their preferences and also enjoy special offers.

[0477] 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.

[0478] 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.

[0479] 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.

[0480] [Second embodiment]

[0481] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0482] 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.

[0483] 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).

[0484] 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.

[0485] 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.

[0486] 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).

[0487] 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.

[0488] 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.

[0489] 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.

[0490] 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.

[0491] 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.

[0492] 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."

[0493] The system of the present invention includes the following components to enable users to easily and specifically search for restaurants.

[0494] 1. Collecting comments and photos

[0495] Users use the app to post comments and photos about restaurants. The device then sends these posts to the server, which then stores the received comments and photos in a database. This process creates a system in which user experiences are accumulated as information.

[0496] 2. Data Analysis and Classification

[0497] The server periodically scans the comments and photos stored in the database to extract new data. The server then analyzes the data using an artificial intelligence model and assigns categories and tags based on the user's preferences. This analysis process extracts characteristics such as ingredients, atmosphere, and price range. The analysis results are reflected in the user's profile and used for future recommendations.

[0498] 3. Recommended Suggestions

[0499] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preferred characteristics to the server. Based on the received information, the server lists the most suitable restaurants from its database. This makes it possible to make personalized recommendations based on the user's current location and preferences. The restaurant information listed by the server is sent to the device and displayed to the user.

[0500] 4. Posting comments and offering rewards

[0501] When a user posts a new comment or photo about a restaurant, the server records that action. If the reward conditions are met, the server issues a coupon or discount. This coupon information is sent to the terminal and notified to the user, allowing the user to use the reward for their next meal.

[0502] 5. Real-time congestion information

[0503] The restaurant's terminals and Wi-Fi devices periodically send their current occupancy status to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when choosing a restaurant.

[0504] Specific examples

[0505] For example, if a user wants to eat "yakiniku" (grilled meat), they search for "yakiniku" in the app, and the device sends their current location and preference data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. The server then sends this list to the device and presents it to the user. When the user visits a specific restaurant and posts new comments or photos there, the server records the action and issues a coupon. This allows the user to receive a discount and increase their motivation to return. Real-time congestion information is also provided, allowing users to avoid waiting times and choose a restaurant efficiently.

[0506] This process allows users to easily find restaurants that perfectly suit their tastes and also receive special benefits, resulting in a system that encourages increased usage.

[0507] The processing flow will be explained below.

[0508] 1. Comment and photo collection

[0509] Step 1:

[0510] The user launches the app and enters or takes a photo or comments about the restaurant.

[0511] Step 2:

[0512] The device sends the comments and photo data entered by the user to the server.

[0513] Step 3:

[0514] The server stores the received comments and photo data in a database.

[0515] 2. Analysis and Classification

[0516] Step 4:

[0517] The server periodically scans the database for new comments and photos.

[0518] Step 5:

[0519] The server uses an artificial intelligence model to analyze the acquired data, specifically extracting characteristics such as ingredients, atmosphere, and price range from the comments.

[0520] Step 6:

[0521] Based on the analysis results, the server assigns categories and tags to each comment and photo.

[0522] Step 7:

[0523] The server reflects the analysis results in the user profile and updates the user's preference data.

[0524] 3. Recommended Suggestions

[0525] Step 8:

[0526] The user presses the "Search for recommended restaurants" button on the app.

[0527] Step 9:

[0528] The device sends the user's location information and data about the user's preferences to the server.

[0529] Step 10:

[0530] Based on the location information and preference data received by the server, the server searches the database for the most suitable restaurant.

[0531] Step 11:

[0532] The server ranks and lists the search results.

[0533] Step 12:

[0534] The server sends the listed restaurant information to the terminal.

[0535] Step 13:

[0536] The terminal displays the recommended restaurant information to the user.

[0537] 4. Posting comments and offering rewards

[0538] Step 14:

[0539] A user posts a new comment or photo.

[0540] Step 15:

[0541] The terminal transmits the posting data to the server.

[0542] Step 16:

[0543] The server analyzes the post and checks whether it meets the conditions for the reward.

[0544] Step 17:

[0545] The server issues coupons and discounts when certain conditions are met.

[0546] Step 18:

[0547] The server transmits the issued coupon information to the terminal and notifies the user.

[0548] Step 19:

[0549] The terminal displays the coupon information to the user.

[0550] 5. Real-time congestion information

[0551] Step 20:

[0552] The restaurant's terminals and WiFi devices send the store's congestion status to the server.

[0553] Step 21:

[0554] The server analyzes the congestion information received.

[0555] Step 22:

[0556] When a user requests congestion information through the app, the server sends the latest congestion information to the device.

[0557] Step 23:

[0558] The terminal displays real-time congestion status to the user.

[0559] Through the above process, users can easily find restaurants that suit their tastes. In addition, they can receive rewards, which motivates them to post, and they can also check the real-time congestion status, which helps them avoid crowded restaurants.

[0560] Example 1

[0561] 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."

[0562] Conventional restaurant search systems make it difficult for users to quickly find suitable restaurants, and they lack real-time information about restaurant congestion and suggestions based on user preferences. This results in a limited user experience and the inconvenience of having to use multiple applications. Furthermore, they lack incentives for users to post information.

[0563] 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.

[0564] In this invention, the server includes: means for receiving comments and photos posted by users and storing the data in a database; means for analyzing the stored comments and photos using an artificial intelligence model and categorizing and tagging them based on the user's preferences; means for suggesting nearby recommended restaurants based on the user's location information based on the analyzed data; means for providing rewards for comments and photos posted by users; and means for receiving congestion status data transmitted by the restaurant's communication terminal or wireless communication device and providing the data to the user in real time. This allows users to easily find restaurants that perfectly match their preferences and makes appropriate choices based on real-time information. Furthermore, providing rewards for user posts increases user engagement.

[0565] "User" means an individual who uses the Application to post comments and photos of restaurants and obtain information.

[0566] A "terminal" refers to an electronic device on which an application is installed, such as a smartphone or tablet used by a user.

[0567] "Server" means a computer system that receives, stores, and processes data from users, analyzes comments and photos, and provides information to users.

[0568] A "database" is a system for organizing and managing data such as comments and photos stored on a server.

[0569] "Artificial Intelligence Model" means a machine learning or deep learning algorithm used to analyze User-Submitted Data and categorize and tag it based on preferences.

[0570] "Location information" refers to information that indicates the user's current geographical data.

[0571] "Rewards" means rewards, coupons, or discounts offered to users for using the Application or posting comments or photos.

[0572] "Occupancy data" refers to information about the current number of customers and how crowded a restaurant is.

[0573] A "communication terminal" refers to an electronic device used by a restaurant to transmit congestion status data to a server.

[0574] A "wireless communication device" is a device that communicates data using wireless technology such as Wi-Fi.

[0575] "Analysis" refers to the process of processing received comments and photo data to extract user preferences and store characteristics.

[0576] The system of the present invention allows users to search for and use restaurants, and includes the following components:

[0577] 1. User comments and photo posting

[0578] Users use the application to post comments and photos about restaurants. At this time, the device sends the user's posted data to the server. The server stores the received comments and photos in a database. This allows the user's experiences to be accumulated as information.

[0579] 2. Analysis and classification of comments and photos

[0580] The server periodically scans the comments and photos stored in the database to extract new data. The server then analyzes this data using an artificial intelligence model (e.g., TensorFlow) to assign categories and tags based on the user's preferences. This analysis process extracts characteristics such as ingredients, atmosphere, and price range. The analysis results are reflected in the user's profile and used to make future recommendations.

[0581] 3. Recommended Suggestions

[0582] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preference data to the server. Based on the received information, the server queries and lists the most suitable restaurants from its database. This enables personalized recommendations based on the user's current location and preferences. The restaurant information listed by the server is sent to the device and displayed to the user.

[0583] 4. Posting comments and offering rewards

[0584] When a user posts a new comment or photo, the server logs the action. If the reward conditions are met, the server generates coupons or discount information, sends it to the user's device, and notifies the user, allowing them to use the reward for their next meal.

[0585] 5. Real-time congestion information

[0586] The restaurant's terminal or wireless communication device (e.g., WiFi device) sends current occupancy data to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when the user chooses a restaurant.

[0587] Specific examples

[0588] For example, if a user wants to eat "yakiniku" (grilled meat), they search for "yakiniku" in the app, and the device sends their current location and preference data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. The server then sends this list to the device and presents it to the user. When the user visits a specific restaurant and posts new comments or photos there, the server records the action and issues a coupon if the conditions for the offer are met. This allows the user to receive a discount, increasing their motivation to return. In addition, the server provides real-time information on the restaurant's congestion status, allowing users to avoid waiting times and choose a restaurant efficiently.

[0589] Prompt Sentence Examples

[0590] An example of a prompt sentence to input into a generative AI model is, "If the user wants to eat yakiniku, list related restaurant recommendations and suggest personalized restaurant recommendations based on the user's current location."

[0591] This process allows users to easily find restaurants that perfectly suit their tastes and also receive special benefits, resulting in a system that encourages increased usage.

[0592] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0593] Program processing flow

[0594] Step 1: User posts comments and photos

[0595] Users open the application and enter comments and photos about restaurants by entering comments in the text box and uploading photos. Once the posting is complete, the device sends the data in JSON format to the server.

[0596] Input: User comments and photos

[0597] Output: Post data sent to the server (JSON format)

[0598] Specific behavior: The user presses the "New Post" button to post the entered text and selected photo.

[0599] Step 2: Receiving and storing comments and photos

[0600] The server receives the posted data sent from the terminal and stores it in a database.

[0601] Input: Post data sent from the device

[0602] Output: Post data stored in the database

[0603] Specific behavior: The server receives the POST request and inserts the received data into an SQL database.

[0604] Step 3: Analyze and classify comments and photos

[0605] The server periodically scans the database to extract new data, which is then analyzed using an artificial intelligence model (e.g., TensorFlow) to assign categories and tags, such as ingredients, atmosphere, and price range.

[0606] Input: New comments and photos extracted from the database

[0607] Output: Classified and tagged data

[0608] What it does: The server runs a Python script, analyzes comments using an NLP model, and classifies photos using an image recognition model.

[0609] Step 4: Recommendations

[0610] When a user presses the "Search for recommended restaurants" button on the application, the device sends the user's location information and preference data to the server, which then queries the database for the most suitable restaurants and creates a list.

[0611] Input: User location and preference data

[0612] Output: A list of the best restaurants

[0613] Specific operation: The server uses GPS data to search for store information near the current location and filters it based on preference data.

[0614] Step 5: Post a comment and receive a reward

[0615] When a user posts a new comment or photo, the server logs the action. If the conditions for the reward are met, the server generates coupons or discount information and sends it to the device.

[0616] Input: New comment and photo post data

[0617] Output: Issued coupons and discount information

[0618] Specific operation: The server checks the conditions, and if the conditions are met, generates a coupon code, sends it to the terminal, and notifies the user.

[0619] Step 6: Providing real-time congestion information

[0620] The restaurant's terminals and wireless communication devices (e.g., WiFi devices) periodically transmit current occupancy data to the server, which analyzes this data and provides it to users in real time.

[0621] Input: Occupancy data sent from restaurants

[0622] Output: Real-time congestion information displayed to the user

[0623] Specific operation: The restaurant's WiFi device sends data such as the number of connections to the server, which then analyzes the information, calculates the level of congestion, and displays it to the user.

[0624] Through these steps, users can easily find restaurants that suit their tastes and get real-time information on how busy they are. In addition, rewards can be offered to increase users' motivation to post.

[0625] (Application example 1)

[0626] 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."

[0627] Today's consumers strongly desire to smoothly find products that match their preferences while shopping in physical stores, to make product selections based on reviews and comments from others, and to act efficiently based on real-time information. However, conventional systems have had difficulty meeting these demands. Specifically, they lack the ability to make personalized suggestions that reflect users' preferences, provide real-time congestion information, and do not smoothly trigger comment and photo posts linked to special offers.

[0628] 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.

[0629] In this invention, the server

[0630] A means for receiving comments and photos posted by users and storing such data in a database;

[0631] A means for analyzing stored comments and photos using an artificial intelligence model and categorizing and tagging them based on user preferences;

[0632] Based on the analyzed data, the system will suggest nearby restaurants and products based on the user's location information.

[0633] A means to provide rewards for posts when users post comments or photos;

[0634] A means for collecting information on the congestion status of a physical store in real time and providing it to users;

[0635] A means for functioning as an application installed on a smartphone, smart glasses, or robot;

[0636] This allows consumers to receive personalized product and restaurant recommendations based on their preferences, and allows them to act efficiently while keeping track of real-time congestion. In addition, the provision of rewards encourages users to take action, leading to further information accumulation and improved user satisfaction.

[0637] A "comment" is information in which a user writes their opinion or impression about a particular restaurant or product.

[0638] A "photo" is image data taken by a user to provide visual information about a particular restaurant or product.

[0639] A "database" is a system for organizing and storing various data in one place, and is used to store user-generated content such as comments and photos.

[0640] An "artificial intelligence model" is a software model that uses machine learning and deep learning techniques to analyze data and identify patterns and features.

[0641] "Classification and tagging" is the process of using artificial intelligence models to analyze data and assign it specific categories or labels.

[0642] "Location information" is information that indicates the user's current geographical location, and is obtained using technology such as GPS.

[0643] "Recommendation suggestions" is the process of recommending the most suitable restaurants and products based on the user's past behavior, preferences, and location information.

[0644] A "benefit" is an incentive such as a coupon or discount that is provided when a user meets certain conditions.

[0645] A "physical store" refers to a physical retail store or restaurant where real-time services are provided.

[0646] "Crowd situation" refers to information about the number of people and their movements in a particular location or store, and is useful for responding to customers in real time.

[0647] A "smartphone" is a mobile phone terminal that can connect to the Internet and run a variety of applications.

[0648] "Smart glasses" are wearable devices that integrate visual and digital information and provide it to users.

[0649] A "robot" is an automated mechanical device that is programmed to perform designated tasks.

[0650] An "application" is a software program that performs a specific function and runs on a smartphone, smart glasses, or robot.

[0651] The system of the present invention is designed to enhance users' shopping experience in physical stores by enabling them to receive personalized services through the posting and analysis of comments and photos, recommendations based on the user's location and preferences, real-time congestion information, and incentives.

[0652] 1. Collecting comments and photos

[0653] Users can use their smartphones, smart glasses, or robots to post comments and photos about products in physical stores. This data is then sent to a server via the device and stored in a database. This process accumulates real-time user feedback.

[0654] 2. Data Analysis and Classification

[0655] The server periodically scans the comments and photos stored in the database and analyzes them using an artificial intelligence model. During this analysis process, categories and tags are assigned based on the product's characteristics and the user's preferences. The analysis results are reflected in the user's profile and used to make future recommendations. The artificial intelligence models used include TensorFlow and PyTorch.

[0656] 3. Recommended Suggestions

[0657] When a user presses the "Search for recommended products" button, the device sends the user's location information and preferred characteristics to the server. Based on the received information, the server selects the most suitable products and nearby restaurants from its database and provides them as detailed information. During this process, a geocoding library (e.g., geopy) is used to obtain accurate location information.

[0658] 4. Posting comments and offering rewards

[0659] When a user posts a new comment or photo, the server records that action and issues a coupon or discount if the conditions for the reward are met. This reward information is sent to the user's device and notified, encouraging them to make their next purchase.

[0660] 5. Real-time congestion information

[0661] Wi-Fi devices and sensors installed in physical stores periodically send current congestion status to a server. The server analyzes this information and provides it to users in real time. Based on this information, users can efficiently choose stores.

[0662] Specific examples

[0663] For example, when a user approaches a particular shelf, the smart glasses will display past comments and reviews related to that shelf. They will also display items on sale and recommended items in the same category. When a user uses their smartphone to "search for recommended items," the server will generate an optimal product list based on their current location and preference data and provide it to the user.

[0664] Example of input prompt for generative AI model

[0665] Prompt: Based on the user's location and preferences, list the best stores and sales information:

[0666] Location: Latitude: 35.6895, Longitude: 139.6917

[0667] Interest data: ["Fashion", "Electronics", "Sports equipment"]

[0668] The system of the present invention allows users to shop efficiently in physical stores based on their preferences and receive optimal service based on real-time information.

[0669] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0670] Step 1:

[0671] A user posts comments and photos about products in a physical store using a smartphone, smart glasses, or a robot. This posted data is sent to the server by the terminal. The input is the comments and photos posted by the user, and the output is the posted data stored on the server. In this step, the comments and photos are accumulated in a database.

[0672] Step 2:

[0673] The server periodically scans the comments and photos stored in the database and analyzes them using an AI model. The input is the comments and photos in the database, and the output is the analyzed data. The AI ​​model analyzes the data using TensorFlow and PyTorch, and assigns categories and tags based on product characteristics and user preferences.

[0674] Step 3:

[0675] When a user presses the "Search for Recommended Products" button, the device sends the user's location information and preferred characteristics to the server. The input is the user's location information and preference data, and the output is a list of the best products and nearby restaurants generated by the server. The server uses the Geopy library to analyze the location information and list the best recommendations from the database.

[0676] Step 4:

[0677] When a user posts a new comment or photo, the server records that action and issues a coupon or discount if the conditions for the reward are met. The input is the newly posted comment or photo, and the output is the coupon information sent to the user's device. In this step, the content of the post is evaluated and a reward is issued.

[0678] Step 5:

[0679] WiFi devices and sensors installed in physical stores periodically send current congestion status to a server. The input is the congestion information of the physical store, and the output is analyzed real-time congestion status data. The server analyzes this information and notifies the user.

[0680] Step 6:

[0681] When a user approaches a specific product shelf in a physical store using smart glasses or a smartphone, related past comments and reviews are displayed on the device. The input is the user's current location information and a product database, and the output is product information and reviews displayed on the device. Specifically, the server obtains relevant data based on the user's location information and sends it to the device in real time.

[0682] Step 7:

[0683] When a user behaves in a way that meets the conditions for a reward, the server checks the conditions and issues a coupon or discount. The input is the user's behavioral data and the conditions for the reward, and the output is the coupon or discount data. The server uses an algorithm to check the behavioral data and issues a reward if the conditions are met. In this step, the process of providing incentives to the user is executed.

[0684] 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.

[0685] The system of the present invention includes the following components to enable users to easily and specifically search for restaurants.

[0686] 1. Collecting comments and photos

[0687] Users use the app to input and take comments and photos about restaurants. The device then sends these posts to the server, which then stores the received comments and photos in a database. This process creates a system in which user experiences are accumulated as information.

[0688] 2. Data Analysis and Classification

[0689] The server periodically scans the comments and photos stored in the database to extract new data. The server then analyzes the data using an artificial intelligence model and assigns categories and tags based on the user's preferences. This analysis process extracts characteristics such as ingredients, atmosphere, and price range. The analysis results are reflected in the user's profile and used for future recommendations.

[0690] 3. Recommended Suggestions

[0691] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preferred characteristics to the server. Based on the received information, the server lists the most suitable restaurants from its database. This makes it possible to make personalized recommendations based on the user's current location and preferences. The restaurant information listed by the server is sent to the device and displayed to the user.

[0692] 4. Posting comments and offering rewards

[0693] When a user posts a new comment or photo about a restaurant, the server records that action. If the reward conditions are met, the server issues a coupon or discount. This coupon information is sent to the terminal and notified to the user, allowing the user to use the reward for their next meal.

[0694] 5. Real-time congestion information

[0695] The restaurant's terminals and Wi-Fi devices periodically send their current occupancy status to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when choosing a restaurant.

[0696] 6. Emotion Recognition by Emotion Engine

[0697] When analyzing comments and photos posted by users, the server also uses an emotion engine to recognize the user's emotions. This emotion data is used for more detailed analysis of user preferences and is reflected in restaurant recommendation results and the provision of special offers.

[0698] Specific examples

[0699] For example, if a user wants to eat "yakiniku" (grilled meat), they search for "yakiniku" in the app, and the device sends their current location and preference data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. At this time, it also uses an emotion engine to reference the user's emotional data and prioritizes restaurants that the user felt happy or satisfied with. The server then sends this list to the device and presents it to the user.

[0700] Furthermore, when a user visits a specific store and posts new comments or photos there, the server analyzes the posts and issues coupons. If the user expresses positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to receive a discount and increase their motivation to visit again. In addition, real-time congestion information is provided, allowing users to avoid waiting times and efficiently choose a store.

[0701] This process allows users to easily find restaurants that perfectly match their preferences and also receive rewards, resulting in a system that encourages frequent use. Furthermore, the use of an emotion engine builds more detailed user profiles, improving recommendation accuracy.

[0702] The processing flow will be explained below.

[0703] 1. Comment and photo collection

[0704] Step 1:

[0705] The user launches the app and enters or takes a photo or comments about the restaurant.

[0706] Step 2:

[0707] The device sends the comments and photo data entered by the user to the server.

[0708] Step 3:

[0709] The server stores the received comments and photo data in a database.

[0710] 2. Data Analysis and Classification

[0711] Step 4:

[0712] The server periodically scans the database for new comments and photos.

[0713] Step 5:

[0714] The server uses an artificial intelligence model to analyze the acquired data, specifically extracting characteristics such as ingredients, atmosphere, and price range from the comments.

[0715] Step 6:

[0716] Based on the analysis results, the server assigns categories and tags to each comment and photo.

[0717] Step 7:

[0718] The server reflects the analysis results in the user profile and updates the user's preference data.

[0719] 3. Recommended Suggestions

[0720] Step 8:

[0721] The user presses the "Search for recommended restaurants" button on the app.

[0722] Step 9:

[0723] The device sends the user's location information and data about the user's preferences to the server.

[0724] Step 10:

[0725] Based on the location information and preference data received by the server, the server searches the database for the most suitable restaurant.

[0726] Step 11:

[0727] The server ranks and lists the search results.

[0728] Step 12:

[0729] The server sends the listed restaurant information to the terminal.

[0730] Step 13:

[0731] The terminal displays the recommended restaurant information to the user.

[0732] 4. Posting comments and offering rewards

[0733] Step 14:

[0734] A user posts a new comment or photo.

[0735] Step 15:

[0736] The terminal transmits the posting data to the server.

[0737] Step 16:

[0738] The server analyzes the post and checks whether it meets the conditions for the reward.

[0739] Step 17:

[0740] The server issues coupons and discounts when certain conditions are met.

[0741] Step 18:

[0742] The server transmits the issued coupon information to the terminal and notifies the user.

[0743] Step 19:

[0744] The terminal displays the coupon information to the user.

[0745] 5. Real-time congestion information

[0746] Step 20:

[0747] The restaurant's terminals and WiFi devices send the store's congestion status to the server.

[0748] Step 21:

[0749] The server analyzes the congestion information received.

[0750] Step 22:

[0751] When a user requests congestion information through the app, the server sends the latest congestion information to the device.

[0752] Step 23:

[0753] The terminal displays real-time congestion status to the user.

[0754] 6. Emotion Recognition by Emotion Engine

[0755] Step 24:

[0756] The server inputs the user's posted data into an emotion engine and analyzes the user's emotions.

[0757] Step 25:

[0758] The server adds the emotion data obtained from the emotion engine to the user profile.

[0759] Step 26:

[0760] The server reflects the user's emotional data in the analysis data and reflects it as a restaurant recommendation result.

[0761] Step 27:

[0762] The server issues a coupon with a higher discount rate based on the emotion data if certain conditions are met.

[0763] Specific examples

[0764] For example, if a user wants to eat "yakiniku" (grilled meat), they can search for "yakiniku" in the app, and the device will send their current location and preference data to the server. The server will then analyze past comments and photos related to "yakiniku" and use an emotion engine to obtain the user's emotional data. The server will prioritize restaurants that the user has positive feelings about, such as being happy or satisfied, and send the list to the device to present to the user.

[0765] Next, when a user visits a specific store and posts new comments or photos, the server analyzes the posts and issues coupons. If the user expresses positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to receive a discount and increase their motivation to visit again. In addition, real-time congestion information is provided, allowing users to avoid waiting times and choose a store efficiently.

[0766] This process allows users to easily find restaurants that perfectly match their preferences and also receive rewards, resulting in a system that encourages frequent use. Furthermore, the use of an emotion engine builds more detailed user profiles, improving recommendation accuracy.

[0767] Example 2

[0768] 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."

[0769] Today's consumers desire diverse dining experiences and want to efficiently find restaurants that suit their preferences. Information reflecting the user's emotions and the actual congestion status of restaurants visited are also important factors in their decision-making. However, conventional systems struggle to provide recommendations that take into account the user's detailed preferences and emotions, and they do not adequately provide real-time congestion status or special offers. Furthermore, they lack the functionality to quickly suggest restaurants that match the user's preferences using the user's location information. This has made it difficult for users to efficiently find restaurants that suit their preferences.

[0770] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving comments and photos posted by users and storing the data in a database, means for analyzing the stored comments and photos using an artificial intelligence model and classifying and tagging them based on the user's preferences, means for suggesting recommended nearby facilities based on the user's location information based on the analyzed data, means for providing rewards for posts made by users when the users post comments and photos, means for collecting information on facility congestion status in real time and providing the information to the users, and means for analyzing user posts and using an emotion engine that recognizes emotions. This improves convenience by allowing users to easily find recommended restaurants that suit their preferences, understand congestion status in real time, and receive rewards for posting.

[0771] "User" refers to an individual who uses the system to post comments and photos, search for restaurants, receive recommendations, and receive special offers.

[0772] "Comments" refer to posted data in which users express their impressions and opinions about restaurants in writing.

[0773] "Photos" refer to image data of restaurants and food taken by users.

[0774] "Database" refers to an information management system that allows the server to store user posted data and analysis results.

[0775] "Artificial intelligence model" refers to technology that uses machine learning algorithms to analyze and classify data.

[0776] "Preferences" refers to personal preferences such as the ingredients, cuisine, atmosphere, and price range that the user prefers.

[0777] "Classification and tagging" refers to the process by which an artificial intelligence model analyzes data and assigns it specific categories or attributes.

[0778] "Location Information" refers to data that indicates a user's current geographic location.

[0779] "Facility" refers to a service providing location that a user visits, including a restaurant.

[0780] "Benefits" refers to rewards such as coupons and discounts that users receive when they post comments or photos.

[0781] "Crowd situation" refers to information showing the current number of customers at a restaurant and waiting times.

[0782] "Real-time" refers to information being updated or provided almost instantly.

[0783] "Emotion engine" refers to technology that analyzes and recognizes emotions from user posted data.

[0784] The system of the present invention includes the following components to enable users to easily and specifically search for restaurants.

[0785] First, users must install an application on their device to post comments and photos. Using this application, users can input and take photos of the food and their impressions after eating. The device used for this is a smartphone, tablet, or other device with an internet connection.

[0786] The device then sends the comments and photos entered or taken by the user to a server, which then receives the posted data and stores it in a database, such as a cloud-based data storage system (the general term used here is "database management system").

[0787] The server then periodically scans the database to extract newly stored data. The extracted data is analyzed using an artificial intelligence model (e.g., a machine learning algorithm like TensorFlow or PyTorch). Based on the analysis results, comments and photos are assigned specific categories and tags (e.g., ingredients, atmosphere, price range). These analysis results are reflected in the user profile and used for future recommendations.

[0788] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and profile data to the server. The server uses this information to create a list of the most suitable restaurants from a database. This process may involve the use of a search engine such as Elasticsearch. The listed restaurant information is then sent to the device and displayed to the user.

[0789] Furthermore, when a user posts a new comment or photo, the post is sent again to the server and stored in the database. The server analyzes the posted data and issues coupons or discounts if the conditions are met. This special offer information is sent to the device and notified to the user. The server uses, for example, a REST API or push notification service to provide these special offers.

[0790] In addition, restaurant terminals and Wi-Fi devices periodically send occupancy data to a server. The server analyzes this data and provides it to users in real time. This analysis is sometimes performed using a real-time analysis engine (e.g., Apache Kafka).

[0791] The emotion engine also runs on the server, analyzing user posted data to recognize emotions. The recognized emotion data is used for more detailed preference analysis and is reflected in recommendation results and reward offers.

[0792] Examples and prompts

[0793] As a concrete example, if a user wants to eat "yakiniku," the following steps are executed: The user searches for "yakiniku" in the app, and the device sends its current location and profile data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. At this time, it also uses an emotion engine to prioritize the list of restaurants for which the user expressed positive emotions (such as joy or satisfaction). The server then sends this list to the device and presents it to the user.

[0794] Furthermore, when a user visits a specific restaurant and posts new comments or photos, the server analyzes the posts and issues coupons. If the user shows positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to use the rewards for their next meal, increasing frequency of use. In addition, real-time congestion information is provided, allowing users to avoid waiting times and efficiently choose a restaurant.

[0795] Prompt Sentence Examples

[0796] "If I want to eat yakiniku, how do I search for restaurants? Also, what kind of benefits do I get for posting comments and photos?"

[0797] Through this process, the present invention realizes a system that allows users to easily find restaurants that suit their preferences and also receive rewards, which increases the frequency of use. In addition, the use of an emotion engine will build more detailed user profiles, improving recommendation accuracy.

[0798] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0799] Step 1:

[0800] The user launches the app, enters comments about the restaurant, and takes a photo if necessary.

[0801] Input: User comments and photos

[0802] Specific operation: The user enters a comment in the text field and takes a photo using the camera function. The device temporarily stores this data in memory.

[0803] Step 2:

[0804] The terminal transmits comments and photos entered or taken by the user to the server.

[0805] Input: User comments and photos (output of step 1)

[0806] Output: Notification that transmission to the server was successful

[0807] How it works: The device generates an HTTP POST request to the server over the Internet, attaches the user's comments and photos, and sends them. If the transmission is successful, the device receives a confirmation response from the server.

[0808] Step 3:

[0809] The server stores the received comments and photos in a database.

[0810] Input: Comments and photos sent from the device (output of Step 2)

[0811] Output: Data ID stored in the database or notification of successful storage

[0812] Specific operation: The server stores the received data in the target database management system. If the storage is successful, it generates an ID for the stored data and notifies the terminal or internal process.

[0813] Step 4:

[0814] The server periodically scans the database and extracts new data.

[0815] Input: All data stored in the database

[0816] Output: A list of the new data

[0817] Specific operation: The server sets up a scheduled job to periodically query the database to extract and list new data.

[0818] Step 5:

[0819] The server inputs the extracted data into an artificial intelligence model for analysis.

[0820] Input: List of new data (output of Step 4)

[0821] Output: Analysis results (categories, tags, sentiment analysis results, etc.)

[0822] How it works: The server analyzes new data using artificial intelligence models (e.g., TensorFlow, PyTorch). The analysis uses text and image analysis algorithms to extract attributes such as ingredients, atmosphere, price range, and sentiment.

[0823] Step 6:

[0824] The server assigns categories and tags to the data based on the analysis results.

[0825] Input: Analysis results (output from Step 5)

[0826] Output: Classified and tagged data

[0827] Specific operation: The server assigns categories and tags (e.g., yakiniku, relaxed atmosphere, high price range, etc.) to the analyzed data and stores it in a database.

[0828] Step 7:

[0829] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preference data to the server.

[0830] Input: User location and preference data

[0831] Output: Notification that transmission to the server was successful

[0832] Specific operation: The device uses the GPS function to obtain its current location and transmits it along with the user profile data to the server. If the transmission is successful, the device receives a confirmation response.

[0833] Step 8:

[0834] The server creates a list of the most suitable restaurants based on the user's location information and preference data.

[0835] Input: User location and preference data (output of step 7)

[0836] Output: List of restaurants

[0837] What it does: The server uses a search engine like Elasticsearch to query the database and return a list of restaurants that fit the criteria, taking into account analytics results and data from the user profile.

[0838] Step 9:

[0839] The server sends the listed restaurant information to the terminal and displays it to the user.

[0840] Input: List of restaurants (output of Step 8)

[0841] Output: List of restaurants sent to the terminal

[0842] Specific operation: The server encodes the listed information in JSON format and sends it to the device as an HTTP response. The device receives this and displays it as a list on the app screen.

[0843] Step 10:

[0844] When a user posts new comments or photos, the device sends them back to the server and stores them in the database.

[0845] Input: New comment and new photo for the user

[0846] Output: Notification of successful transmission to the server and notification of completion of database storage

[0847] Specific operation: Similar to steps 1 to 3, the terminal sends new data to the server, and the server stores it in the database.

[0848] Step 11:

[0849] The server analyzes new posts and issues coupons or discounts if the conditions are met.

[0850] Input: New comment and new photo (input from step 10)

[0851] Output: Issued benefits (coupons and discounts) information

[0852] Specific operation: The server analyzes the new data and generates coupons and discounts for posts that meet the conditions. The generated reward information is sent to the terminal and notified to the user.

[0853] Step 12:

[0854] The restaurant's terminal or Wi-Fi device sends the current congestion status to the server.

[0855] Input: Restaurant congestion data

[0856] Output: Notification of successful transmission to the server

[0857] Specific operation: Restaurant terminals and Wi-Fi devices periodically send congestion status data such as the number of connections and bandwidth usage to the server. The server receives this data and returns an acknowledgement.

[0858] Step 13:

[0859] The server analyzes the congestion data and provides it to users in real time.

[0860] Input: Restaurant congestion data (output of Step 12)

[0861] Output: Real-time provision of analyzed congestion information

[0862] Specific operation: The server uses a real-time analysis engine (e.g., Apache Kafka) to analyze the congestion data and provide the analysis results to the user in real time.

[0863] Step 14:

[0864] The server analyzes the user's posted data using an emotion engine to recognize emotions.

[0865] Input: User comments and photos

[0866] Output: User emotion data

[0867] Specific operation: The server inputs the posted data (text and images) into the emotion engine, and recognizes the user's emotions through natural language processing and image analysis. The output emotion data is saved in the user profile.

[0868] Step 15:

[0869] The server uses the emotional data to make recommendations and provide rewards.

[0870] Input: User emotion data

[0871] Output: Improved recommendations and rewards information

[0872] Specific operation: The server reflects the emotional data in the user profile and uses it to improve the accuracy of the next restaurant recommendation and reward offer, thereby providing services that are more suited to the user's preferences.

[0873] (Application example 2)

[0874] 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."

[0875] In food delivery services, it is not easy for users to efficiently search and select restaurants that suit their preferences. In particular, there is a demand for personalized recommendations that take into account a variety of information, such as users' past ratings and real-time congestion status. It is also important to properly analyze comments and photos posted by users and provide rewards based on them, but there is no centralized system for this.

[0876] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving comments and photos posted by users and storing the data in a database, means for analyzing the stored comments and photos using an artificial intelligence model and classifying and tagging them based on the user's preferences, means for suggesting recommended nearby restaurants based on the user's location information based on the analyzed data, means for providing rewards for comments and photos posted by users, means for collecting restaurant congestion information in real time and providing the information to the user, means for understanding the comments and photos stored in the database using TF-IDF-based analysis and calculating similarity, and means for listing and providing food delivery services that best suit the user's preferences based on the similarity analysis. This allows users to easily find restaurants and food delivery services that best suit their preferences and also enjoy rewards.

[0877] "User" refers to an individual user who uses the system to search for restaurants, rate them, and post comments and photos.

[0878] "Comments" refer to text-based evaluations and opinions posted by users about restaurants.

[0879] "Photos" refer to image data that users take of restaurants and food and post.

[0880] "Database" refers to a storage system managed on a server for storing comments and photos collected from users.

[0881] "Artificial intelligence model" refers to a program that uses machine learning technology to analyze user comments and photos and categorize and tag them based on preferences.

[0882] "Preferences" refers to a user's likes, dislikes, and interests, and includes factors such as ingredients, atmosphere, and price range.

[0883] "Classification" refers to the process of sorting analyzed data into specific categories.

[0884] "Tagging" refers to the process of assigning appropriate labels to analyzed data.

[0885] "Location information" refers to geographical data about a user's current location.

[0886] "Suggestion" refers to the act of recommending restaurants suitable for the user based on the analysis results.

[0887] "Benefits" refer to rewards such as coupons and discount vouchers that are beneficial to users.

[0888] "Crowd situation" refers to information such as the current number of customers at a restaurant and waiting times.

[0889] "Real-time" refers to providing nearly instantaneous, up-to-date information.

[0890] "TF-IDF-based analysis" refers to the process of analyzing data using a technique that calculates significant words in a sentence.

[0891] "Similarity" refers to an index that calculates how similar different comments or photos are.

[0892] "Food delivery service" refers to a service that delivers meals ordered online by users to their homes or designated locations.

[0893] The system of this invention provides a series of processes that enable users to efficiently search for and select restaurants and food delivery services that suit their preferences. The system is composed of the following components and processes.

[0894] 1. Collecting comments and photos

[0895] Users use devices such as smartphones and tablets to input and take photos and comments about restaurants, and then send them to the server. A mobile application is installed on the user's device as an interface. Through this application, users can easily input comments and upload photos. The server receives these posts and stores them in a database.

[0896] 2. Data Analysis and Classification

[0897] The server periodically analyzes the comments and photos stored in the database using an artificial intelligence model. Specifically, it uses TF-IDF-based analysis to extract important words in sentences and calculate similarity. This data analysis then categorizes and tags each post based on the user's preferences. For example, categories such as ingredients, atmosphere, and price range are generated.

[0898] 3. Recommended Suggestions

[0899] When a user presses the "Search for recommended food delivery services" button, the device sends the user's location information and previous preference data to the server. Based on the received information, the server selects the most suitable food delivery services from its database. The server provides the list to the user, taking into account real-time congestion and available delivery times.

[0900] 4. Posting comments and offering rewards

[0901] When a user posts a new comment or photo about a food delivery service or restaurant, the server records the action. If the conditions for the reward are met, the server issues a coupon or discount and notifies the user's device.

[0902] 5. Real-time congestion information

[0903] The terminals and installed devices of the food delivery service periodically send information about current congestion and available delivery times to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when users choose a food delivery service.

[0904] Specific examples

[0905] For example, if a user wants to eat "sushi," they search for "sushi" in the app, and their location information and preference data are sent to the server. The server then analyzes past comments and photos related to "sushi" and lists recommended food delivery services in the vicinity. It also uses an emotion engine to prioritize restaurants and services that the user has positive feelings about, such as being happy or satisfied with. The server then sends this list to the user's device and presents it to the user.

[0906] Furthermore, when a user uses a specific food delivery service and posts new comments or photos, the server analyzes the posts and issues coupons. If the user expresses positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to receive a discount and increase their motivation to use the service again. Real-time congestion information is also provided, allowing users to avoid waiting times and use the service efficiently.

[0907] Prompt Sentence Examples

[0908] "Can you recommend any restaurants near my location that serve good sushi? Also, can you show me any coupons or special offers I can use?"

[0909] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0910] Step 1:

[0911] Users use a smartphone or tablet application to input and take comments and photos about restaurants. The input comments (text data) and photos (image data) are collected as data. This data is saved on the device via an interface and sent to a server. Input is performed manually by the user, and output is the transfer of data to the server.

[0912] Step 2:

[0913] The server receives comments and photos sent from the devices and stores them in a database. This database serves as a repository of information to be used for future data analysis and searches. The input is the comments and photos received from the devices, and the output is storage in the database. The stored data is used in subsequent analysis processes.

[0914] Step 3:

[0915] The server periodically scans the comments and photos stored in the database and extracts the latest data. The extracted data is then analyzed using an artificial intelligence model. Specifically, TF-IDF-based analysis is used to extract important words in the text and calculate their similarity. The input is the extracted comments and photos, and the output is classified and tagged data as the analysis results.

[0916] Step 4:

[0917] The server updates the user profile based on the analyzed data. The updated profile is classified into categories such as ingredients, atmosphere, and price range. This profile will be used in a future recommendation system. The input is the analysis results, and the output is the updated user profile.

[0918] Step 5:

[0919] When a user presses the "Search for recommended food delivery services" button in the application, the device sends its current location and past preference data to the server. Location information is obtained via GPS, and preference data is extracted from the user profile. The input is location information and preference data, and the output is a request sent to the server.

[0920] Step 6:

[0921] The server uses the received location information and preference data to create a list of optimal food delivery services from a database. The list also takes into account real-time congestion and available delivery times. The listed services are generated as an analysis result and provided to the user. The input is location information and preference data, and the output is the listed service information.

[0922] Step 7:

[0923] The server checks the analysis results and the conditions for the rewards, and issues a coupon or discount if the user meets the conditions. The issued reward information is sent to the terminal and notified to the user. The input is the reward conditions and the analysis results, and the output is the coupon or discount information.

[0924] Step 8:

[0925] Users use the provided food delivery service and post new comments and photos about the service. These posts are also sent to the server, stored in a database, and analyzed. This allows new feedback to be continuously collected, contributing to improving the accuracy of the system. The input is newly posted data, and the output is data transfer and storage to the server.

[0926] Step 9:

[0927] Users can check the congestion status provided in real time and efficiently select a food delivery service. This information is collected from the restaurant's terminal or installed device, analyzed by the server, and then provided to the user. The input is data from the restaurant, and the output is real-time congestion status information.

[0928] This series of processing steps allows users to easily find restaurants and food delivery services that suit their preferences and also enjoy special offers.

[0929] 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.

[0930] 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.

[0931] 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.

[0932] [Third embodiment]

[0933] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0934] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0935] 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).

[0936] 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.

[0937] 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.

[0938] 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).

[0939] 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.

[0940] 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.

[0941] 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.

[0942] 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.

[0943] 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.

[0944] 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."

[0945] The system of the present invention includes the following components to enable users to easily and specifically search for restaurants.

[0946] 1. Collecting comments and photos

[0947] Users use the app to post comments and photos about restaurants. The device then sends these posts to the server, which then stores the received comments and photos in a database. This process creates a system in which user experiences are accumulated as information.

[0948] 2. Data Analysis and Classification

[0949] The server periodically scans the comments and photos stored in the database to extract new data. The server then analyzes the data using an artificial intelligence model and assigns categories and tags based on the user's preferences. This analysis process extracts characteristics such as ingredients, atmosphere, and price range. The analysis results are reflected in the user's profile and used for future recommendations.

[0950] 3. Recommended Suggestions

[0951] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preferred characteristics to the server. Based on the received information, the server lists the most suitable restaurants from its database. This makes it possible to make personalized recommendations based on the user's current location and preferences. The restaurant information listed by the server is sent to the device and displayed to the user.

[0952] 4. Posting comments and offering rewards

[0953] When a user posts a new comment or photo about a restaurant, the server records that action. If the reward conditions are met, the server issues a coupon or discount. This coupon information is sent to the terminal and notified to the user, allowing the user to use the reward for their next meal.

[0954] 5. Real-time congestion information

[0955] The restaurant's terminals and Wi-Fi devices periodically send their current occupancy status to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when choosing a restaurant.

[0956] Specific examples

[0957] For example, if a user wants to eat "yakiniku" (grilled meat), they search for "yakiniku" in the app, and the device sends their current location and preference data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. The server then sends this list to the device and presents it to the user. When the user visits a specific restaurant and posts new comments or photos there, the server records the action and issues a coupon. This allows the user to receive a discount and increase their motivation to return. Real-time congestion information is also provided, allowing users to avoid waiting times and choose a restaurant efficiently.

[0958] This process allows users to easily find restaurants that perfectly suit their tastes and also receive special benefits, resulting in a system that encourages increased usage.

[0959] The processing flow will be explained below.

[0960] 1. Comment and photo collection

[0961] Step 1:

[0962] The user launches the app and enters or takes a photo or comments about the restaurant.

[0963] Step 2:

[0964] The device sends the comments and photo data entered by the user to the server.

[0965] Step 3:

[0966] The server stores the received comments and photo data in a database.

[0967] 2. Analysis and Classification

[0968] Step 4:

[0969] The server periodically scans the database for new comments and photos.

[0970] Step 5:

[0971] The server uses an artificial intelligence model to analyze the acquired data, specifically extracting characteristics such as ingredients, atmosphere, and price range from the comments.

[0972] Step 6:

[0973] Based on the analysis results, the server assigns categories and tags to each comment and photo.

[0974] Step 7:

[0975] The server reflects the analysis results in the user profile and updates the user's preference data.

[0976] 3. Recommended Suggestions

[0977] Step 8:

[0978] The user presses the "Search for recommended restaurants" button on the app.

[0979] Step 9:

[0980] The device sends the user's location information and data about the user's preferences to the server.

[0981] Step 10:

[0982] Based on the location information and preference data received by the server, the server searches the database for the most suitable restaurant.

[0983] Step 11:

[0984] The server ranks and lists the search results.

[0985] Step 12:

[0986] The server sends the listed restaurant information to the terminal.

[0987] Step 13:

[0988] The terminal displays the recommended restaurant information to the user.

[0989] 4. Posting comments and offering rewards

[0990] Step 14:

[0991] A user posts a new comment or photo.

[0992] Step 15:

[0993] The terminal transmits the posting data to the server.

[0994] Step 16:

[0995] The server analyzes the post and checks whether it meets the conditions for the reward.

[0996] Step 17:

[0997] The server issues coupons and discounts when certain conditions are met.

[0998] Step 18:

[0999] The server transmits the issued coupon information to the terminal and notifies the user.

[1000] Step 19:

[1001] The terminal displays the coupon information to the user.

[1002] 5. Real-time congestion information

[1003] Step 20:

[1004] The restaurant's terminals and WiFi devices send the store's congestion status to the server.

[1005] Step 21:

[1006] The server analyzes the congestion information received.

[1007] Step 22:

[1008] When a user requests congestion information through the app, the server sends the latest congestion information to the device.

[1009] Step 23:

[1010] The terminal displays real-time congestion status to the user.

[1011] Through the above process, users can easily find restaurants that suit their tastes. In addition, they can receive rewards, which motivates them to post, and they can also check the real-time congestion status, which helps them avoid crowded restaurants.

[1012] Example 1

[1013] 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."

[1014] Conventional restaurant search systems make it difficult for users to quickly find suitable restaurants, and they lack real-time information about restaurant congestion and suggestions based on user preferences. This results in a limited user experience and the inconvenience of having to use multiple applications. Furthermore, they lack incentives for users to post information.

[1015] 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.

[1016] In this invention, the server includes: means for receiving comments and photos posted by users and storing the data in a database; means for analyzing the stored comments and photos using an artificial intelligence model and categorizing and tagging them based on the user's preferences; means for suggesting nearby recommended restaurants based on the user's location information based on the analyzed data; means for providing rewards for comments and photos posted by users; and means for receiving congestion status data transmitted by the restaurant's communication terminal or wireless communication device and providing the data to the user in real time. This allows users to easily find restaurants that perfectly match their preferences and makes appropriate choices based on real-time information. Furthermore, providing rewards for user posts increases user engagement.

[1017] "User" means an individual who uses the Application to post comments and photos of restaurants and obtain information.

[1018] A "terminal" refers to an electronic device on which an application is installed, such as a smartphone or tablet used by a user.

[1019] "Server" means a computer system that receives, stores, and processes data from users, analyzes comments and photos, and provides information to users.

[1020] A "database" is a system for organizing and managing data such as comments and photos stored on a server.

[1021] "Artificial Intelligence Model" means a machine learning or deep learning algorithm used to analyze User-Submitted Data and categorize and tag it based on preferences.

[1022] "Location information" refers to information that indicates the user's current geographical data.

[1023] "Rewards" means rewards, coupons, or discounts offered to users for using the Application or posting comments or photos.

[1024] "Occupancy data" refers to information about the current number of customers and how crowded a restaurant is.

[1025] A "communication terminal" refers to an electronic device used by a restaurant to transmit congestion status data to a server.

[1026] A "wireless communication device" is a device that communicates data using wireless technology such as Wi-Fi.

[1027] "Analysis" refers to the process of processing received comments and photo data to extract user preferences and store characteristics.

[1028] The system of the present invention allows users to search for and use restaurants, and includes the following components:

[1029] 1. User comments and photo posting

[1030] Users use the application to post comments and photos about restaurants. At this time, the device sends the user's posted data to the server. The server stores the received comments and photos in a database. This allows the user's experiences to be accumulated as information.

[1031] 2. Analysis and classification of comments and photos

[1032] The server periodically scans the comments and photos stored in the database to extract new data. The server then analyzes this data using an artificial intelligence model (e.g., TensorFlow) to assign categories and tags based on the user's preferences. This analysis process extracts characteristics such as ingredients, atmosphere, and price range. The analysis results are reflected in the user's profile and used to make future recommendations.

[1033] 3. Recommended Suggestions

[1034] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preference data to the server. Based on the received information, the server queries and lists the most suitable restaurants from its database. This enables personalized recommendations based on the user's current location and preferences. The restaurant information listed by the server is sent to the device and displayed to the user.

[1035] 4. Posting comments and offering rewards

[1036] When a user posts a new comment or photo, the server logs the action. If the reward conditions are met, the server generates coupons or discount information, sends it to the user's device, and notifies the user, allowing them to use the reward for their next meal.

[1037] 5. Real-time congestion information

[1038] The restaurant's terminal or wireless communication device (e.g., WiFi device) sends current occupancy data to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when the user chooses a restaurant.

[1039] Specific examples

[1040] For example, if a user wants to eat "yakiniku" (grilled meat), they search for "yakiniku" in the app, and the device sends their current location and preference data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. The server then sends this list to the device and presents it to the user. When the user visits a specific restaurant and posts new comments or photos there, the server records the action and issues a coupon if the conditions for the offer are met. This allows the user to receive a discount, increasing their motivation to return. In addition, the server provides real-time information on the restaurant's congestion status, allowing users to avoid waiting times and choose a restaurant efficiently.

[1041] Prompt Sentence Examples

[1042] An example of a prompt sentence to input into a generative AI model is, "If the user wants to eat yakiniku, list related restaurant recommendations and suggest personalized restaurant recommendations based on the user's current location."

[1043] This process allows users to easily find restaurants that perfectly suit their tastes and also receive special benefits, resulting in a system that encourages increased usage.

[1044] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1045] Program processing flow

[1046] Step 1: User posts comments and photos

[1047] Users open the application and enter comments and photos about restaurants by entering comments in the text box and uploading photos. Once the posting is complete, the device sends the data in JSON format to the server.

[1048] Input: User comments and photos

[1049] Output: Post data sent to the server (JSON format)

[1050] Specific behavior: The user presses the "New Post" button to post the entered text and selected photo.

[1051] Step 2: Receiving and storing comments and photos

[1052] The server receives the posted data sent from the terminal and stores it in a database.

[1053] Input: Post data sent from the device

[1054] Output: Post data stored in the database

[1055] Specific behavior: The server receives the POST request and inserts the received data into an SQL database.

[1056] Step 3: Analyze and classify comments and photos

[1057] The server periodically scans the database to extract new data, which is then analyzed using an artificial intelligence model (e.g., TensorFlow) to assign categories and tags, such as ingredients, atmosphere, and price range.

[1058] Input: New comments and photos extracted from the database

[1059] Output: Classified and tagged data

[1060] What it does: The server runs a Python script, analyzes comments using an NLP model, and classifies photos using an image recognition model.

[1061] Step 4: Recommendations

[1062] When a user presses the "Search for recommended restaurants" button on the application, the device sends the user's location information and preference data to the server, which then queries the database for the most suitable restaurants and creates a list.

[1063] Input: User location and preference data

[1064] Output: A list of the best restaurants

[1065] Specific operation: The server uses GPS data to search for store information near the current location and filters it based on preference data.

[1066] Step 5: Post a comment and receive a reward

[1067] When a user posts a new comment or photo, the server logs the action. If the conditions for the reward are met, the server generates coupons or discount information and sends it to the device.

[1068] Input: New comment and photo post data

[1069] Output: Issued coupons and discount information

[1070] Specific operation: The server checks the conditions, and if the conditions are met, generates a coupon code, sends it to the terminal, and notifies the user.

[1071] Step 6: Providing real-time congestion information

[1072] The restaurant's terminals and wireless communication devices (e.g., WiFi devices) periodically transmit current occupancy data to the server, which analyzes this data and provides it to users in real time.

[1073] Input: Occupancy data sent from restaurants

[1074] Output: Real-time congestion information displayed to the user

[1075] Specific operation: The restaurant's WiFi device sends data such as the number of connections to the server, which then analyzes the information, calculates the level of congestion, and displays it to the user.

[1076] Through these steps, users can easily find restaurants that suit their tastes and get real-time information on how busy they are. In addition, rewards can be offered to increase users' motivation to post.

[1077] (Application example 1)

[1078] 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."

[1079] Today's consumers strongly desire to smoothly find products that match their preferences while shopping in physical stores, to make product selections based on reviews and comments from others, and to act efficiently based on real-time information. However, conventional systems have had difficulty meeting these demands. Specifically, they lack the ability to make personalized suggestions that reflect users' preferences, provide real-time congestion information, and do not smoothly trigger comment and photo posts linked to special offers.

[1080] 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.

[1081] In this invention, the server

[1082] A means for receiving comments and photos posted by users and storing such data in a database;

[1083] A means for analyzing stored comments and photos using an artificial intelligence model and categorizing and tagging them based on user preferences;

[1084] Based on the analyzed data, the system will suggest nearby restaurants and products based on the user's location information.

[1085] A means to provide rewards for posts when users post comments or photos;

[1086] A means for collecting information on the congestion status of a physical store in real time and providing it to users;

[1087] A means for functioning as an application installed on a smartphone, smart glasses, or robot;

[1088] This allows consumers to receive personalized product and restaurant recommendations based on their preferences, and allows them to act efficiently while keeping track of real-time congestion. In addition, the provision of rewards encourages users to take action, leading to further information accumulation and improved user satisfaction.

[1089] A "comment" is information in which a user writes their opinion or impression about a particular restaurant or product.

[1090] A "photo" is image data taken by a user to provide visual information about a particular restaurant or product.

[1091] A "database" is a system for organizing and storing various data in one place, and is used to store user-generated content such as comments and photos.

[1092] An "artificial intelligence model" is a software model that uses machine learning and deep learning techniques to analyze data and identify patterns and features.

[1093] "Classification and tagging" is the process of using artificial intelligence models to analyze data and assign it specific categories or labels.

[1094] "Location information" is information that indicates the user's current geographical location, and is obtained using technology such as GPS.

[1095] "Recommendation suggestions" is the process of recommending the most suitable restaurants and products based on the user's past behavior, preferences, and location information.

[1096] A "benefit" is an incentive such as a coupon or discount that is provided when a user meets certain conditions.

[1097] A "physical store" refers to a physical retail store or restaurant where real-time services are provided.

[1098] "Crowd situation" refers to information about the number of people and their movements in a particular location or store, and is useful for responding to customers in real time.

[1099] A "smartphone" is a mobile phone terminal that can connect to the Internet and run a variety of applications.

[1100] "Smart glasses" are wearable devices that integrate visual and digital information and provide it to users.

[1101] A "robot" is an automated mechanical device that is programmed to perform designated tasks.

[1102] An "application" is a software program that performs a specific function and runs on a smartphone, smart glasses, or robot.

[1103] The system of the present invention is designed to enhance users' shopping experience in physical stores by enabling them to receive personalized services through the posting and analysis of comments and photos, recommendations based on the user's location and preferences, real-time congestion information, and incentives.

[1104] 1. Collecting comments and photos

[1105] Users can use their smartphones, smart glasses, or robots to post comments and photos about products in physical stores. This data is then sent to a server via the device and stored in a database. This process accumulates real-time user feedback.

[1106] 2. Data Analysis and Classification

[1107] The server periodically scans the comments and photos stored in the database and analyzes them using an artificial intelligence model. During this analysis process, categories and tags are assigned based on the product's characteristics and the user's preferences. The analysis results are reflected in the user's profile and used to make future recommendations. The artificial intelligence models used include TensorFlow and PyTorch.

[1108] 3. Recommended Suggestions

[1109] When a user presses the "Search for recommended products" button, the device sends the user's location information and preferred characteristics to the server. Based on the received information, the server selects the most suitable products and nearby restaurants from its database and provides them as detailed information. During this process, a geocoding library (e.g., geopy) is used to obtain accurate location information.

[1110] 4. Posting comments and offering rewards

[1111] When a user posts a new comment or photo, the server records that action and issues a coupon or discount if the conditions for the reward are met. This reward information is sent to the user's device and notified, encouraging them to make their next purchase.

[1112] 5. Real-time congestion information

[1113] Wi-Fi devices and sensors installed in physical stores periodically send current congestion status to a server. The server analyzes this information and provides it to users in real time. Based on this information, users can efficiently choose stores.

[1114] Specific examples

[1115] For example, when a user approaches a particular shelf, the smart glasses will display past comments and reviews related to that shelf. They will also display items on sale and recommended items in the same category. When a user uses their smartphone to "search for recommended items," the server will generate an optimal product list based on their current location and preference data and provide it to the user.

[1116] Example of input prompt for generative AI model

[1117] Prompt: Based on the user's location and preferences, list the best stores and sales information:

[1118] Location: Latitude: 35.6895, Longitude: 139.6917

[1119] Interest data: ["Fashion", "Electronics", "Sports equipment"]

[1120] The system of the present invention allows users to shop efficiently in physical stores based on their preferences and receive optimal service based on real-time information.

[1121] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1122] Step 1:

[1123] A user posts comments and photos about products in a physical store using a smartphone, smart glasses, or a robot. This posted data is sent to the server by the terminal. The input is the comments and photos posted by the user, and the output is the posted data stored on the server. In this step, the comments and photos are accumulated in a database.

[1124] Step 2:

[1125] The server periodically scans the comments and photos stored in the database and analyzes them using an AI model. The input is the comments and photos in the database, and the output is the analyzed data. The AI ​​model analyzes the data using TensorFlow and PyTorch, and assigns categories and tags based on product characteristics and user preferences.

[1126] Step 3:

[1127] When a user presses the "Search for Recommended Products" button, the device sends the user's location information and preferred characteristics to the server. The input is the user's location information and preference data, and the output is a list of the best products and nearby restaurants generated by the server. The server uses the Geopy library to analyze the location information and list the best recommendations from the database.

[1128] Step 4:

[1129] When a user posts a new comment or photo, the server records that action and issues a coupon or discount if the conditions for the reward are met. The input is the newly posted comment or photo, and the output is the coupon information sent to the user's device. In this step, the content of the post is evaluated and a reward is issued.

[1130] Step 5:

[1131] WiFi devices and sensors installed in physical stores periodically send current congestion status to a server. The input is the congestion information of the physical store, and the output is analyzed real-time congestion status data. The server analyzes this information and notifies the user.

[1132] Step 6:

[1133] When a user approaches a specific product shelf in a physical store using smart glasses or a smartphone, related past comments and reviews are displayed on the device. The input is the user's current location information and a product database, and the output is product information and reviews displayed on the device. Specifically, the server obtains relevant data based on the user's location information and sends it to the device in real time.

[1134] Step 7:

[1135] When a user behaves in a way that meets the conditions for a reward, the server checks the conditions and issues a coupon or discount. The input is the user's behavioral data and the conditions for the reward, and the output is the coupon or discount data. The server uses an algorithm to check the behavioral data and issues a reward if the conditions are met. In this step, the process of providing incentives to the user is executed.

[1136] 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.

[1137] The system of the present invention includes the following components to enable users to easily and specifically search for restaurants.

[1138] 1. Collecting comments and photos

[1139] Users use the app to input and take comments and photos about restaurants. The device then sends these posts to the server, which then stores the received comments and photos in a database. This process creates a system in which user experiences are accumulated as information.

[1140] 2. Data Analysis and Classification

[1141] The server periodically scans the comments and photos stored in the database to extract new data. The server then analyzes the data using an artificial intelligence model and assigns categories and tags based on the user's preferences. This analysis process extracts characteristics such as ingredients, atmosphere, and price range. The analysis results are reflected in the user's profile and used for future recommendations.

[1142] 3. Recommended Suggestions

[1143] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preferred characteristics to the server. Based on the received information, the server lists the most suitable restaurants from its database. This makes it possible to make personalized recommendations based on the user's current location and preferences. The restaurant information listed by the server is sent to the device and displayed to the user.

[1144] 4. Posting comments and offering rewards

[1145] When a user posts a new comment or photo about a restaurant, the server records that action. If the reward conditions are met, the server issues a coupon or discount. This coupon information is sent to the terminal and notified to the user, allowing the user to use the reward for their next meal.

[1146] 5. Real-time congestion information

[1147] The restaurant's terminals and Wi-Fi devices periodically send their current occupancy status to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when choosing a restaurant.

[1148] 6. Emotion Recognition by Emotion Engine

[1149] When analyzing comments and photos posted by users, the server also uses an emotion engine to recognize the user's emotions. This emotion data is used for more detailed analysis of user preferences and is reflected in restaurant recommendation results and the provision of special offers.

[1150] Specific examples

[1151] For example, if a user wants to eat "yakiniku" (grilled meat), they search for "yakiniku" in the app, and the device sends their current location and preference data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. At this time, it also uses an emotion engine to reference the user's emotional data and prioritizes restaurants that the user felt happy or satisfied with. The server then sends this list to the device and presents it to the user.

[1152] Furthermore, when a user visits a specific store and posts new comments or photos there, the server analyzes the posts and issues coupons. If the user expresses positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to receive a discount and increase their motivation to visit again. In addition, real-time congestion information is provided, allowing users to avoid waiting times and efficiently choose a store.

[1153] This process allows users to easily find restaurants that perfectly match their preferences and also receive rewards, resulting in a system that encourages frequent use. Furthermore, the use of an emotion engine builds more detailed user profiles, improving recommendation accuracy.

[1154] The processing flow will be explained below.

[1155] 1. Comment and photo collection

[1156] Step 1:

[1157] The user launches the app and enters or takes a photo or comments about the restaurant.

[1158] Step 2:

[1159] The device sends the comments and photo data entered by the user to the server.

[1160] Step 3:

[1161] The server stores the received comments and photo data in a database.

[1162] 2. Data Analysis and Classification

[1163] Step 4:

[1164] The server periodically scans the database for new comments and photos.

[1165] Step 5:

[1166] The server uses an artificial intelligence model to analyze the acquired data, specifically extracting characteristics such as ingredients, atmosphere, and price range from the comments.

[1167] Step 6:

[1168] Based on the analysis results, the server assigns categories and tags to each comment and photo.

[1169] Step 7:

[1170] The server reflects the analysis results in the user profile and updates the user's preference data.

[1171] 3. Recommended Suggestions

[1172] Step 8:

[1173] The user presses the "Search for recommended restaurants" button on the app.

[1174] Step 9:

[1175] The device sends the user's location information and data about the user's preferences to the server.

[1176] Step 10:

[1177] Based on the location information and preference data received by the server, the server searches the database for the most suitable restaurant.

[1178] Step 11:

[1179] The server ranks and lists the search results.

[1180] Step 12:

[1181] The server sends the listed restaurant information to the terminal.

[1182] Step 13:

[1183] The terminal displays the recommended restaurant information to the user.

[1184] 4. Posting comments and offering rewards

[1185] Step 14:

[1186] A user posts a new comment or photo.

[1187] Step 15:

[1188] The terminal transmits the posting data to the server.

[1189] Step 16:

[1190] The server analyzes the post and checks whether it meets the conditions for the reward.

[1191] Step 17:

[1192] The server issues coupons and discounts when certain conditions are met.

[1193] Step 18:

[1194] The server transmits the issued coupon information to the terminal and notifies the user.

[1195] Step 19:

[1196] The terminal displays the coupon information to the user.

[1197] 5. Real-time congestion information

[1198] Step 20:

[1199] The restaurant's terminals and WiFi devices send the store's congestion status to the server.

[1200] Step 21:

[1201] The server analyzes the congestion information received.

[1202] Step 22:

[1203] When a user requests congestion information through the app, the server sends the latest congestion information to the device.

[1204] Step 23:

[1205] The terminal displays real-time congestion status to the user.

[1206] 6. Emotion Recognition by Emotion Engine

[1207] Step 24:

[1208] The server inputs the user's posted data into an emotion engine and analyzes the user's emotions.

[1209] Step 25:

[1210] The server adds the emotion data obtained from the emotion engine to the user profile.

[1211] Step 26:

[1212] The server reflects the user's emotional data in the analysis data and reflects it as a restaurant recommendation result.

[1213] Step 27:

[1214] The server issues a coupon with a higher discount rate based on the emotion data if certain conditions are met.

[1215] Specific examples

[1216] For example, if a user wants to eat "yakiniku" (grilled meat), they can search for "yakiniku" in the app, and the device will send their current location and preference data to the server. The server will then analyze past comments and photos related to "yakiniku" and use an emotion engine to obtain the user's emotional data. The server will prioritize restaurants that the user has positive feelings about, such as being happy or satisfied, and send the list to the device to present to the user.

[1217] Next, when a user visits a specific store and posts new comments or photos, the server analyzes the posts and issues coupons. If the user expresses positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to receive a discount and increase their motivation to visit again. In addition, real-time congestion information is provided, allowing users to avoid waiting times and choose a store efficiently.

[1218] This process allows users to easily find restaurants that perfectly match their preferences and also receive rewards, resulting in a system that encourages frequent use. Furthermore, the use of an emotion engine builds more detailed user profiles, improving recommendation accuracy.

[1219] Example 2

[1220] 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."

[1221] Today's consumers desire diverse dining experiences and want to efficiently find restaurants that suit their preferences. Information reflecting the user's emotions and the actual congestion status of restaurants visited are also important factors in their decision-making. However, conventional systems struggle to provide recommendations that take into account the user's detailed preferences and emotions, and they do not adequately provide real-time congestion status or special offers. Furthermore, they lack the functionality to quickly suggest restaurants that match the user's preferences using the user's location information. This has made it difficult for users to efficiently find restaurants that suit their preferences.

[1222] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving comments and photos posted by users and storing the data in a database, means for analyzing the stored comments and photos using an artificial intelligence model and classifying and tagging them based on the user's preferences, means for suggesting recommended nearby facilities based on the user's location information based on the analyzed data, means for providing rewards for posts made by users when the users post comments and photos, means for collecting information on facility congestion status in real time and providing the information to the users, and means for analyzing user posts and using an emotion engine that recognizes emotions. This improves convenience by allowing users to easily find recommended restaurants that suit their preferences, understand congestion status in real time, and receive rewards for posting.

[1223] "User" refers to an individual who uses the system to post comments and photos, search for restaurants, receive recommendations, and receive special offers.

[1224] "Comments" refer to posted data in which users express their impressions and opinions about restaurants in writing.

[1225] "Photos" refer to image data of restaurants and food taken by users.

[1226] "Database" refers to an information management system that allows the server to store user posted data and analysis results.

[1227] "Artificial intelligence model" refers to technology that uses machine learning algorithms to analyze and classify data.

[1228] "Preferences" refers to personal preferences such as the ingredients, cuisine, atmosphere, and price range that the user prefers.

[1229] "Classification and tagging" refers to the process by which an artificial intelligence model analyzes data and assigns it specific categories or attributes.

[1230] "Location Information" refers to data that indicates a user's current geographic location.

[1231] "Facility" refers to a service providing location that a user visits, including a restaurant.

[1232] "Benefits" refers to rewards such as coupons and discounts that users receive when they post comments or photos.

[1233] "Crowd situation" refers to information showing the current number of customers at a restaurant and waiting times.

[1234] "Real-time" refers to information being updated or provided almost instantly.

[1235] "Emotion engine" refers to technology that analyzes and recognizes emotions from user posted data.

[1236] The system of the present invention includes the following components to enable users to easily and specifically search for restaurants.

[1237] First, users must install an application on their device to post comments and photos. Using this application, users can input and take photos of the food and their impressions after eating. The device used for this is a smartphone, tablet, or other device with an internet connection.

[1238] The device then sends the comments and photos entered or taken by the user to a server, which then receives the posted data and stores it in a database, such as a cloud-based data storage system (the general term used here is "database management system").

[1239] The server then periodically scans the database to extract newly stored data. The extracted data is analyzed using an artificial intelligence model (e.g., a machine learning algorithm like TensorFlow or PyTorch). Based on the analysis results, comments and photos are assigned specific categories and tags (e.g., ingredients, atmosphere, price range). These analysis results are reflected in the user profile and used for future recommendations.

[1240] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and profile data to the server. The server uses this information to create a list of the most suitable restaurants from a database. This process may involve the use of a search engine such as Elasticsearch. The listed restaurant information is then sent to the device and displayed to the user.

[1241] Furthermore, when a user posts a new comment or photo, the post is sent again to the server and stored in the database. The server analyzes the posted data and issues coupons or discounts if the conditions are met. This special offer information is sent to the device and notified to the user. The server uses, for example, a REST API or push notification service to provide these special offers.

[1242] In addition, restaurant terminals and Wi-Fi devices periodically send occupancy data to a server. The server analyzes this data and provides it to users in real time. This analysis is sometimes performed using a real-time analysis engine (e.g., Apache Kafka).

[1243] The emotion engine also runs on the server, analyzing user posted data to recognize emotions. The recognized emotion data is used for more detailed preference analysis and is reflected in recommendation results and reward offers.

[1244] Examples and prompts

[1245] As a concrete example, if a user wants to eat "yakiniku," the following steps are executed: The user searches for "yakiniku" in the app, and the device sends its current location and profile data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. At this time, it also uses an emotion engine to prioritize the list of restaurants for which the user expressed positive emotions (such as joy or satisfaction). The server then sends this list to the device and presents it to the user.

[1246] Furthermore, when a user visits a specific restaurant and posts new comments or photos, the server analyzes the posts and issues coupons. If the user shows positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to use the rewards for their next meal, increasing frequency of use. In addition, real-time congestion information is provided, allowing users to avoid waiting times and efficiently choose a restaurant.

[1247] Prompt Sentence Examples

[1248] "If I want to eat yakiniku, how do I search for restaurants? Also, what kind of benefits do I get for posting comments and photos?"

[1249] Through this process, the present invention realizes a system that allows users to easily find restaurants that suit their preferences and also receive rewards, which increases the frequency of use. In addition, the use of an emotion engine will build more detailed user profiles, improving recommendation accuracy.

[1250] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1251] Step 1:

[1252] The user launches the app, enters comments about the restaurant, and takes a photo if necessary.

[1253] Input: User comments and photos

[1254] Specific operation: The user enters a comment in the text field and takes a photo using the camera function. The device temporarily stores this data in memory.

[1255] Step 2:

[1256] The terminal transmits comments and photos entered or taken by the user to the server.

[1257] Input: User comments and photos (output of step 1)

[1258] Output: Notification that transmission to the server was successful

[1259] How it works: The device generates an HTTP POST request to the server over the Internet, attaches the user's comments and photos, and sends them. If the transmission is successful, the device receives a confirmation response from the server.

[1260] Step 3:

[1261] The server stores the received comments and photos in a database.

[1262] Input: Comments and photos sent from the device (output of Step 2)

[1263] Output: Data ID stored in the database or notification of successful storage

[1264] Specific operation: The server stores the received data in the target database management system. If the storage is successful, it generates an ID for the stored data and notifies the terminal or internal process.

[1265] Step 4:

[1266] The server periodically scans the database and extracts new data.

[1267] Input: All data stored in the database

[1268] Output: A list of the new data

[1269] Specific operation: The server sets up a scheduled job to periodically query the database to extract and list new data.

[1270] Step 5:

[1271] The server inputs the extracted data into an artificial intelligence model for analysis.

[1272] Input: List of new data (output of Step 4)

[1273] Output: Analysis results (categories, tags, sentiment analysis results, etc.)

[1274] How it works: The server analyzes new data using artificial intelligence models (e.g., TensorFlow, PyTorch). The analysis uses text and image analysis algorithms to extract attributes such as ingredients, atmosphere, price range, and sentiment.

[1275] Step 6:

[1276] The server assigns categories and tags to the data based on the analysis results.

[1277] Input: Analysis results (output from Step 5)

[1278] Output: Classified and tagged data

[1279] Specific operation: The server assigns categories and tags (e.g., yakiniku, relaxed atmosphere, high price range, etc.) to the analyzed data and stores it in a database.

[1280] Step 7:

[1281] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preference data to the server.

[1282] Input: User location and preference data

[1283] Output: Notification that transmission to the server was successful

[1284] Specific operation: The device uses the GPS function to obtain its current location and transmits it along with the user profile data to the server. If the transmission is successful, the device receives a confirmation response.

[1285] Step 8:

[1286] The server creates a list of the most suitable restaurants based on the user's location information and preference data.

[1287] Input: User location and preference data (output of step 7)

[1288] Output: List of restaurants

[1289] What it does: The server uses a search engine like Elasticsearch to query the database and return a list of restaurants that fit the criteria, taking into account analytics results and data from the user profile.

[1290] Step 9:

[1291] The server sends the listed restaurant information to the terminal and displays it to the user.

[1292] Input: List of restaurants (output of Step 8)

[1293] Output: List of restaurants sent to the terminal

[1294] Specific operation: The server encodes the listed information in JSON format and sends it to the device as an HTTP response. The device receives this and displays it as a list on the app screen.

[1295] Step 10:

[1296] When a user posts new comments or photos, the device sends them back to the server and stores them in the database.

[1297] Input: New comment and new photo for the user

[1298] Output: Notification of successful transmission to the server and notification of completion of database storage

[1299] Specific operation: Similar to steps 1 to 3, the terminal sends new data to the server, and the server stores it in the database.

[1300] Step 11:

[1301] The server analyzes new posts and issues coupons or discounts if the conditions are met.

[1302] Input: New comment and new photo (input from step 10)

[1303] Output: Issued benefits (coupons and discounts) information

[1304] Specific operation: The server analyzes the new data and generates coupons and discounts for posts that meet the conditions. The generated reward information is sent to the terminal and notified to the user.

[1305] Step 12:

[1306] The restaurant's terminal or Wi-Fi device sends the current congestion status to the server.

[1307] Input: Restaurant congestion data

[1308] Output: Notification of successful transmission to the server

[1309] Specific operation: Restaurant terminals and Wi-Fi devices periodically send congestion status data such as the number of connections and bandwidth usage to the server. The server receives this data and returns an acknowledgement.

[1310] Step 13:

[1311] The server analyzes the congestion data and provides it to users in real time.

[1312] Input: Restaurant congestion data (output of Step 12)

[1313] Output: Real-time provision of analyzed congestion information

[1314] Specific operation: The server uses a real-time analysis engine (e.g., Apache Kafka) to analyze the congestion data and provide the analysis results to the user in real time.

[1315] Step 14:

[1316] The server analyzes the user's posted data using an emotion engine to recognize emotions.

[1317] Input: User comments and photos

[1318] Output: User emotion data

[1319] Specific operation: The server inputs the posted data (text and images) into the emotion engine, and recognizes the user's emotions through natural language processing and image analysis. The output emotion data is saved in the user profile.

[1320] Step 15:

[1321] The server uses the emotional data to make recommendations and provide rewards.

[1322] Input: User emotion data

[1323] Output: Improved recommendations and rewards information

[1324] Specific operation: The server reflects the emotional data in the user profile and uses it to improve the accuracy of the next restaurant recommendation and reward offer, thereby providing services that are more suited to the user's preferences.

[1325] (Application example 2)

[1326] 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."

[1327] In food delivery services, it is not easy for users to efficiently search and select restaurants that suit their preferences. In particular, there is a demand for personalized recommendations that take into account a variety of information, such as users' past ratings and real-time congestion status. It is also important to properly analyze comments and photos posted by users and provide rewards based on them, but there is no centralized system for this.

[1328] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving comments and photos posted by users and storing the data in a database, means for analyzing the stored comments and photos using an artificial intelligence model and classifying and tagging them based on the user's preferences, means for suggesting recommended nearby restaurants based on the user's location information based on the analyzed data, means for providing rewards for comments and photos posted by users, means for collecting restaurant congestion information in real time and providing the information to the user, means for understanding the comments and photos stored in the database using TF-IDF-based analysis and calculating similarity, and means for listing and providing food delivery services that best suit the user's preferences based on the similarity analysis. This allows users to easily find restaurants and food delivery services that best suit their preferences and also enjoy rewards.

[1329] "User" refers to an individual user who uses the system to search for restaurants, rate them, and post comments and photos.

[1330] "Comments" refer to text-based evaluations and opinions posted by users about restaurants.

[1331] "Photos" refer to image data that users take of restaurants and food and post.

[1332] "Database" refers to a storage system managed on a server for storing comments and photos collected from users.

[1333] "Artificial intelligence model" refers to a program that uses machine learning technology to analyze user comments and photos and categorize and tag them based on preferences.

[1334] "Preferences" refers to a user's likes, dislikes, and interests, and includes factors such as ingredients, atmosphere, and price range.

[1335] "Classification" refers to the process of sorting analyzed data into specific categories.

[1336] "Tagging" refers to the process of assigning appropriate labels to analyzed data.

[1337] "Location information" refers to geographical data about a user's current location.

[1338] "Suggestion" refers to the act of recommending restaurants suitable for the user based on the analysis results.

[1339] "Benefits" refer to rewards such as coupons and discount vouchers that are beneficial to users.

[1340] "Crowd situation" refers to information such as the current number of customers at a restaurant and waiting times.

[1341] "Real-time" refers to providing nearly instantaneous, up-to-date information.

[1342] "TF-IDF-based analysis" refers to the process of analyzing data using a technique that calculates significant words in a sentence.

[1343] "Similarity" refers to an index that calculates how similar different comments or photos are.

[1344] "Food delivery service" refers to a service that delivers meals ordered online by users to their homes or designated locations.

[1345] The system of this invention provides a series of processes that enable users to efficiently search for and select restaurants and food delivery services that suit their preferences. The system is composed of the following components and processes.

[1346] 1. Collecting comments and photos

[1347] Users use devices such as smartphones and tablets to input and take photos and comments about restaurants, and then send them to the server. A mobile application is installed on the user's device as an interface. Through this application, users can easily input comments and upload photos. The server receives these posts and stores them in a database.

[1348] 2. Data Analysis and Classification

[1349] The server periodically analyzes the comments and photos stored in the database using an artificial intelligence model. Specifically, it uses TF-IDF-based analysis to extract important words in sentences and calculate similarity. This data analysis then categorizes and tags each post based on the user's preferences. For example, categories such as ingredients, atmosphere, and price range are generated.

[1350] 3. Recommended Suggestions

[1351] When a user presses the "Search for recommended food delivery services" button, the device sends the user's location information and previous preference data to the server. Based on the received information, the server selects the most suitable food delivery services from its database. The server provides the list to the user, taking into account real-time congestion and available delivery times.

[1352] 4. Posting comments and offering rewards

[1353] When a user posts a new comment or photo about a food delivery service or restaurant, the server records the action. If the conditions for the reward are met, the server issues a coupon or discount and notifies the user's device.

[1354] 5. Real-time congestion information

[1355] The terminals and installed devices of the food delivery service periodically send information about current congestion and available delivery times to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when users choose a food delivery service.

[1356] Specific examples

[1357] For example, if a user wants to eat "sushi," they search for "sushi" in the app, and their location information and preference data are sent to the server. The server then analyzes past comments and photos related to "sushi" and lists recommended food delivery services in the vicinity. It also uses an emotion engine to prioritize restaurants and services that the user has positive feelings about, such as being happy or satisfied with. The server then sends this list to the user's device and presents it to the user.

[1358] Furthermore, when a user uses a specific food delivery service and posts new comments or photos, the server analyzes the posts and issues coupons. If the user expresses positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to receive a discount and increase their motivation to use the service again. Real-time congestion information is also provided, allowing users to avoid waiting times and use the service efficiently.

[1359] Prompt Sentence Examples

[1360] "Can you recommend any restaurants near my location that serve good sushi? Also, can you show me any coupons or special offers I can use?"

[1361] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1362] Step 1:

[1363] Users use a smartphone or tablet application to input and take comments and photos about restaurants. The input comments (text data) and photos (image data) are collected as data. This data is saved on the device via an interface and sent to a server. Input is performed manually by the user, and output is the transfer of data to the server.

[1364] Step 2:

[1365] The server receives comments and photos sent from the devices and stores them in a database. This database serves as a repository of information to be used for future data analysis and searches. The input is the comments and photos received from the devices, and the output is storage in the database. The stored data is used in subsequent analysis processes.

[1366] Step 3:

[1367] The server periodically scans the comments and photos stored in the database and extracts the latest data. The extracted data is then analyzed using an artificial intelligence model. Specifically, TF-IDF-based analysis is used to extract important words in the text and calculate their similarity. The input is the extracted comments and photos, and the output is classified and tagged data as the analysis results.

[1368] Step 4:

[1369] The server updates the user profile based on the analyzed data. The updated profile is classified into categories such as ingredients, atmosphere, and price range. This profile will be used in a future recommendation system. The input is the analysis results, and the output is the updated user profile.

[1370] Step 5:

[1371] When a user presses the "Search for recommended food delivery services" button in the application, the device sends its current location and past preference data to the server. Location information is obtained via GPS, and preference data is extracted from the user profile. The input is location information and preference data, and the output is a request sent to the server.

[1372] Step 6:

[1373] The server uses the received location information and preference data to create a list of optimal food delivery services from a database. The list also takes into account real-time congestion and available delivery times. The listed services are generated as an analysis result and provided to the user. The input is location information and preference data, and the output is the listed service information.

[1374] Step 7:

[1375] The server checks the analysis results and the conditions for the rewards, and issues a coupon or discount if the user meets the conditions. The issued reward information is sent to the terminal and notified to the user. The input is the reward conditions and the analysis results, and the output is the coupon or discount information.

[1376] Step 8:

[1377] Users use the provided food delivery service and post new comments and photos about the service. These posts are also sent to the server, stored in a database, and analyzed. This allows new feedback to be continuously collected, contributing to improving the accuracy of the system. The input is newly posted data, and the output is data transfer and storage to the server.

[1378] Step 9:

[1379] Users can check the congestion status provided in real time and efficiently select a food delivery service. This information is collected from the restaurant's terminal or installed device, analyzed by the server, and then provided to the user. The input is data from the restaurant, and the output is real-time congestion status information.

[1380] This series of processing steps allows users to easily find restaurants and food delivery services that suit their preferences and also enjoy special offers.

[1381] 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.

[1382] 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.

[1383] 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.

[1384] [Fourth embodiment]

[1385] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1386] 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.

[1387] 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).

[1388] 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.

[1389] 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.

[1390] 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).

[1391] 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.

[1392] 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.

[1393] 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.

[1394] 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.

[1395] 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.

[1396] 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.

[1397] 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."

[1398] The system of the present invention includes the following components to enable users to easily and specifically search for restaurants.

[1399] 1. Collecting comments and photos

[1400] Users use the app to post comments and photos about restaurants. The device then sends these posts to the server, which then stores the received comments and photos in a database. This process creates a system in which user experiences are accumulated as information.

[1401] 2. Data Analysis and Classification

[1402] The server periodically scans the comments and photos stored in the database to extract new data. The server then analyzes the data using an artificial intelligence model and assigns categories and tags based on the user's preferences. This analysis process extracts characteristics such as ingredients, atmosphere, and price range. The analysis results are reflected in the user's profile and used for future recommendations.

[1403] 3. Recommended Suggestions

[1404] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preferred characteristics to the server. Based on the received information, the server lists the most suitable restaurants from its database. This makes it possible to make personalized recommendations based on the user's current location and preferences. The restaurant information listed by the server is sent to the device and displayed to the user.

[1405] 4. Posting comments and offering rewards

[1406] When a user posts a new comment or photo about a restaurant, the server records that action. If the reward conditions are met, the server issues a coupon or discount. This coupon information is sent to the terminal and notified to the user, allowing the user to use the reward for their next meal.

[1407] 5. Real-time congestion information

[1408] The restaurant's terminals and Wi-Fi devices periodically send their current occupancy status to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when choosing a restaurant.

[1409] Specific examples

[1410] For example, if a user wants to eat "yakiniku" (grilled meat), they search for "yakiniku" in the app, and the device sends their current location and preference data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. The server then sends this list to the device and presents it to the user. When the user visits a specific restaurant and posts new comments or photos there, the server records the action and issues a coupon. This allows the user to receive a discount and increase their motivation to return. Real-time congestion information is also provided, allowing users to avoid waiting times and choose a restaurant efficiently.

[1411] This process allows users to easily find restaurants that perfectly suit their tastes and also receive special benefits, resulting in a system that encourages increased usage.

[1412] The processing flow will be explained below.

[1413] 1. Comment and photo collection

[1414] Step 1:

[1415] The user launches the app and enters or takes a photo or comments about the restaurant.

[1416] Step 2:

[1417] The device sends the comments and photo data entered by the user to the server.

[1418] Step 3:

[1419] The server stores the received comments and photo data in a database.

[1420] 2. Analysis and Classification

[1421] Step 4:

[1422] The server periodically scans the database for new comments and photos.

[1423] Step 5:

[1424] The server uses an artificial intelligence model to analyze the acquired data, specifically extracting characteristics such as ingredients, atmosphere, and price range from the comments.

[1425] Step 6:

[1426] Based on the analysis results, the server assigns categories and tags to each comment and photo.

[1427] Step 7:

[1428] The server reflects the analysis results in the user profile and updates the user's preference data.

[1429] 3. Recommended Suggestions

[1430] Step 8:

[1431] The user presses the "Search for recommended restaurants" button on the app.

[1432] Step 9:

[1433] The device sends the user's location information and data about the user's preferences to the server.

[1434] Step 10:

[1435] Based on the location information and preference data received by the server, the server searches the database for the most suitable restaurant.

[1436] Step 11:

[1437] The server ranks and lists the search results.

[1438] Step 12:

[1439] The server sends the listed restaurant information to the terminal.

[1440] Step 13:

[1441] The terminal displays the recommended restaurant information to the user.

[1442] 4. Posting comments and offering rewards

[1443] Step 14:

[1444] A user posts a new comment or photo.

[1445] Step 15:

[1446] The terminal transmits the posting data to the server.

[1447] Step 16:

[1448] The server analyzes the post and checks whether it meets the conditions for the reward.

[1449] Step 17:

[1450] The server issues coupons and discounts when certain conditions are met.

[1451] Step 18:

[1452] The server transmits the issued coupon information to the terminal and notifies the user.

[1453] Step 19:

[1454] The terminal displays the coupon information to the user.

[1455] 5. Real-time congestion information

[1456] Step 20:

[1457] The restaurant's terminals and WiFi devices send the store's congestion status to the server.

[1458] Step 21:

[1459] The server analyzes the congestion information received.

[1460] Step 22:

[1461] When a user requests congestion information through the app, the server sends the latest congestion information to the device.

[1462] Step 23:

[1463] The terminal displays real-time congestion status to the user.

[1464] Through the above process, users can easily find restaurants that suit their tastes. In addition, they can receive rewards, which motivates them to post, and they can also check the real-time congestion status, which helps them avoid crowded restaurants.

[1465] Example 1

[1466] 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."

[1467] Conventional restaurant search systems make it difficult for users to quickly find suitable restaurants, and they lack real-time information about restaurant congestion and suggestions based on user preferences. This results in a limited user experience and the inconvenience of having to use multiple applications. Furthermore, they lack incentives for users to post information.

[1468] 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.

[1469] In this invention, the server includes: means for receiving comments and photos posted by users and storing the data in a database; means for analyzing the stored comments and photos using an artificial intelligence model and categorizing and tagging them based on the user's preferences; means for suggesting nearby recommended restaurants based on the user's location information based on the analyzed data; means for providing rewards for comments and photos posted by users; and means for receiving congestion status data transmitted by the restaurant's communication terminal or wireless communication device and providing the data to the user in real time. This allows users to easily find restaurants that perfectly match their preferences and makes appropriate choices based on real-time information. Furthermore, providing rewards for user posts increases user engagement.

[1470] "User" means an individual who uses the Application to post comments and photos of restaurants and obtain information.

[1471] A "terminal" refers to an electronic device on which an application is installed, such as a smartphone or tablet used by a user.

[1472] "Server" means a computer system that receives, stores, and processes data from users, analyzes comments and photos, and provides information to users.

[1473] A "database" is a system for organizing and managing data such as comments and photos stored on a server.

[1474] "Artificial Intelligence Model" means a machine learning or deep learning algorithm used to analyze User-Submitted Data and categorize and tag it based on preferences.

[1475] "Location information" refers to information that indicates the user's current geographical data.

[1476] "Rewards" means rewards, coupons, or discounts offered to users for using the Application or posting comments or photos.

[1477] "Occupancy data" refers to information about the current number of customers and how crowded a restaurant is.

[1478] A "communication terminal" refers to an electronic device used by a restaurant to transmit congestion status data to a server.

[1479] A "wireless communication device" is a device that communicates data using wireless technology such as Wi-Fi.

[1480] "Analysis" refers to the process of processing received comments and photo data to extract user preferences and store characteristics.

[1481] The system of the present invention allows users to search for and use restaurants, and includes the following components:

[1482] 1. User comments and photo posting

[1483] Users use the application to post comments and photos about restaurants. At this time, the device sends the user's posted data to the server. The server stores the received comments and photos in a database. This allows the user's experiences to be accumulated as information.

[1484] 2. Analysis and classification of comments and photos

[1485] The server periodically scans the comments and photos stored in the database to extract new data. The server then analyzes this data using an artificial intelligence model (e.g., TensorFlow) to assign categories and tags based on the user's preferences. This analysis process extracts characteristics such as ingredients, atmosphere, and price range. The analysis results are reflected in the user's profile and used to make future recommendations.

[1486] 3. Recommended Suggestions

[1487] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preference data to the server. Based on the received information, the server queries and lists the most suitable restaurants from its database. This enables personalized recommendations based on the user's current location and preferences. The restaurant information listed by the server is sent to the device and displayed to the user.

[1488] 4. Posting comments and offering rewards

[1489] When a user posts a new comment or photo, the server logs the action. If the reward conditions are met, the server generates coupons or discount information, sends it to the user's device, and notifies the user, allowing them to use the reward for their next meal.

[1490] 5. Real-time congestion information

[1491] The restaurant's terminal or wireless communication device (e.g., WiFi device) sends current occupancy data to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when the user chooses a restaurant.

[1492] Specific examples

[1493] For example, if a user wants to eat "yakiniku" (grilled meat), they search for "yakiniku" in the app, and the device sends their current location and preference data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. The server then sends this list to the device and presents it to the user. When the user visits a specific restaurant and posts new comments or photos there, the server records the action and issues a coupon if the conditions for the offer are met. This allows the user to receive a discount, increasing their motivation to return. In addition, the server provides real-time information on the restaurant's congestion status, allowing users to avoid waiting times and choose a restaurant efficiently.

[1494] Prompt Sentence Examples

[1495] An example of a prompt sentence to input into a generative AI model is, "If the user wants to eat yakiniku, list related restaurant recommendations and suggest personalized restaurant recommendations based on the user's current location."

[1496] This process allows users to easily find restaurants that perfectly suit their tastes and also receive special benefits, resulting in a system that encourages increased usage.

[1497] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1498] Program processing flow

[1499] Step 1: User posts comments and photos

[1500] Users open the application and enter comments and photos about restaurants by entering comments in the text box and uploading photos. Once the posting is complete, the device sends the data in JSON format to the server.

[1501] Input: User comments and photos

[1502] Output: Post data sent to the server (JSON format)

[1503] Specific behavior: The user presses the "New Post" button to post the entered text and selected photo.

[1504] Step 2: Receiving and storing comments and photos

[1505] The server receives the posted data sent from the terminal and stores it in a database.

[1506] Input: Post data sent from the device

[1507] Output: Post data stored in the database

[1508] Specific behavior: The server receives the POST request and inserts the received data into an SQL database.

[1509] Step 3: Analyze and classify comments and photos

[1510] The server periodically scans the database to extract new data, which is then analyzed using an artificial intelligence model (e.g., TensorFlow) to assign categories and tags, such as ingredients, atmosphere, and price range.

[1511] Input: New comments and photos extracted from the database

[1512] Output: Classified and tagged data

[1513] What it does: The server runs a Python script, analyzes comments using an NLP model, and classifies photos using an image recognition model.

[1514] Step 4: Recommendations

[1515] When a user presses the "Search for recommended restaurants" button on the application, the device sends the user's location information and preference data to the server, which then queries the database for the most suitable restaurants and creates a list.

[1516] Input: User location and preference data

[1517] Output: A list of the best restaurants

[1518] Specific operation: The server uses GPS data to search for store information near the current location and filters it based on preference data.

[1519] Step 5: Post a comment and receive a reward

[1520] When a user posts a new comment or photo, the server logs the action. If the conditions for the reward are met, the server generates coupons or discount information and sends it to the device.

[1521] Input: New comment and photo post data

[1522] Output: Issued coupons and discount information

[1523] Specific operation: The server checks the conditions, and if the conditions are met, generates a coupon code, sends it to the terminal, and notifies the user.

[1524] Step 6: Providing real-time congestion information

[1525] The restaurant's terminals and wireless communication devices (e.g., WiFi devices) periodically transmit current occupancy data to the server, which analyzes this data and provides it to users in real time.

[1526] Input: Occupancy data sent from restaurants

[1527] Output: Real-time congestion information displayed to the user

[1528] Specific operation: The restaurant's WiFi device sends data such as the number of connections to the server, which then analyzes the information, calculates the level of congestion, and displays it to the user.

[1529] Through these steps, users can easily find restaurants that suit their tastes and get real-time information on how busy they are. In addition, rewards can be offered to increase users' motivation to post.

[1530] (Application example 1)

[1531] 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."

[1532] Today's consumers strongly desire to smoothly find products that match their preferences while shopping in physical stores, to make product selections based on reviews and comments from others, and to act efficiently based on real-time information. However, conventional systems have had difficulty meeting these demands. Specifically, they lack the ability to make personalized suggestions that reflect users' preferences, provide real-time congestion information, and do not smoothly trigger comment and photo posts linked to special offers.

[1533] 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.

[1534] In this invention, the server

[1535] A means for receiving comments and photos posted by users and storing such data in a database;

[1536] A means for analyzing stored comments and photos using an artificial intelligence model and categorizing and tagging them based on user preferences;

[1537] Based on the analyzed data, the system will suggest nearby restaurants and products based on the user's location information.

[1538] A means to provide rewards for posts when users post comments or photos;

[1539] A means for collecting information on the congestion status of a physical store in real time and providing it to users;

[1540] A means for functioning as an application installed on a smartphone, smart glasses, or robot;

[1541] This allows consumers to receive personalized product and restaurant recommendations based on their preferences, and allows them to act efficiently while keeping track of real-time congestion. In addition, the provision of rewards encourages users to take action, leading to further information accumulation and improved user satisfaction.

[1542] A "comment" is information in which a user writes their opinion or impression about a particular restaurant or product.

[1543] A "photo" is image data taken by a user to provide visual information about a particular restaurant or product.

[1544] A "database" is a system for organizing and storing various data in one place, and is used to store user-generated content such as comments and photos.

[1545] An "artificial intelligence model" is a software model that uses machine learning and deep learning techniques to analyze data and identify patterns and features.

[1546] "Classification and tagging" is the process of using artificial intelligence models to analyze data and assign it specific categories or labels.

[1547] "Location information" is information that indicates the user's current geographical location, and is obtained using technology such as GPS.

[1548] "Recommendation suggestions" is the process of recommending the most suitable restaurants and products based on the user's past behavior, preferences, and location information.

[1549] A "benefit" is an incentive such as a coupon or discount that is provided when a user meets certain conditions.

[1550] A "physical store" refers to a physical retail store or restaurant where real-time services are provided.

[1551] "Crowd situation" refers to information about the number of people and their movements in a particular location or store, and is useful for responding to customers in real time.

[1552] A "smartphone" is a mobile phone terminal that can connect to the Internet and run a variety of applications.

[1553] "Smart glasses" are wearable devices that integrate visual and digital information and provide it to users.

[1554] A "robot" is an automated mechanical device that is programmed to perform designated tasks.

[1555] An "application" is a software program that performs a specific function and runs on a smartphone, smart glasses, or robot.

[1556] The system of the present invention is designed to enhance users' shopping experience in physical stores by enabling them to receive personalized services through the posting and analysis of comments and photos, recommendations based on the user's location and preferences, real-time congestion information, and incentives.

[1557] 1. Collecting comments and photos

[1558] Users can use their smartphones, smart glasses, or robots to post comments and photos about products in physical stores. This data is then sent to a server via the device and stored in a database. This process accumulates real-time user feedback.

[1559] 2. Data Analysis and Classification

[1560] The server periodically scans the comments and photos stored in the database and analyzes them using an artificial intelligence model. During this analysis process, categories and tags are assigned based on the product's characteristics and the user's preferences. The analysis results are reflected in the user's profile and used to make future recommendations. The artificial intelligence models used include TensorFlow and PyTorch.

[1561] 3. Recommended Suggestions

[1562] When a user presses the "Search for recommended products" button, the device sends the user's location information and preferred characteristics to the server. Based on the received information, the server selects the most suitable products and nearby restaurants from its database and provides them as detailed information. During this process, a geocoding library (e.g., geopy) is used to obtain accurate location information.

[1563] 4. Posting comments and offering rewards

[1564] When a user posts a new comment or photo, the server records that action and issues a coupon or discount if the conditions for the reward are met. This reward information is sent to the user's device and notified, encouraging them to make their next purchase.

[1565] 5. Real-time congestion information

[1566] Wi-Fi devices and sensors installed in physical stores periodically send current congestion status to a server. The server analyzes this information and provides it to users in real time. Based on this information, users can efficiently choose stores.

[1567] Specific examples

[1568] For example, when a user approaches a particular shelf, the smart glasses will display past comments and reviews related to that shelf. They will also display items on sale and recommended items in the same category. When a user uses their smartphone to "search for recommended items," the server will generate an optimal product list based on their current location and preference data and provide it to the user.

[1569] Example of input prompt for generative AI model

[1570] Prompt: Based on the user's location and preferences, list the best stores and sales information:

[1571] Location: Latitude: 35.6895, Longitude: 139.6917

[1572] Interest data: ["Fashion", "Electronics", "Sports equipment"]

[1573] The system of the present invention allows users to shop efficiently in physical stores based on their preferences and receive optimal service based on real-time information.

[1574] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1575] Step 1:

[1576] A user posts comments and photos about products in a physical store using a smartphone, smart glasses, or a robot. This posted data is sent to the server by the terminal. The input is the comments and photos posted by the user, and the output is the posted data stored on the server. In this step, the comments and photos are accumulated in a database.

[1577] Step 2:

[1578] The server periodically scans the comments and photos stored in the database and analyzes them using an AI model. The input is the comments and photos in the database, and the output is the analyzed data. The AI ​​model analyzes the data using TensorFlow and PyTorch, and assigns categories and tags based on product characteristics and user preferences.

[1579] Step 3:

[1580] When a user presses the "Search for Recommended Products" button, the device sends the user's location information and preferred characteristics to the server. The input is the user's location information and preference data, and the output is a list of the best products and nearby restaurants generated by the server. The server uses the Geopy library to analyze the location information and list the best recommendations from the database.

[1581] Step 4:

[1582] When a user posts a new comment or photo, the server records that action and issues a coupon or discount if the conditions for the reward are met. The input is the newly posted comment or photo, and the output is the coupon information sent to the user's device. In this step, the content of the post is evaluated and a reward is issued.

[1583] Step 5:

[1584] WiFi devices and sensors installed in physical stores periodically send current congestion status to a server. The input is the congestion information of the physical store, and the output is analyzed real-time congestion status data. The server analyzes this information and notifies the user.

[1585] Step 6:

[1586] When a user approaches a specific product shelf in a physical store using smart glasses or a smartphone, related past comments and reviews are displayed on the device. The input is the user's current location information and a product database, and the output is product information and reviews displayed on the device. Specifically, the server obtains relevant data based on the user's location information and sends it to the device in real time.

[1587] Step 7:

[1588] When a user behaves in a way that meets the conditions for a reward, the server checks the conditions and issues a coupon or discount. The input is the user's behavioral data and the conditions for the reward, and the output is the coupon or discount data. The server uses an algorithm to check the behavioral data and issues a reward if the conditions are met. In this step, the process of providing incentives to the user is executed.

[1589] 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.

[1590] The system of the present invention includes the following components to enable users to easily and specifically search for restaurants.

[1591] 1. Collecting comments and photos

[1592] Users use the app to input and take comments and photos about restaurants. The device then sends these posts to the server, which then stores the received comments and photos in a database. This process creates a system in which user experiences are accumulated as information.

[1593] 2. Data Analysis and Classification

[1594] The server periodically scans the comments and photos stored in the database to extract new data. The server then analyzes the data using an artificial intelligence model and assigns categories and tags based on the user's preferences. This analysis process extracts characteristics such as ingredients, atmosphere, and price range. The analysis results are reflected in the user's profile and used for future recommendations.

[1595] 3. Recommended Suggestions

[1596] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preferred characteristics to the server. Based on the received information, the server lists the most suitable restaurants from its database. This makes it possible to make personalized recommendations based on the user's current location and preferences. The restaurant information listed by the server is sent to the device and displayed to the user.

[1597] 4. Posting comments and offering rewards

[1598] When a user posts a new comment or photo about a restaurant, the server records that action. If the reward conditions are met, the server issues a coupon or discount. This coupon information is sent to the terminal and notified to the user, allowing the user to use the reward for their next meal.

[1599] 5. Real-time congestion information

[1600] The restaurant's terminals and Wi-Fi devices periodically send their current occupancy status to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when choosing a restaurant.

[1601] 6. Emotion Recognition by Emotion Engine

[1602] When analyzing comments and photos posted by users, the server also uses an emotion engine to recognize the user's emotions. This emotion data is used for more detailed analysis of user preferences and is reflected in restaurant recommendation results and the provision of special offers.

[1603] Specific examples

[1604] For example, if a user wants to eat "yakiniku" (grilled meat), they search for "yakiniku" in the app, and the device sends their current location and preference data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. At this time, it also uses an emotion engine to reference the user's emotional data and prioritizes restaurants that the user felt happy or satisfied with. The server then sends this list to the device and presents it to the user.

[1605] Furthermore, when a user visits a specific store and posts new comments or photos there, the server analyzes the posts and issues coupons. If the user expresses positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to receive a discount and increase their motivation to visit again. In addition, real-time congestion information is provided, allowing users to avoid waiting times and efficiently choose a store.

[1606] This process allows users to easily find restaurants that perfectly match their preferences and also receive rewards, resulting in a system that encourages frequent use. Furthermore, the use of an emotion engine builds more detailed user profiles, improving recommendation accuracy.

[1607] The processing flow will be explained below.

[1608] 1. Comment and photo collection

[1609] Step 1:

[1610] The user launches the app and enters or takes a photo or comments about the restaurant.

[1611] Step 2:

[1612] The device sends the comments and photo data entered by the user to the server.

[1613] Step 3:

[1614] The server stores the received comments and photo data in a database.

[1615] 2. Data Analysis and Classification

[1616] Step 4:

[1617] The server periodically scans the database for new comments and photos.

[1618] Step 5:

[1619] The server uses an artificial intelligence model to analyze the acquired data, specifically extracting characteristics such as ingredients, atmosphere, and price range from the comments.

[1620] Step 6:

[1621] Based on the analysis results, the server assigns categories and tags to each comment and photo.

[1622] Step 7:

[1623] The server reflects the analysis results in the user profile and updates the user's preference data.

[1624] 3. Recommended Suggestions

[1625] Step 8:

[1626] The user presses the "Search for recommended restaurants" button on the app.

[1627] Step 9:

[1628] The device sends the user's location information and data about the user's preferences to the server.

[1629] Step 10:

[1630] Based on the location information and preference data received by the server, the server searches the database for the most suitable restaurant.

[1631] Step 11:

[1632] The server ranks and lists the search results.

[1633] Step 12:

[1634] The server sends the listed restaurant information to the terminal.

[1635] Step 13:

[1636] The terminal displays the recommended restaurant information to the user.

[1637] 4. Posting comments and offering rewards

[1638] Step 14:

[1639] A user posts a new comment or photo.

[1640] Step 15:

[1641] The terminal transmits the posting data to the server.

[1642] Step 16:

[1643] The server analyzes the post and checks whether it meets the conditions for the reward.

[1644] Step 17:

[1645] The server issues coupons and discounts when certain conditions are met.

[1646] Step 18:

[1647] The server transmits the issued coupon information to the terminal and notifies the user.

[1648] Step 19:

[1649] The terminal displays the coupon information to the user.

[1650] 5. Real-time congestion information

[1651] Step 20:

[1652] The restaurant's terminals and WiFi devices send the store's congestion status to the server.

[1653] Step 21:

[1654] The server analyzes the congestion information received.

[1655] Step 22:

[1656] When a user requests congestion information through the app, the server sends the latest congestion information to the device.

[1657] Step 23:

[1658] The terminal displays real-time congestion status to the user.

[1659] 6. Emotion Recognition by Emotion Engine

[1660] Step 24:

[1661] The server inputs the user's posted data into an emotion engine and analyzes the user's emotions.

[1662] Step 25:

[1663] The server adds the emotion data obtained from the emotion engine to the user profile.

[1664] Step 26:

[1665] The server reflects the user's emotional data in the analysis data and reflects it as a restaurant recommendation result.

[1666] Step 27:

[1667] The server issues a coupon with a higher discount rate based on the emotion data if certain conditions are met.

[1668] Specific examples

[1669] For example, if a user wants to eat "yakiniku" (grilled meat), they can search for "yakiniku" in the app, and the device will send their current location and preference data to the server. The server will then analyze past comments and photos related to "yakiniku" and use an emotion engine to obtain the user's emotional data. The server will prioritize restaurants that the user has positive feelings about, such as being happy or satisfied, and send the list to the device to present to the user.

[1670] Next, when a user visits a specific store and posts new comments or photos, the server analyzes the posts and issues coupons. If the user expresses positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to receive a discount and increase their motivation to visit again. In addition, real-time congestion information is provided, allowing users to avoid waiting times and choose a store efficiently.

[1671] This process allows users to easily find restaurants that perfectly match their preferences and also receive rewards, resulting in a system that encourages frequent use. Furthermore, the use of an emotion engine builds more detailed user profiles, improving recommendation accuracy.

[1672] Example 2

[1673] 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."

[1674] Today's consumers desire diverse dining experiences and want to efficiently find restaurants that suit their preferences. Information reflecting the user's emotions and the actual congestion status of restaurants visited are also important factors in their decision-making. However, conventional systems struggle to provide recommendations that take into account the user's detailed preferences and emotions, and they do not adequately provide real-time congestion status or special offers. Furthermore, they lack the functionality to quickly suggest restaurants that match the user's preferences using the user's location information. This has made it difficult for users to efficiently find restaurants that suit their preferences.

[1675] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving comments and photos posted by users and storing the data in a database, means for analyzing the stored comments and photos using an artificial intelligence model and classifying and tagging them based on the user's preferences, means for suggesting recommended nearby facilities based on the user's location information based on the analyzed data, means for providing rewards for posts made by users when the users post comments and photos, means for collecting information on facility congestion status in real time and providing the information to the users, and means for analyzing user posts and using an emotion engine that recognizes emotions. This improves convenience by allowing users to easily find recommended restaurants that suit their preferences, understand congestion status in real time, and receive rewards for posting.

[1676] "User" refers to an individual who uses the system to post comments and photos, search for restaurants, receive recommendations, and receive special offers.

[1677] "Comments" refer to posted data in which users express their impressions and opinions about restaurants in writing.

[1678] "Photos" refer to image data of restaurants and food taken by users.

[1679] "Database" refers to an information management system that allows the server to store user posted data and analysis results.

[1680] "Artificial intelligence model" refers to technology that uses machine learning algorithms to analyze and classify data.

[1681] "Preferences" refers to personal preferences such as the ingredients, cuisine, atmosphere, and price range that the user prefers.

[1682] "Classification and tagging" refers to the process by which an artificial intelligence model analyzes data and assigns it specific categories or attributes.

[1683] "Location Information" refers to data that indicates a user's current geographic location.

[1684] "Facility" refers to a service providing location that a user visits, including a restaurant.

[1685] "Benefits" refers to rewards such as coupons and discounts that users receive when they post comments or photos.

[1686] "Crowd situation" refers to information showing the current number of customers at a restaurant and waiting times.

[1687] "Real-time" refers to information being updated or provided almost instantly.

[1688] "Emotion engine" refers to technology that analyzes and recognizes emotions from user posted data.

[1689] The system of the present invention includes the following components to enable users to easily and specifically search for restaurants.

[1690] First, users must install an application on their device to post comments and photos. Using this application, users can input and take photos of the food and their impressions after eating. The device used for this is a smartphone, tablet, or other device with an internet connection.

[1691] The device then sends the comments and photos entered or taken by the user to a server, which then receives the posted data and stores it in a database, such as a cloud-based data storage system (the general term used here is "database management system").

[1692] The server then periodically scans the database to extract newly stored data. The extracted data is analyzed using an artificial intelligence model (e.g., a machine learning algorithm like TensorFlow or PyTorch). Based on the analysis results, comments and photos are assigned specific categories and tags (e.g., ingredients, atmosphere, price range). These analysis results are reflected in the user profile and used for future recommendations.

[1693] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and profile data to the server. The server uses this information to create a list of the most suitable restaurants from a database. This process may involve the use of a search engine such as Elasticsearch. The listed restaurant information is then sent to the device and displayed to the user.

[1694] Furthermore, when a user posts a new comment or photo, the post is sent again to the server and stored in the database. The server analyzes the posted data and issues coupons or discounts if the conditions are met. This special offer information is sent to the device and notified to the user. The server uses, for example, a REST API or push notification service to provide these special offers.

[1695] In addition, restaurant terminals and Wi-Fi devices periodically send occupancy data to a server. The server analyzes this data and provides it to users in real time. This analysis is sometimes performed using a real-time analysis engine (e.g., Apache Kafka).

[1696] The emotion engine also runs on the server, analyzing user posted data to recognize emotions. The recognized emotion data is used for more detailed preference analysis and is reflected in recommendation results and reward offers.

[1697] Examples and prompts

[1698] As a concrete example, if a user wants to eat "yakiniku," the following steps are executed: The user searches for "yakiniku" in the app, and the device sends its current location and profile data to the server. The server analyzes past comments and photos related to "yakiniku" and creates a list of recommended nearby restaurants. At this time, it also uses an emotion engine to prioritize the list of restaurants for which the user expressed positive emotions (such as joy or satisfaction). The server then sends this list to the device and presents it to the user.

[1699] Furthermore, when a user visits a specific restaurant and posts new comments or photos, the server analyzes the posts and issues coupons. If the user shows positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to use the rewards for their next meal, increasing frequency of use. In addition, real-time congestion information is provided, allowing users to avoid waiting times and efficiently choose a restaurant.

[1700] Prompt Sentence Examples

[1701] "If I want to eat yakiniku, how do I search for restaurants? Also, what kind of benefits do I get for posting comments and photos?"

[1702] Through this process, the present invention realizes a system that allows users to easily find restaurants that suit their preferences and also receive rewards, which increases the frequency of use. In addition, the use of an emotion engine will build more detailed user profiles, improving recommendation accuracy.

[1703] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1704] Step 1:

[1705] The user launches the app, enters comments about the restaurant, and takes a photo if necessary.

[1706] Input: User comments and photos

[1707] Specific operation: The user enters a comment in the text field and takes a photo using the camera function. The device temporarily stores this data in memory.

[1708] Step 2:

[1709] The terminal transmits comments and photos entered or taken by the user to the server.

[1710] Input: User comments and photos (output of step 1)

[1711] Output: Notification that transmission to the server was successful

[1712] How it works: The device generates an HTTP POST request to the server over the Internet, attaches the user's comments and photos, and sends them. If the transmission is successful, the device receives a confirmation response from the server.

[1713] Step 3:

[1714] The server stores the received comments and photos in a database.

[1715] Input: Comments and photos sent from the device (output of Step 2)

[1716] Output: Data ID stored in the database or notification of successful storage

[1717] Specific operation: The server stores the received data in the target database management system. If the storage is successful, it generates an ID for the stored data and notifies the terminal or internal process.

[1718] Step 4:

[1719] The server periodically scans the database and extracts new data.

[1720] Input: All data stored in the database

[1721] Output: A list of the new data

[1722] Specific operation: The server sets up a scheduled job to periodically query the database to extract and list new data.

[1723] Step 5:

[1724] The server inputs the extracted data into an artificial intelligence model for analysis.

[1725] Input: List of new data (output of Step 4)

[1726] Output: Analysis results (categories, tags, sentiment analysis results, etc.)

[1727] How it works: The server analyzes new data using artificial intelligence models (e.g., TensorFlow, PyTorch). The analysis uses text and image analysis algorithms to extract attributes such as ingredients, atmosphere, price range, and sentiment.

[1728] Step 6:

[1729] The server assigns categories and tags to the data based on the analysis results.

[1730] Input: Analysis results (output from Step 5)

[1731] Output: Classified and tagged data

[1732] Specific operation: The server assigns categories and tags (e.g., yakiniku, relaxed atmosphere, high price range, etc.) to the analyzed data and stores it in a database.

[1733] Step 7:

[1734] When a user presses the "Search for recommended restaurants" button, the device sends the user's location information and preference data to the server.

[1735] Input: User location and preference data

[1736] Output: Notification that transmission to the server was successful

[1737] Specific operation: The device uses the GPS function to obtain its current location and transmits it along with the user profile data to the server. If the transmission is successful, the device receives a confirmation response.

[1738] Step 8:

[1739] The server creates a list of the most suitable restaurants based on the user's location information and preference data.

[1740] Input: User location and preference data (output of step 7)

[1741] Output: List of restaurants

[1742] What it does: The server uses a search engine like Elasticsearch to query the database and return a list of restaurants that fit the criteria, taking into account analytics results and data from the user profile.

[1743] Step 9:

[1744] The server sends the listed restaurant information to the terminal and displays it to the user.

[1745] Input: List of restaurants (output of Step 8)

[1746] Output: List of restaurants sent to the terminal

[1747] Specific operation: The server encodes the listed information in JSON format and sends it to the device as an HTTP response. The device receives this and displays it as a list on the app screen.

[1748] Step 10:

[1749] When a user posts new comments or photos, the device sends them back to the server and stores them in the database.

[1750] Input: New comment and new photo for the user

[1751] Output: Notification of successful transmission to the server and notification of completion of database storage

[1752] Specific operation: Similar to steps 1 to 3, the terminal sends new data to the server, and the server stores it in the database.

[1753] Step 11:

[1754] The server analyzes new posts and issues coupons or discounts if the conditions are met.

[1755] Input: New comment and new photo (input from step 10)

[1756] Output: Issued benefits (coupons and discounts) information

[1757] Specific operation: The server analyzes the new data and generates coupons and discounts for posts that meet the conditions. The generated reward information is sent to the terminal and notified to the user.

[1758] Step 12:

[1759] The restaurant's terminal or Wi-Fi device sends the current congestion status to the server.

[1760] Input: Restaurant congestion data

[1761] Output: Notification of successful transmission to the server

[1762] Specific operation: Restaurant terminals and Wi-Fi devices periodically send congestion status data such as the number of connections and bandwidth usage to the server. The server receives this data and returns an acknowledgement.

[1763] Step 13:

[1764] The server analyzes the congestion data and provides it to users in real time.

[1765] Input: Restaurant congestion data (output of Step 12)

[1766] Output: Real-time provision of analyzed congestion information

[1767] Specific operation: The server uses a real-time analysis engine (e.g., Apache Kafka) to analyze the congestion data and provide the analysis results to the user in real time.

[1768] Step 14:

[1769] The server analyzes the user's posted data using an emotion engine to recognize emotions.

[1770] Input: User comments and photos

[1771] Output: User emotion data

[1772] Specific operation: The server inputs the posted data (text and images) into the emotion engine, and recognizes the user's emotions through natural language processing and image analysis. The output emotion data is saved in the user profile.

[1773] Step 15:

[1774] The server uses the emotional data to make recommendations and provide rewards.

[1775] Input: User emotion data

[1776] Output: Improved recommendations and rewards information

[1777] Specific operation: The server reflects the emotional data in the user profile and uses it to improve the accuracy of the next restaurant recommendation and reward offer, thereby providing services that are more suited to the user's preferences.

[1778] (Application example 2)

[1779] 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."

[1780] In food delivery services, it is not easy for users to efficiently search and select restaurants that suit their preferences. In particular, there is a demand for personalized recommendations that take into account a variety of information, such as users' past ratings and real-time congestion status. It is also important to properly analyze comments and photos posted by users and provide rewards based on them, but there is no centralized system for this.

[1781] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving comments and photos posted by users and storing the data in a database, means for analyzing the stored comments and photos using an artificial intelligence model and classifying and tagging them based on the user's preferences, means for suggesting recommended nearby restaurants based on the user's location information based on the analyzed data, means for providing rewards for comments and photos posted by users, means for collecting restaurant congestion information in real time and providing the information to the user, means for understanding the comments and photos stored in the database using TF-IDF-based analysis and calculating similarity, and means for listing and providing food delivery services that best suit the user's preferences based on the similarity analysis. This allows users to easily find restaurants and food delivery services that best suit their preferences and also enjoy rewards.

[1782] "User" refers to an individual user who uses the system to search for restaurants, rate them, and post comments and photos.

[1783] "Comments" refer to text-based evaluations and opinions posted by users about restaurants.

[1784] "Photos" refer to image data that users take of restaurants and food and post.

[1785] "Database" refers to a storage system managed on a server for storing comments and photos collected from users.

[1786] "Artificial intelligence model" refers to a program that uses machine learning technology to analyze user comments and photos and categorize and tag them based on preferences.

[1787] "Preferences" refers to a user's likes, dislikes, and interests, and includes factors such as ingredients, atmosphere, and price range.

[1788] "Classification" refers to the process of sorting analyzed data into specific categories.

[1789] "Tagging" refers to the process of assigning appropriate labels to analyzed data.

[1790] "Location information" refers to geographical data about a user's current location.

[1791] "Suggestion" refers to the act of recommending restaurants suitable for the user based on the analysis results.

[1792] "Benefits" refer to rewards such as coupons and discount vouchers that are beneficial to users.

[1793] "Crowd situation" refers to information such as the current number of customers at a restaurant and waiting times.

[1794] "Real-time" refers to providing nearly instantaneous, up-to-date information.

[1795] "TF-IDF-based analysis" refers to the process of analyzing data using a technique that calculates significant words in a sentence.

[1796] "Similarity" refers to an index that calculates how similar different comments or photos are.

[1797] "Food delivery service" refers to a service that delivers meals ordered online by users to their homes or designated locations.

[1798] The system of this invention provides a series of processes that enable users to efficiently search for and select restaurants and food delivery services that suit their preferences. The system is composed of the following components and processes.

[1799] 1. Collecting comments and photos

[1800] Users use devices such as smartphones and tablets to input and take photos and comments about restaurants, and then send them to the server. A mobile application is installed on the user's device as an interface. Through this application, users can easily input comments and upload photos. The server receives these posts and stores them in a database.

[1801] 2. Data Analysis and Classification

[1802] The server periodically analyzes the comments and photos stored in the database using an artificial intelligence model. Specifically, it uses TF-IDF-based analysis to extract important words in sentences and calculate similarity. This data analysis then categorizes and tags each post based on the user's preferences. For example, categories such as ingredients, atmosphere, and price range are generated.

[1803] 3. Recommended Suggestions

[1804] When a user presses the "Search for recommended food delivery services" button, the device sends the user's location information and previous preference data to the server. Based on the received information, the server selects the most suitable food delivery services from its database. The server provides the list to the user, taking into account real-time congestion and available delivery times.

[1805] 4. Posting comments and offering rewards

[1806] When a user posts a new comment or photo about a food delivery service or restaurant, the server records the action. If the conditions for the reward are met, the server issues a coupon or discount and notifies the user's device.

[1807] 5. Real-time congestion information

[1808] The terminals and installed devices of the food delivery service periodically send information about current congestion and available delivery times to the server. The server analyzes this information and provides it to the user in real time. This information is an important indicator when users choose a food delivery service.

[1809] Specific examples

[1810] For example, if a user wants to eat "sushi," they search for "sushi" in the app, and their location information and preference data are sent to the server. The server then analyzes past comments and photos related to "sushi" and lists recommended food delivery services in the vicinity. It also uses an emotion engine to prioritize restaurants and services that the user has positive feelings about, such as being happy or satisfied with. The server then sends this list to the user's device and presents it to the user.

[1811] Furthermore, when a user uses a specific food delivery service and posts new comments or photos, the server analyzes the posts and issues coupons. If the user expresses positive emotions, the server can provide a coupon with a higher discount rate. This allows the user to receive a discount and increase their motivation to use the service again. Real-time congestion information is also provided, allowing users to avoid waiting times and use the service efficiently.

[1812] Prompt Sentence Examples

[1813] "Can you recommend any restaurants near my location that serve good sushi? Also, can you show me any coupons or special offers I can use?"

[1814] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1815] Step 1:

[1816] Users use a smartphone or tablet application to input and take comments and photos about restaurants. The input comments (text data) and photos (image data) are collected as data. This data is saved on the device via an interface and sent to a server. Input is performed manually by the user, and output is the transfer of data to the server.

[1817] Step 2:

[1818] The server receives comments and photos sent from the devices and stores them in a database. This database serves as a repository of information to be used for future data analysis and searches. The input is the comments and photos received from the devices, and the output is storage in the database. The stored data is used in subsequent analysis processes.

[1819] Step 3:

[1820] The server periodically scans the comments and photos stored in the database and extracts the latest data. The extracted data is then analyzed using an artificial intelligence model. Specifically, TF-IDF-based analysis is used to extract important words in the text and calculate their similarity. The input is the extracted comments and photos, and the output is classified and tagged data as the analysis results.

[1821] Step 4:

[1822] The server updates the user profile based on the analyzed data. The updated profile is classified into categories such as ingredients, atmosphere, and price range. This profile will be used in a future recommendation system. The input is the analysis results, and the output is the updated user profile.

[1823] Step 5:

[1824] When a user presses the "Search for recommended food delivery services" button in the application, the device sends its current location and past preference data to the server. Location information is obtained via GPS, and preference data is extracted from the user profile. The input is location information and preference data, and the output is a request sent to the server.

[1825] Step 6:

[1826] The server uses the received location information and preference data to create a list of optimal food delivery services from a database. The list also takes into account real-time congestion and available delivery times. The listed services are generated as an analysis result and provided to the user. The input is location information and preference data, and the output is the listed service information.

[1827] Step 7:

[1828] The server checks the analysis results and the conditions for the rewards, and issues a coupon or discount if the user meets the conditions. The issued reward information is sent to the terminal and notified to the user. The input is the reward conditions and the analysis results, and the output is the coupon or discount information.

[1829] Step 8:

[1830] Users use the provided food delivery service and post new comments and photos about the service. These posts are also sent to the server, stored in a database, and analyzed. This allows new feedback to be continuously collected, contributing to improving the accuracy of the system. The input is newly posted data, and the output is data transfer and storage to the server.

[1831] Step 9:

[1832] Users can check the congestion status provided in real time and efficiently select a food delivery service. This information is collected from the restaurant's terminal or installed device, analyzed by the server, and then provided to the user. The input is data from the restaurant, and the output is real-time congestion status information.

[1833] This series of processing steps allows users to easily find restaurants and food delivery services that suit their preferences and also enjoy special offers.

[1834] 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.

[1835] 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.

[1836] 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.

[1837] 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.

[1838] 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.

[1839] 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.

[1840] 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).

[1841] 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, motorcycles, and other devices, 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.

[1842] 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."

[1843] 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.

[1844] 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).

[1845] 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.

[1846] 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.

[1847] 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.

[1848] 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.

[1849] 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.

[1850] 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.

[1851] 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.

[1852] 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.

[1853] 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.

[1854] 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.

[1855] The following is further disclosed regarding the above embodiment.

[1856] (Claim 1)

[1857] A means for receiving comments and photos posted by users and storing such data in a database;

[1858] A means for analyzing stored comments and photos using an artificial intelligence model and categorizing and tagging them based on user preferences;

[1859] Based on the analyzed data, a method is provided to suggest nearby restaurants based on the user's location information.

[1860] A means to provide rewards for posts when users post comments or photos;

[1861] A means for collecting information on the congestion status of restaurants in real time and providing it to users;

[1862] A system including:

[1863] (Claim 2)

[1864] 10. The system of claim 1, further comprising means for extracting characteristics such as ingredients, atmosphere, and price range when categorizing and tagging based on user preferences.

[1865] (Claim 3)

[1866] 10. The system of claim 1, further comprising means for issuing a coupon or discount when a user meets a reward condition.

[1867] "Example 1"

[1868] (Claim 1)

[1869] A means for receiving comments and photos posted by users and storing such data in a database;

[1870] A means for analyzing stored comments and photos using an artificial intelligence model and categorizing and tagging them based on user preferences;

[1871] Based on the analyzed data, a method is provided to suggest nearby restaurants based on the user's location information.

[1872] A means to provide rewards for posts when users post comments or photos;

[1873] a means for receiving the congestion status data transmitted by a communication terminal or a wireless communication device of the restaurant and providing the data to a user in real time;

[1874] A system including:

[1875] (Claim 2)

[1876] 10. The system of claim 1, further comprising means for extracting characteristics such as ingredients, atmosphere, and price range when categorizing and tagging based on user preferences.

[1877] (Claim 3)

[1878] 10. The system of claim 1, further comprising means for issuing a coupon or discount when a user meets a reward condition.

[1879] "Application Example 1"

[1880] (Claim 1)

[1881] A means for receiving comments and photos posted by users and storing such data in a database;

[1882] A means for analyzing stored comments and photos using an artificial intelligence model and categorizing and tagging them based on user preferences;

[1883] Based on the analyzed data, the system will suggest nearby restaurants and products based on the user's location information.

[1884] A means to provide rewards for posts when users post comments or photos;

[1885] A means for collecting information on the congestion status of a physical store in real time and providing it to users;

[1886] A means for functioning as an application installed on a smartphone, smart glasses, or robot;

[1887] A system including:

[1888] (Claim 2)

[1889] 10. The system of claim 1, further comprising means for extracting characteristics such as products, services, price ranges, etc., when categorizing and tagging based on user preferences.

[1890] (Claim 3)

[1891] 10. The system of claim 1, further comprising means for issuing discounts or coupons when a user meets reward conditions.

[1892] "Example 2: Combining Emotion Engines"

[1893] (Claim 1)

[1894] A means for receiving comments and photos posted by users and storing such data in a database;

[1895] A means for analyzing stored comments and photos using an artificial intelligence model and categorizing and tagging them based on user preferences;

[1896] Based on the analyzed data, a method is provided to suggest nearby recommended facilities based on the user's location information.

[1897] A means to provide rewards for posts when users post comments or photos;

[1898] A means for collecting the congestion status of facilities in real time and providing it to users;

[1899] a means for analyzing user posts and using an emotion engine to recognize emotions;

[1900] A system including:

[1901] (Claim 2)

[1902] 10. The system of claim 1, further comprising means for extracting characteristics such as elements, atmosphere, price range, etc., when classifying and tagging based on user preferences.

[1903] (Claim 3)

[1904] 10. The system of claim 1, further comprising means for issuing a co...

Claims

1. A means for receiving comments and photos posted by users and storing such data in a database; A means for analyzing the stored comments and photos using an artificial intelligence model and categorizing and tagging them based on the user's preferences; Based on the analyzed data, a method is provided to suggest nearby restaurants based on the user's location information. A means to provide rewards for posts when users post comments or photos; A means for collecting information on the congestion status of restaurants in real time and providing it to users; A system including:

2. The system according to claim 1, further comprising means for extracting characteristics such as ingredients, atmosphere, and price range when classifying and tagging based on user preferences.

3. The system of claim 1 further comprising means for issuing a coupon or discount when a user meets a reward condition.

Images