System

Abstract

A system is provided.SOLUTION: A system comprising: means for converting a user's voice input to text; means for transmitting the converted text data; means for parsing the received text data; means for obtaining user profile data; means for obtaining user location and environmental data; means for generating suggestions based on the parsed data and the obtained profile and environmental data; means for transmitting the generated suggestions; means for displaying the transmitted suggestions; and means for receiving user feedback and updating the profile data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, people lead busy lives. They need fast and appropriate advice in a variety of situations, including shopping, choosing meals, romance, work, and friendships. However, conventional systems have struggled to fully understand individual users' preferences and lifestyles and provide accurate advice. This has resulted in users wasting a lot of time and effort, resulting in a decline in their quality of life. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides a system including means for converting a user's voice input into text, means for transmitting the converted text data, means for analyzing the received text data, means for acquiring user profile data, means for acquiring user location information and environmental data, means for generating suggestions based on the analyzed data and the acquired profile data and environmental data, means for transmitting the generated suggestions, means for displaying the transmitted suggestions, and means for receiving user feedback and updating the profile data, thereby enabling users to quickly receive individually optimized advice for all aspects of their daily lives and improving their quality of life.

[0006] "User" refers to an individual who uses the System.

[0007] "Voice input" refers to the act of a user giving instructions or asking questions to a system by voice.

[0008] "Convert to text" refers to the process of converting voice input into text information.

[0009] "Text data" refers to data in which voice is converted into text information.

[0010] "Transmitting" refers to the act of sending data from one system to another.

[0011] "Server" refers to the computer system that analyzes the received data, obtains profile data, and generates recommendations.

[0012] "Analyzing" refers to the process of understanding received data and extracting its meaning and intent.

[0013] "Profile data" refers to data that accumulates information such as a user's preferences, past behavior, and characteristics.

[0014] "Location Information" refers to geographic information about a user's current location.

[0015] "Environmental data" refers to information about the user's surroundings, such as the weather and time of day.

[0016] "Suggestion" refers to the recommendations or advice the system provides to the user.

[0017] "Generate" refers to creating new information based on analyzed data.

[0018] "Display" means to present suggestions or information to the user visually or audibly.

[0019] "Feedback" refers to the evaluations and opinions that users provide to the system.

[0020] "Updating" refers to replacing existing data or information with new data or information. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] This invention relates to a system that learns a user's personal information and provides various daily advice based on that information. This system consists of three main components: a server, a terminal, and the user.

[0043] System Overview

[0044] Users use voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. User feedback allows the system to further improve its accuracy.

[0045] Program processing

[0046] The system operates sequentially as follows:

[0047] User registration and initial data entry

[0048] When a user first uses the system, they register and enter a self-introduction and basic information. This information is sent to the server by the device and stored in a database as profile data.

[0049] Continuous data collection and analysis

[0050] In everyday life, users ask questions or make requests to the system. For example, they might say, "What should I eat today?" The device converts this speech into text data and sends it to the server. The server then uses a natural language processing (NLP) engine to analyze this text data and understand the user's intent.

[0051] Next, the server retrieves the user's profile data from the database, including the user's past behavioral history, preferences, allergy information, etc. Additionally, the server retrieves the user's current location, weather information, and other environmental data.

[0052] Proposal generation and presentation

[0053] The server uses AI models based on this data to generate optimal suggestions. For example, if a user wants a low-calorie meal, the server searches for appropriate restaurants and generates a suggestion such as, "We recommend a nearby low-calorie restaurant called 'Healthy Dinner.'" This suggestion is then displayed to the user via their device.

[0054] Feedback and Learning

[0055] The user provides feedback on the suggestions to the system. For example, they might input feedback like, "I tried this restaurant and it was great." The device then sends this feedback to the server, which analyzes it and updates the user's profile data. Through this process, the system gains a more accurate understanding of the user's preferences and tendencies, improving the accuracy of future suggestions.

[0056] Specific examples

[0057] Example 1: Restaurant suggestions

[0058] 1. The user utters, "What should I eat today?"

[0059] 2. The device converts the speech into text and sends it to the server.

[0060] 3. The server analyzes the question and searches for suitable restaurants based on the user's profile data and location.

[0061] 4. The server sends the generated proposal to the device, which displays it to the user.

[0062] Example 2: Fashion advice

[0063] 1. The user types into the system, "Please give me some advice on what to wear today."

[0064] 2. The device sends this input to the server.

[0065] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information.

[0066] 4. The server sends the generated proposal to the device, which notifies the user.

[0067] As described above, the system of the present invention can provide accurate advice to the user in various situations throughout his or her life, thereby improving the quality of the user's life.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] The user voice-inputs, "What should I eat today?"

[0071] Step 2:

[0072] The device converts voice input into text data in real time.

[0073] Step 3:

[0074] The terminal sends the converted text data to the server along with the user ID.

[0075] Step 4:

[0076] The text data received by the server is analyzed using a natural language processing (NLP) engine.

[0077] Specifically, it extracts the user's intent from text data and understands that the user is looking for suggestions on what to eat today.

[0078] Step 5:

[0079] The server retrieves the user's profile data (past dietary history, preferences, allergy information, etc.) from the database.

[0080] Step 6:

[0081] The server retrieves current location and environmental data (weather, time, etc.) from an external API.

[0082] Step 7:

[0083] The server uses AI models to generate restaurant suggestions based on the parsed data, retrieved profile data, and environmental data.

[0084] Specifically, the system searches for restaurants that meet certain criteria, such as "close to the user's location" and "have low-calorie menu items."

[0085] Step 8:

[0086] The server generates a list of restaurant suggestions that are optimized based on the user's profile data and past feedback.

[0087] Specifically, highly rated restaurants and restaurants that users have previously liked will be placed at the top of the list.

[0088] Step 9:

[0089] The server sends optimized restaurant suggestions in JSON format to the device.

[0090] Step 10:

[0091] The device displays the received proposal data to the user.

[0092] Specifically, the screen will display, "We recommend a nearby low-calorie restaurant called 'Healthy Dinner'."

[0093] Step 11:

[0094] The user enters feedback on the suggestion (e.g., "I tried this restaurant and it was great").

[0095] Step 12:

[0096] The device sends the user's feedback to the server.

[0097] Step 13:

[0098] The server analyzes the received feedback and updates the user's profile data.

[0099] Specifically, it will set the restaurant's rating to "good" and prioritize similar restaurants in future suggestions.

[0100] By repeating this series of steps, the system learns the user's preferences and lifestyle habits and can make more appropriate and personalized suggestions.

[0101] Example 1

[0102] 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."

[0103] Conventional technologies generally provide suggestions and advice to users, but have the problem of not being able to fully address the individual needs and preferences of each user. In particular, there is a need for a system that can efficiently and accurately process users' voice input and, based on the results, generate optimal suggestions that reflect the user's profile data and environmental data.

[0104] 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.

[0105] In this invention, the server includes means for converting a user's voice input into text data, means for transmitting the converted text data, means for analyzing the received text data, means for acquiring user profile data, means for acquiring user location data and environmental data, means for generating suggestions using a generative AI model based on the analyzed text data and the acquired profile data and environmental data, means for transmitting the generated suggestions, means for displaying the transmitted suggestions, and means for receiving user feedback and updating the profile data, thereby enabling accurate suggestions to be made in accordance with each user's individual needs and preferences.

[0106] A "user" is someone who uses the system to provide voice input and receive suggestions and advice.

[0107] "Voice input" refers to the act of a user asking a question or making a request to a system by voice.

[0108] "Text data" is character information converted from voice input.

[0109] "Means for converting" refers to the technology or algorithm used to convert voice input into text data.

[0110] "Transmission means" refers to the communication technology or protocol used to transmit text data to the server.

[0111] The "receiving means" is a means by which the server receives text data sent from the terminal.

[0112] "Means of analysis" refers to the technology and algorithms used to understand the received text data and grasp the user's intent.

[0113] "Profile data" refers to individual data such as a user's basic information, past behavioral history, preferences, and allergy information.

[0114] "Means of acquisition" refers to the technology or protocol used to acquire the required data from a database or external system.

[0115] "Environmental data" refers to data about the user's environment, such as the user's current location and weather information.

[0116] A "generative AI model" is an artificial intelligence model that generates optimal suggestions based on user data.

[0117] The "means for generating suggestions" is a generative AI model that runs on the basis of the analyzed text data and the acquired profile and environmental data.

[0118] "Displaying means" refers to the techniques or methods for presenting the generated suggestions to the user.

[0119] "Feedback" refers to the evaluation or opinion that a user gives to the system after receiving a suggestion.

[0120] "Means for receiving feedback" refers to the means for collecting feedback from users.

[0121] An "updating means" is a technique or algorithm for correcting or adding to profile data based on feedback received.

[0122] This invention relates to a system that learns a user's personal information and provides various daily advice using a generative AI model. This system consists of three main components: a server, a terminal, and the user.

[0123] System Overview

[0124] Users use voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. User feedback allows the system to further improve its accuracy.

[0125] Hardware and Software Configuration

[0126] This system uses the following hardware and software:

[0127] 1. Device:

[0128] Smartphone (iOS, Android)

[0129] Smart speakers (voice assistant devices for the general home)

[0130] 2. Server:

[0131] Cloud services (AWS, Azure, Google Cloud)

[0132] 3. Natural Language Processing (NLP) Engine:

[0133] OpenAI GPT

[0134] Google NLP API

[0135] 4. Database:

[0136] MySQL

[0137] PostgreSQL

[0138] What the program does

[0139] This system performs the following processes sequentially.

[0140] User registration and initial data entry

[0141] When a user first uses the system, they register and enter a self-introduction and basic information. The device sends this input data to the server, which then stores it in a database. For example, a user might install an app and enter their name, age, gender, allergy information, etc.

[0142] Voice to text conversion

[0143] The user can ask a question or make a request by voice. For example, they can say, "What should I eat today?" The device converts the voice into text using voice recognition technology such as the Google Speech-to-Text API and sends this text data to the server.

[0144] Text analysis and suggestion generation

[0145] The server uses an NLP engine such as OpenAI GPT to analyze the received text data. Based on the analysis results, the user's profile data and environmental data (such as current location and weather information) are retrieved from a database, and based on this, a generative AI model is used to generate optimal suggestions. An example of a prompt sentence is, "I'm looking for a low-calorie meal. Can you recommend any restaurants?"

[0146] Submitting suggestions and providing feedback

[0147] The generated suggestions are sent from the server to the device and displayed to the user through the device. For example, a suggestion such as "We recommend a nearby low-calorie restaurant for a healthy dinner" may be displayed. The user enters feedback on the suggestions, and the device sends the feedback to the server. The server analyzes the feedback and updates the user's profile data. This feedback improves the accuracy of future suggestions.

[0148] Specific examples

[0149] Specific examples of how this system can be used include:

[0150] Example 1: Restaurant suggestions

[0151] 1. The user utters, "What should I eat today?"

[0152] 2. The device converts the speech into text and sends it to the server.

[0153] 3. The server analyzes the question and searches for appropriate restaurants based on the user's profile data and location, using a generative AI model to generate a suggestion such as "Recommend a nearby low-calorie restaurant for a healthy dinner."

[0154] 4. The server sends the generated proposal to the device, which displays it to the user.

[0155] Example 2: Fashion advice

[0156] 1. The user types into the system, "Please give me some advice on what to wear today."

[0157] 2. The device sends this input to the server.

[0158] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information, for example, "It's raining today, so I recommend a raincoat and waterproof shoes."

[0159] 4. The server sends the generated proposal to the device, which notifies the user.

[0160] As described above, the system of the present invention provides accurate advice that corresponds to the individual needs and environment of the user, thereby improving the quality of life of the user.

[0161] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0162] Step 1:

[0163] When a user first uses the system, they register and enter basic information. The user then installs the app and enters their name, age, gender, allergy information, etc.

[0164] Input: User's basic information (name, age, gender, allergy information, etc.)

[0165] Data processing / calculation: Basic information entered is collected

[0166] Output: Basic information dataset

[0167] Step 2:

[0168] The device sends the user's basic information to the server. The device sends the basic information dataset to the server using an HTTP request.

[0169] Input: User basic information dataset

[0170] Data processing / calculation: Convert basic information dataset into HTTP request

[0171] Output: Send request

[0172] Step 3:

[0173] The server receives the basic information and stores it in a database. The server receives the basic information dataset and stores it in a database (MySQL or PostgreSQL).

[0174] Input: Basic information dataset

[0175] Data processing / calculation: Inserting basic information datasets into the database

[0176] Output: Basic information stored in the database

[0177] Step 4:

[0178] The user asks a question or makes a request by voice, for example, "What should I eat today?"

[0179] Input: User voice input

[0180] Data processing / calculation: Collection of voice data

[0181] Output: Audio data

[0182] Step 5:

[0183] The device converts the voice input into text data. The device converts the voice data into text data using speech recognition technology such as the Google Speech-to-Text API.

[0184] Input: Audio data

[0185] Data processing / calculation: Converting voice data into text data

[0186] Output: Text data

[0187] Step 6:

[0188] The device sends text data to the server. The device sends text data to the server using an HTTP request.

[0189] Input: Text data

[0190] Data processing / calculation: Convert text data into a transmission request

[0191] Output: Send request

[0192] Step 7:

[0193] The server analyzes the received text data. The server uses an NLP engine such as OpenAI GPT to analyze the text data and understand the user's intent.

[0194] Input: Text data

[0195] Data processing / calculation: Text analysis using NLP engines

[0196] Output: Analysis results

[0197] Step 8:

[0198] The server retrieves the user's profile data and environmental data. The server retrieves the user's profile data (past behavioral history, preferences, allergy information, etc.) from the database, and collects environmental data using GPS data and weather information APIs.

[0199] Input: Analysis results

[0200] Data manipulation / computation: database queries and API requests

[0201] Output: Profile data and environment data

[0202] Step 9:

[0203] The server generates suggestions using a generative AI model. Based on the analysis results and the acquired profile and environmental data, the server inputs prompt statements into the generative AI model to generate optimal suggestions.

[0204] Input: Analysis results, profile data, environmental data

[0205] Data processing / calculation: Proposal generation using generative AI models

[0206] Output: Proposal

[0207] Step 10:

[0208] The server sends the generated proposal to the device using an HTTP request.

[0209] Input: Proposal

[0210] Data processing / calculation: Converting proposals into submission requests

[0211] Output: Send request

[0212] Step 11:

[0213] Display suggestions received by the device to the user, using notifications and / or in-app displays to inform the user about the suggestions.

[0214] Input: Proposal

[0215] Data processing / calculation: Displaying proposals in the user interface

[0216] Output: User notification

[0217] Step 12:

[0218] The user enters feedback on the proposal. The user enters their evaluation and opinion on the proposal.

[0219] Input: User feedback

[0220] Data processing / calculation: Gathering feedback

[0221] Output: Feedback data

[0222] Step 13:

[0223] The device sends the feedback to the server. It uses an HTTP request to send the feedback data to the server.

[0224] Input: Feedback data

[0225] Data processing / calculation: Convert feedback data into transmission requests

[0226] Output: Send request

[0227] Step 14:

[0228] The server analyzes the feedback and updates the user's profile data. The server analyzes the feedback with its NLP engine and modifies or adds to the profile data.

[0229] Input: Feedback data

[0230] Data processing / calculation: Feedback analysis and database updates

[0231] Output: Updated profile data

[0232] These processing steps allow the system to provide accurate suggestions tailored to the user's individual needs and preferences, and to improve its accuracy as feedback is received.

[0233] (Application example 1)

[0234] 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."

[0235] One issue with virtual stores is that it is difficult for users to select the most suitable products without trying them on in person. Furthermore, there is a lack of systems that can make appropriate product recommendations based on users' preferences and past purchase history. This can lead to users being unable to make satisfactory product selections, which can lead to a decline in customer satisfaction.

[0236] 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.

[0237] In this invention, the server includes means for converting a user's voice input into text, means for transmitting the converted text data, means for analyzing the received text data, means for acquiring user profile data, means for acquiring user location information and environmental data, means for generating optimal proposals using a generative AI model based on the analyzed data and the acquired profile data and environmental data, means for transmitting the generated proposals, means for displaying the transmitted proposals, means for receiving user feedback and updating the profile data, and means for making optimal product proposals in a virtual store based on the user's profile data. This allows the user to receive optimal product proposals in the virtual store and select products without trying them on.

[0238] "User" refers to an individual who uses the System.

[0239] "Voice input" refers to a method in which a user provides information to a system by speaking.

[0240] "Means for converting to text" refers to a device or software that implements the process of converting voice input into text data.

[0241] "Text data" refers to data that has been converted from voice input into text information.

[0242] "Means for sending" refers to a device or software that implements the process of sending text data to another system, such as a server.

[0243] "Means for analyzing" refers to a device or software that realizes the process of understanding the content of the transmitted text data and extracting the necessary information.

[0244] "Profile data" refers to data such as a user's personal information, past behavioral history, and preferences.

[0245] "Means of collection" refers to the device or software that enables the process of collecting profile data, location information, and environmental data.

[0246] "Location Information" means information that indicates a User's current geographic location.

[0247] "Environmental data" refers to information about the user's environment, such as weather, temperature, and surrounding conditions.

[0248] A "generative AI model" refers to an algorithm or software that generates optimal suggestions based on a user's preferences and environment.

[0249] "Means for generating suggestions" refers to a device or software that enables the process of creating the most suitable suggestions for the user based on the analyzed data and / or acquired profile data.

[0250] "Means for displaying submitted suggestions" refers to a device or software that implements the process of visually presenting generated suggestions to a user.

[0251] "Feedback" refers to the opinions and evaluations that users provide to the system.

[0252] "Means for updating" refers to the device or software that enables the process of changing or adding profile data based on feedback.

[0253] A "virtual store" refers to a virtual commercial facility where users can browse, select, and purchase products online.

[0254] "Product Suggestions" refers to product information recommended to users based on their preferences and profile data.

[0255] "Means for viewing products without trying them on" refers to devices or software that enable a user to visually view product displays and descriptions without physically handling or trying on the product.

[0256] This invention relates to a system that proposes optimal products in a virtual store based on the user's personal information and environmental data. This system consists of three main elements: the user, a smart device (such as smart glasses), and a server.

[0257] System Overview

[0258] Wearing smart glasses, users walk around the virtual store and ask questions or make requests about products by voice. The smart glasses convert this voice input into text data and send it to the server. The server analyzes the received text data and generates optimal product suggestions using the user's profile data and environmental data. These suggestions are presented to the user through the smart glasses' display. The system continues to improve based on user feedback, providing a superior customer experience.

[0259] A natural language description of the program's operation

[0260] Hardware / Software Used

[0261] Smart glasses: Google Glass, Microsoft HoloLens

[0262] Speech recognition engine: Google Speech-to-Text API

[0263] NLP engine: Google Cloud Natural Language

[0264] Generative AI models: TensorFlow, PyTorch

[0265] Database: MySQL, MongoDB

[0266] Program processing steps

[0267] 1. Handling voice input:

[0268] The server receives the voice data sent from the smart glasses and converts it into text data using a voice recognition engine. Through this process, the user's speech is stored as text information on the server.

[0269] 2. Text data analysis:

[0270] The server uses an NLP engine to analyze the content of the text data and understand the user's intent and the type of question.

[0271] 3. Acquire profile and environmental data:

[0272] The server retrieves user profile data (past purchase history, preferences, etc.) and environmental data (location, weather information, etc.) from a database.

[0273] 4. Proposal generation using generative AI model:

[0274] The server uses a generative AI model based on this data to generate optimal product suggestions for the user, for example recommending specific products based on past purchase history and preferences.

[0275] 5. Show suggestions:

[0276] The server sends the generated proposal data to the smart glasses, and the proposals are displayed on the glasses' display.

[0277] 6. Feedback Processing:

[0278] The server receives feedback from users and updates the user profile data based on that feedback, improving the accuracy of future suggestions.

[0279] Specific examples

[0280] Example 1: Clothing suggestions

[0281] 1. A user points to a specific product in a virtual store and says, "Write a review for this jacket."

[0282] 2. The smart glasses convert the speech into text and send it to the server.

[0283] 3. The server analyzes the text data and generates the most appropriate review based on the user's profile data (similar jackets purchased in the past and preferred colors).

[0284] 4. The smart glasses will display the suggestions on the screen.

[0285] Prompt Sentence Examples

[0286] "Write a review about this product"

[0287] "Generate optimal product suggestions based on user profile data."

[0288] In this way, the system of the present invention can provide real-time and personalized product suggestions to users within the virtual store, greatly improving the user experience.

[0289] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0290] Step 1:

[0291] The user provides voice input. The user points to a specific product in the virtual store and says, "Please give me a review of this jacket." The microphone in the smart glasses captures this voice and stores it as voice data. The input is the user's voice data, and the output is the captured voice data.

[0292] Step 2:

[0293] The device converts the voice data into text data. The voice recognition engine (Google Speech-to-Text API) analyzes the voice data and converts it into text data. The input is voice data and the output is text data. Specifically, the voice recognition engine analyzes the user's speech and generates a corresponding string of characters.

[0294] Step 3:

[0295] The terminal transmits the converted text data to the server, where the text data is sent to the server via network communication. The input is the text data, and the output is the text data transmitted to the server.

[0296] Step 4:

[0297] The server analyzes the received text data. The NLP engine (Google Cloud Natural Language) analyzes the text data to understand the user's intent and the type of question. The input is text data, and the output is the analysis results (user's intent and type of question). Specifically, the NLP engine analyzes the text data grammatically and semantically to extract key keywords and content.

[0298] Step 5:

[0299] The server retrieves the user's profile data and environmental data. It retrieves the user's past purchase history, preferences, location information, and environmental data (weather and surrounding conditions) from the database. The input is the analysis result, and the output is the user's profile data and environmental data. Specifically, the server executes a database query to retrieve the required data.

[0300] Step 6:

[0301] The server uses a generative AI model to generate optimal proposals. Based on the acquired profile data and environmental data, an AI model (TensorFlow or PyTorch) is used to generate optimal product proposals for the user. The input is the profile data and environmental data, and the output is the generated proposal. Specifically, the AI ​​model analyzes the data and selects the optimal product.

[0302] Step 7:

[0303] The server sends the generated proposal to the terminal. The server sends the proposal data to the smart glasses, which then transmits it over the network. The input is the generated proposal, and the output is the transmitted proposal.

[0304] Step 8:

[0305] The terminal displays the sent suggestion. The suggestion is displayed on the display of the smart glasses. The input is the sent suggestion, and the output is the suggestion displayed on the display. As a specific operation, the display visually displays the suggestion.

[0306] Step 9:

[0307] Collect user feedback and send it to the server. Users can voice-input their feedback about the proposed products, which the smart glasses will capture and convert into text. The input is the user's voice feedback, and the output is text feedback.

[0308] Step 10:

[0309] The server updates the profile data based on the feedback. It analyzes the user's feedback and improves the profile data. The input is text feedback and the output is updated profile data. Specifically, the server analyzes the feedback and updates the user profile appropriately.

[0310] 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.

[0311] This invention relates to a system that learns a user's personal information and provides various daily advice based on it. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[0312] System Overview

[0313] The user uses voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. The system can further improve its accuracy by providing feedback from the user. A particular feature of this invention is that the emotion engine recognizes the user's emotions and reflects them in the suggestions and feedback.

[0314] Program processing

[0315] The system operates sequentially as follows:

[0316] User registration and initial data entry

[0317] When a user first uses the system, they register and enter a self-introduction and basic information. This information is sent to the server by the device and stored in a database as profile data.

[0318] Continuous data collection and analysis

[0319] In everyday life, users ask questions or make requests to the system. For example, they might say, "What should I eat today?" The device converts this speech into text data and sends it to the server. The server then uses a natural language processing (NLP) engine to analyze this text data and understand the user's intent.

[0320] Next, the server retrieves the user's profile data from the database, including the user's past behavioral history, preferences, allergy information, etc. Additionally, the server retrieves the user's current location, weather information, and other environmental data.

[0321] Utilizing the Emotion Engine

[0322] The server uses an emotion engine to recognize the user's emotions based on the text and voice data, and this emotion information is used to generate suggestions and update the user profile.

[0323] Proposal generation and presentation

[0324] The server uses an AI model based on the analyzed data, acquired profile data, and environmental data, as well as the user's recognized emotions, to generate optimal suggestions. For example, if the user is emotionally exhausted, it may suggest a relaxing restaurant. These suggestions are displayed to the user through their device.

[0325] Feedback and Learning

[0326] The user provides feedback on the suggestions to the system. For example, the user can input feedback such as "I tried this restaurant and it was good." The device then sends this feedback to the server, which analyzes it and updates the user's profile data. The emotion engine also uses the feedback to learn the user's emotional tendencies. Through this process, the system gains a more accurate understanding of the user's preferences and tendencies, improving the accuracy of future suggestions.

[0327] Specific examples

[0328] Example 1: Restaurant suggestions

[0329] 1. The user utters, "What should I eat today?"

[0330] 2. The device converts the speech into text and sends it to the server.

[0331] 3. The server analyzes the question and searches for suitable restaurants based on the user's profile data and location.

[0332] 4. The emotion engine analyzes the user's emotions and prioritizes restaurants where they can relax, for example, if they are tired.

[0333] 5. The server sends the generated proposal to the device, which displays it to the user.

[0334] Example 2: Fashion advice

[0335] 1. The user types into the system, "Please give me some advice on what to wear today."

[0336] 2. The device sends this input to the server.

[0337] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information.

[0338] 4. The emotion engine analyzes the user's emotions and suggests uplifting clothing if, for example, they are feeling down.

[0339] 5. The server sends the generated proposal to the device, which notifies the user.

[0340] As described above, the system of the present invention can provide accurate advice in various situations throughout the user's life, and can improve the quality of life by taking into consideration the user's emotions in particular.

[0341] The processing flow will be explained below.

[0342] Processing steps of the invention combined with an emotion engine that recognizes user emotions

[0343] Step 1:

[0344] The user voice-inputs, "What should I eat today?"

[0345] Step 2:

[0346] The device converts voice input into text data in real time.

[0347] Step 3:

[0348] The terminal sends the converted text data to the server along with the user ID.

[0349] Step 4:

[0350] The text data received by the server is analyzed using a natural language processing (NLP) engine.

[0351] Specifically, it extracts the user's intent from text data and understands that the user is looking for suggestions on what to eat today.

[0352] Step 5:

[0353] The server uses an emotion engine to recognize the user's emotion from the received text data and voice data.

[0354] Specifically, it analyzes the user's emotional state (e.g., tiredness, joy, stress) from the tone of voice and text content.

[0355] Step 6:

[0356] The server retrieves the user's profile data (past dietary history, preferences, allergy information, etc.) from the database.

[0357] Step 7:

[0358] The server retrieves the user's current location and environmental data (weather, time, etc.) from an external API.

[0359] Step 8:

[0360] The server uses AI models to generate restaurant suggestions based on the parsed data, retrieved profile data, environmental data, and recognized user sentiment.

[0361] Specifically, the app searches for restaurants that meet criteria such as "close to the user's location," "have low-calorie menu items," and "have a relaxing atmosphere."

[0362] Step 9:

[0363] The server generates a list of restaurant suggestions that are optimized based on the user's profile data and past feedback.

[0364] Specifically, highly rated restaurants and restaurants that users have previously liked will be placed at the top of the list.

[0365] Step 10:

[0366] The server sends optimized restaurant suggestions in JSON format to the device.

[0367] Step 11:

[0368] The device displays the received proposal data to the user.

[0369] Specifically, the screen will display, "We recommend a nearby low-calorie restaurant called 'Healthy Dinner'."

[0370] Step 12:

[0371] The user enters feedback on the suggestion (e.g., "I tried this restaurant and it was great").

[0372] Step 13:

[0373] The device sends the user's feedback to the server.

[0374] Step 14:

[0375] The server analyzes the received feedback and updates the user's profile data and the learning data of the emotion engine.

[0376] Specifically, it marks the restaurant as "good" and prioritizes similar restaurants in future suggestions, while also improving the accuracy of its sentiment engine based on user feedback.

[0377] By repeating this series of steps, the system learns not only the user's preferences and lifestyle habits, but also their emotional state, allowing it to make more appropriate and personalized suggestions.

[0378] Example 2

[0379] 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."

[0380] Conventional recommendation systems have the problem of low user satisfaction because they do not adequately consider the user's individual needs or real-time emotions when making recommendations. Specifically, they have limited use of profile data and environmental data, and lack the functionality to analyze user emotions and reflect them in recommendations. Furthermore, they lack a means to effectively utilize user feedback to improve the system.

[0381] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0382] In this invention, the server includes means for converting a user's voice input into text, means for transmitting the converted text data, means for analyzing the received text data, means for acquiring the user's profile data, means for acquiring the user's location information and environmental data, means for generating suggestions based on the analyzed data and the acquired profile data and environmental data, means for transmitting the generated suggestions, means for displaying the transmitted suggestions, means for receiving user feedback and updating the profile data, means for analyzing the user's emotions, and means for generating suggestions based on the analyzed user's emotions. This enables the generation of detailed suggestions that take the user's emotions into consideration, thereby improving user satisfaction. Furthermore, by utilizing feedback, the system learns and improves, and even more accurate suggestions can be made in the future.

[0383] "Voice input" refers to voice data provided by the user via a microphone or the like.

[0384] "Means for converting to text" refers to technology or equipment for analyzing voice data and converting it into text information.

[0385] "Text data" refers to digital data obtained by converting voice data into text information.

[0386] A "transmitting means" is any technique or device used to send data over a network to another system or device.

[0387] "Means of analysis" refers to technology or equipment for analyzing text data and understanding the user's intentions and emotions.

[0388] "Profile data" refers to data such as basic information about a user, past behavioral history, and preferences.

[0389] "Location information" refers to data that indicates a user's current location.

[0390] "Environmental data" refers to data that indicates the user's surroundings, including, for example, weather information and information about nearby facilities.

[0391] The "means for generating suggestions" refers to a technology or device that generates suggestions suited to the user based on the analyzed data and the acquired data.

[0392] "Means for displaying" refers to a technique or device for visually presenting generated suggestions to a user.

[0393] "Feedback" refers to opinions and thoughts about suggestions that users provide to the system.

[0394] "Means for updating" refers to the technology or equipment used to modify or add to the contents of the database based on feedback.

[0395] "Means for analyzing emotions" refers to technology or devices for determining emotions from a user's text data or voice data.

[0396] A "means for generating suggestions based on emotions" is a technique or device that takes into account the analyzed emotion data to generate suggestions that are appropriate for the user.

[0397] The present invention relates to a system that takes into account a user's emotions and generates suggestions based on personal information. The system consists of four main components: a server, a terminal, a user, and an emotion analysis engine.

[0398] System Overview

[0399] The user uses voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. The system can further improve its accuracy by providing feedback from the user. A particular feature of this invention is that the emotion analysis engine recognizes the user's emotions and reflects them in the suggestions and feedback.

[0400] Program processing

[0401] Hardware and software used

[0402] 1. A microphone device that allows the user to input voice information.

[0403] 2. Software that allows your device to convert speech to text (e.g., Google Speech-to-Text API).

[0404] 3. A natural language processing (NLP) engine (e.g., spaCy, NLTK) to analyze the text data received by the server.

[0405] 4. A database (e.g., MySQL) where the server stores and retrieves user profile data.

[0406] 5. Third-party APIs (e.g. OpenWeatherMap API) through which the server can obtain environmental data.

[0407] 6. An emotion analysis engine (e.g., Microsoft Azure Emotion API) for the server to perform emotion analysis.

[0408] 7. A generative AI model (e.g., GPT-3) for the server to generate proposals.

[0409] Data processing and calculation

[0410] 1. The device converts voice input into text data.

[0411] Audio waveform data is captured and processed for filtering and noise reduction.

[0412] The filtered voice data is converted into text in real time to generate text data.

[0413] 2. The device sends the text data to the server.

[0414] The text data is packaged in JSON format and sent using the HTTPS protocol.

[0415] 3. The server parses the text data.

[0416] Use a natural language processing (NLP) engine to tokenize text data and analyze user intent.

[0417] Use a sentiment analysis engine to extract sentiment labels from text data.

[0418] 4. The server retrieves the user profile data and environment data.

[0419] Retrieve profile data from a database and environmental data using third-party APIs.

[0420] 5. The server generates a proposal.

[0421] Based on the analyzed and acquired data, an AI model is used to generate optimal recommendations.

[0422] 6. The server sends the generated proposal to the device.

[0423] The proposal results are packaged in JSON format and sent to the terminal.

[0424] 7. The device displays suggestions to the user.

[0425] The proposed results are displayed to the user in a visually easy-to-understand format.

[0426] 8. Users provide feedback on suggestions.

[0427] Feedback is input as text data or audio data.

[0428] 9. The device sends the feedback to the server.

[0429] The feedback data is packaged in JSON format and sent to the server.

[0430] 10. The server analyzes the feedback and updates the profile data.

[0431] Analyze feedback data and update user profile data.

[0432] Use a sentiment analysis engine to extract additional emotional data from the feedback.

[0433] Specific examples

[0434] Example 1: Restaurant suggestions

[0435] 1. The user utters, "What should I eat today?"

[0436] 2. The device converts the speech into text and sends it to the server.

[0437] 3. The server analyzes the question and searches for suitable restaurants based on the user's profile data and location.

[0438] 4. The sentiment analysis engine analyzes the user's emotions and prioritizes restaurants where they can relax, for example, if they are tired.

[0439] 5. The server uses an appropriate AI model to generate a list of relaxing restaurants.

[0440] 6. The server sends the generated proposal to the device, which displays it to the user.

[0441] Example 2: Fashion advice

[0442] 1. The user types into the system, "Please give me some advice on what to wear today."

[0443] 2. The device sends this input to the server.

[0444] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information.

[0445] 4. The emotion analysis engine analyzes the user's emotions and suggests uplifting clothing if, for example, they are feeling down.

[0446] 5. The server sends the generated proposal to the device, which notifies the user.

[0447] Prompt Sentence Examples

[0448] Restaurant Suggestion Prompt

[0449] The user types, "What should I eat today?" In response, the app should suggest a relaxing restaurant based on the user's past eating history, current location, weather information, and data on how tired the user is currently feeling.

[0450] Fashion Advice Prompt

[0451] The user types, "Please give me some advice on what to wear today." In response, the app should suggest an uplifting outfit based on the user's past clothing preferences, current weather information, and data indicating the user is feeling depressed.

[0452] The above is an embodiment of the system of the present invention. This system can generate detailed suggestions that take into account the user's emotions and improve user satisfaction.

[0453] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0454] Step 1: User registration and initial data entry

[0455] When a user first uses the system, they access it and enter a self-introduction and basic information.

[0456] Input: The user enters their name, age, gender, food preferences, allergy information, hobbies, etc.

[0457] Data processing: This information is converted into JSON format by the terminal.

[0458] Output: The data converted to JSON format is sent to the server.

[0459] Step 2: Save your basic information

[0460] The server stores the received user information in a database.

[0461] Input: User information sent from the device in JSON format.

[0462] Data processing: Parse and validate JSON data to ensure there is no invalid data.

[0463] Output: Save the validated data to the database.

[0464] Step 3: Speak your question or request

[0465] Users can ask questions or make requests to the system by voice input.

[0466] Input: Speech data (e.g., "What should I eat today?").

[0467] Data processing: Audio is captured in real time and undergoes filtering and noise reduction.

[0468] Output: The filtered audio data is converted into text data and stored in the device.

[0469] Step 4: Sending text data

[0470] The device converts the voice into text data and sends it to the server.

[0471] Input: Text data generated from audio data.

[0472] Data processing: Packaging text data into JSON format.

[0473] Output: JSON formatted text data is sent to the server.

[0474] Step 5: Analyzing the text data

[0475] The server analyzes the received text data.

[0476] Input: Text data sent from the terminal.

[0477] Data processing: Using a natural language processing (NLP) engine, we tokenize the text data and understand the intent of the question or request.

[0478] Output: The analysis results in user intent and emotional data.

[0479] Step 6: Obtaining profile and environment data

[0480] The server retrieves the user's profile data and environment data.

[0481] Input: User's ID and location information.

[0482] Data Transformation: Query profile data from databases and use third-party APIs to retrieve environmental data.

[0483] Output: The acquired profile data and environmental data are aggregated on the server.

[0484] Step 7: Sentiment Analysis

[0485] The server uses a sentiment analysis engine to analyze the user's sentiment.

[0486] Input: Text and audio data.

[0487] Data processing: Extract emotion labels (e.g., joy, sadness, anger) using a sentiment analysis engine.

[0488] Output: The parsed emotion data is generated.

[0489] Step 8: Generate proposals

[0490] The server generates optimal suggestions based on the analyzed data.

[0491] Input: Acquired profile data, environmental data, parsed emotion data.

[0492] Data processing: Input prompt sentences into a generative AI model (e.g., GPT-3) to generate suggestions.

[0493] Output: The generated proposals are output in JSON format.

[0494] Step 9: Submit your proposal

[0495] The server sends the generated proposal to the terminal.

[0496] Input: Generated proposal data.

[0497] Data processing: The proposed data is packaged in JSON format.

[0498] Output: The proposal data in JSON format is sent to the device.

[0499] Step 10: Viewing Proposals

[0500] The device displays the suggestions to the user.

[0501] Input: Proposal data sent by the server.

[0502] Data Processing: Converting the proposed data into a user-friendly format.

[0503] Output: The proposed results are displayed on the screen.

[0504] Step 11: Enter your feedback

[0505] Users provide feedback on the suggestions.

[0506] Input: Feedback text or audio (e.g., "I tried this restaurant and it was great").

[0507] Data processing: Convert the feedback into text data.

[0508] Output: The converted feedback data is stored in the terminal.

[0509] Step 12: Submit your feedback

[0510] The terminal sends the feedback to the server.

[0511] Input: Feedback text data.

[0512] Data processing: Packaging the feedback data into JSON format.

[0513] Output: Feedback data in JSON format is sent to the server.

[0514] Step 13: Analyze feedback

[0515] The server analyzes the feedback and updates the profile data.

[0516] Input: Feedback data sent from the device.

[0517] Data Processing: Analyzes the feedback data to update user profile data and also uses a sentiment analysis engine to extract additional sentiment data from the feedback.

[0518] Output: Updated profile data is saved to the database.

[0519] The above are the specific processing steps of the system and details of its operation.

[0520] (Application example 2)

[0521] 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."

[0522] Conventional advice-providing systems only provide generic suggestions without considering the user's emotions, making it difficult to provide optimal suggestions that meet the needs of individual users. Furthermore, feedback and profile data updates to improve the accuracy of suggestions were not effectively provided. The present invention aims to solve these problems by providing a system that can analyze a user's emotions and suggest optimal products based on those emotions.

[0523] 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 converting a user's voice input into text, means for transmitting the converted text data, and means for analyzing the received text data. This makes it possible to accurately analyze the received data and generate optimal suggestions based on the user's emotions and profile data.

[0524] The system further includes means for acquiring user profile data, means for acquiring user location and environmental data, and means for generating suggestions based on the analyzed data and the acquired profile and environmental data, thereby enabling suggestions to be provided that are tailored to the user's individual situation.

[0525] The system also includes a means for transmitting the generated proposals, a means for displaying the transmitted proposals, a means for analyzing the user's emotions and reflecting the same in generating proposals and updating the profile data, and a means for using a generative AI model to generate optimal product proposals based on the emotions and profile data, thereby enabling highly accurate proposals incorporating emotion analysis.

[0526] Furthermore, the system includes means for receiving user feedback and updating the profile data, thereby enabling the system to reflect the user feedback and improve the accuracy of suggestions.

[0527] "Means for converting user voice input into text" means a device or software that recognizes a user's voice and converts it into text data.

[0528] The "means for transmitting converted text data" is a network communication device for transmitting the text data converted from the voice to the server.

[0529] The "means for analyzing received text data" refers to a system that analyzes the text data received by the server using techniques such as natural language processing and sentiment analysis.

[0530] "Means for obtaining user profile data" refers to a system for collecting profile data such as a user's personal information and past behavioral history.

[0531] "Means for acquiring user location information and environmental data" refers to technology for collecting information about the user's current location and the surrounding environment (such as the weather).

[0532] A "means for generating suggestions" is an algorithm or model for automatically generating optimal suggestions based on the analyzed data and the acquired profile and environmental data.

[0533] The "means for transmitting the generated proposal" is a communication means for sending the generated proposal to the user's terminal.

[0534] A "means for displaying submitted suggestions" is a device (such as a display) for visually displaying submitted suggestions to a user.

[0535] The "means for analyzing user emotions and reflecting the results in generating suggestions and updating profile data" is a system for analyzing user emotions and using the results in generating suggestions and updating profile data.

[0536] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and generates optimal suggestions based on user emotions and profile data.

[0537] The "means for generating optimal product suggestions" is a mechanism for selecting and suggesting products based on the user's emotions and profile data.

[0538] The "means for receiving user feedback and updating profile data" is a system for collecting user ratings and opinions and updating profile data based on them.

[0539] The present invention relates to a system for virtual stores that makes optimal product suggestions based on a user's personal information and emotional state. This system is composed of the following elements: a means for converting a user's voice input into text, a data transmission means, a text data analysis means, a profile data acquisition means, a location information and environmental data acquisition means, a suggestion generation means, a suggestion transmission means, a suggestion display means, an emotion analysis means, a generative AI model, an optimal product suggestion means, and a feedback reception means.

[0540] Each component of the system operates as follows.

[0541] Voice input and data transmission

[0542] When a user speaks, the device converts the speech into text data using a speech recognition library (e.g., the SpeechRecognition library), which is then sent to the server via the network.

[0543] Data analysis and profile data acquisition

[0544] The server analyzes the received text data and uses natural language processing techniques (e.g., TextBlob) to understand its content. The server also retrieves user profile data (e.g., age, gender, interests) and environmental data (e.g., current location, weather) from a database.

[0545] Sentiment Analysis and Suggestion Generation

[0546] Based on the analyzed text data and the acquired profile data, the server uses a sentiment analysis engine (e.g., TextBlob's sentiment analysis function) to determine the user's sentiment. Based on this sentiment information and profile data, a generative AI model generates optimal product recommendations.

[0547] Submitting and Viewing Proposals

[0548] The generated proposal is sent to the user's terminal via the proposal sending means and displayed on the terminal's display, allowing the user to check the proposed products in the virtual store.

[0549] Feedback and profile data updates

[0550] The feedback provided by the user is then sent back from the device to the server, which analyzes it and updates the profile data, thereby improving the accuracy of future suggestions.

[0551] Specific examples

[0552] 1. User: "I've been feeling stressed lately. Can you suggest some products that will help me relax?"

[0553] 2. System: Converts speech into text and analyzes it. The emotion analysis engine determines the user's emotion as negative.

[0554] 3. The server suggests relaxation products based on the user's profile data and emotional information.

[0555] 4. Device: Show users relaxation products such as "aromatherapy sets" and "massage devices."

[0556] 5. User: "This suggestion is very helpful" provides feedback.

[0557] 6. The server receives the feedback and updates the profile data.

[0558] Prompt Sentence Examples

[0559] Input prompt: "I've been feeling stressed lately. Can you suggest some products that will help me relax?"

[0560] Input to generative AI model: "User's sentiment is negative. Suggest products that will help them relax. User's interests are not related to fitness."

[0561] In this way, the present invention provides a system that can make highly accurate product suggestions by taking into account the user's emotions and personal information.

[0562] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0563] Step 1:

[0564] The user performs voice input. The device captures the user's voice through the microphone. This voice data is used as input and converted into text data using a speech recognition library. The converted text data is generated as output.

[0565] Step 2:

[0566] The converted text data is sent to the server. The device uses a network communication module to send the text data to the server, along with metadata such as the user's ID information.

[0567] Step 3:

[0568] The server parses the received text data, uses a natural language processing library (e.g., TextBlob) to understand the meaning of the text data and extract the user's intent, and generates the results of the parsing as output.

[0569] Step 4:

[0570] The server retrieves the user's profile data from the database, which includes the user's basic information, past behavior history, interests, etc. After receiving this profile data as input, it is used for the next analysis step.

[0571] Step 5:

[0572] The server obtains the user's location and environmental data. Location information is obtained from GPS data, and environmental data such as weather and time of day is obtained from an API. These data are used as inputs to generate the next proposal.

[0573] Step 6:

[0574] Using the sentiment analysis engine, the server analyzes the user's sentiment from the text data. It uses the sentiment analysis function of TextBlob to classify the user's sentiment as positive, negative, or neutral. It generates this sentiment data as output.

[0575] Step 7:

[0576] Using a generative AI model, the server generates optimal product suggestions based on the user's profile data, location information, environmental data, and emotional data. The AI ​​model is trained from past data and generates suggestions based on prompts. This suggestion data is generated as output.

[0577] Step 8:

[0578] The generated proposal is transmitted to the user's terminal. The server uses a communication module to transmit the generated proposal data to the user's terminal. The transmitted proposal data is displayed on the user's terminal.

[0579] Step 9:

[0580] The user provides feedback. The user inputs their evaluation or opinion on the provided suggestion by voice or text. The device sends this feedback data to the server.

[0581] Step 10:

[0582] The server analyzes the user's feedback and updates the profile data. The feedback analysis converts the user's ratings into text data, and the server updates the user's profile data based on the text data. This updated data is used to generate suggestions from the next time onwards.

[0583] 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.

[0584] 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.

[0585] 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.

[0586] [Second embodiment]

[0587] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0588] 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.

[0589] 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).

[0590] 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.

[0591] 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.

[0592] 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).

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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."

[0599] This invention relates to a system that learns a user's personal information and provides various daily advice based on that information. This system consists of three main components: a server, a terminal, and the user.

[0600] System Overview

[0601] Users use voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. User feedback allows the system to further improve its accuracy.

[0602] Program processing

[0603] The system operates sequentially as follows:

[0604] User registration and initial data entry

[0605] When a user first uses the system, they register and enter a self-introduction and basic information. This information is sent to the server by the device and stored in a database as profile data.

[0606] Continuous data collection and analysis

[0607] In everyday life, users ask questions or make requests to the system. For example, they might say, "What should I eat today?" The device converts this speech into text data and sends it to the server. The server then uses a natural language processing (NLP) engine to analyze this text data and understand the user's intent.

[0608] Next, the server retrieves the user's profile data from the database, including the user's past behavioral history, preferences, allergy information, etc. Additionally, the server retrieves the user's current location, weather information, and other environmental data.

[0609] Proposal generation and presentation

[0610] The server uses AI models based on this data to generate optimal suggestions. For example, if a user wants a low-calorie meal, the server searches for appropriate restaurants and generates a suggestion such as, "We recommend a nearby low-calorie restaurant called 'Healthy Dinner.'" This suggestion is then displayed to the user via their device.

[0611] Feedback and Learning

[0612] The user provides feedback on the suggestions to the system. For example, they might input feedback like, "I tried this restaurant and it was great." The device then sends this feedback to the server, which analyzes it and updates the user's profile data. Through this process, the system gains a more accurate understanding of the user's preferences and tendencies, improving the accuracy of future suggestions.

[0613] Specific examples

[0614] Example 1: Restaurant suggestions

[0615] 1. The user utters, "What should I eat today?"

[0616] 2. The device converts the speech into text and sends it to the server.

[0617] 3. The server analyzes the question and searches for suitable restaurants based on the user's profile data and location.

[0618] 4. The server sends the generated proposal to the device, which displays it to the user.

[0619] Example 2: Fashion advice

[0620] 1. The user types into the system, "Please give me some advice on what to wear today."

[0621] 2. The device sends this input to the server.

[0622] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information.

[0623] 4. The server sends the generated proposal to the device, which notifies the user.

[0624] As described above, the system of the present invention can provide accurate advice to the user in various situations throughout his or her life, thereby improving the quality of the user's life.

[0625] The processing flow will be explained below.

[0626] Step 1:

[0627] The user voice-inputs, "What should I eat today?"

[0628] Step 2:

[0629] The device converts voice input into text data in real time.

[0630] Step 3:

[0631] The terminal sends the converted text data to the server along with the user ID.

[0632] Step 4:

[0633] The text data received by the server is analyzed using a natural language processing (NLP) engine.

[0634] Specifically, it extracts the user's intent from text data and understands that the user is looking for suggestions on what to eat today.

[0635] Step 5:

[0636] The server retrieves the user's profile data (past dietary history, preferences, allergy information, etc.) from the database.

[0637] Step 6:

[0638] The server retrieves current location and environmental data (weather, time, etc.) from an external API.

[0639] Step 7:

[0640] The server uses AI models to generate restaurant suggestions based on the parsed data, retrieved profile data, and environmental data.

[0641] Specifically, the system searches for restaurants that meet certain criteria, such as "close to the user's location" and "have low-calorie menu items."

[0642] Step 8:

[0643] The server generates a list of restaurant suggestions that are optimized based on the user's profile data and past feedback.

[0644] Specifically, highly rated restaurants and restaurants that users have previously liked will be placed at the top of the list.

[0645] Step 9:

[0646] The server sends optimized restaurant suggestions in JSON format to the device.

[0647] Step 10:

[0648] The device displays the received proposal data to the user.

[0649] Specifically, the screen will display, "We recommend a nearby low-calorie restaurant called 'Healthy Dinner'."

[0650] Step 11:

[0651] The user enters feedback on the suggestion (e.g., "I tried this restaurant and it was great").

[0652] Step 12:

[0653] The device sends the user's feedback to the server.

[0654] Step 13:

[0655] The server analyzes the received feedback and updates the user's profile data.

[0656] Specifically, it will set the restaurant's rating to "good" and prioritize similar restaurants in future suggestions.

[0657] By repeating this series of steps, the system learns the user's preferences and lifestyle habits and can make more appropriate and personalized suggestions.

[0658] Example 1

[0659] 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."

[0660] Conventional technologies generally provide suggestions and advice to users, but have the problem of not being able to fully address the individual needs and preferences of each user. In particular, there is a need for a system that can efficiently and accurately process users' voice input and, based on the results, generate optimal suggestions that reflect the user's profile data and environmental data.

[0661] 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.

[0662] In this invention, the server includes means for converting a user's voice input into text data, means for transmitting the converted text data, means for analyzing the received text data, means for acquiring user profile data, means for acquiring user location data and environmental data, means for generating suggestions using a generative AI model based on the analyzed text data and the acquired profile data and environmental data, means for transmitting the generated suggestions, means for displaying the transmitted suggestions, and means for receiving user feedback and updating the profile data, thereby enabling accurate suggestions to be made in accordance with each user's individual needs and preferences.

[0663] A "user" is someone who uses the system to provide voice input and receive suggestions and advice.

[0664] "Voice input" refers to the act of a user asking a question or making a request to a system by voice.

[0665] "Text data" is character information converted from voice input.

[0666] "Means for converting" refers to the technology or algorithm used to convert voice input into text data.

[0667] "Transmission means" refers to the communication technology or protocol used to transmit text data to the server.

[0668] The "receiving means" is a means by which the server receives text data sent from the terminal.

[0669] "Means of analysis" refers to the technology and algorithms used to understand the received text data and grasp the user's intent.

[0670] "Profile data" refers to individual data such as a user's basic information, past behavioral history, preferences, and allergy information.

[0671] "Means of acquisition" refers to the technology or protocol used to acquire the required data from a database or external system.

[0672] "Environmental data" refers to data about the user's environment, such as the user's current location and weather information.

[0673] A "generative AI model" is an artificial intelligence model that generates optimal suggestions based on user data.

[0674] The "means for generating suggestions" is a generative AI model that runs on the basis of the analyzed text data and the acquired profile and environmental data.

[0675] "Displaying means" refers to the techniques or methods for presenting the generated suggestions to the user.

[0676] "Feedback" refers to the evaluation or opinion that a user gives to the system after receiving a suggestion.

[0677] "Means for receiving feedback" refers to the means for collecting feedback from users.

[0678] An "updating means" is a technique or algorithm for correcting or adding to profile data based on feedback received.

[0679] This invention relates to a system that learns a user's personal information and provides various daily advice using a generative AI model. This system consists of three main components: a server, a terminal, and the user.

[0680] System Overview

[0681] Users use voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. User feedback allows the system to further improve its accuracy.

[0682] Hardware and Software Configuration

[0683] This system uses the following hardware and software:

[0684] 1. Device:

[0685] Smartphone (iOS, Android)

[0686] Smart speakers (voice assistant devices for the general home)

[0687] 2. Server:

[0688] Cloud services (AWS, Azure, Google Cloud)

[0689] 3. Natural Language Processing (NLP) Engine:

[0690] OpenAI GPT

[0691] Google NLP API

[0692] 4. Database:

[0693] MySQL

[0694] PostgreSQL

[0695] What the program does

[0696] This system performs the following processes sequentially.

[0697] User registration and initial data entry

[0698] When a user first uses the system, they register and enter a self-introduction and basic information. The device sends this input data to the server, which then stores it in a database. For example, a user might install an app and enter their name, age, gender, allergy information, etc.

[0699] Voice to text conversion

[0700] The user can ask a question or make a request by voice. For example, they can say, "What should I eat today?" The device converts the voice into text using voice recognition technology such as the Google Speech-to-Text API and sends this text data to the server.

[0701] Text analysis and suggestion generation

[0702] The server uses an NLP engine such as OpenAI GPT to analyze the received text data. Based on the analysis results, the user's profile data and environmental data (such as current location and weather information) are retrieved from a database, and based on this, a generative AI model is used to generate optimal suggestions. An example of a prompt sentence is, "I'm looking for a low-calorie meal. Can you recommend any restaurants?"

[0703] Submitting suggestions and providing feedback

[0704] The generated suggestions are sent from the server to the device and displayed to the user through the device. For example, a suggestion such as "We recommend a nearby low-calorie restaurant for a healthy dinner" may be displayed. The user enters feedback on the suggestions, and the device sends the feedback to the server. The server analyzes the feedback and updates the user's profile data. This feedback improves the accuracy of future suggestions.

[0705] Specific examples

[0706] Specific examples of how this system can be used include:

[0707] Example 1: Restaurant suggestions

[0708] 1. The user utters, "What should I eat today?"

[0709] 2. The device converts the speech into text and sends it to the server.

[0710] 3. The server analyzes the question and searches for appropriate restaurants based on the user's profile data and location, using a generative AI model to generate a suggestion such as "Recommend a nearby low-calorie restaurant for a healthy dinner."

[0711] 4. The server sends the generated proposal to the device, which displays it to the user.

[0712] Example 2: Fashion advice

[0713] 1. The user types into the system, "Please give me some advice on what to wear today."

[0714] 2. The device sends this input to the server.

[0715] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information, for example, "It's raining today, so I recommend a raincoat and waterproof shoes."

[0716] 4. The server sends the generated proposal to the device, which notifies the user.

[0717] As described above, the system of the present invention provides accurate advice that corresponds to the individual needs and environment of the user, thereby improving the quality of life of the user.

[0718] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0719] Step 1:

[0720] When a user first uses the system, they register and enter basic information. The user then installs the app and enters their name, age, gender, allergy information, etc.

[0721] Input: User's basic information (name, age, gender, allergy information, etc.)

[0722] Data processing / calculation: Basic information entered is collected

[0723] Output: Basic information dataset

[0724] Step 2:

[0725] The device sends the user's basic information to the server. The device sends the basic information dataset to the server using an HTTP request.

[0726] Input: User basic information dataset

[0727] Data processing / calculation: Convert basic information dataset into HTTP request

[0728] Output: Send request

[0729] Step 3:

[0730] The server receives the basic information and stores it in a database. The server receives the basic information dataset and stores it in a database (MySQL or PostgreSQL).

[0731] Input: Basic information dataset

[0732] Data processing / calculation: Inserting basic information datasets into the database

[0733] Output: Basic information stored in the database

[0734] Step 4:

[0735] The user asks a question or makes a request by voice, for example, "What should I eat today?"

[0736] Input: User voice input

[0737] Data processing / calculation: Collection of voice data

[0738] Output: Audio data

[0739] Step 5:

[0740] The device converts the voice input into text data. The device converts the voice data into text data using speech recognition technology such as the Google Speech-to-Text API.

[0741] Input: Audio data

[0742] Data processing / calculation: Converting voice data into text data

[0743] Output: Text data

[0744] Step 6:

[0745] The device sends text data to the server. The device sends text data to the server using an HTTP request.

[0746] Input: Text data

[0747] Data processing / calculation: Convert text data into a transmission request

[0748] Output: Send request

[0749] Step 7:

[0750] The server analyzes the received text data. The server uses an NLP engine such as OpenAI GPT to analyze the text data and understand the user's intent.

[0751] Input: Text data

[0752] Data processing / calculation: Text analysis using NLP engines

[0753] Output: Analysis results

[0754] Step 8:

[0755] The server retrieves the user's profile data and environmental data. The server retrieves the user's profile data (past behavioral history, preferences, allergy information, etc.) from the database, and collects environmental data using GPS data and weather information APIs.

[0756] Input: Analysis results

[0757] Data manipulation / computation: database queries and API requests

[0758] Output: Profile data and environment data

[0759] Step 9:

[0760] The server generates suggestions using a generative AI model. Based on the analysis results and the acquired profile and environmental data, the server inputs prompt statements into the generative AI model to generate optimal suggestions.

[0761] Input: Analysis results, profile data, environmental data

[0762] Data processing / calculation: Proposal generation using generative AI models

[0763] Output: Proposal

[0764] Step 10:

[0765] The server sends the generated proposal to the device using an HTTP request.

[0766] Input: Proposal

[0767] Data processing / calculation: Converting proposals into submission requests

[0768] Output: Send request

[0769] Step 11:

[0770] Display suggestions received by the device to the user, using notifications and / or in-app displays to inform the user about the suggestions.

[0771] Input: Proposal

[0772] Data processing / calculation: Displaying proposals in the user interface

[0773] Output: User notification

[0774] Step 12:

[0775] The user enters feedback on the proposal. The user enters their evaluation and opinion on the proposal.

[0776] Input: User feedback

[0777] Data processing / calculation: Gathering feedback

[0778] Output: Feedback data

[0779] Step 13:

[0780] The device sends the feedback to the server. It uses an HTTP request to send the feedback data to the server.

[0781] Input: Feedback data

[0782] Data processing / calculation: Convert feedback data into transmission requests

[0783] Output: Send request

[0784] Step 14:

[0785] The server analyzes the feedback and updates the user's profile data. The server analyzes the feedback with its NLP engine and modifies or adds to the profile data.

[0786] Input: Feedback data

[0787] Data processing / calculation: Feedback analysis and database updates

[0788] Output: Updated profile data

[0789] These processing steps allow the system to provide accurate suggestions tailored to the user's individual needs and preferences, and to improve its accuracy as feedback is received.

[0790] (Application example 1)

[0791] 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."

[0792] One issue with virtual stores is that it is difficult for users to select the most suitable products without trying them on in person. Furthermore, there is a lack of systems that can make appropriate product recommendations based on users' preferences and past purchase history. This can lead to users being unable to make satisfactory product selections, which can lead to a decline in customer satisfaction.

[0793] 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.

[0794] In this invention, the server includes means for converting a user's voice input into text, means for transmitting the converted text data, means for analyzing the received text data, means for acquiring user profile data, means for acquiring user location information and environmental data, means for generating optimal proposals using a generative AI model based on the analyzed data and the acquired profile data and environmental data, means for transmitting the generated proposals, means for displaying the transmitted proposals, means for receiving user feedback and updating the profile data, and means for making optimal product proposals in a virtual store based on the user's profile data. This allows the user to receive optimal product proposals in the virtual store and select products without trying them on.

[0795] "User" refers to an individual who uses the System.

[0796] "Voice input" refers to a method in which a user provides information to a system by speaking.

[0797] "Means for converting to text" refers to a device or software that implements the process of converting voice input into text data.

[0798] "Text data" refers to data that has been converted from voice input into text information.

[0799] "Means for sending" refers to a device or software that implements the process of sending text data to another system, such as a server.

[0800] "Means for analyzing" refers to a device or software that realizes the process of understanding the content of the transmitted text data and extracting the necessary information.

[0801] "Profile data" refers to data such as a user's personal information, past behavioral history, and preferences.

[0802] "Means of collection" refers to the device or software that enables the process of collecting profile data, location information, and environmental data.

[0803] "Location Information" means information that indicates a User's current geographic location.

[0804] "Environmental data" refers to information about the user's environment, such as weather, temperature, and surrounding conditions.

[0805] A "generative AI model" refers to an algorithm or software that generates optimal suggestions based on a user's preferences and environment.

[0806] "Means for generating suggestions" refers to a device or software that enables the process of creating the most suitable suggestions for the user based on the analyzed data and / or acquired profile data.

[0807] "Means for displaying submitted suggestions" refers to a device or software that implements the process of visually presenting generated suggestions to a user.

[0808] "Feedback" refers to the opinions and evaluations that users provide to the system.

[0809] "Means for updating" refers to the device or software that enables the process of changing or adding profile data based on feedback.

[0810] A "virtual store" refers to a virtual commercial facility where users can browse, select, and purchase products online.

[0811] "Product Suggestions" refers to product information recommended to users based on their preferences and profile data.

[0812] "Means for viewing products without trying them on" refers to devices or software that enable a user to visually view product displays and descriptions without physically handling or trying on the product.

[0813] This invention relates to a system that proposes optimal products in a virtual store based on the user's personal information and environmental data. This system consists of three main elements: the user, a smart device (such as smart glasses), and a server.

[0814] System Overview

[0815] Wearing smart glasses, users walk around the virtual store and ask questions or make requests about products by voice. The smart glasses convert this voice input into text data and send it to the server. The server analyzes the received text data and generates optimal product suggestions using the user's profile data and environmental data. These suggestions are presented to the user through the smart glasses' display. The system continues to improve based on user feedback, providing a superior customer experience.

[0816] A natural language description of the program's operation

[0817] Hardware / Software Used

[0818] Smart glasses: Google Glass, Microsoft HoloLens

[0819] Speech recognition engine: Google Speech-to-Text API

[0820] NLP engine: Google Cloud Natural Language

[0821] Generative AI models: TensorFlow, PyTorch

[0822] Database: MySQL, MongoDB

[0823] Program processing steps

[0824] 1. Handling voice input:

[0825] The server receives the voice data sent from the smart glasses and converts it into text data using a voice recognition engine. Through this process, the user's speech is stored as text information on the server.

[0826] 2. Text data analysis:

[0827] The server uses an NLP engine to analyze the content of the text data and understand the user's intent and the type of question.

[0828] 3. Acquire profile and environmental data:

[0829] The server retrieves user profile data (past purchase history, preferences, etc.) and environmental data (location, weather information, etc.) from a database.

[0830] 4. Proposal generation using generative AI model:

[0831] The server uses a generative AI model based on this data to generate optimal product suggestions for the user, for example recommending specific products based on past purchase history and preferences.

[0832] 5. Show suggestions:

[0833] The server sends the generated proposal data to the smart glasses, and the proposals are displayed on the glasses' display.

[0834] 6. Feedback Processing:

[0835] The server receives feedback from users and updates the user profile data based on that feedback, improving the accuracy of future suggestions.

[0836] Specific examples

[0837] Example 1: Clothing suggestions

[0838] 1. A user points to a specific product in a virtual store and says, "Write a review for this jacket."

[0839] 2. The smart glasses convert the speech into text and send it to the server.

[0840] 3. The server analyzes the text data and generates the most appropriate review based on the user's profile data (similar jackets purchased in the past and preferred colors).

[0841] 4. The smart glasses will display the suggestions on the screen.

[0842] Prompt Sentence Examples

[0843] "Write a review about this product"

[0844] "Generate optimal product suggestions based on user profile data."

[0845] In this way, the system of the present invention can provide real-time and personalized product suggestions to users within the virtual store, greatly improving the user experience.

[0846] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0847] Step 1:

[0848] The user provides voice input. The user points to a specific product in the virtual store and says, "Please give me a review of this jacket." The microphone in the smart glasses captures this voice and stores it as voice data. The input is the user's voice data, and the output is the captured voice data.

[0849] Step 2:

[0850] The device converts the voice data into text data. The voice recognition engine (Google Speech-to-Text API) analyzes the voice data and converts it into text data. The input is voice data and the output is text data. Specifically, the voice recognition engine analyzes the user's speech and generates a corresponding string of characters.

[0851] Step 3:

[0852] The terminal transmits the converted text data to the server, where the text data is sent to the server via network communication. The input is the text data, and the output is the text data transmitted to the server.

[0853] Step 4:

[0854] The server analyzes the received text data. The NLP engine (Google Cloud Natural Language) analyzes the text data to understand the user's intent and the type of question. The input is text data, and the output is the analysis results (user's intent and type of question). Specifically, the NLP engine analyzes the text data grammatically and semantically to extract key keywords and content.

[0855] Step 5:

[0856] The server retrieves the user's profile data and environmental data. It retrieves the user's past purchase history, preferences, location information, and environmental data (weather and surrounding conditions) from the database. The input is the analysis result, and the output is the user's profile data and environmental data. Specifically, the server executes a database query to retrieve the required data.

[0857] Step 6:

[0858] The server uses a generative AI model to generate optimal proposals. Based on the acquired profile data and environmental data, an AI model (TensorFlow or PyTorch) is used to generate optimal product proposals for the user. The input is the profile data and environmental data, and the output is the generated proposal. Specifically, the AI ​​model analyzes the data and selects the optimal product.

[0859] Step 7:

[0860] The server sends the generated proposal to the terminal. The server sends the proposal data to the smart glasses, which then transmits it over the network. The input is the generated proposal, and the output is the transmitted proposal.

[0861] Step 8:

[0862] The terminal displays the sent suggestion. The suggestion is displayed on the display of the smart glasses. The input is the sent suggestion, and the output is the suggestion displayed on the display. As a specific operation, the display visually displays the suggestion.

[0863] Step 9:

[0864] Collect user feedback and send it to the server. Users can voice-input their feedback about the proposed products, which the smart glasses will capture and convert into text. The input is the user's voice feedback, and the output is text feedback.

[0865] Step 10:

[0866] The server updates the profile data based on the feedback. It analyzes the user's feedback and improves the profile data. The input is text feedback and the output is updated profile data. Specifically, the server analyzes the feedback and updates the user profile appropriately.

[0867] 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.

[0868] This invention relates to a system that learns a user's personal information and provides various daily advice based on it. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[0869] System Overview

[0870] The user uses voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. The system can further improve its accuracy by providing feedback from the user. A particular feature of this invention is that the emotion engine recognizes the user's emotions and reflects them in the suggestions and feedback.

[0871] Program processing

[0872] The system operates sequentially as follows:

[0873] User registration and initial data entry

[0874] When a user first uses the system, they register and enter a self-introduction and basic information. This information is sent to the server by the device and stored in a database as profile data.

[0875] Continuous data collection and analysis

[0876] In everyday life, users ask questions or make requests to the system. For example, they might say, "What should I eat today?" The device converts this speech into text data and sends it to the server. The server then uses a natural language processing (NLP) engine to analyze this text data and understand the user's intent.

[0877] Next, the server retrieves the user's profile data from the database, including the user's past behavioral history, preferences, allergy information, etc. Additionally, the server retrieves the user's current location, weather information, and other environmental data.

[0878] Utilizing the Emotion Engine

[0879] The server uses an emotion engine to recognize the user's emotions based on the text and voice data, and this emotion information is used to generate suggestions and update the user profile.

[0880] Proposal generation and presentation

[0881] The server uses an AI model based on the analyzed data, acquired profile data, and environmental data, as well as the user's recognized emotions, to generate optimal suggestions. For example, if the user is emotionally exhausted, it may suggest a relaxing restaurant. These suggestions are displayed to the user through their device.

[0882] Feedback and Learning

[0883] The user provides feedback on the suggestions to the system. For example, the user can input feedback such as "I tried this restaurant and it was good." The device then sends this feedback to the server, which analyzes it and updates the user's profile data. The emotion engine also uses the feedback to learn the user's emotional tendencies. Through this process, the system gains a more accurate understanding of the user's preferences and tendencies, improving the accuracy of future suggestions.

[0884] Specific examples

[0885] Example 1: Restaurant suggestions

[0886] 1. The user utters, "What should I eat today?"

[0887] 2. The device converts the speech into text and sends it to the server.

[0888] 3. The server analyzes the question and searches for suitable restaurants based on the user's profile data and location.

[0889] 4. The emotion engine analyzes the user's emotions and prioritizes restaurants where they can relax, for example, if they are tired.

[0890] 5. The server sends the generated proposal to the device, which displays it to the user.

[0891] Example 2: Fashion advice

[0892] 1. The user types into the system, "Please give me some advice on what to wear today."

[0893] 2. The device sends this input to the server.

[0894] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information.

[0895] 4. The emotion engine analyzes the user's emotions and suggests uplifting clothing if, for example, they are feeling down.

[0896] 5. The server sends the generated proposal to the device, which notifies the user.

[0897] As described above, the system of the present invention can provide accurate advice in various situations throughout the user's life, and can improve the quality of life by taking into consideration the user's emotions in particular.

[0898] The processing flow will be explained below.

[0899] Processing steps of the invention combined with an emotion engine that recognizes user emotions

[0900] Step 1:

[0901] The user voice-inputs, "What should I eat today?"

[0902] Step 2:

[0903] The device converts voice input into text data in real time.

[0904] Step 3:

[0905] The terminal sends the converted text data to the server along with the user ID.

[0906] Step 4:

[0907] The text data received by the server is analyzed using a natural language processing (NLP) engine.

[0908] Specifically, it extracts the user's intent from text data and understands that the user is looking for suggestions on what to eat today.

[0909] Step 5:

[0910] The server uses an emotion engine to recognize the user's emotion from the received text data and voice data.

[0911] Specifically, it analyzes the user's emotional state (e.g., tiredness, joy, stress) from the tone of voice and text content.

[0912] Step 6:

[0913] The server retrieves the user's profile data (past dietary history, preferences, allergy information, etc.) from the database.

[0914] Step 7:

[0915] The server retrieves the user's current location and environmental data (weather, time, etc.) from an external API.

[0916] Step 8:

[0917] The server uses AI models to generate restaurant suggestions based on the parsed data, retrieved profile data, environmental data, and recognized user sentiment.

[0918] Specifically, the app searches for restaurants that meet criteria such as "close to the user's location," "have low-calorie menu items," and "have a relaxing atmosphere."

[0919] Step 9:

[0920] The server generates a list of restaurant suggestions that are optimized based on the user's profile data and past feedback.

[0921] Specifically, highly rated restaurants and restaurants that users have previously liked will be placed at the top of the list.

[0922] Step 10:

[0923] The server sends optimized restaurant suggestions in JSON format to the device.

[0924] Step 11:

[0925] The device displays the received proposal data to the user.

[0926] Specifically, the screen will display, "We recommend a nearby low-calorie restaurant called 'Healthy Dinner'."

[0927] Step 12:

[0928] The user enters feedback on the suggestion (e.g., "I tried this restaurant and it was great").

[0929] Step 13:

[0930] The device sends the user's feedback to the server.

[0931] Step 14:

[0932] The server analyzes the received feedback and updates the user's profile data and the learning data of the emotion engine.

[0933] Specifically, it marks the restaurant as "good" and prioritizes similar restaurants in future suggestions, while also improving the accuracy of its sentiment engine based on user feedback.

[0934] By repeating this series of steps, the system learns not only the user's preferences and lifestyle habits, but also their emotional state, allowing it to make more appropriate and personalized suggestions.

[0935] Example 2

[0936] 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."

[0937] Conventional recommendation systems have the problem of low user satisfaction because they do not adequately consider the user's individual needs or real-time emotions when making recommendations. Specifically, they have limited use of profile data and environmental data, and lack the functionality to analyze user emotions and reflect them in recommendations. Furthermore, they lack a means to effectively utilize user feedback to improve the system.

[0938] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0939] In this invention, the server includes means for converting a user's voice input into text, means for transmitting the converted text data, means for analyzing the received text data, means for acquiring the user's profile data, means for acquiring the user's location information and environmental data, means for generating suggestions based on the analyzed data and the acquired profile data and environmental data, means for transmitting the generated suggestions, means for displaying the transmitted suggestions, means for receiving user feedback and updating the profile data, means for analyzing the user's emotions, and means for generating suggestions based on the analyzed user's emotions. This enables the generation of detailed suggestions that take the user's emotions into consideration, thereby improving user satisfaction. Furthermore, by utilizing feedback, the system learns and improves, and even more accurate suggestions can be made in the future.

[0940] "Voice input" refers to voice data provided by the user via a microphone or the like.

[0941] "Means for converting to text" refers to technology or equipment for analyzing voice data and converting it into text information.

[0942] "Text data" refers to digital data obtained by converting voice data into text information.

[0943] A "transmitting means" is any technique or device used to send data over a network to another system or device.

[0944] "Means of analysis" refers to technology or equipment for analyzing text data and understanding the user's intentions and emotions.

[0945] "Profile data" refers to data such as basic information about a user, past behavioral history, and preferences.

[0946] "Location information" refers to data that indicates a user's current location.

[0947] "Environmental data" refers to data that indicates the user's surroundings, including, for example, weather information and information about nearby facilities.

[0948] The "means for generating suggestions" refers to a technology or device that generates suggestions suited to the user based on the analyzed data and the acquired data.

[0949] "Means for displaying" refers to a technique or device for visually presenting generated suggestions to a user.

[0950] "Feedback" refers to opinions and thoughts about suggestions that users provide to the system.

[0951] "Means for updating" refers to the technology or equipment used to modify or add to the contents of the database based on feedback.

[0952] "Means for analyzing emotions" refers to technology or devices for determining emotions from a user's text data or voice data.

[0953] A "means for generating suggestions based on emotions" is a technique or device that takes into account the analyzed emotion data to generate suggestions that are appropriate for the user.

[0954] The present invention relates to a system that takes into account a user's emotions and generates suggestions based on personal information. The system consists of four main components: a server, a terminal, a user, and an emotion analysis engine.

[0955] System Overview

[0956] The user uses voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. The system can further improve its accuracy by providing feedback from the user. A particular feature of this invention is that the emotion analysis engine recognizes the user's emotions and reflects them in the suggestions and feedback.

[0957] Program processing

[0958] Hardware and software used

[0959] 1. A microphone device that allows the user to input voice information.

[0960] 2. Software that allows your device to convert speech to text (e.g., Google Speech-to-Text API).

[0961] 3. A natural language processing (NLP) engine (e.g., spaCy, NLTK) to analyze the text data received by the server.

[0962] 4. A database (e.g., MySQL) where the server stores and retrieves user profile data.

[0963] 5. Third-party APIs (e.g. OpenWeatherMap API) through which the server can obtain environmental data.

[0964] 6. An emotion analysis engine (e.g., Microsoft Azure Emotion API) for the server to perform emotion analysis.

[0965] 7. A generative AI model (e.g., GPT-3) for the server to generate proposals.

[0966] Data processing and calculation

[0967] 1. The device converts voice input into text data.

[0968] Audio waveform data is captured and processed for filtering and noise reduction.

[0969] The filtered voice data is converted into text in real time to generate text data.

[0970] 2. The device sends the text data to the server.

[0971] The text data is packaged in JSON format and sent using the HTTPS protocol.

[0972] 3. The server parses the text data.

[0973] Use a natural language processing (NLP) engine to tokenize text data and analyze user intent.

[0974] Use a sentiment analysis engine to extract sentiment labels from text data.

[0975] 4. The server retrieves the user profile data and environment data.

[0976] Retrieve profile data from a database and environmental data using third-party APIs.

[0977] 5. The server generates a proposal.

[0978] Based on the analyzed and acquired data, an AI model is used to generate optimal recommendations.

[0979] 6. The server sends the generated proposal to the device.

[0980] The proposal results are packaged in JSON format and sent to the terminal.

[0981] 7. The device displays suggestions to the user.

[0982] The proposed results are displayed to the user in a visually easy-to-understand format.

[0983] 8. Users provide feedback on suggestions.

[0984] Feedback is input as text data or audio data.

[0985] 9. The device sends the feedback to the server.

[0986] The feedback data is packaged in JSON format and sent to the server.

[0987] 10. The server analyzes the feedback and updates the profile data.

[0988] Analyze feedback data and update user profile data.

[0989] Use a sentiment analysis engine to extract additional emotional data from the feedback.

[0990] Specific examples

[0991] Example 1: Restaurant suggestions

[0992] 1. The user utters, "What should I eat today?"

[0993] 2. The device converts the speech into text and sends it to the server.

[0994] 3. The server analyzes the question and searches for suitable restaurants based on the user's profile data and location.

[0995] 4. The sentiment analysis engine analyzes the user's emotions and prioritizes restaurants where they can relax, for example, if they are tired.

[0996] 5. The server uses an appropriate AI model to generate a list of relaxing restaurants.

[0997] 6. The server sends the generated proposal to the device, which displays it to the user.

[0998] Example 2: Fashion advice

[0999] 1. The user types into the system, "Please give me some advice on what to wear today."

[1000] 2. The device sends this input to the server.

[1001] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information.

[1002] 4. The emotion analysis engine analyzes the user's emotions and suggests uplifting clothing if, for example, they are feeling down.

[1003] 5. The server sends the generated proposal to the device, which notifies the user.

[1004] Prompt Sentence Examples

[1005] Restaurant Suggestion Prompt

[1006] The user types, "What should I eat today?" In response, the app should suggest a relaxing restaurant based on the user's past eating history, current location, weather information, and data on how tired the user is currently feeling.

[1007] Fashion Advice Prompt

[1008] The user types, "Please give me some advice on what to wear today." In response, the app should suggest an uplifting outfit based on the user's past clothing preferences, current weather information, and data indicating the user is feeling depressed.

[1009] The above is an embodiment of the system of the present invention. This system can generate detailed suggestions that take into account the user's emotions and improve user satisfaction.

[1010] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1011] Step 1: User registration and initial data entry

[1012] When a user first uses the system, they access it and enter a self-introduction and basic information.

[1013] Input: The user enters their name, age, gender, food preferences, allergy information, hobbies, etc.

[1014] Data processing: This information is converted into JSON format by the terminal.

[1015] Output: The data converted to JSON format is sent to the server.

[1016] Step 2: Save your basic information

[1017] The server stores the received user information in a database.

[1018] Input: User information sent from the device in JSON format.

[1019] Data processing: Parse and validate JSON data to ensure there is no invalid data.

[1020] Output: Save the validated data to the database.

[1021] Step 3: Speak your question or request

[1022] Users can ask questions or make requests to the system by voice input.

[1023] Input: Speech data (e.g., "What should I eat today?").

[1024] Data processing: Audio is captured in real time and undergoes filtering and noise reduction.

[1025] Output: The filtered audio data is converted into text data and stored in the device.

[1026] Step 4: Sending text data

[1027] The device converts the voice into text data and sends it to the server.

[1028] Input: Text data generated from audio data.

[1029] Data processing: Packaging text data into JSON format.

[1030] Output: JSON formatted text data is sent to the server.

[1031] Step 5: Analyzing the text data

[1032] The server analyzes the received text data.

[1033] Input: Text data sent from the terminal.

[1034] Data processing: Using a natural language processing (NLP) engine, we tokenize the text data and understand the intent of the question or request.

[1035] Output: The analysis results in user intent and emotional data.

[1036] Step 6: Obtaining profile and environment data

[1037] The server retrieves the user's profile data and environment data.

[1038] Input: User's ID and location information.

[1039] Data Transformation: Query profile data from databases and use third-party APIs to retrieve environmental data.

[1040] Output: The acquired profile data and environmental data are aggregated on the server.

[1041] Step 7: Sentiment Analysis

[1042] The server uses a sentiment analysis engine to analyze the user's sentiment.

[1043] Input: Text and audio data.

[1044] Data processing: Extract emotion labels (e.g., joy, sadness, anger) using a sentiment analysis engine.

[1045] Output: The parsed emotion data is generated.

[1046] Step 8: Generate proposals

[1047] The server generates optimal suggestions based on the analyzed data.

[1048] Input: Acquired profile data, environmental data, parsed emotion data.

[1049] Data processing: Input prompt sentences into a generative AI model (e.g., GPT-3) to generate suggestions.

[1050] Output: The generated proposals are output in JSON format.

[1051] Step 9: Submit your proposal

[1052] The server sends the generated proposal to the terminal.

[1053] Input: Generated proposal data.

[1054] Data processing: The proposed data is packaged in JSON format.

[1055] Output: The proposal data in JSON format is sent to the device.

[1056] Step 10: Viewing Proposals

[1057] The device displays the suggestions to the user.

[1058] Input: Proposal data sent by the server.

[1059] Data Processing: Converting the proposed data into a user-friendly format.

[1060] Output: The proposed results are displayed on the screen.

[1061] Step 11: Enter your feedback

[1062] Users provide feedback on the suggestions.

[1063] Input: Feedback text or audio (e.g., "I tried this restaurant and it was great").

[1064] Data processing: Convert the feedback into text data.

[1065] Output: The converted feedback data is stored in the terminal.

[1066] Step 12: Submit your feedback

[1067] The terminal sends the feedback to the server.

[1068] Input: Feedback text data.

[1069] Data processing: Packaging the feedback data into JSON format.

[1070] Output: Feedback data in JSON format is sent to the server.

[1071] Step 13: Analyze feedback

[1072] The server analyzes the feedback and updates the profile data.

[1073] Input: Feedback data sent from the device.

[1074] Data Processing: Analyzes the feedback data to update user profile data and also uses a sentiment analysis engine to extract additional sentiment data from the feedback.

[1075] Output: Updated profile data is saved to the database.

[1076] The above are the specific processing steps of the system and details of its operation.

[1077] (Application example 2)

[1078] 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."

[1079] Conventional advice-providing systems only provide generic suggestions without considering the user's emotions, making it difficult to provide optimal suggestions that meet the needs of individual users. Furthermore, feedback and profile data updates to improve the accuracy of suggestions were not effectively provided. The present invention aims to solve these problems by providing a system that can analyze a user's emotions and suggest optimal products based on those emotions.

[1080] 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 converting a user's voice input into text, means for transmitting the converted text data, and means for analyzing the received text data. This makes it possible to accurately analyze the received data and generate optimal suggestions based on the user's emotions and profile data.

[1081] The system further includes means for acquiring user profile data, means for acquiring user location and environmental data, and means for generating suggestions based on the analyzed data and the acquired profile and environmental data, thereby enabling suggestions to be provided that are tailored to the user's individual situation.

[1082] The system also includes a means for transmitting the generated proposals, a means for displaying the transmitted proposals, a means for analyzing the user's emotions and reflecting the same in generating proposals and updating the profile data, and a means for using a generative AI model to generate optimal product proposals based on the emotions and profile data, thereby enabling highly accurate proposals incorporating emotion analysis.

[1083] Furthermore, the system includes means for receiving user feedback and updating the profile data, thereby enabling the system to reflect the user feedback and improve the accuracy of suggestions.

[1084] "Means for converting user voice input into text" means a device or software that recognizes a user's voice and converts it into text data.

[1085] The "means for transmitting converted text data" is a network communication device for transmitting the text data converted from the voice to the server.

[1086] The "means for analyzing received text data" refers to a system that analyzes the text data received by the server using techniques such as natural language processing and sentiment analysis.

[1087] "Means for obtaining user profile data" refers to a system for collecting profile data such as a user's personal information and past behavioral history.

[1088] "Means for acquiring user location information and environmental data" refers to technology for collecting information about the user's current location and the surrounding environment (such as the weather).

[1089] A "means for generating suggestions" is an algorithm or model for automatically generating optimal suggestions based on the analyzed data and the acquired profile and environmental data.

[1090] The "means for transmitting the generated proposal" is a communication means for sending the generated proposal to the user's terminal.

[1091] A "means for displaying submitted suggestions" is a device (such as a display) for visually displaying submitted suggestions to a user.

[1092] The "means for analyzing user emotions and reflecting the results in generating suggestions and updating profile data" is a system for analyzing user emotions and using the results in generating suggestions and updating profile data.

[1093] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and generates optimal suggestions based on user emotions and profile data.

[1094] The "means for generating optimal product suggestions" is a mechanism for selecting and suggesting products based on the user's emotions and profile data.

[1095] The "means for receiving user feedback and updating profile data" is a system for collecting user ratings and opinions and updating profile data based on them.

[1096] The present invention relates to a system for virtual stores that makes optimal product suggestions based on a user's personal information and emotional state. This system is composed of the following elements: a means for converting a user's voice input into text, a data transmission means, a text data analysis means, a profile data acquisition means, a location information and environmental data acquisition means, a suggestion generation means, a suggestion transmission means, a suggestion display means, an emotion analysis means, a generative AI model, an optimal product suggestion means, and a feedback reception means.

[1097] Each component of the system operates as follows.

[1098] Voice input and data transmission

[1099] When a user speaks, the device converts the speech into text data using a speech recognition library (e.g., the SpeechRecognition library), which is then sent to the server via the network.

[1100] Data analysis and profile data acquisition

[1101] The server analyzes the received text data and uses natural language processing techniques (e.g., TextBlob) to understand its content. The server also retrieves user profile data (e.g., age, gender, interests) and environmental data (e.g., current location, weather) from a database.

[1102] Sentiment Analysis and Suggestion Generation

[1103] Based on the analyzed text data and the acquired profile data, the server uses a sentiment analysis engine (e.g., TextBlob's sentiment analysis function) to determine the user's sentiment. Based on this sentiment information and profile data, a generative AI model generates optimal product recommendations.

[1104] Submitting and Viewing Proposals

[1105] The generated proposal is sent to the user's terminal via the proposal sending means and displayed on the terminal's display, allowing the user to check the proposed products in the virtual store.

[1106] Feedback and profile data updates

[1107] The feedback provided by the user is then sent back from the device to the server, which analyzes it and updates the profile data, thereby improving the accuracy of future suggestions.

[1108] Specific examples

[1109] 1. User: "I've been feeling stressed lately. Can you suggest some products that will help me relax?"

[1110] 2. System: Converts speech into text and analyzes it. The emotion analysis engine determines the user's emotion as negative.

[1111] 3. The server suggests relaxation products based on the user's profile data and emotional information.

[1112] 4. Device: Show users relaxation products such as "aromatherapy sets" and "massage devices."

[1113] 5. User: "This suggestion is very helpful" provides feedback.

[1114] 6. The server receives the feedback and updates the profile data.

[1115] Prompt Sentence Examples

[1116] Input prompt: "I've been feeling stressed lately. Can you suggest some products that will help me relax?"

[1117] Input to generative AI model: "User's sentiment is negative. Suggest products that will help them relax. User's interests are not related to fitness."

[1118] In this way, the present invention provides a system that can make highly accurate product suggestions by taking into account the user's emotions and personal information.

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

[1120] Step 1:

[1121] The user performs voice input. The device captures the user's voice through the microphone. This voice data is used as input and converted into text data using a speech recognition library. The converted text data is generated as output.

[1122] Step 2:

[1123] The converted text data is sent to the server. The device uses a network communication module to send the text data to the server, along with metadata such as the user's ID information.

[1124] Step 3:

[1125] The server parses the received text data, uses a natural language processing library (e.g., TextBlob) to understand the meaning of the text data and extract the user's intent, and generates the results of the parsing as output.

[1126] Step 4:

[1127] The server retrieves the user's profile data from the database, which includes the user's basic information, past behavior history, interests, etc. After receiving this profile data as input, it is used for the next analysis step.

[1128] Step 5:

[1129] The server obtains the user's location and environmental data. Location information is obtained from GPS data, and environmental data such as weather and time of day is obtained from an API. These data are used as inputs to generate the next proposal.

[1130] Step 6:

[1131] Using the sentiment analysis engine, the server analyzes the user's sentiment from the text data. It uses the sentiment analysis function of TextBlob to classify the user's sentiment as positive, negative, or neutral. It generates this sentiment data as output.

[1132] Step 7:

[1133] Using a generative AI model, the server generates optimal product suggestions based on the user's profile data, location information, environmental data, and emotional data. The AI ​​model is trained from past data and generates suggestions based on prompts. This suggestion data is generated as output.

[1134] Step 8:

[1135] The generated proposal is transmitted to the user's terminal. The server uses a communication module to transmit the generated proposal data to the user's terminal. The transmitted proposal data is displayed on the user's terminal.

[1136] Step 9:

[1137] The user provides feedback. The user inputs their evaluation or opinion on the provided suggestion by voice or text. The device sends this feedback data to the server.

[1138] Step 10:

[1139] The server analyzes the user's feedback and updates the profile data. The feedback analysis converts the user's ratings into text data, and the server updates the user's profile data based on the text data. This updated data is used to generate suggestions from the next time onwards.

[1140] 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.

[1141] 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.

[1142] 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.

[1143] [Third embodiment]

[1144] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1145] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1146] 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).

[1147] 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.

[1148] 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.

[1149] 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).

[1150] 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.

[1151] 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.

[1152] 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.

[1153] 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.

[1154] 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.

[1155] 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."

[1156] This invention relates to a system that learns a user's personal information and provides various daily advice based on that information. This system consists of three main components: a server, a terminal, and the user.

[1157] System Overview

[1158] Users use voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. User feedback allows the system to further improve its accuracy.

[1159] Program processing

[1160] The system operates sequentially as follows:

[1161] User registration and initial data entry

[1162] When a user first uses the system, they register and enter a self-introduction and basic information. This information is sent to the server by the device and stored in a database as profile data.

[1163] Continuous data collection and analysis

[1164] In everyday life, users ask questions or make requests to the system. For example, they might say, "What should I eat today?" The device converts this speech into text data and sends it to the server. The server then uses a natural language processing (NLP) engine to analyze this text data and understand the user's intent.

[1165] Next, the server retrieves the user's profile data from the database, including the user's past behavioral history, preferences, allergy information, etc. Additionally, the server retrieves the user's current location, weather information, and other environmental data.

[1166] Proposal generation and presentation

[1167] The server uses AI models based on this data to generate optimal suggestions. For example, if a user wants a low-calorie meal, the server searches for appropriate restaurants and generates a suggestion such as, "We recommend a nearby low-calorie restaurant called 'Healthy Dinner.'" This suggestion is then displayed to the user via their device.

[1168] Feedback and Learning

[1169] The user provides feedback on the suggestions to the system. For example, they might input feedback like, "I tried this restaurant and it was great." The device then sends this feedback to the server, which analyzes it and updates the user's profile data. Through this process, the system gains a more accurate understanding of the user's preferences and tendencies, improving the accuracy of future suggestions.

[1170] Specific examples

[1171] Example 1: Restaurant suggestions

[1172] 1. The user utters, "What should I eat today?"

[1173] 2. The device converts the speech into text and sends it to the server.

[1174] 3. The server analyzes the question and searches for suitable restaurants based on the user's profile data and location.

[1175] 4. The server sends the generated proposal to the device, which displays it to the user.

[1176] Example 2: Fashion advice

[1177] 1. The user types into the system, "Please give me some advice on what to wear today."

[1178] 2. The device sends this input to the server.

[1179] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information.

[1180] 4. The server sends the generated proposal to the device, which notifies the user.

[1181] As described above, the system of the present invention can provide accurate advice to the user in various situations throughout his or her life, thereby improving the quality of the user's life.

[1182] The processing flow will be explained below.

[1183] Step 1:

[1184] The user voice-inputs, "What should I eat today?"

[1185] Step 2:

[1186] The device converts voice input into text data in real time.

[1187] Step 3:

[1188] The terminal sends the converted text data to the server along with the user ID.

[1189] Step 4:

[1190] The text data received by the server is analyzed using a natural language processing (NLP) engine.

[1191] Specifically, it extracts the user's intent from text data and understands that the user is looking for suggestions on what to eat today.

[1192] Step 5:

[1193] The server retrieves the user's profile data (past dietary history, preferences, allergy information, etc.) from the database.

[1194] Step 6:

[1195] The server retrieves current location and environmental data (weather, time, etc.) from an external API.

[1196] Step 7:

[1197] The server uses AI models to generate restaurant suggestions based on the parsed data, retrieved profile data, and environmental data.

[1198] Specifically, the system searches for restaurants that meet certain criteria, such as "close to the user's location" and "have low-calorie menu items."

[1199] Step 8:

[1200] The server generates a list of restaurant suggestions that are optimized based on the user's profile data and past feedback.

[1201] Specifically, highly rated restaurants and restaurants that users have previously liked will be placed at the top of the list.

[1202] Step 9:

[1203] The server sends optimized restaurant suggestions in JSON format to the device.

[1204] Step 10:

[1205] The device displays the received proposal data to the user.

[1206] Specifically, the screen will display, "We recommend a nearby low-calorie restaurant called 'Healthy Dinner'."

[1207] Step 11:

[1208] The user enters feedback on the suggestion (e.g., "I tried this restaurant and it was great").

[1209] Step 12:

[1210] The device sends the user's feedback to the server.

[1211] Step 13:

[1212] The server analyzes the received feedback and updates the user's profile data.

[1213] Specifically, it will set the restaurant's rating to "good" and prioritize similar restaurants in future suggestions.

[1214] By repeating this series of steps, the system learns the user's preferences and lifestyle habits and can make more appropriate and personalized suggestions.

[1215] Example 1

[1216] 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."

[1217] Conventional technologies generally provide suggestions and advice to users, but have the problem of not being able to fully address the individual needs and preferences of each user. In particular, there is a need for a system that can efficiently and accurately process users' voice input and, based on the results, generate optimal suggestions that reflect the user's profile data and environmental data.

[1218] 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.

[1219] In this invention, the server includes means for converting a user's voice input into text data, means for transmitting the converted text data, means for analyzing the received text data, means for acquiring user profile data, means for acquiring user location data and environmental data, means for generating suggestions using a generative AI model based on the analyzed text data and the acquired profile data and environmental data, means for transmitting the generated suggestions, means for displaying the transmitted suggestions, and means for receiving user feedback and updating the profile data, thereby enabling accurate suggestions to be made in accordance with each user's individual needs and preferences.

[1220] A "user" is someone who uses the system to provide voice input and receive suggestions and advice.

[1221] "Voice input" refers to the act of a user asking a question or making a request to a system by voice.

[1222] "Text data" is character information converted from voice input.

[1223] "Means for converting" refers to the technology or algorithm used to convert voice input into text data.

[1224] "Transmission means" refers to the communication technology or protocol used to transmit text data to the server.

[1225] The "receiving means" is a means by which the server receives text data sent from the terminal.

[1226] "Means of analysis" refers to the technology and algorithms used to understand the received text data and grasp the user's intent.

[1227] "Profile data" refers to individual data such as a user's basic information, past behavioral history, preferences, and allergy information.

[1228] "Means of acquisition" refers to the technology or protocol used to acquire the required data from a database or external system.

[1229] "Environmental data" refers to data about the user's environment, such as the user's current location and weather information.

[1230] A "generative AI model" is an artificial intelligence model that generates optimal suggestions based on user data.

[1231] The "means for generating suggestions" is a generative AI model that runs on the basis of the analyzed text data and the acquired profile and environmental data.

[1232] "Displaying means" refers to the techniques or methods for presenting the generated suggestions to the user.

[1233] "Feedback" refers to the evaluation or opinion that a user gives to the system after receiving a suggestion.

[1234] "Means for receiving feedback" refers to the means for collecting feedback from users.

[1235] An "updating means" is a technique or algorithm for correcting or adding to profile data based on feedback received.

[1236] This invention relates to a system that learns a user's personal information and provides various daily advice using a generative AI model. This system consists of three main components: a server, a terminal, and the user.

[1237] System Overview

[1238] Users use voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. User feedback allows the system to further improve its accuracy.

[1239] Hardware and Software Configuration

[1240] This system uses the following hardware and software:

[1241] 1. Device:

[1242] Smartphone (iOS, Android)

[1243] Smart speakers (voice assistant devices for the general home)

[1244] 2. Server:

[1245] Cloud services (AWS, Azure, Google Cloud)

[1246] 3. Natural Language Processing (NLP) Engine:

[1247] OpenAI GPT

[1248] Google NLP API

[1249] 4. Database:

[1250] MySQL

[1251] PostgreSQL

[1252] What the program does

[1253] This system performs the following processes sequentially.

[1254] User registration and initial data entry

[1255] When a user first uses the system, they register and enter a self-introduction and basic information. The device sends this input data to the server, which then stores it in a database. For example, a user might install an app and enter their name, age, gender, allergy information, etc.

[1256] Voice to text conversion

[1257] The user can ask a question or make a request by voice. For example, they can say, "What should I eat today?" The device converts the voice into text using voice recognition technology such as the Google Speech-to-Text API and sends this text data to the server.

[1258] Text analysis and suggestion generation

[1259] The server uses an NLP engine such as OpenAI GPT to analyze the received text data. Based on the analysis results, the user's profile data and environmental data (such as current location and weather information) are retrieved from a database, and based on this, a generative AI model is used to generate optimal suggestions. An example of a prompt sentence is, "I'm looking for a low-calorie meal. Can you recommend any restaurants?"

[1260] Submitting suggestions and providing feedback

[1261] The generated suggestions are sent from the server to the device and displayed to the user through the device. For example, a suggestion such as "We recommend a nearby low-calorie restaurant for a healthy dinner" may be displayed. The user enters feedback on the suggestions, and the device sends the feedback to the server. The server analyzes the feedback and updates the user's profile data. This feedback improves the accuracy of future suggestions.

[1262] Specific examples

[1263] Specific examples of how this system can be used include:

[1264] Example 1: Restaurant suggestions

[1265] 1. The user utters, "What should I eat today?"

[1266] 2. The device converts the speech into text and sends it to the server.

[1267] 3. The server analyzes the question and searches for appropriate restaurants based on the user's profile data and location, using a generative AI model to generate a suggestion such as "Recommend a nearby low-calorie restaurant for a healthy dinner."

[1268] 4. The server sends the generated proposal to the device, which displays it to the user.

[1269] Example 2: Fashion advice

[1270] 1. The user types into the system, "Please give me some advice on what to wear today."

[1271] 2. The device sends this input to the server.

[1272] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information, for example, "It's raining today, so I recommend a raincoat and waterproof shoes."

[1273] 4. The server sends the generated proposal to the device, which notifies the user.

[1274] As described above, the system of the present invention provides accurate advice that corresponds to the individual needs and environment of the user, thereby improving the quality of life of the user.

[1275] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1276] Step 1:

[1277] When a user first uses the system, they register and enter basic information. The user then installs the app and enters their name, age, gender, allergy information, etc.

[1278] Input: User's basic information (name, age, gender, allergy information, etc.)

[1279] Data processing / calculation: Basic information entered is collected

[1280] Output: Basic information dataset

[1281] Step 2:

[1282] The device sends the user's basic information to the server. The device sends the basic information dataset to the server using an HTTP request.

[1283] Input: User basic information dataset

[1284] Data processing / calculation: Convert basic information dataset into HTTP request

[1285] Output: Send request

[1286] Step 3:

[1287] The server receives the basic information and stores it in a database. The server receives the basic information dataset and stores it in a database (MySQL or PostgreSQL).

[1288] Input: Basic information dataset

[1289] Data processing / calculation: Inserting basic information datasets into the database

[1290] Output: Basic information stored in the database

[1291] Step 4:

[1292] The user asks a question or makes a request by voice, for example, "What should I eat today?"

[1293] Input: User voice input

[1294] Data processing / calculation: Collection of voice data

[1295] Output: Audio data

[1296] Step 5:

[1297] The device converts voice input into text data. The device converts voice data into text data using speech recognition technology such as the Google Speech-to-Text API.

[1298] Input: Audio data

[1299] Data processing / calculation: Converting voice data into text data

[1300] Output: Text data

[1301] Step 6:

[1302] The device sends text data to the server. The device sends text data to the server using an HTTP request.

[1303] Input: Text data

[1304] Data processing / calculation: Convert text data into a transmission request

[1305] Output: Send request

[1306] Step 7:

[1307] The server analyzes the received text data. The server uses an NLP engine such as OpenAI GPT to analyze the text data and understand the user's intent.

[1308] Input: Text data

[1309] Data processing / calculation: Text analysis using NLP engines

[1310] Output: Analysis results

[1311] Step 8:

[1312] The server retrieves the user's profile data and environmental data. The server retrieves the user's profile data (past behavioral history, preferences, allergy information, etc.) from the database, and collects environmental data using GPS data and weather information APIs.

[1313] Input: Analysis results

[1314] Data manipulation / computation: database queries and API requests

[1315] Output: Profile data and environment data

[1316] Step 9:

[1317] The server generates suggestions using a generative AI model. Based on the analysis results and the acquired profile and environmental data, the server inputs prompt sentences into the generative AI model to generate optimal suggestions.

[1318] Input: Analysis results, profile data, environmental data

[1319] Data processing / calculation: Proposal generation using generative AI models

[1320] Output: Proposal

[1321] Step 10:

[1322] The server sends the generated proposal to the device using an HTTP request.

[1323] Input: Proposal

[1324] Data processing / calculation: Converting proposals into submission requests

[1325] Output: Send request

[1326] Step 11:

[1327] Display suggestions received by the device to the user, using notifications and / or in-app displays to inform the user about the suggestions.

[1328] Input: Proposal

[1329] Data processing / calculation: Displaying proposals in the user interface

[1330] Output: User notification

[1331] Step 12:

[1332] The user enters feedback on the proposal. The user enters their evaluation and opinion on the proposal.

[1333] Input: User feedback

[1334] Data processing / calculation: Gathering feedback

[1335] Output: Feedback data

[1336] Step 13:

[1337] The device sends the feedback to the server. It uses an HTTP request to send the feedback data to the server.

[1338] Input: Feedback data

[1339] Data processing / calculation: Convert feedback data into transmission requests

[1340] Output: Send request

[1341] Step 14:

[1342] The server analyzes the feedback and updates the user's profile data. The server analyzes the feedback with its NLP engine and modifies or adds to the profile data.

[1343] Input: Feedback data

[1344] Data processing / calculation: Feedback analysis and database updates

[1345] Output: Updated profile data

[1346] These processing steps allow the system to provide accurate suggestions tailored to the user's individual needs and preferences, and to improve its accuracy as feedback is received.

[1347] (Application example 1)

[1348] 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."

[1349] One issue with virtual stores is that it is difficult for users to select the most suitable products without trying them on in person. Furthermore, there is a lack of systems that can make appropriate product recommendations based on users' preferences and past purchase history. This can lead to users being unable to make satisfactory product selections, which can lead to a decline in customer satisfaction.

[1350] 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.

[1351] In this invention, the server includes means for converting a user's voice input into text, means for transmitting the converted text data, means for analyzing the received text data, means for acquiring user profile data, means for acquiring user location information and environmental data, means for generating optimal proposals using a generative AI model based on the analyzed data and the acquired profile data and environmental data, means for transmitting the generated proposals, means for displaying the transmitted proposals, means for receiving user feedback and updating the profile data, and means for making optimal product proposals in a virtual store based on the user's profile data. This allows the user to receive optimal product proposals in the virtual store and select products without trying them on.

[1352] "User" refers to an individual who uses the System.

[1353] "Voice input" refers to a method in which a user provides information to a system by speaking.

[1354] "Means for converting to text" refers to a device or software that implements the process of converting voice input into text data.

[1355] "Text data" refers to data that has been converted from voice input into text information.

[1356] "Means for sending" refers to a device or software that implements the process of sending text data to another system, such as a server.

[1357] "Means for analyzing" refers to a device or software that realizes the process of understanding the content of the transmitted text data and extracting the necessary information.

[1358] "Profile data" refers to data such as a user's personal information, past behavioral history, and preferences.

[1359] "Means of collection" refers to the device or software that enables the process of collecting profile data, location information, and environmental data.

[1360] "Location Information" means information that indicates a User's current geographic location.

[1361] "Environmental data" refers to information about the user's environment, such as weather, temperature, and surrounding conditions.

[1362] A "generative AI model" refers to an algorithm or software that generates optimal suggestions based on a user's preferences and environment.

[1363] "Means for generating suggestions" refers to a device or software that enables the process of creating the most suitable suggestions for the user based on the analyzed data and / or acquired profile data.

[1364] "Means for displaying submitted suggestions" refers to a device or software that implements the process of visually presenting generated suggestions to a user.

[1365] "Feedback" refers to the opinions and evaluations that users provide to the system.

[1366] "Means for updating" refers to the device or software that enables the process of changing or adding profile data based on feedback.

[1367] A "virtual store" refers to a virtual commercial facility where users can browse, select, and purchase products online.

[1368] "Product Suggestions" refers to product information recommended to users based on their preferences and profile data.

[1369] "Means for viewing products without trying them on" refers to devices or software that enable a user to visually view product displays and descriptions without physically handling or trying on the product.

[1370] This invention relates to a system that proposes optimal products in a virtual store based on the user's personal information and environmental data. This system consists of three main elements: the user, a smart device (such as smart glasses), and a server.

[1371] System Overview

[1372] Wearing smart glasses, users walk around the virtual store and ask questions or make requests about products by voice. The smart glasses convert this voice input into text data and send it to the server. The server analyzes the received text data and generates optimal product suggestions using the user's profile data and environmental data. These suggestions are presented to the user through the smart glasses' display. The system continues to improve based on user feedback, providing a superior customer experience.

[1373] A natural language description of the program's operation

[1374] Hardware / Software Used

[1375] Smart glasses: Google Glass, Microsoft HoloLens

[1376] Speech recognition engine: Google Speech-to-Text API

[1377] NLP engine: Google Cloud Natural Language

[1378] Generative AI models: TensorFlow, PyTorch

[1379] Database: MySQL, MongoDB

[1380] Program processing steps

[1381] 1. Handling voice input:

[1382] The server receives the voice data sent from the smart glasses and converts it into text data using a voice recognition engine. Through this process, the user's speech is stored as text information on the server.

[1383] 2. Text data analysis:

[1384] The server uses an NLP engine to analyze the content of the text data and understand the user's intent and the type of question.

[1385] 3. Acquire profile and environmental data:

[1386] The server retrieves user profile data (past purchase history, preferences, etc.) and environmental data (location, weather information, etc.) from a database.

[1387] 4. Proposal generation using generative AI model:

[1388] The server uses a generative AI model based on this data to generate optimal product suggestions for the user, for example recommending specific products based on past purchase history and preferences.

[1389] 5. Show suggestions:

[1390] The server sends the generated proposal data to the smart glasses, and the proposals are displayed on the glasses' display.

[1391] 6. Feedback Processing:

[1392] The server receives feedback from users and updates the user profile data based on that feedback, improving the accuracy of future suggestions.

[1393] Specific examples

[1394] Example 1: Clothing suggestions

[1395] 1. A user points to a specific product in a virtual store and says, "Write a review for this jacket."

[1396] 2. The smart glasses convert the speech into text and send it to the server.

[1397] 3. The server analyzes the text data and generates the most appropriate review based on the user's profile data (similar jackets purchased in the past and preferred colors).

[1398] 4. The smart glasses will display the suggestions on the screen.

[1399] Prompt Sentence Examples

[1400] "Write a review about this product"

[1401] "Generate optimal product suggestions based on user profile data."

[1402] In this way, the system of the present invention can provide real-time and personalized product suggestions to users within the virtual store, greatly improving the user experience.

[1403] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1404] Step 1:

[1405] The user provides voice input. The user points to a specific product in the virtual store and says, "Please give me a review of this jacket." The microphone in the smart glasses captures this voice and stores it as voice data. The input is the user's voice data, and the output is the captured voice data.

[1406] Step 2:

[1407] The device converts the voice data into text data. The voice recognition engine (Google Speech-to-Text API) analyzes the voice data and converts it into text data. The input is voice data and the output is text data. Specifically, the voice recognition engine analyzes the user's speech and generates a corresponding string of characters.

[1408] Step 3:

[1409] The terminal transmits the converted text data to the server, where the text data is sent to the server via network communication. The input is the text data, and the output is the text data transmitted to the server.

[1410] Step 4:

[1411] The server analyzes the received text data. The NLP engine (Google Cloud Natural Language) analyzes the text data to understand the user's intent and the type of question. The input is text data, and the output is the analysis results (user's intent and type of question). Specifically, the NLP engine analyzes the text data grammatically and semantically to extract key keywords and content.

[1412] Step 5:

[1413] The server retrieves the user's profile data and environmental data. It retrieves the user's past purchase history, preferences, location information, and environmental data (weather and surrounding conditions) from the database. The input is the analysis result, and the output is the user's profile data and environmental data. Specifically, the server executes a database query to retrieve the required data.

[1414] Step 6:

[1415] The server uses a generative AI model to generate optimal proposals. Based on the acquired profile data and environmental data, an AI model (TensorFlow or PyTorch) is used to generate optimal product proposals for the user. The input is the profile data and environmental data, and the output is the generated proposal. Specifically, the AI ​​model analyzes the data and selects the optimal product.

[1416] Step 7:

[1417] The server sends the generated proposal to the terminal. The server sends the proposal data to the smart glasses, which then transmits it over the network. The input is the generated proposal, and the output is the transmitted proposal.

[1418] Step 8:

[1419] The terminal displays the sent suggestion. The suggestion is displayed on the display of the smart glasses. The input is the sent suggestion, and the output is the suggestion displayed on the display. As a specific operation, the display visually displays the suggestion.

[1420] Step 9:

[1421] Collect user feedback and send it to the server. Users can voice-input their feedback about the proposed products, which the smart glasses will capture and convert into text. The input is the user's voice feedback, and the output is text feedback.

[1422] Step 10:

[1423] The server updates the profile data based on the feedback. It analyzes the user's feedback and improves the profile data. The input is text feedback and the output is updated profile data. Specifically, the server analyzes the feedback and updates the user profile appropriately.

[1424] 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.

[1425] This invention relates to a system that learns a user's personal information and provides various daily advice based on it. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[1426] System Overview

[1427] The user uses voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. The system can further improve its accuracy by providing feedback from the user. A particular feature of this invention is that the emotion engine recognizes the user's emotions and reflects them in the suggestions and feedback.

[1428] Program processing

[1429] The system operates sequentially as follows:

[1430] User registration and initial data entry

[1431] When a user first uses the system, they register and enter a self-introduction and basic information. This information is sent to the server by the device and stored in a database as profile data.

[1432] Continuous data collection and analysis

[1433] In everyday life, users ask questions or make requests to the system. For example, they might say, "What should I eat today?" The device converts this speech into text data and sends it to the server. The server then uses a natural language processing (NLP) engine to analyze this text data and understand the user's intent.

[1434] Next, the server retrieves the user's profile data from the database, including the user's past behavioral history, preferences, allergy information, etc. Additionally, the server retrieves the user's current location, weather information, and other environmental data.

[1435] Utilizing the Emotion Engine

[1436] The server uses an emotion engine to recognize the user's emotions based on the text and voice data, and this emotion information is used to generate suggestions and update the user profile.

[1437] Proposal generation and presentation

[1438] The server uses an AI model based on the analyzed data, acquired profile data, and environmental data, as well as the user's recognized emotions, to generate optimal suggestions. For example, if the user is emotionally exhausted, it may suggest a relaxing restaurant. These suggestions are displayed to the user through their device.

[1439] Feedback and Learning

[1440] The user provides feedback on the suggestions to the system. For example, the user can input feedback such as "I tried this restaurant and it was good." The device then sends this feedback to the server, which analyzes it and updates the user's profile data. The emotion engine also uses the feedback to learn the user's emotional tendencies. Through this process, the system gains a more accurate understanding of the user's preferences and tendencies, improving the accuracy of future suggestions.

[1441] Specific examples

[1442] Example 1: Restaurant suggestions

[1443] 1. The user utters, "What should I eat today?"

[1444] 2. The device converts the speech into text and sends it to the server.

[1445] 3. The server analyzes the question and searches for suitable restaurants based on the user's profile data and location.

[1446] 4. The emotion engine analyzes the user's emotions and prioritizes restaurants where they can relax, for example, if they are tired.

[1447] 5. The server sends the generated proposal to the device, which displays it to the user.

[1448] Example 2: Fashion advice

[1449] 1. The user types into the system, "Please give me some advice on what to wear today."

[1450] 2. The device sends this input to the server.

[1451] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information.

[1452] 4. The emotion engine analyzes the user's emotions and suggests uplifting clothing if, for example, they are feeling down.

[1453] 5. The server sends the generated proposal to the device, which notifies the user.

[1454] As described above, the system of the present invention can provide accurate advice in various situations throughout the user's life, and can improve the quality of life by taking into consideration the user's emotions in particular.

[1455] The processing flow will be explained below.

[1456] Processing steps of the invention combined with an emotion engine that recognizes user emotions

[1457] Step 1:

[1458] The user voice-inputs, "What should I eat today?"

[1459] Step 2:

[1460] The device converts voice input into text data in real time.

[1461] Step 3:

[1462] The terminal sends the converted text data to the server along with the user ID.

[1463] Step 4:

[1464] The text data received by the server is analyzed using a natural language processing (NLP) engine.

[1465] Specifically, it extracts the user's intent from text data and understands that the user is looking for suggestions on what to eat today.

[1466] Step 5:

[1467] The server uses an emotion engine to recognize the user's emotion from the received text data and voice data.

[1468] Specifically, it analyzes the user's emotional state (e.g., tiredness, joy, stress) from the tone of voice and text content.

[1469] Step 6:

[1470] The server retrieves the user's profile data (past dietary history, preferences, allergy information, etc.) from the database.

[1471] Step 7:

[1472] The server retrieves the user's current location and environmental data (weather, time, etc.) from an external API.

[1473] Step 8:

[1474] The server uses AI models to generate restaurant suggestions based on the parsed data, captured profile data, environmental data, and perceived user sentiment.

[1475] Specifically, the app searches for restaurants that meet criteria such as "close to the user's location," "have low-calorie menu items," and "have a relaxing atmosphere."

[1476] Step 9:

[1477] The server generates a list of restaurant suggestions that are optimized based on the user's profile data and past feedback.

[1478] Specifically, highly rated restaurants and restaurants that users have previously liked will be placed at the top of the list.

[1479] Step 10:

[1480] The server sends optimized restaurant suggestions in JSON format to the device.

[1481] Step 11:

[1482] The device displays the received proposal data to the user.

[1483] Specifically, the screen will display, "We recommend a nearby low-calorie restaurant called 'Healthy Dinner'."

[1484] Step 12:

[1485] The user enters feedback on the suggestion (e.g., "I tried this restaurant and it was great").

[1486] Step 13:

[1487] The device sends the user's feedback to the server.

[1488] Step 14:

[1489] The server analyzes the received feedback and updates the user's profile data and the learning data of the emotion engine.

[1490] Specifically, it marks the restaurant as "good" and prioritizes similar restaurants in future suggestions, while also improving the accuracy of its sentiment engine based on user feedback.

[1491] By repeating this series of steps, the system learns not only the user's preferences and lifestyle habits, but also their emotional state, allowing it to make more appropriate and personalized suggestions.

[1492] Example 2

[1493] 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."

[1494] Conventional recommendation systems have the problem of low user satisfaction because they do not adequately consider the user's individual needs or real-time emotions when making recommendations. Specifically, they have limited use of profile data and environmental data, and lack the functionality to analyze user emotions and reflect them in recommendations. Furthermore, they lack a means to effectively utilize user feedback to improve the system.

[1495] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1496] In this invention, the server includes means for converting a user's voice input into text, means for transmitting the converted text data, means for analyzing the received text data, means for acquiring user profile data, means for acquiring user location information and environmental data, means for generating suggestions based on the analyzed data and the acquired profile data and environmental data, means for transmitting the generated suggestions, means for displaying the transmitted suggestions, means for receiving user feedback and updating the profile data, means for analyzing user emotions, and means for generating suggestions based on the analyzed user emotions. This enables the generation of detailed suggestions that take user emotions into consideration, thereby improving user satisfaction. Furthermore, by utilizing feedback, the system learns and improves, and even more accurate suggestions can be made in the future.

[1497] "Voice input" refers to voice data provided by the user via a microphone or the like.

[1498] "Means for converting to text" refers to technology or equipment for analyzing voice data and converting it into text information.

[1499] "Text data" refers to digital data obtained by converting voice data into text information.

[1500] A "transmitting means" is any technique or device used to send data over a network to another system or device.

[1501] "Means of analysis" refers to technology or equipment for analyzing text data and understanding the user's intentions and emotions.

[1502] "Profile data" refers to data such as basic information about a user, past behavioral history, and preferences.

[1503] "Location information" refers to data that indicates a user's current location.

[1504] "Environmental data" refers to data that indicates the user's surroundings, including, for example, weather information and information about nearby facilities.

[1505] The "means for generating suggestions" refers to a technology or device that generates suggestions suited to the user based on the analyzed data and the acquired data.

[1506] "Means for displaying" refers to a technique or device for visually presenting generated suggestions to a user.

[1507] "Feedback" refers to opinions and thoughts about suggestions that users provide to the system.

[1508] "Means for updating" refers to the technology or equipment used to modify or add to the contents of the database based on feedback.

[1509] "Means for analyzing emotions" refers to technology or devices for determining emotions from a user's text data or voice data.

[1510] A "means for generating suggestions based on emotions" is a technique or device that takes into account the analyzed emotion data to generate suggestions that are appropriate for the user.

[1511] The present invention relates to a system that takes into account a user's emotions and generates suggestions based on personal information. The system consists of four main components: a server, a terminal, a user, and an emotion analysis engine.

[1512] System Overview

[1513] The user uses voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. The system can further improve its accuracy by providing feedback from the user. A particular feature of this invention is that the emotion analysis engine recognizes the user's emotions and reflects them in the suggestions and feedback.

[1514] Program processing

[1515] Hardware and software used

[1516] 1. A microphone device that allows the user to input voice information.

[1517] 2. Software that allows your device to convert speech to text (e.g., Google Speech-to-Text API).

[1518] 3. A natural language processing (NLP) engine (e.g., spaCy, NLTK) to analyze the text data received by the server.

[1519] 4. A database (e.g., MySQL) where the server stores and retrieves user profile data.

[1520] 5. Third-party APIs (e.g. OpenWeatherMap API) through which the server can obtain environmental data.

[1521] 6. An emotion analysis engine (e.g., Microsoft Azure Emotion API) for the server to perform emotion analysis.

[1522] 7. A generative AI model (e.g., GPT-3) for the server to generate proposals.

[1523] Data processing and data calculation

[1524] 1. The device converts voice input into text data.

[1525] Audio waveform data is captured and processed for filtering and noise reduction.

[1526] The filtered voice data is converted into text in real time to generate text data.

[1527] 2. The device sends the text data to the server.

[1528] The text data is packaged in JSON format and sent using the HTTPS protocol.

[1529] 3. The server parses the text data.

[1530] Use a natural language processing (NLP) engine to tokenize text data and analyze user intent.

[1531] Use a sentiment analysis engine to extract sentiment labels from text data.

[1532] 4. The server retrieves the user profile data and environment data.

[1533] Retrieve profile data from a database and environmental data using third-party APIs.

[1534] 5. The server generates a proposal.

[1535] Based on the analyzed and acquired data, an AI model is used to generate optimal recommendations.

[1536] 6. The server sends the generated proposal to the device.

[1537] The proposal results are packaged in JSON format and sent to the terminal.

[1538] 7. The device displays suggestions to the user.

[1539] The proposed results are displayed to the user in a visually easy-to-understand format.

[1540] 8. Users provide feedback on suggestions.

[1541] Feedback is input as text data or audio data.

[1542] 9. The device sends the feedback to the server.

[1543] The feedback data is packaged in JSON format and sent to the server.

[1544] 10. The server analyzes the feedback and updates the profile data.

[1545] Analyze feedback data and update user profile data.

[1546] Use a sentiment analysis engine to extract additional emotional data from the feedback.

[1547] Specific examples

[1548] Example 1: Restaurant suggestions

[1549] 1. The user utters, "What should I eat today?"

[1550] 2. The device converts the speech into text and sends it to the server.

[1551] 3. The server analyzes the question and searches for suitable restaurants based on the user's profile data and location.

[1552] 4. The sentiment analysis engine analyzes the user's emotions and prioritizes restaurants where they can relax, for example, if they are tired.

[1553] 5. The server uses an appropriate AI model to generate a list of relaxing restaurants.

[1554] 6. The server sends the generated proposal to the device, which displays it to the user.

[1555] Example 2: Fashion advice

[1556] 1. The user types into the system, "Please give me some advice on what to wear today."

[1557] 2. The device sends this input to the server.

[1558] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information.

[1559] 4. The emotion analysis engine analyzes the user's emotions and suggests clothing that will cheer them up, for example, if they are feeling down.

[1560] 5. The server sends the generated proposal to the device, which notifies the user.

[1561] Prompt Sentence Examples

[1562] Restaurant Suggestion Prompt

[1563] The user types, "What should I eat today?" In response, the app should suggest a relaxing restaurant based on the user's past eating history, current location, weather information, and data on how tired the user is currently feeling.

[1564] Fashion Advice Prompt

[1565] The user types, "Please give me some advice on what to wear today." In response, the app should suggest an uplifting outfit based on the user's past clothing preferences, current weather information, and data indicating the user is feeling depressed.

[1566] The above is an embodiment of the system of the present invention. This system can generate detailed suggestions that take into account the user's emotions and improve user satisfaction.

[1567] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1568] Step 1: User registration and initial data entry

[1569] When a user first uses the system, they access it and enter a self-introduction and basic information.

[1570] Input: The user enters their name, age, gender, food preferences, allergy information, hobbies, etc.

[1571] Data processing: This information is converted into JSON format by the terminal.

[1572] Output: The data converted to JSON format is sent to the server.

[1573] Step 2: Save your basic information

[1574] The server stores the received user information in a database.

[1575] Input: User information sent from the device in JSON format.

[1576] Data processing: Parse and validate JSON data to ensure there is no invalid data.

[1577] Output: Save the validated data to the database.

[1578] Step 3: Speak your question or request

[1579] Users can ask questions or make requests to the system by voice input.

[1580] Input: Speech data (e.g., "What should I eat today?").

[1581] Data processing: Audio is captured in real time and undergoes filtering and noise reduction.

[1582] Output: The filtered audio data is converted into text data and stored in the device.

[1583] Step 4: Sending text data

[1584] The device converts the voice into text data and sends it to the server.

[1585] Input: Text data generated from audio data.

[1586] Data processing: Packaging text data into JSON format.

[1587] Output: JSON formatted text data is sent to the server.

[1588] Step 5: Analyzing the text data

[1589] The server analyzes the received text data.

[1590] Input: Text data sent from the terminal.

[1591] Data processing: Using a natural language processing (NLP) engine, we tokenize the text data and understand the intent of the question or request.

[1592] Output: The analysis results in user intent and emotional data.

[1593] Step 6: Obtaining profile and environment data

[1594] The server retrieves the user's profile data and environment data.

[1595] Input: User's ID and location information.

[1596] Data Transformation: Query profile data from databases and use third-party APIs to retrieve environmental data.

[1597] Output: The acquired profile data and environmental data are aggregated on the server.

[1598] Step 7: Sentiment Analysis

[1599] The server uses a sentiment analysis engine to analyze the user's sentiment.

[1600] Input: Text and audio data.

[1601] Data processing: Extract emotion labels (e.g., joy, sadness, anger) using a sentiment analysis engine.

[1602] Output: The parsed emotion data is generated.

[1603] Step 8: Generate proposals

[1604] The server generates optimal suggestions based on the analyzed data.

[1605] Input: Acquired profile data, environmental data, parsed emotion data.

[1606] Data processing: Input prompt sentences into a generative AI model (e.g., GPT-3) to generate suggestions.

[1607] Output: The generated proposals are output in JSON format.

[1608] Step 9: Submit your proposal

[1609] The server sends the generated proposal to the terminal.

[1610] Input: Generated proposal data.

[1611] Data processing: The proposed data is packaged in JSON format.

[1612] Output: The proposal data in JSON format is sent to the device.

[1613] Step 10: Viewing Proposals

[1614] The device displays the suggestions to the user.

[1615] Input: Proposal data sent by the server.

[1616] Data Processing: Converting the proposed data into a user-friendly format.

[1617] Output: The proposed results are displayed on the screen.

[1618] Step 11: Enter your feedback

[1619] Users provide feedback on the suggestions.

[1620] Input: Feedback text or audio (e.g., "I tried this restaurant and it was great").

[1621] Data processing: Convert the feedback into text data.

[1622] Output: The converted feedback data is stored in the terminal.

[1623] Step 12: Submit your feedback

[1624] The terminal sends the feedback to the server.

[1625] Input: Feedback text data.

[1626] Data processing: Packaging the feedback data into JSON format.

[1627] Output: Feedback data in JSON format is sent to the server.

[1628] Step 13: Analyze feedback

[1629] The server analyzes the feedback and updates the profile data.

[1630] Input: Feedback data sent from the device.

[1631] Data Processing: Analyzes the feedback data to update user profile data and also uses a sentiment analysis engine to extract additional sentiment data from the feedback.

[1632] Output: Updated profile data is saved to the database.

[1633] The above are the specific processing steps of the system and details of its operation.

[1634] (Application example 2)

[1635] 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."

[1636] Conventional advice-providing systems only provide generic suggestions without considering the user's emotions, making it difficult to provide optimal suggestions that meet the needs of individual users. Furthermore, feedback and profile data updates to improve the accuracy of suggestions were not effectively provided. The present invention aims to solve these problems by providing a system that can analyze a user's emotions and suggest optimal products based on those emotions.

[1637] 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 converting a user's voice input into text, means for transmitting the converted text data, and means for analyzing the received text data. This makes it possible to accurately analyze the received data and generate optimal suggestions based on the user's emotions and profile data.

[1638] The system further includes means for acquiring user profile data, means for acquiring user location and environmental data, and means for generating suggestions based on the analyzed data and the acquired profile and environmental data, thereby enabling suggestions to be provided that are tailored to the user's individual situation.

[1639] The system also includes a means for transmitting the generated proposals, a means for displaying the transmitted proposals, a means for analyzing the user's emotions and reflecting the same in generating proposals and updating the profile data, and a means for using a generative AI model to generate optimal product proposals based on the emotions and profile data, thereby enabling highly accurate proposals incorporating emotion analysis.

[1640] Furthermore, the system includes means for receiving user feedback and updating the profile data, thereby enabling the system to reflect the user feedback and improve the accuracy of suggestions.

[1641] "Means for converting user voice input into text" means a device or software that recognizes a user's voice and converts it into text data.

[1642] The "means for transmitting converted text data" is a network communication device for transmitting the text data converted from the voice to the server.

[1643] The "means for analyzing received text data" refers to a system that analyzes the text data received by the server using techniques such as natural language processing and sentiment analysis.

[1644] "Means for obtaining user profile data" refers to a system for collecting profile data such as a user's personal information and past behavioral history.

[1645] "Means for acquiring user location information and environmental data" refers to technology for collecting information about the user's current location and the surrounding environment (such as the weather).

[1646] A "means for generating suggestions" is an algorithm or model for automatically generating optimal suggestions based on the analyzed data and the acquired profile and environmental data.

[1647] The "means for transmitting the generated proposal" is a communication means for sending the generated proposal to the user's terminal.

[1648] A "means for displaying submitted suggestions" is a device (such as a display) for visually displaying submitted suggestions to a user.

[1649] The "means for analyzing user emotions and reflecting the results in generating suggestions and updating profile data" is a system for analyzing user emotions and using the results in generating suggestions and updating profile data.

[1650] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and generates optimal suggestions based on user emotions and profile data.

[1651] The "means for generating optimal product suggestions" is a mechanism for selecting and suggesting products based on the user's emotions and profile data.

[1652] The "means for receiving user feedback and updating profile data" is a system for collecting user ratings and opinions and updating profile data based on them.

[1653] The present invention relates to a system for virtual stores that makes optimal product suggestions based on a user's personal information and emotional state. This system is composed of the following elements: a means for converting a user's voice input into text, a data transmission means, a text data analysis means, a profile data acquisition means, a location information and environmental data acquisition means, a suggestion generation means, a suggestion transmission means, a suggestion display means, an emotion analysis means, a generative AI model, an optimal product suggestion means, and a feedback reception means.

[1654] Each component of the system operates as follows.

[1655] Voice input and data transmission

[1656] When a user speaks, the device converts the speech into text data using a speech recognition library (e.g., the SpeechRecognition library), which is then sent to the server via the network.

[1657] Data analysis and profile data acquisition

[1658] The server analyzes the received text data and uses natural language processing techniques (e.g., TextBlob) to understand its content. The server also retrieves user profile data (e.g., age, gender, interests) and environmental data (e.g., current location, weather) from a database.

[1659] Sentiment Analysis and Suggestion Generation

[1660] Based on the analyzed text data and the acquired profile data, the server uses a sentiment analysis engine (e.g., TextBlob's sentiment analysis function) to determine the user's sentiment. Based on this sentiment information and profile data, a generative AI model generates optimal product recommendations.

[1661] Submitting and Viewing Proposals

[1662] The generated proposal is sent to the user's terminal via the proposal sending means and displayed on the terminal's display, allowing the user to check the proposed products in the virtual store.

[1663] Feedback and profile data updates

[1664] The feedback provided by the user is then sent back from the device to the server, which analyzes it and updates the profile data, thereby improving the accuracy of future suggestions.

[1665] Specific examples

[1666] 1. User: "I've been feeling stressed lately. Can you suggest some products that will help me relax?"

[1667] 2. System: Converts speech into text and analyzes it. The emotion analysis engine determines the user's emotion as negative.

[1668] 3. The server suggests relaxation products based on the user's profile data and emotional information.

[1669] 4. Device: Show users relaxation products such as "aromatherapy sets" and "massage devices."

[1670] 5. User: "This suggestion is very helpful" provides feedback.

[1671] 6. The server receives the feedback and updates the profile data.

[1672] Prompt Sentence Examples

[1673] Input prompt: "I've been feeling stressed lately. Can you suggest some products that will help me relax?"

[1674] Input to generative AI model: "User's sentiment is negative. Suggest products that will help them relax. User's interests are not related to fitness."

[1675] In this way, the present invention provides a system that can make highly accurate product suggestions by taking into account the user's emotions and personal information.

[1676] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1677] Step 1:

[1678] The user performs voice input. The device captures the user's voice through the microphone. This voice data is used as input and converted into text data using a speech recognition library. The converted text data is generated as output.

[1679] Step 2:

[1680] The converted text data is sent to the server. The device uses a network communication module to send the text data to the server, along with metadata such as the user's ID information.

[1681] Step 3:

[1682] The server parses the received text data, uses a natural language processing library (e.g., TextBlob) to understand the meaning of the text data and extract the user's intent, and generates the results of the parsing as output.

[1683] Step 4:

[1684] The server retrieves the user's profile data from the database, which includes the user's basic information, past behavior history, interests, etc. After receiving this profile data as input, it is used for the next analysis step.

[1685] Step 5:

[1686] The server obtains the user's location and environmental data. Location information is obtained from GPS data, and environmental data such as weather and time of day is obtained from an API. These data are used as inputs to generate the next proposal.

[1687] Step 6:

[1688] Using the sentiment analysis engine, the server analyzes the user's sentiment from the text data. It uses the sentiment analysis function of TextBlob to classify the user's sentiment as positive, negative, or neutral. It generates this sentiment data as output.

[1689] Step 7:

[1690] Using a generative AI model, the server generates optimal product suggestions based on the user's profile data, location information, environmental data, and emotional data. The AI ​​model is trained from past data and generates suggestions based on prompts. This suggestion data is generated as output.

[1691] Step 8:

[1692] The generated proposal is transmitted to the user's terminal. The server uses a communication module to transmit the generated proposal data to the user's terminal. The transmitted proposal data is displayed on the user's terminal.

[1693] Step 9:

[1694] The user provides feedback. The user inputs their evaluation or opinion on the provided suggestion by voice or text. The device sends this feedback data to the server.

[1695] Step 10:

[1696] The server analyzes the user's feedback and updates the profile data. The feedback analysis converts the user's ratings into text data, and the server updates the user's profile data based on the text data. This updated data is used to generate suggestions from the next time onwards.

[1697] 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.

[1698] 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.

[1699] 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.

[1700] [Fourth embodiment]

[1701] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1702] 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.

[1703] 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).

[1704] 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.

[1705] 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.

[1706] 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).

[1707] 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.

[1708] 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.

[1709] 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.

[1710] 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.

[1711] 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.

[1712] 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.

[1713] 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."

[1714] This invention relates to a system that learns a user's personal information and provides various daily advice based on that information. This system consists of three main components: a server, a terminal, and the user.

[1715] System Overview

[1716] Users use voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. User feedback allows the system to further improve its accuracy.

[1717] Program processing

[1718] The system operates sequentially as follows:

[1719] User registration and initial data entry

[1720] When a user first uses the system, they register and enter a self-introduction and basic information. This information is sent to the server by the device and stored in a database as profile data.

[1721] Continuous data collection and analysis

[1722] In everyday life, users ask questions or make requests to the system. For example, they might say, "What should I eat today?" The device converts this speech into text data and sends it to the server. The server then uses a natural language processing (NLP) engine to analyze this text data and understand the user's intent.

[1723] Next, the server retrieves the user's profile data from the database, including the user's past behavioral history, preferences, allergy information, etc. Additionally, the server retrieves the user's current location, weather information, and other environmental data.

[1724] Proposal generation and presentation

[1725] The server uses AI models based on this data to generate optimal suggestions. For example, if a user wants a low-calorie meal, the server searches for appropriate restaurants and generates a suggestion such as, "We recommend a nearby low-calorie restaurant called 'Healthy Dinner.'" This suggestion is then displayed to the user via their device.

[1726] Feedback and Learning

[1727] The user provides feedback on the suggestions to the system. For example, they might input feedback like, "I tried this restaurant and it was great." The device then sends this feedback to the server, which analyzes it and updates the user's profile data. Through this process, the system gains a more accurate understanding of the user's preferences and tendencies, improving the accuracy of future suggestions.

[1728] Specific examples

[1729] Example 1: Restaurant suggestions

[1730] 1. The user utters, "What should I eat today?"

[1731] 2. The device converts the speech into text and sends it to the server.

[1732] 3. The server analyzes the question and searches for suitable restaurants based on the user's profile data and location.

[1733] 4. The server sends the generated proposal to the device, which displays it to the user.

[1734] Example 2: Fashion advice

[1735] 1. The user types into the system, "Please give me some advice on what to wear today."

[1736] 2. The device sends this input to the server.

[1737] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information.

[1738] 4. The server sends the generated proposal to the device, which notifies the user.

[1739] As described above, the system of the present invention can provide accurate advice to the user in various situations throughout his or her life, thereby improving the quality of the user's life.

[1740] The processing flow will be explained below.

[1741] Step 1:

[1742] The user voice-inputs, "What should I eat today?"

[1743] Step 2:

[1744] The device converts voice input into text data in real time.

[1745] Step 3:

[1746] The terminal sends the converted text data to the server along with the user ID.

[1747] Step 4:

[1748] The text data received by the server is analyzed using a natural language processing (NLP) engine.

[1749] Specifically, it extracts the user's intent from text data and understands that the user is looking for suggestions on what to eat today.

[1750] Step 5:

[1751] The server retrieves the user's profile data (past dietary history, preferences, allergy information, etc.) from the database.

[1752] Step 6:

[1753] The server retrieves current location and environmental data (weather, time, etc.) from an external API.

[1754] Step 7:

[1755] The server uses AI models to generate restaurant suggestions based on the parsed data, retrieved profile data, and environmental data.

[1756] Specifically, the system searches for restaurants that meet certain criteria, such as "close to the user's location" and "have low-calorie menu items."

[1757] Step 8:

[1758] The server generates a list of restaurant suggestions that are optimized based on the user's profile data and past feedback.

[1759] Specifically, highly rated restaurants and restaurants that users have previously liked will be placed at the top of the list.

[1760] Step 9:

[1761] The server sends optimized restaurant suggestions in JSON format to the device.

[1762] Step 10:

[1763] The device displays the received proposal data to the user.

[1764] Specifically, the screen will display, "We recommend a nearby low-calorie restaurant called 'Healthy Dinner'."

[1765] Step 11:

[1766] The user enters feedback on the suggestion (e.g., "I tried this restaurant and it was great").

[1767] Step 12:

[1768] The device sends the user's feedback to the server.

[1769] Step 13:

[1770] The server analyzes the received feedback and updates the user's profile data.

[1771] Specifically, it will set the restaurant's rating to "good" and prioritize similar restaurants in future suggestions.

[1772] By repeating this series of steps, the system learns the user's preferences and lifestyle habits and can make more appropriate and personalized suggestions.

[1773] Example 1

[1774] 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."

[1775] Conventional technologies generally provide suggestions and advice to users, but have the problem of not being able to fully address the individual needs and preferences of each user. In particular, there is a need for a system that can efficiently and accurately process users' voice input and, based on the results, generate optimal suggestions that reflect the user's profile data and environmental data.

[1776] 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.

[1777] In this invention, the server includes means for converting a user's voice input into text data, means for transmitting the converted text data, means for analyzing the received text data, means for acquiring user profile data, means for acquiring user location data and environmental data, means for generating suggestions using a generative AI model based on the analyzed text data and the acquired profile data and environmental data, means for transmitting the generated suggestions, means for displaying the transmitted suggestions, and means for receiving user feedback and updating the profile data, thereby enabling accurate suggestions to be made in accordance with each user's individual needs and preferences.

[1778] A "user" is someone who uses the system to provide voice input and receive suggestions and advice.

[1779] "Voice input" refers to the act of a user asking a question or making a request to a system by voice.

[1780] "Text data" is character information converted from voice input.

[1781] "Means for converting" refers to the technology or algorithm used to convert voice input into text data.

[1782] "Transmission means" refers to the communication technology or protocol used to transmit text data to the server.

[1783] The "receiving means" is a means by which the server receives text data sent from the terminal.

[1784] "Means of analysis" refers to the technology and algorithms used to understand the received text data and grasp the user's intent.

[1785] "Profile data" refers to individual data such as a user's basic information, past behavioral history, preferences, and allergy information.

[1786] "Means of acquisition" refers to the technology or protocol used to acquire the required data from a database or external system.

[1787] "Environmental data" refers to data about the user's environment, such as the user's current location and weather information.

[1788] A "generative AI model" is an artificial intelligence model that generates optimal suggestions based on user data.

[1789] The "means for generating suggestions" is a generative AI model that runs on the basis of the analyzed text data and the acquired profile and environmental data.

[1790] "Displaying means" refers to the techniques or methods for presenting the generated suggestions to the user.

[1791] "Feedback" refers to the evaluation or opinion that a user gives to the system after receiving a suggestion.

[1792] "Means for receiving feedback" refers to the means for collecting feedback from users.

[1793] An "updating means" is a technique or algorithm for correcting or adding to profile data based on feedback received.

[1794] This invention relates to a system that learns a user's personal information and provides various daily advice using a generative AI model. This system consists of three main components: a server, a terminal, and the user.

[1795] System Overview

[1796] Users use voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. User feedback allows the system to further improve its accuracy.

[1797] Hardware and Software Configuration

[1798] This system uses the following hardware and software:

[1799] 1. Device:

[1800] Smartphone (iOS, Android)

[1801] Smart speakers (voice assistant devices for the general home)

[1802] 2. Server:

[1803] Cloud services (AWS, Azure, Google Cloud)

[1804] 3. Natural Language Processing (NLP) Engine:

[1805] OpenAI GPT

[1806] Google NLP API

[1807] 4. Database:

[1808] MySQL

[1809] PostgreSQL

[1810] What the program does

[1811] This system performs the following processes sequentially.

[1812] User registration and initial data entry

[1813] When a user first uses the system, they register and enter a self-introduction and basic information. The device sends this input data to the server, which then stores it in a database. For example, a user might install an app and enter their name, age, gender, allergy information, etc.

[1814] Voice to text conversion

[1815] The user can ask a question or make a request by voice. For example, they can say, "What should I eat today?" The device converts the voice into text using voice recognition technology such as the Google Speech-to-Text API and sends this text data to the server.

[1816] Text analysis and suggestion generation

[1817] The server uses an NLP engine such as OpenAI GPT to analyze the received text data. Based on the analysis results, the user's profile data and environmental data (such as current location and weather information) are retrieved from a database, and based on this, a generative AI model is used to generate optimal suggestions. An example of a prompt sentence is, "I'm looking for a low-calorie meal. Can you recommend any restaurants?"

[1818] Submitting suggestions and providing feedback

[1819] The generated suggestions are sent from the server to the device and displayed to the user through the device. For example, a suggestion such as "We recommend a nearby low-calorie restaurant for a healthy dinner" may be displayed. The user enters feedback on the suggestions, and the device sends the feedback to the server. The server analyzes the feedback and updates the user's profile data. This feedback improves the accuracy of future suggestions.

[1820] Specific examples

[1821] Specific examples of how this system can be used include:

[1822] Example 1: Restaurant suggestions

[1823] 1. The user utters, "What should I eat today?"

[1824] 2. The device converts the speech into text and sends it to the server.

[1825] 3. The server analyzes the question and searches for appropriate restaurants based on the user's profile data and location, using a generative AI model to generate a suggestion such as "Recommend a nearby low-calorie restaurant for a healthy dinner."

[1826] 4. The server sends the generated proposal to the device, which displays it to the user.

[1827] Example 2: Fashion advice

[1828] 1. The user types into the system, "Please give me some advice on what to wear today."

[1829] 2. The device sends this input to the server.

[1830] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information, for example, "It's raining today, so I recommend a raincoat and waterproof shoes."

[1831] 4. The server sends the generated proposal to the device, which notifies the user.

[1832] As described above, the system of the present invention provides accurate advice that corresponds to the individual needs and environment of the user, thereby improving the quality of life of the user.

[1833] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1834] Step 1:

[1835] When a user first uses the system, they register and enter basic information. The user then installs the app and enters their name, age, gender, allergy information, etc.

[1836] Input: User's basic information (name, age, gender, allergy information, etc.)

[1837] Data processing / calculation: Basic information entered is collected

[1838] Output: Basic information dataset

[1839] Step 2:

[1840] The device sends the user's basic information to the server. The device sends the basic information dataset to the server using an HTTP request.

[1841] Input: User basic information dataset

[1842] Data processing / calculation: Convert basic information dataset into HTTP request

[1843] Output: Send request

[1844] Step 3:

[1845] The server receives the basic information and stores it in a database. The server receives the basic information dataset and stores it in a database (MySQL or PostgreSQL).

[1846] Input: Basic information dataset

[1847] Data processing / calculation: Inserting basic information datasets into the database

[1848] Output: Basic information stored in the database

[1849] Step 4:

[1850] The user asks a question or makes a request by voice, for example, "What should I eat today?"

[1851] Input: User voice input

[1852] Data processing / calculation: Collection of voice data

[1853] Output: Audio data

[1854] Step 5:

[1855] The device converts voice input into text data. The device converts voice data into text data using speech recognition technology such as the Google Speech-to-Text API.

[1856] Input: Audio data

[1857] Data processing / calculation: Converting voice data into text data

[1858] Output: Text data

[1859] Step 6:

[1860] The device sends text data to the server. The device sends text data to the server using an HTTP request.

[1861] Input: Text data

[1862] Data processing / calculation: Convert text data into a transmission request

[1863] Output: Send request

[1864] Step 7:

[1865] The server analyzes the received text data. The server uses an NLP engine such as OpenAI GPT to analyze the text data and understand the user's intent.

[1866] Input: Text data

[1867] Data processing / calculation: Text analysis using NLP engines

[1868] Output: Analysis results

[1869] Step 8:

[1870] The server retrieves the user's profile data and environmental data. The server retrieves the user's profile data (past behavioral history, preferences, allergy information, etc.) from the database, and collects environmental data using GPS data and weather information APIs.

[1871] Input: Analysis results

[1872] Data manipulation / computation: database queries and API requests

[1873] Output: Profile data and environment data

[1874] Step 9:

[1875] The server generates suggestions using a generative AI model. Based on the analysis results and the acquired profile and environmental data, the server inputs prompt sentences into the generative AI model to generate optimal suggestions.

[1876] Input: Analysis results, profile data, environmental data

[1877] Data processing / calculation: Proposal generation using generative AI models

[1878] Output: Proposal

[1879] Step 10:

[1880] The server sends the generated proposal to the device using an HTTP request.

[1881] Input: Proposal

[1882] Data processing / calculation: Converting proposals into submission requests

[1883] Output: Send request

[1884] Step 11:

[1885] Display suggestions received by the device to the user, using notifications and / or in-app displays to inform the user about the suggestions.

[1886] Input: Proposal

[1887] Data processing / calculation: Displaying proposals in the user interface

[1888] Output: User notification

[1889] Step 12:

[1890] The user enters feedback on the proposal. The user enters their evaluation and opinion on the proposal.

[1891] Input: User feedback

[1892] Data processing / calculation: Gathering feedback

[1893] Output: Feedback data

[1894] Step 13:

[1895] The device sends the feedback to the server. It uses an HTTP request to send the feedback data to the server.

[1896] Input: Feedback data

[1897] Data processing / calculation: Convert feedback data into transmission requests

[1898] Output: Send request

[1899] Step 14:

[1900] The server analyzes the feedback and updates the user's profile data. The server analyzes the feedback with its NLP engine and modifies or adds to the profile data.

[1901] Input: Feedback data

[1902] Data processing / calculation: Feedback analysis and database updates

[1903] Output: Updated profile data

[1904] These processing steps allow the system to provide accurate suggestions tailored to the user's individual needs and preferences, and to improve its accuracy as feedback is received.

[1905] (Application example 1)

[1906] 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."

[1907] One issue with virtual stores is that it is difficult for users to select the most suitable products without trying them on in person. Furthermore, there is a lack of systems that can make appropriate product recommendations based on users' preferences and past purchase history. This can lead to users being unable to make satisfactory product selections, which can lead to a decline in customer satisfaction.

[1908] 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.

[1909] In this invention, the server includes means for converting a user's voice input into text, means for transmitting the converted text data, means for analyzing the received text data, means for acquiring user profile data, means for acquiring user location information and environmental data, means for generating optimal proposals using a generative AI model based on the analyzed data and the acquired profile data and environmental data, means for transmitting the generated proposals, means for displaying the transmitted proposals, means for receiving user feedback and updating the profile data, and means for making optimal product proposals in a virtual store based on the user's profile data. This allows the user to receive optimal product proposals in the virtual store and select products without trying them on.

[1910] "User" refers to an individual who uses the System.

[1911] "Voice input" refers to a method in which a user provides information to a system by speaking.

[1912] "Means for converting to text" refers to a device or software that implements the process of converting voice input into text data.

[1913] "Text data" refers to data that has been converted from voice input into text information.

[1914] "Means for sending" refers to a device or software that implements the process of sending text data to another system, such as a server.

[1915] "Means for analyzing" refers to a device or software that realizes the process of understanding the content of the transmitted text data and extracting the necessary information.

[1916] "Profile data" refers to data such as a user's personal information, past behavioral history, and preferences.

[1917] "Means of collection" refers to the device or software that enables the process of collecting profile data, location information, and environmental data.

[1918] "Location Information" means information that indicates a User's current geographic location.

[1919] "Environmental data" refers to information about the user's environment, such as weather, temperature, and surrounding conditions.

[1920] A "generative AI model" refers to an algorithm or software that generates optimal suggestions based on a user's preferences and environment.

[1921] "Means for generating suggestions" refers to a device or software that enables the process of creating the most suitable suggestions for the user based on the analyzed data and / or acquired profile data.

[1922] "Means for displaying submitted suggestions" refers to a device or software that implements the process of visually presenting generated suggestions to a user.

[1923] "Feedback" refers to the opinions and evaluations that users provide to the system.

[1924] "Means for updating" refers to the device or software that enables the process of changing or adding profile data based on feedback.

[1925] A "virtual store" refers to a virtual commercial facility where users can browse, select, and purchase products online.

[1926] "Product Suggestions" refers to product information recommended to users based on their preferences and profile data.

[1927] "Means for viewing products without trying them on" refers to devices or software that enable a user to visually view product displays and descriptions without physically handling or trying on the product.

[1928] This invention relates to a system that proposes optimal products in a virtual store based on the user's personal information and environmental data. This system consists of three main elements: the user, a smart device (such as smart glasses), and a server.

[1929] System Overview

[1930] Wearing smart glasses, users walk around the virtual store and ask questions or make requests about products by voice. The smart glasses convert this voice input into text data and send it to the server. The server analyzes the received text data and generates optimal product suggestions using the user's profile data and environmental data. These suggestions are presented to the user through the smart glasses' display. The system continues to improve based on user feedback, providing a superior customer experience.

[1931] A natural language description of the program's operation

[1932] Hardware / Software Used

[1933] Smart glasses: Google Glass, Microsoft HoloLens

[1934] Speech recognition engine: Google Speech-to-Text API

[1935] NLP engine: Google Cloud Natural Language

[1936] Generative AI models: TensorFlow, PyTorch

[1937] Database: MySQL, MongoDB

[1938] Program processing steps

[1939] 1. Handling voice input:

[1940] The server receives the voice data sent from the smart glasses and converts it into text data using a voice recognition engine. Through this process, the user's speech is stored as text information on the server.

[1941] 2. Text data analysis:

[1942] The server uses an NLP engine to analyze the content of the text data and understand the user's intent and the type of question.

[1943] 3. Acquire profile and environmental data:

[1944] The server retrieves user profile data (past purchase history, preferences, etc.) and environmental data (location, weather information, etc.) from a database.

[1945] 4. Proposal generation using generative AI model:

[1946] The server uses a generative AI model based on this data to generate optimal product suggestions for the user, for example recommending specific products based on past purchase history and preferences.

[1947] 5. Show suggestions:

[1948] The server sends the generated proposal data to the smart glasses, and the proposals are displayed on the glasses' display.

[1949] 6. Feedback Processing:

[1950] The server receives feedback from users and updates the user profile data based on that feedback, improving the accuracy of future suggestions.

[1951] Specific examples

[1952] Example 1: Clothing suggestions

[1953] 1. A user points to a specific product in a virtual store and says, "Write a review for this jacket."

[1954] 2. The smart glasses convert the speech into text and send it to the server.

[1955] 3. The server analyzes the text data and generates the most appropriate review based on the user's profile data (similar jackets purchased in the past and preferred colors).

[1956] 4. The smart glasses will display the suggestions on the screen.

[1957] Prompt Sentence Examples

[1958] "Write a review about this product"

[1959] "Generate optimal product suggestions based on user profile data."

[1960] In this way, the system of the present invention can provide real-time and personalized product suggestions to users within the virtual store, greatly improving the user experience.

[1961] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1962] Step 1:

[1963] The user provides voice input. The user points to a specific product in the virtual store and says, "Please give me a review of this jacket." The microphone in the smart glasses captures this voice and stores it as voice data. The input is the user's voice data, and the output is the captured voice data.

[1964] Step 2:

[1965] The device converts the voice data into text data. The voice recognition engine (Google Speech-to-Text API) analyzes the voice data and converts it into text data. The input is voice data and the output is text data. Specifically, the voice recognition engine analyzes the user's speech and generates a corresponding string of characters.

[1966] Step 3:

[1967] The terminal transmits the converted text data to the server, where the text data is sent to the server via network communication. The input is the text data, and the output is the text data transmitted to the server.

[1968] Step 4:

[1969] The server analyzes the received text data. The NLP engine (Google Cloud Natural Language) analyzes the text data to understand the user's intent and the type of question. The input is text data, and the output is the analysis results (user's intent and type of question). Specifically, the NLP engine analyzes the text data grammatically and semantically to extract key keywords and content.

[1970] Step 5:

[1971] The server retrieves the user's profile data and environmental data. It retrieves the user's past purchase history, preferences, location information, and environmental data (weather and surrounding conditions) from the database. The input is the analysis result, and the output is the user's profile data and environmental data. Specifically, the server executes a database query to retrieve the required data.

[1972] Step 6:

[1973] The server uses a generative AI model to generate optimal proposals. Based on the acquired profile data and environmental data, an AI model (TensorFlow or PyTorch) is used to generate optimal product proposals for the user. The input is the profile data and environmental data, and the output is the generated proposal. Specifically, the AI ​​model analyzes the data and selects the optimal product.

[1974] Step 7:

[1975] The server sends the generated proposal to the terminal. The server sends the proposal data to the smart glasses, which then transmits it over the network. The input is the generated proposal, and the output is the transmitted proposal.

[1976] Step 8:

[1977] The terminal displays the sent suggestion. The suggestion is displayed on the display of the smart glasses. The input is the sent suggestion, and the output is the suggestion displayed on the display. As a specific operation, the display visually displays the suggestion.

[1978] Step 9:

[1979] Collect user feedback and send it to the server. Users can voice-input their feedback about the proposed products, which the smart glasses will capture and convert into text. The input is the user's voice feedback, and the output is text feedback.

[1980] Step 10:

[1981] The server updates the profile data based on the feedback. It analyzes the user's feedback and improves the profile data. The input is text feedback and the output is updated profile data. Specifically, the server analyzes the feedback and updates the user profile appropriately.

[1982] 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.

[1983] This invention relates to a system that learns a user's personal information and provides various daily advice based on it. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[1984] System Overview

[1985] The user uses voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. The system can further improve its accuracy by providing feedback from the user. A particular feature of this invention is that the emotion engine recognizes the user's emotions and reflects them in the suggestions and feedback.

[1986] Program processing

[1987] The system operates sequentially as follows:

[1988] User registration and initial data entry

[1989] When a user first uses the system, they register and enter a self-introduction and basic information. This information is sent to the server by the device and stored in a database as profile data.

[1990] Continuous data collection and analysis

[1991] In everyday life, users ask questions or make requests to the system. For example, they might say, "What should I eat today?" The device converts this speech into text data and sends it to the server. The server then uses a natural language processing (NLP) engine to analyze this text data and understand the user's intent.

[1992] Next, the server retrieves the user's profile data from the database, including the user's past behavioral history, preferences, allergy information, etc. Additionally, the server retrieves the user's current location, weather information, and other environmental data.

[1993] Utilizing the Emotion Engine

[1994] The server uses an emotion engine to recognize the user's emotions based on the text and voice data, and this emotion information is used to generate suggestions and update the user profile.

[1995] Proposal generation and presentation

[1996] The server uses an AI model based on the analyzed data, acquired profile data, and environmental data, as well as the user's recognized emotions, to generate optimal suggestions. For example, if the user is emotionally exhausted, it may suggest a relaxing restaurant. These suggestions are displayed to the user through their device.

[1997] Feedback and Learning

[1998] The user provides feedback on the suggestions to the system. For example, the user can input feedback such as "I tried this restaurant and it was good." The device then sends this feedback to the server, which analyzes it and updates the user's profile data. The emotion engine also uses the feedback to learn the user's emotional tendencies. Through this process, the system gains a more accurate understanding of the user's preferences and tendencies, improving the accuracy of future suggestions.

[1999] Specific examples

[2000] Example 1: Restaurant suggestions

[2001] 1. The user utters, "What should I eat today?"

[2002] 2. The device converts the speech into text and sends it to the server.

[2003] 3. The server analyzes the question and searches for suitable restaurants based on the user's profile data and location.

[2004] 4. The emotion engine analyzes the user's emotions and prioritizes restaurants where they can relax, for example, if they are tired.

[2005] 5. The server sends the generated proposal to the device, which displays it to the user.

[2006] Example 2: Fashion advice

[2007] 1. The user types into the system, "Please give me some advice on what to wear today."

[2008] 2. The device sends this input to the server.

[2009] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information.

[2010] 4. The emotion engine analyzes the user's emotions and suggests uplifting clothing if, for example, they are feeling down.

[2011] 5. The server sends the generated proposal to the device, which notifies the user.

[2012] As described above, the system of the present invention can provide accurate advice in various situations throughout the user's life, and can improve the quality of life by taking into consideration the user's emotions in particular.

[2013] The processing flow will be explained below.

[2014] Processing steps of the invention combined with an emotion engine that recognizes user emotions

[2015] Step 1:

[2016] The user voice-inputs, "What should I eat today?"

[2017] Step 2:

[2018] The device converts voice input into text data in real time.

[2019] Step 3:

[2020] The terminal sends the converted text data to the server along with the user ID.

[2021] Step 4:

[2022] The text data received by the server is analyzed using a natural language processing (NLP) engine.

[2023] Specifically, it extracts the user's intent from text data and understands that the user is looking for suggestions on what to eat today.

[2024] Step 5:

[2025] The server uses an emotion engine to recognize the user's emotion from the received text data and voice data.

[2026] Specifically, it analyzes the user's emotional state (e.g., tiredness, joy, stress) from the tone of voice and text content.

[2027] Step 6:

[2028] The server retrieves the user's profile data (past dietary history, preferences, allergy information, etc.) from the database.

[2029] Step 7:

[2030] The server retrieves the user's current location and environmental data (weather, time, etc.) from an external API.

[2031] Step 8:

[2032] The server uses AI models to generate restaurant suggestions based on the parsed data, captured profile data, environmental data, and perceived user sentiment.

[2033] Specifically, the app searches for restaurants that meet criteria such as "close to the user's location," "have low-calorie menu items," and "have a relaxing atmosphere."

[2034] Step 9:

[2035] The server generates a list of restaurant suggestions that are optimized based on the user's profile data and past feedback.

[2036] Specifically, highly rated restaurants and restaurants that users have previously liked will be placed at the top of the list.

[2037] Step 10:

[2038] The server sends optimized restaurant suggestions in JSON format to the device.

[2039] Step 11:

[2040] The device displays the received proposal data to the user.

[2041] Specifically, the screen will display, "We recommend a nearby low-calorie restaurant called 'Healthy Dinner'."

[2042] Step 12:

[2043] The user enters feedback on the suggestion (e.g., "I tried this restaurant and it was great").

[2044] Step 13:

[2045] The device sends the user's feedback to the server.

[2046] Step 14:

[2047] The server analyzes the received feedback and updates the user's profile data and the learning data of the emotion engine.

[2048] Specifically, it marks the restaurant as "good" and prioritizes similar restaurants in future suggestions, while also improving the accuracy of its sentiment engine based on user feedback.

[2049] By repeating this series of steps, the system learns not only the user's preferences and lifestyle habits, but also their emotional state, allowing it to make more appropriate and personalized suggestions.

[2050] Example 2

[2051] 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."

[2052] Conventional recommendation systems have the problem of low user satisfaction because they do not adequately consider the user's individual needs or real-time emotions when making recommendations. Specifically, they have limited use of profile data and environmental data, and lack the functionality to analyze user emotions and reflect them in recommendations. Furthermore, they lack a means to effectively utilize user feedback to improve the system.

[2053] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2054] In this invention, the server includes means for converting a user's voice input into text, means for transmitting the converted text data, means for analyzing the received text data, means for acquiring user profile data, means for acquiring user location information and environmental data, means for generating suggestions based on the analyzed data and the acquired profile data and environmental data, means for transmitting the generated suggestions, means for displaying the transmitted suggestions, means for receiving user feedback and updating the profile data, means for analyzing user emotions, and means for generating suggestions based on the analyzed user emotions. This enables the generation of detailed suggestions that take user emotions into consideration, thereby improving user satisfaction. Furthermore, by utilizing feedback, the system learns and improves, and even more accurate suggestions can be made in the future.

[2055] "Voice input" refers to voice data provided by the user via a microphone or the like.

[2056] "Means for converting to text" refers to technology or equipment for analyzing voice data and converting it into text information.

[2057] "Text data" refers to digital data obtained by converting voice data into text information.

[2058] A "transmitting means" is any technique or device used to send data over a network to another system or device.

[2059] "Means of analysis" refers to technology or equipment for analyzing text data and understanding the user's intentions and emotions.

[2060] "Profile data" refers to data such as basic information about a user, past behavioral history, and preferences.

[2061] "Location information" refers to data that indicates a user's current location.

[2062] "Environmental data" refers to data that indicates the user's surroundings, including, for example, weather information and information about nearby facilities.

[2063] The "means for generating suggestions" refers to a technology or device that generates suggestions suited to the user based on the analyzed data and the acquired data.

[2064] "Means for displaying" refers to a technique or device for visually presenting generated suggestions to a user.

[2065] "Feedback" refers to opinions and thoughts about suggestions that users provide to the system.

[2066] "Means for updating" refers to the technology or equipment used to modify or add to the contents of the database based on feedback.

[2067] "Means for analyzing emotions" refers to technology or devices for determining emotions from a user's text data or voice data.

[2068] A "means for generating suggestions based on emotions" is a technique or device that takes into account the analyzed emotion data to generate suggestions that are appropriate for the user.

[2069] The present invention relates to a system that takes into account a user's emotions and generates suggestions based on personal information. The system consists of four main components: a server, a terminal, a user, and an emotion analysis engine.

[2070] System Overview

[2071] The user uses voice input to ask questions or make requests to the system. The device converts this voice input into text data and sends it to the server. The server analyzes the received text data and generates optimal suggestions based on the user's profile data and environmental data. These suggestions are then presented to the user again via the device. The system can further improve its accuracy by providing feedback from the user. A particular feature of this invention is that the emotion analysis engine recognizes the user's emotions and reflects them in the suggestions and feedback.

[2072] Program processing

[2073] Hardware and software used

[2074] 1. A microphone device that allows the user to input voice information.

[2075] 2. Software that allows your device to convert speech to text (e.g., Google Speech-to-Text API).

[2076] 3. A natural language processing (NLP) engine (e.g., spaCy, NLTK) to analyze the text data received by the server.

[2077] 4. A database (e.g., MySQL) where the server stores and retrieves user profile data.

[2078] 5. Third-party APIs (e.g. OpenWeatherMap API) through which the server can obtain environmental data.

[2079] 6. An emotion analysis engine (e.g., Microsoft Azure Emotion API) for the server to perform emotion analysis.

[2080] 7. A generative AI model (e.g., GPT-3) for the server to generate proposals.

[2081] Data processing and data calculation

[2082] 1. The device converts voice input into text data.

[2083] Audio waveform data is captured and processed for filtering and noise reduction.

[2084] The filtered voice data is converted into text in real time to generate text data.

[2085] 2. The device sends the text data to the server.

[2086] The text data is packaged in JSON format and sent using the HTTPS protocol.

[2087] 3. The server parses the text data.

[2088] Use a natural language processing (NLP) engine to tokenize text data and analyze user intent.

[2089] Use a sentiment analysis engine to extract sentiment labels from text data.

[2090] 4. The server retrieves the user profile data and environment data.

[2091] Retrieve profile data from a database and environmental data using third-party APIs.

[2092] 5. The server generates a proposal.

[2093] Based on the analyzed and acquired data, an AI model is used to generate optimal recommendations.

[2094] 6. The server sends the generated proposal to the device.

[2095] The proposal results are packaged in JSON format and sent to the terminal.

[2096] 7. The device displays suggestions to the user.

[2097] The proposed results are displayed to the user in a visually easy-to-understand format.

[2098] 8. Users provide feedback on suggestions.

[2099] Feedback is input as text data or audio data.

[2100] 9. The device sends the feedback to the server.

[2101] The feedback data is packaged in JSON format and sent to the server.

[2102] 10. The server analyzes the feedback and updates the profile data.

[2103] Analyze feedback data and update user profile data.

[2104] Use a sentiment analysis engine to extract additional emotional data from the feedback.

[2105] Specific examples

[2106] Example 1: Restaurant suggestions

[2107] 1. The user utters, "What should I eat today?"

[2108] 2. The device converts the speech into text and sends it to the server.

[2109] 3. The server analyzes the question and searches for suitable restaurants based on the user's profile data and location.

[2110] 4. The sentiment analysis engine analyzes the user's emotions and prioritizes restaurants where they can relax, for example, if they are tired.

[2111] 5. The server uses an appropriate AI model to generate a list of relaxing restaurants.

[2112] 6. The server sends the generated proposal to the device, which displays it to the user.

[2113] Example 2: Fashion advice

[2114] 1. The user types into the system, "Please give me some advice on what to wear today."

[2115] 2. The device sends this input to the server.

[2116] 3. The server analyzes the question and generates optimal fashion advice based on the user's profile data and weather information.

[2117] 4. The emotion analysis engine analyzes the user's emotions and suggests clothing that will cheer them up, for example, if they are feeling down.

[2118] 5. The server sends the generated proposal to the device, which notifies the user.

[2119] Prompt Sentence Examples

[2120] Restaurant Suggestion Prompt

[2121] The user types, "What should I eat today?" In response, the app should suggest a relaxing restaurant based on the user's past eating history, current location, weather information, and data on how tired the user is currently feeling.

[2122] Fashion Advice Prompt

[2123] The user types, "Please give me some advice on what to wear today." In response, the app should suggest an uplifting outfit based on the user's past clothing preferences, current weather information, and data indicating the user is feeling depressed.

[2124] The above is an embodiment of the system of the present invention. This system can generate detailed suggestions that take into account the user's emotions and improve user satisfaction.

[2125] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2126] Step 1: User registration and initial data entry

[2127] When a user first uses the system, they access it and enter a self-introduction and basic information.

[2128] Input: The user enters their name, age, gender, food preferences, allergy information, hobbies, etc.

[2129] Data processing: This information is converted into JSON format by the terminal.

[2130] Output: The data converted to JSON format is sent to the server.

[2131] Step 2: Save your basic information

[2132] The server stores the received user information in a database.

[2133] Input: User information sent from the device in JSON format.

[2134] Data processing: Parse and validate JSON data to ensure there is no invalid data.

[2135] Output: Save the validated data to the database.

[2136] Step 3: Speak your question or request

[2137] Users can ask questions or make requests to the system by voice input.

[2138] Input: Speech data (e.g., "What should I eat today?").

[2139] Data processing: Audio is captured in real time and undergoes filtering and noise reduction.

[2140] Output: The filtered audio data is converted into text data and stored in the device.

[2141] Step 4: Sending text data

[2142] The device converts the voice into text data and sends it to the server.

[2143] Input: Text data generated from audio data.

[2144] Data processing: Packaging text data into JSON format.

[2145] Output: JSON formatted text data is sent to the server.

[2146] Step 5: Analyzing the text data

[2147] The server analyzes the received text data.

[2148] Input: Text data sent from the terminal.

[2149] Data processing: Using a natural language processing (NLP) engine, we tokenize the text data and understand the intent of the question or request.

[2150] Output: The analysis results in user intent and emotional data.

[2151] Step 6: Obtaining profile and environment data

[2152] The server retrieves the user's profile data and environment data.

[2153] Input: User's ID and location information.

[2154] Data Transformation: Query profile data from databases and use third-party APIs to retrieve environmental data.

[2155] Output: The acquired profile data and environmental data are aggregated on the server.

[2156] Step 7: Sentiment Analysis

[2157] The server uses a sentiment analysis engine to analyze the user's sentiment.

[2158] Input: Text and audio data.

[2159] Data processing: Extract emotion labels (e.g., joy, sadness, anger) using a sentiment analysis engine.

[2160] Output: The parsed emotion data is generated.

[2161] Step 8: Generate proposals

[2162] The server generates optimal suggestions based on the analyzed data.

[2163] Input: Acquired profile data, environmental data, parsed emotion data.

[2164] Data processing: Input prompt sentences into a generative AI model (e.g., GPT-3) to generate suggestions.

[2165] Output: The generated proposals are output in JSON format.

[2166] Step 9: Submit your proposal

[2167] The server sends the generated proposal to the terminal.

[2168] Input: Generated proposal data.

[2169] Data processing: The proposed data is packaged in JSON format.

[2170] Output: The proposal data in JSON format is sent to the device.

[2171] Step 10: Viewing Proposals

[2172] The device displays the suggestions to the user.

[2173] Input: Proposal data sent by the server.

[2174] Data Processing: Converting the proposed data into a user-friendly format.

[2175] Output: The proposed results are displayed on the screen.

[2176] Step 11: Enter your feedback

[2177] Users provide feedback on the suggestions.

[2178] Input: Feedback text or audio (e.g., "I tried this restaurant and it was great").

[2179] Data processing: Convert the feedback into text data.

[2180] Output: The converted feedback data is stored in the terminal.

[2181] Step 12: Submit your feedback

[2182] The terminal sends the feedback to the server.

[2183] Input: Feedback text data.

[2184] Data processing: Packaging the feedback data into JSON format.

[2185] Output: Feedback data in JSON format is sent to the server.

[2186] Step 13: Analyze feedback

[2187] The server analyzes the feedback and updates the profile data.

[2188] Input: Feedback data sent from the device.

[2189] Data Processing: Analyzes the feedback data to update user profile data and also uses a sentiment analysis engine to extract additional sentiment data from the feedback.

[2190] Output: Updated profile data is saved to the database.

[2191] The above are the specific processing steps of the system and details of its operation.

[2192] (Application example 2)

[2193] 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."

[2194] Conventional advice-providing systems only provide generic suggestions without considering the user's emotions, making it difficult to provide optimal suggestions that meet the needs of individual users. Furthermore, feedback and profile data updates to improve the accuracy of suggestions were not effectively provided. The present invention aims to solve these problems by providing a system that can analyze a user's emotions and suggest optimal products based on those emotions.

[2195] 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 converting a user's voice input into text, means for transmitting the converted text data, and means for analyzing the received text data. This makes it possible to accurately analyze the received data and generate optimal suggestions based on the user's emotions and profile data.

[2196] The system further includes means for acquiring user profile data, means for acquiring user location and environmental data, and means for generating suggestions based on the analyzed data and the acquired profile and environmental data, thereby enabling suggestions to be provided that are tailored to the user's individual situation.

[2197] The system also includes a means for transmitting the generated proposals, a means for displaying the transmitted proposals, a means for analyzing the user's emotions and reflecting the same in generating proposals and updating the profile data, and a means for using a generative AI model to generate optimal product proposals based on the emotions and profile data, thereby enabling highly accurate proposals incorporating emotion analysis.

[2198] Furthermore, the system includes means for receiving user feedback and updating the profile data, thereby enabling the system to reflect the user feedback and improve the accuracy of suggestions.

[2199] "Means for converting user voice input into text" means a device or software that recognizes a user's voice and converts it into text data.

[2200] The "means for transmitting converted text data" is a network communication device for transmitting the text data converted from the voice to the server.

[2201] The "means for analyzing received text data" refers to a system that analyzes the text data received by the server using techniques such as natural language processing and sentiment analysis.

[2202] "Means for obtaining user profile data" refers to a system for collecting profile data such as a user's personal information and past behavioral history.

[2203] "Means for acquiring user location information and environmental data" refers to technology for collecting information about the user's current location and the surrounding environment (such as the weather).

[2204] A "means for generating suggestions" is an algorithm or model for automatically generating optimal suggestions based on the analyzed data and the acquired profile and environmental data.

[2205] The "means for transmitting the generated proposal" is a communication means for sending the generated proposal to the user's terminal.

[2206] A "means for displaying submitted suggestions" is a device (such as a display) for visually displaying submitted suggestions to a user.

[2207] The "means for analyzing user emotions and reflecting the results in generating suggestions and updating profile data" is a system for analyzing user emotions and using the results in generating suggestions and updating profile data.

[2208] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and generates optimal suggestions based on user emotions and profile data.

[2209] The "means for generating optimal product suggestions" is a mechanism for selecting and suggesting products based on the user's emotions and profile data.

[2210] The "means for receiving user feedback and updating profile data" is a system for collecting user ratings and opinions and updating profile data based on them.

[2211] The present invention relates to a system for virtual stores that makes optimal product suggestions based on a user's personal information and emotional state. This system is composed of the following elements: a means for converting a user's voice input into text, a data transmission means, a text data analysis means, a profile data acquisition means, a location information and environmental data acquisition means, a suggestion generation means, a suggestion transmission means, a suggestion display means, an emotion analysis means, a generative AI model, an optimal product suggestion means, and a feedback reception means.

[2212] Each component of the system operates as follows.

[2213] Voice input and data transmission

[2214] When a user speaks, the device converts the speech into text data using a speech recognition library (e.g., the SpeechRecognition library), which is then sent to the server via the network.

[2215] Data analysis and profile data acquisition

[2216] The server analyzes the received text data and uses natural language processing techniques (e.g., TextBlob) to understand its content. The server also retrieves user profile data (e.g., age, gender, interests) and environmental data (e.g., current location, weather) from a database.

[2217] Sentiment Analysis and Suggestion Generation

[2218] Based on the analyzed text data and the acquired profile data, the server uses a sentiment analysis engine (e.g., TextBlob's sentiment analysis function) to determine the user's sentiment. Based on this sentiment information and profile data, a generative AI model generates optimal product recommendations.

[2219] Submitting and Viewing Proposals

[2220] The generated proposal is sent to the user's terminal via the proposal sending means and displayed on the terminal's display, allowing the user to check the proposed products in the virtual store.

[2221] Feedback and profile data updates

[2222] The feedback provided by the user is then sent back from the device to the server, which analyzes it and updates the profile data, thereby improving the accuracy of future suggestions.

[2223] Specific examples

[2224] 1. User: "I've been feeling stressed lately. Can you suggest some products that will help me relax?"

[2225] 2. System: Converts speech into text and analyzes it. The emotion analysis engine determines the user's emotion as negative.

[2226] 3. The server suggests relaxation products based on the user's profile data and emotional information.

[2227] 4. Device: Show users relaxation products such as "aromatherapy sets" and "massage devices."

[2228] 5. User: "This suggestion is very helpful" provides feedback.

[2229] 6. The server receives the feedback and updates the profile data.

[2230] Prompt Sentence Examples

[2231] Input prompt: "I've been feeling stressed lately. Can you suggest some products that will help me relax?"

[2232] Input to generative AI model: "User's sentiment is negative. Suggest products that will help them relax. User's interests are not related to fitness."

[2233] In this way, the present invention provides a system that can make highly accurate product suggestions by taking into account the user's emotions and personal information.

[2234] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2235] Step 1:

[2236] The user performs voice input. The device captures the user's voice through the microphone. This voice data is used as input and converted into text data using a speech recognition library. The converted text data is generated as output.

[2237] Step 2:

[2238] The converted text data is sent to the server. The device uses a network communication module to send the text data to the server, along with metadata such as the user's ID information.

[2239] Step 3:

[2240] The server parses the received text data, uses a natural language processing library (e.g., TextBlob) to understand the meaning of the text data and extract the user's intent, and generates the results of the parsing as output.

[2241] Step 4:

[2242] The server retrieves the user's profile data from the database, which includes the user's basic information, past behavior history, interests, etc. After receiving this profile data as input, it is used for the next analysis step.

[2243] Step 5:

[2244] The server obtains the user's location and environmental data. Location information is obtained from GPS data, and environmental data such as weather and time of day is obtained from an API. These data are used as inputs to generate the next proposal.

[2245] Step 6:

[2246] Using the sentiment analysis engine, the server analyzes the user's sentiment from the text data. It uses the sentiment analysis function of TextBlob to classify the user's sentiment as positive, negative, or neutral. It generates this sentiment data as output.

[2247] Step 7:

[2248] Using a generative AI model, the server generates optimal product suggestions based on the user's profile data, location information, environmental data, and emotional data. The AI ​​model is trained from past data and generates suggestions based on prompts. This suggestion data is generated as output.

[2249] Step 8:

[2250] The generated proposal is transmitted to the user's terminal. The server uses a communication module to transmit the generated proposal data to the user's terminal. The transmitted proposal data is displayed on the user's terminal.

[2251] Step 9:

[2252] The user provides feedback. The user inputs their evaluation or opinion on the provided suggestion by voice or text. The device sends this feedback data to the server.

[2253] Step 10:

[2254] The server analyzes the user's feedback and updates the profile data. The feedback analysis converts the user's ratings into text data, and the server updates the user's profile data based on the text data. This updated data is used to generate suggestions from the next time onwards.

[2255] 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.

[2256] 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.

[2257] 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.

[2258] 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.

[2259] 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.

[2260] 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.

[2261] 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).

[2262] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2263] 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."

[2264] 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.

[2265] 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).

[2266] 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.

[2267] 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.

[2268] 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.

[2269] 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.

[2270] 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.

[2271] 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.

[2272] 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.

[2273] 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.

[2274] 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, funct...

Claims

1. a means for converting a user's voice input into text; and means for transmitting the converted text data; means for analyzing the received text data; a means for obtaining user profile data; a means for obtaining user location and environmental data; means for generating recommendations based on the analyzed data and the acquired profile and environmental data; means for transmitting the generated proposal; means for displaying submitted proposals; A means to receive user feedback and update profile data A system including:

2. The system of claim 1 , further comprising: means for generating restaurant suggestions based on the analyzed data and the acquired profile and environmental data.

3. The system of claim 1 , further comprising means for generating fashion suggestions based on the analyzed data and the acquired profile and environmental data.

Images