System

Abstract

A system is provided.SOLUTION: A system, comprising: means for inputting a question by a user through a terminal; means for transmitting the question from the terminal to a server; means for receiving the question and analyzing the question through natural language processing; means for searching for related action big data based on a result of the analysis; means for generating a proposal based on a result of the search; means for displaying the generated proposal on a terminal of a user; and means for displaying the proposal on the terminal of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] While the importance of data analysis has increased in recent years, there is a challenge in that it is difficult for individuals and companies without specialized knowledge of data to utilize it effectively. In particular, the visualization and analysis of data necessary for business growth and research advancement requires a high level of expertise, which poses a major barrier for small and medium-sized enterprises and individuals. Furthermore, traditional data consulting services are often expensive and difficult to use. Against this backdrop, there is a demand for systems that lower the barrier to data utilization and make it easy to use. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system including: means for allowing a user to input a question via a terminal; means for transmitting the question to a server; means for analyzing the received question using natural language processing; means for searching for related behavioral big data based on the analysis results; generation AI means for analyzing data based on the search results and generating proposals; means for transmitting the generated proposals to the user's terminal; and means for displaying the proposals on the user's terminal. This system allows users without specialized data knowledge to easily receive data analysis and proposals, lowering the barrier to data utilization and enabling data utilization to meet a variety of needs.

[0006] "User" refers to an individual or organization that utilizes the system to enter questions and receive suggestions.

[0007] "Terminal" refers to the device through which a user accesses the system to enter questions and view suggestions.

[0008] "Server" refers to a centralized computing device that receives user queries, performs analysis and data processing, and generates and transmits final recommendations to the terminal.

[0009] "Natural language processing" refers to techniques and methods for analyzing and understanding natural human language.

[0010] "Behavioral big data" refers to large amounts of diverse behavioral data, such as user search information and location information.

[0011] "Generative AI" refers to artificial intelligence (AI) models used to analyze data and generate recommendations.

[0012] "Data analysis" refers to the process of analyzing collected data to derive useful information and insights.

[0013] "Suggestions" refer to specific answers or strategic advice generated by the system to a user's questions. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention relates to a system that enables users to effectively utilize data. In this system, users input questions via a terminal, and a server analyzes the data based on the questions and provides specific suggestions. Below, the program processing of this system is explained in natural language, with specific examples.

[0036] System Overview

[0037] The system itself works by allowing users to ask questions through an interface, and the generative AI responds with appropriate suggestions. The user's device, the server, and the behavioral big database work together.

[0038] Program processing explanation

[0039] User question input

[0040] The user uses the terminal interface to input a question, for example, a question of the form "What is the best menu for opening a new cafe?"

[0041] Submit a Question

[0042] The terminal sends the entered question to the server as an HTTP request.

[0043] Question Analysis

[0044] The server passes the received question to a natural language processing (NLP) module for text analysis, which identifies what the user is looking for and what data is needed. For example, it extracts keywords such as "new cafe" or "best menu" and identifies the problem domain based on those.

[0045] Finding related data

[0046] The server searches for relevant behavioral big data based on the identified problem domain, such as search trends, location data, and customer visitor information by time of day for cafes.

[0047] Data analysis and proposal generation

[0048] The server passes the searched data to the AI ​​generator, which analyzes it. Using machine learning models and statistical analysis methods, the AI ​​generates the most effective suggestions. For example, it might generate a suggestion like, "The most popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. It would be especially effective to strengthen these menu items during weekday lunch hours."

[0049] Submit a proposal

[0050] The server sends the generated proposal to the user's terminal as an HTTP response.

[0051] View Suggestions

[0052] The terminal displays the received suggestions on a user interface, allowing the user to review the suggestions and take specific actions based on them.

[0053] Specific examples

[0054] For example, if a user asks a question about a new smartphone project, the following steps are taken:

[0055] User question input

[0056] The user types, "What market trends should I look for to help me think about new smartphone features?"

[0057] Submit a Question

[0058] The terminal sends a query to the server.

[0059] Question Analysis

[0060] The server uses natural language processing to analyze keywords such as "smartphone" and "market trends."

[0061] Finding related data

[0062] The server searches behavioral big data and extracts market trends such as high-performance cameras, 5G compatibility, and large-capacity batteries.

[0063] Data analysis and proposal generation

[0064] The server uses generative AI to analyze smartphone features that are in high demand in the market and generate proposals, such as "Recent market trends show an increasing demand for high-performance cameras, 5G compatibility, and large-capacity batteries."

[0065] Submit a proposal

[0066] The server transmits the generated proposal to the user's terminal.

[0067] View Suggestions

[0068] The device displays the suggestions to the user, allowing them to incorporate features based on market trends into new products.

[0069] In this way, the system is designed to enable users to effectively utilize the results of data analysis without having specialized knowledge.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] A user uses the device interface to input a question, for example, "What is the best menu item for opening a new cafe?"

[0073] Step 2:

[0074] The device sends the entered question to the server as an HTTP request, which is structured as text data.

[0075] Step 3:

[0076] The server passes the received question to a Natural Language Processing (NLP) module, which performs text analysis of the question, identifying key keywords and context, to understand the user's intent and identify the information they need.

[0077] Step 4:

[0078] The server searches for relevant behavioral big data based on the keywords and context analyzed through the NLP module, and generates and executes queries to extract the required datasets from the behavioral big database.

[0079] Step 5:

[0080] The server passes the searched data to the Generative AI, which then uses machine learning algorithms to analyze the data and generate specific suggestions based on the analysis results.

[0081] Step 6:

[0082] The server sends the generated proposal to the user's device as an HTTP response. The response consists of JSON format data containing the proposal content.

[0083] Step 7:

[0084] The device displays the received suggestions on the user interface. It parses the received JSON data and presents it to the user in a visually easy-to-understand format. For example, it might say, "Popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. It would be particularly effective to strengthen these menu items during weekday lunch hours."

[0085] In this way, the system provides appropriate data analysis and suggestions based on user questions throughout all processing steps.

[0086] Example 1

[0087] 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."

[0088] In conventional data utilization systems, it is difficult for users without specialized knowledge to effectively analyze data and obtain specific proposals based on the results. In particular, it is extremely time-consuming and requires many steps to properly analyze a user's question, search for appropriate data based on that analysis, and generate proposals. For this reason, there is a demand for an efficient and easy-to-use data utilization system.

[0089] 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.

[0090] In this invention, the server includes means for a user to input a question via an information processing device, means for transmitting the question from the information processing device to the information processing device, means for receiving the question and analyzing it using natural language processing, means for searching a large amount of related data based on the analysis results, generation AI means for performing data analysis based on the search results and generating a proposal, means for transmitting the generated proposal to the user's information processing device, and means for displaying the proposal on the user's information processing device. This enables a user to quickly obtain effective data analysis and specific proposals based on the results of the analysis, even without specialized knowledge.

[0091] An "information processing device" is a device that allows a user to input a question and transmit the question to a server, and refers to electronic devices such as computers, smartphones, and tablets.

[0092] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, extracting meaning from text data and providing appropriate information.

[0093] "Big data" refers to a huge collection of data related to a user's question, including databases and cloud storage for searching and retrieving specific information.

[0094] "Generative AI" is an artificial intelligence technology that uses machine learning models to analyze data, make predictions, and make suggestions.

[0095] "Data analysis" is the process of analyzing acquired data using statistical methods and machine learning models to derive useful information and suggestions.

[0096] "Suggestions" refer to specific actions or ideas presented to users based on the results of data analysis.

[0097] A "user interface" refers to a display screen or operating means that allows a user to interact with a system through an information processing device, and includes a web browser and a mobile application.

[0098] The present invention relates to a system for enabling users to effectively utilize data. In this system, a user inputs a question via an information processing device, and a server analyzes the data based on the question and provides specific suggestions. The following describes in detail an embodiment of this system.

[0099] System Overview

[0100] The system mainly consists of a user's information processing device, a server, and a large database. A question entered by the user is sent from the information processing device to the server, which analyzes the question, searches for and analyzes appropriate data, and returns the results to the user's information processing device.

[0101] Hardware and software used

[0102] Information processing devices: computers, smartphones, tablets, etc.

[0103] Server: Hardware that includes a database management system (DBMS) and data storage such as cloud storage.

[0104] Software: Natural language processing libraries (e.g., NLTK, spaCy), machine learning libraries (e.g., Scikit Learn, TensorFlow).

[0105] Program processing

[0106] User question input

[0107] The user inputs a question using the interface of the information processing device, for example, a question in the format "What is the best menu for opening a new cafe?"

[0108] Submit a Question

[0109] The device sends the user-entered question to the server as an HTTP POST request, which converts the question into JSON format and sends it to the API endpoint.

[0110] Question Analysis

[0111] The server decodes the received HTTP request and extracts the question. It then uses a natural language processing (NLP) module to analyze the text and extract keywords, such as "new cafe" or "best menu."

[0112] Finding related data

[0113] The server searches a large database based on the analyzed keywords, using a database management system (DBMS) or cloud storage to obtain relevant data (e.g., search trends and customer data related to cafes).

[0114] Data analysis and proposal generation

[0115] The server passes the acquired data to a generative AI model for data analysis. The generative AI model generates optimal suggestions based on machine learning algorithms (using, for example, Scikit Learn or TensorFlow). For example, a suggestion might be generated such as, "Popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. It would be particularly effective to strengthen these menu items during weekday lunch hours."

[0116] Submit a proposal

[0117] The server sends the generated proposal to the user's information processing device as an HTTP response. The proposal content is serialized in JSON format and included in the response body.

[0118] View Suggestions

[0119] The device deserializes the received suggestions and displays them in the user interface: in the browser, by dynamically adding the suggestions to HTML using JavaScript; in the mobile app, by updating a dedicated UI component to display the suggestions.

[0120] Specific operation example

[0121] For example, if a user inputs "Please tell me the market trends that will help me think about new smartphone features," the processing will be carried out in the following steps.

[0122] User question input

[0123] The user types, "What market trends should I look for to help me think about new smartphone features?"

[0124] Submit a Question

[0125] The terminal sends a query to the server.

[0126] Question Analysis

[0127] The server uses a natural language processing module to analyze keywords such as "smartphone" and "market trends" and extract information to search for appropriate data.

[0128] Finding related data

[0129] The server searches a large database based on the analyzed keywords and extracts market trends such as high-performance cameras, 5G compatibility, and large-capacity batteries.

[0130] Data analysis and proposal generation

[0131] The server analyzes the data using a generative AI model and generates optimal recommendations for the user, such as, "Recent market trends show an increasing demand for high-performance cameras, 5G compatibility, and large-capacity batteries."

[0132] Submit a proposal

[0133] The server transmits the generated proposal to the user's information processing device.

[0134] View Suggestions

[0135] The terminal displays the proposals on the user interface, allowing users to check the proposals based on market trends and take specific actions.

[0136] In this way, the system is designed to enable users to effectively utilize the results of data analysis without having specialized knowledge.

[0137] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0138] Step 1: User enters question

[0139] A user uses the interface of a data processing device to input a question, such as "What is the best menu item for opening a new cafe?", into a text field. The input is done via a web form or a text box in a mobile app.

[0140] Input: The user's question text.

[0141] Output: The user's question text.

[0142] Step 2: Send the question to the server

[0143] The device sends the user-entered question to the server as an HTTP POST request, which converts the question into JSON format and sends it to the API endpoint.

[0144] Input: The user's question text.

[0145] Output: The HTTP request sent to the server.

[0146] Step 3: The server receives the query

[0147] The server decrypts the received HTTP request and extracts the question text from the request body.

[0148] Input: HTTP request.

[0149] Output: The extracted question text.

[0150] Step 4: Parse the question

[0151] The server passes the extracted question text to a natural language processing (NLP) module for text analysis, for example, using Python's NLTK or spaCy libraries to extract keywords such as "new cafe" or "best menu."

[0152] Input: Question text.

[0153] Output: Extracted keywords.

[0154] Step 5: Find related data

[0155] The server searches a large database based on the extracted keywords. It uses a database management system (DBMS) or cloud storage to retrieve relevant data (e.g., search trends and customer data related to cafes). It performs searches using SQL queries or NoSQL query languages.

[0156] Input: Keywords.

[0157] Output: The relevant data found.

[0158] Step 6: Conduct data analysis

[0159] The server then passes the acquired data to a generative AI model for data analysis, which then analyzes the data using machine learning algorithms (for example, using Scikit Learn or TensorFlow) to generate optimal recommendations.

[0160] Input: The relevant data found.

[0161] Output: The generated proposals.

[0162] Step 7: Submit your proposal

[0163] The server sends the generated proposal to the user's information processing device as an HTTP response. The proposal content is serialized in JSON format and included in the response body.

[0164] Input: The generated proposals.

[0165] Output: The HTTP response sent to the user device.

[0166] Step 8: View suggestions

[0167] The device deserializes the received suggestions and displays them in the user interface: in the browser, by dynamically adding the suggestions to HTML using JavaScript; in the mobile app, by updating a dedicated UI component to display the suggestions.

[0168] Input: The proposal received as an HTTP response.

[0169] Output: The proposal displayed in the user interface.

[0170] (Application example 1)

[0171] 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."

[0172] On conventional online shopping sites, users often have difficulty choosing products and it can take a long time to find the right one. Furthermore, there is a lack of systems that can efficiently gather the information users need and make optimal recommendations based on that information. This leads to issues such as a poor user experience and a decrease in purchasing motivation.

[0173] 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.

[0174] In this invention, the server includes: means for a user to input a question via a terminal; means for transmitting the question from the terminal to the server; means for receiving the question and analyzing it using natural language processing; means for searching for related behavioral big data based on the analysis results; generation AI means for performing data analysis based on the search results and generating proposals; means for transmitting the generated proposals to the user's terminal; means for displaying the proposals on the user's terminal; and means for searching market trend data and customer review data based on a question about product selection and suggesting optimal products through data analysis using behavioral big data including these. This enables the user to efficiently select appropriate products.

[0175] A "user terminal" is a communications-enabled device that a user uses to enter questions and receive suggestions.

[0176] The "means for inputting a question" is a function of the interface that allows a user to input a question in text format via a terminal.

[0177] The "means for transmitting to the server" is a communication means for transferring the question entered by the user at the terminal to the server.

[0178] The "means for receiving a question and analyzing it using natural language processing" is a function in which the server receives a question sent and analyzes it using natural language processing technology.

[0179] "Means for searching related behavioral big data" refers to a function that searches a database for related behavioral data based on the analysis results.

[0180] "Generative AI means for analyzing data and generating proposals" refers to AI technology that uses machine learning models to analyze behavioral big data and generate specific proposals for users.

[0181] The "means for transmitting the generated proposal to the user's terminal" is a communication means for transferring the proposal generated by the server to the user's terminal.

[0182] The "means for displaying the proposal on the user's terminal" is an interface function that allows the user to check the received proposal on the display screen of the terminal.

[0183] "Market trend data" refers to data that indicates current market demand and trends.

[0184] "Customer review data" refers to data regarding ratings and reviews given by customers who have purchased a product.

[0185] "Behavioral big data" refers to large datasets about user behavior and preferences.

[0186] This invention relates to a system in which a user inputs a question via a terminal, a server analyzes the data in response to the question, and generates a proposal and responds. Below, the configuration and operation of the system will be described along with each processing step.

[0187] System Configuration

[0188] This system consists of a terminal used by users, a server that processes data, and a database that integrates them.

[0189] Device: A device with communication capabilities used by a user, such as a smartphone or tablet.

[0190] Server: Backend system using Node.js and Express.js.

[0191] Natural Language Processing Module: A natural language processing engine built using TensorFlow.js.

[0192] Database: MongoDB is used.

[0193] Generative AI model: OpenAI GPT-4 is used.

[0194] Operation process

[0195] 1. User enters question:

[0196] Users input their questions through a terminal interface, which is easy to use and built with React Native.

[0197] 2. Submit your question:

[0198] The question entered by the user is sent to the server as an HTTP POST request.

[0199] 3. Question Analysis:

[0200] The server receives the question and analyzes it using a natural language processing module (TensorFlow.js), extracting keywords from the question and understanding its meaning.

[0201] 4. Search for relevant data:

[0202] Based on the analysis results, the server retrieves relevant behavioral big data from a MongoDB database, including market trend data and customer review data.

[0203] 5. Data analysis and proposal generation:

[0204] The server passes the analyzed data to a generative AI model (OpenAI GPT-4) to generate optimal proposals. Based on the machine learning model, data analysis is performed on market trends and other data to create specific proposals for users.

[0205] 6. Submitting and Viewing Proposals:

[0206] The generated proposal is sent to the user's device as an HTTP response, where the user can view the proposal in the device interface.

[0207] Specific examples

[0208] For example, if a user enters the question, "What are the best suggestions for choosing a new smartphone model?", the system operates as follows: The server receives the question and analyzes keywords such as "smartphone" and "model selection" through natural language processing. Next, it searches related market trend data and customer review data and generates optimal suggestions using a generative AI model. It provides the user with suggestions such as, "According to the latest market trends, models with high camera performance are popular. The Model X in particular has high ratings, and its battery tends to be large-capacity and long-lasting."

[0209] Example prompts for generative AI models

[0210] What are your best suggestions for choosing a new smartphone model?

[0211] Input data: customer reviews, sales data, rating rankings

[0212] This allows users to quickly and accurately select the most suitable product, improving the quality of the user experience.

[0213] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0214] Step 1:

[0215] The user uses a device such as a smartphone or tablet to input a question through the interface of the online shopping app.

[0216] Input: User question (e.g., "What are your best suggestions for choosing a new smartphone model?")

[0217] Output: The question text entered

[0218] What happens: The user types a question into the text box and taps the "Submit" button.

[0219] Step 2:

[0220] The terminal sends the entered question to the server as an HTTP POST request.

[0221] Input: The question text entered by the user

[0222] Output: HTTP request sent to the server

[0223] How it works: The question text is sent in the body of an HTTP request to the server's API endpoint.

[0224] Step 3:

[0225] The server receives the received question and passes it to the natural language processing (NLP) module for analysis.

[0226] Input: The question text received by the server

[0227] Output: Analysis results (keywords and their semantic information)

[0228] How it works: The server uses TensorFlow.js to analyze the question text and extract keywords and their meanings. For example, keywords such as "smartphone" and "model selection" are extracted.

[0229] Step 4:

[0230] The server searches for relevant behavioral big data based on the analysis results.

[0231] Input: Analysis results (e.g., keywords "smartphone" and "model selection")

[0232] Output: Relevant datasets (market trend data, customer review data, etc.)

[0233] How it works: The server queries MongoDB to find and retrieve data (market trends, customer reviews) that matches the set criteria.

[0234] Step 5:

[0235] The server passes the retrieved data to a generative AI model to generate optimal suggestions.

[0236] Input: Related datasets

[0237] Output: Generated suggestions (e.g., "According to the latest market trends, models with high camera performance are popular. The Model X in particular is highly rated.")

[0238] How it works: The server uses OpenAI GPT-4 to generate suggestions based on the provided dataset, and outputs the suggestions in text format.

[0239] Step 6:

[0240] The server sends the generated proposal to the user's terminal as an HTTP response.

[0241] Input: Generated suggested text

[0242] Output: Suggested text sent to the user's device

[0243] How it works: The server places the generated proposal in the body of an HTTP response and sends it to the user's device.

[0244] Step 7:

[0245] The terminal displays the received proposals on its interface.

[0246] Input: Suggested text received from the server

[0247] Output: The suggestions displayed

[0248] Operation: The user's device displays the received suggested text on the screen for the user to review.

[0249] 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.

[0250] The present invention relates to a system in which a generative AI uses an emotion engine to recognize emotions in response to user questions and make optimal suggestions. Below, the processing of the system's program is explained in natural language, and specific examples based on the claims are also provided.

[0251] System Overview

[0252] In this system, users input questions via their devices, the server performs data analysis and sentiment analysis based on the questions, and the generative AI generates appropriate suggestions and provides them to the user. The system includes the following elements:

[0253] The device where the user enters their question

[0254] A server that identifies problem areas and analyzes related behavioral big data and emotional information

[0255] Emotion Engine

[0256] Generation AI

[0257] An interface that presents suggestions to the user

[0258] Program processing explanation

[0259] User question input

[0260] The user inputs a question using the terminal interface, such as "What is the best menu for opening a new cafe?"

[0261] Submit a Question

[0262] The terminal sends the entered question to the server as an HTTP request.

[0263] Question analysis and emotion recognition

[0264] The server passes the received question to a natural language processing (NLP) module for text analysis and keyword extraction, thereby understanding what the user is asking.

[0265] The server simultaneously analyzes the emotion contained in the question using an emotion engine, determining, for example, whether the entered text indicates an emotional state such as "excitement," "confusion," or "happiness."

[0266] Retrieval of relevant data and integration of emotional information

[0267] The server searches for relevant data from the behavioral big database based on keywords and context derived from NLP analysis.

[0268] The server also incorporates emotional information obtained from the emotion engine into the data analysis. For example, a passionate message can generate a proposal that requires innovation, while a confused message can generate a proposal that requires clarity and a sense of security.

[0269] Data analysis and proposal generation

[0270] The server uses a generative AI to analyze behavioral big data and emotional information to generate suggestions. The generative AI then uses a machine learning model to analyze this data and provide the most appropriate suggestions.

[0271] Submit a proposal

[0272] The server sends the generated proposal to the user's device as an HTTP response. The proposal is structured in JSON format or similar.

[0273] View Suggestions

[0274] The device displays the received suggestions on a user interface, where the suggestions are presented to the user in a visually easy-to-understand format.

[0275] Specific examples

[0276] For example, consider the case where a user asks a question about a new smartphone project.

[0277] User question input

[0278] User: "What market trends are driving new smartphone features?"

[0279] Submit a Question

[0280] Terminal: Send the above question to the server.

[0281] Question analysis and emotion recognition

[0282] Server: Analyzes questions using natural language processing to extract keywords such as "smartphone" and "market trends," and uses an emotion engine to analyze user emotions and detect rising levels of "excitement."

[0283] Retrieval of relevant data and integration of emotional information

[0284] Server: Searches for market trends such as high-performance cameras, 5G compatibility, and large-capacity batteries from behavioral big data. At the same time, it analyzes emotional information and considers innovative proposals based on the user's excitement level.

[0285] Data analysis and proposal generation

[0286] Server: Generative AI analyzes data and emotional information to generate recommendations tailored to the user. For example, it might generate a recommendation like, "The latest market trends demand high-performance cameras, 5G compatibility, and large-capacity batteries. By incorporating these features into your new product, you can increase your competitiveness."

[0287] Submit a proposal

[0288] Server: Sends the generated proposals to the user's device.

[0289] View Suggestions

[0290] On the device: The received suggestions are displayed in the user interface, allowing the user to review the suggestions and take specific actions based on them.

[0291] In this way, the system allows users to receive useful suggestions based on data analysis and sentiment information without requiring specialized knowledge.

[0292] The processing flow will be explained below.

[0293] This invention relates to a system in which a generative AI uses an emotion engine to recognize emotions in response to user questions and make optimal suggestions. The system's processing flow and specific operations are explained in the following steps.

[0294] System processing steps

[0295] Step 1:

[0296] A user uses the device interface to input a question, for example, "What is the best menu item for opening a new cafe?"

[0297] Step 2:

[0298] The device sends the entered question to the server as an HTTP request, which is structured as text data.

[0299] Step 3:

[0300] The server passes the received question to a natural language processing (NLP) module for text analysis and keyword extraction. For example, it extracts keywords such as "cafe," "opening," "optimal," and "menu," and analyzes the context.

[0301] Step 4:

[0302] The server uses an emotion engine to analyze the emotion contained in the question. For example, it identifies emotions such as "excitement" or "anxiety" from the wording. This is done using a sentiment analysis algorithm.

[0303] Step 5:

[0304] The server searches for relevant behavioral big data based on keywords extracted by NLP and emotional information recognized by the emotion engine. For example, it searches for search trends related to "cafes" and "menus" or regional characteristic data based on the user's location information.

[0305] Step 6:

[0306] The server then passes the searched data and sentiment information to the AI ​​generator, which then uses machine learning algorithms to determine, for example, that "latte art cafe latte" and "homemade cinnamon rolls" are popular in the area.

[0307] Step 7:

[0308] The server uses generative AI to generate specific suggestions, taking into account the user's emotional state, such as, "The most popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. In particular, based on your excitement level, we highly recommend you try a new menu item."

[0309] Step 8:

[0310] The server sends the generated proposal to the user's device as an HTTP response, which is typically structured in JSON format.

[0311] Step 9:

[0312] The device displays the received suggestions on the user interface, using graphs, lists, and other formats that are visually easy for the user to understand.

[0313] Specific examples

[0314] For example, if a user asks a question about a new smartphone project:

[0315] Step 1:

[0316] A user types, "What market trends will help me think about new smartphone features?"

[0317] Step 2:

[0318] The terminal sends a question to the server.

[0319] Step 3:

[0320] The server uses NLP to analyze the text and extract keywords such as "smartphone" and "market trends."

[0321] Step 4:

[0322] The server uses an emotion engine to identify emotions such as "excitement" or "expectation" contained in the user's question.

[0323] Step 5:

[0324] The server searches for relevant data from the behavioral big data based on the extracted keywords and emotional information. For example, it searches for trend data such as "high-performance camera," "5G compatible," and "large-capacity battery."

[0325] Step 6:

[0326] The server passes the searched data and sentiment information to the generative AI, which then performs data analysis. For example, based on market trends, it determines that a high-performance camera, 5G compatibility, and a large-capacity battery are important.

[0327] Step 7:

[0328] The server uses generative AI to generate suggestions, such as, "Recent market trends demand high-performance cameras, 5G compatibility, and large-capacity batteries. In particular, based on your excitement level, we strongly recommend that you actively adopt new technologies."

[0329] Step 8:

[0330] The server transmits the generated proposal to the user's terminal.

[0331] Step 9:

[0332] The device displays the received proposals on the user interface, allowing the user to come up with specific project ideas based on the proposals.

[0333] In this way, the system allows users to receive useful suggestions based on data analysis and sentiment information without requiring specialized knowledge.

[0334] Example 2

[0335] 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."

[0336] Conventional systems simply analyze data based on questions entered by users and generate suggestions, making it difficult to fully understand the user's emotions and intentions and provide optimal suggestions. As a result, the suggestions often do not meet the user's needs, resulting in a decrease in user satisfaction.

[0337] 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.

[0338] In this invention, the server includes means for analyzing questions using natural language processing, means for acquiring emotional information using an emotion analysis engine, means for searching for related data based on the analysis results and the emotional information, and means for generating suggestions based on the analysis results and the emotional information using a generation AI, thereby enabling optimal suggestions that take into account the user's emotions and intentions.

[0339] A "user" is an entity that utilizes the system to enter questions and receive suggestions.

[0340] A "terminal" is a computing device or interface through which a user enters a query and communicates with a server.

[0341] A "question" is information or a problem that a user inputs via a terminal.

[0342] A "server" is a computer system that receives user-entered questions and performs analysis and suggestion generation.

[0343] "Natural language processing" is a technology that analyzes questions and extracts keywords and intent from text.

[0344] An "emotion analysis engine" is software or a module for analyzing the emotional information contained in an input question.

[0345] "Relevant data" refers to information required for generating suggestions, retrieved based on natural language processing and sentiment information.

[0346] "Generative AI" is artificial intelligence that uses machine learning models to generate suggestions based on analysis results and emotional information.

[0347] A "suggestion" is an answer or recommendation that the generative AI creates based on the user's question and related data.

[0348] The present invention relates to a system in which a generation AI uses an emotion engine to recognize emotions in response to a user's question and make optimal suggestions. In this system, the user inputs a question via a terminal, a server performs data analysis and emotion analysis based on the question, and the generation AI generates appropriate suggestions and provides them to the user. The system includes the following elements:

[0349] The device where the user enters their question

[0350] A server that identifies problem areas and analyzes related behavioral big data and emotional information

[0351] Emotion Engine

[0352] Generation AI

[0353] An interface that presents suggestions to the user

[0354] User question input

[0355] The user uses the device interface to input a specific question, such as "What is the best menu for opening a new cafe?"

[0356] Submit a Question

[0357] The device sends the entered question as an HTTP request to the server, with the data packaged in JSON format.

[0358] Question analysis and emotion recognition

[0359] The server passes the received question to a natural language processing (NLP) module for text analysis and keyword extraction. This allows it to understand what the user is asking. At the same time, it uses an emotion engine to analyze the emotion contained in the question. For example, it determines whether the input text indicates an emotional state such as "excitement," "confusion," or "joy."

[0360] Retrieval of relevant data and integration of emotional information

[0361] The server searches for relevant data from the behavioral big database based on keywords and context derived from NLP analysis. At the same time, emotional information obtained from the emotion engine is also incorporated into the data analysis. For example, a passionate message will generate a proposal that requires innovation, while a confused message will generate a proposal that requires clarity and a sense of security.

[0362] Data analysis and proposal generation

[0363] The server uses generative AI to analyze behavioral big data and emotional information to generate proposals. Generative AI then uses machine learning models to analyze this data and make the most appropriate proposals. For example, it generates specific proposals such as, "The latest market trends call for high-performance cameras, 5G compatibility, and large-capacity batteries. By incorporating these features into your new product, you can increase your competitiveness."

[0364] Submit a proposal

[0365] The server sends the generated proposal to the user's device as an HTTP response, structured in JSON format.

[0366] View Suggestions

[0367] The device displays the received suggestions in a user interface, where the suggestions are presented to the user in a visually understandable format, such as charts, tables, or text descriptions.

[0368] Specific examples

[0369] For example, consider the case where a user asks a question about a new smartphone project.

[0370] User: "What market trends are driving new smartphone features?"

[0371] Terminal: Package it in JSON format and send an HTTP request to the API endpoint.

[0372] Server: Interprets the received request and performs analysis using the NLP module and emotion engine.

[0373] Server: Obtains relevant market trend data from the behavioral big database and generates proposals using the generative AI model.

[0374] Server: Sends the generated proposal in JSON format to the device.

[0375] Terminal: Proposals are displayed on the user interface, and the user can review the suggestions and take specific action based on them.

[0376] In this way, the system allows users to receive useful suggestions based on data analysis and sentiment information without having to have specialized knowledge.

[0377] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0378] Step 1: User enters question

[0379] The user opens the device interface and inputs a specific question, for example, "What is the best menu for opening a new cafe?" The question entered through the device interface is stored in the device's internal memory.

[0380] Step 2: Triggering a Question to be Submitted

[0381] The user clicks the send button, which triggers the sending of the entered question to the server. This causes the question data to be formatted into an HTTP request format on the terminal. The input is the user's click, and the output is the question data packaged in JSON format.

[0382] Step 3: Sending an HTTP request

[0383] The terminal sends question data packaged in JSON format to the server. The input is the packaged question data, and the output is an HTTP request to the server.

[0384] Step 4: Receiving the request

[0385] The server receives an HTTP request sent from a terminal. The input is the question data sent from the terminal, and the output is the temporary storage of the question data in the server.

[0386] Step 5: Passing to the Natural Language Processing (NLP) module

[0387] The server passes the question to a natural language processing (NLP) module, which tokenizes the text, tags it with parts of speech, and extracts keywords. The input is the question data, and the output is the tokenized text and extracted keywords.

[0388] Step 6: Sentiment analysis using a sentiment analysis engine

[0389] The server passes the text and keywords obtained from the NLP analysis to an emotion analysis engine to estimate the emotional state. The input is the NLP analysis result, and the output is an emotion tag such as "excitement," "confusion," or "joy."

[0390] Step 7: Generate Database Queries

[0391] The server generates a query to search the behavioral big database based on the keywords and emotion information obtained from the NLP module. The input is the keywords and emotion information, and the output is the database query.

[0392] Step 8: Database Search

[0393] The server uses the generated query to search for relevant data from the behavioral big database. The input is the database query, and the output is a relevant dataset, which may contain, for example, information about cafe menus or market trends.

[0394] Step 9: Proposal generation by generative AI

[0395] The server passes the acquired data and emotional information to the generative AI model to generate recommendations. The input is the relevant dataset and emotional information, and the output is a specific recommendation to the user. For example, a specific recommendation such as "According to the latest market trends, high-performance cameras, 5G compatibility, and large-capacity batteries are required" may be generated.

[0396] Step 10: Formatting the Proposal Data

[0397] The server structures the generated proposal in JSON format and packages it as an HTTP response. The input is the generated proposal and the output is structured data in JSON format.

[0398] Step 11: Send HTTP response

[0399] The server sends formatted proposal data to the user's device. The input is the proposal data in JSON format, and the output is an HTTP response sent to the device.

[0400] Step 12: Receiving Proposal Data

[0401] The terminal receives the proposed data sent from the server as an HTTP response. The input is the proposed data from the server, and the output is the data stored in the terminal.

[0402] Step 13: Display in the User Interface

[0403] The device parses the received suggestion data and displays it on the user interface. The suggestion content is presented in a visually easy-to-understand format. The input is the received suggestion data, and the output is the display on the user interface. The user can check the suggestion content and decide on a specific action based on it.

[0404] (Application example 2)

[0405] 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."

[0406] Conventional systems typically respond to user questions by simply analyzing or searching for answers, making it difficult to provide suggestions that take into account the emotional state of the questioner. Furthermore, particularly in the security field, there is a need for systems that can appropriately recognize emotions such as tension and anxiety among on-site staff and provide sophisticated suggestions. The present invention aims to solve these problems and provide a system that generates suggestions optimized for the user's emotions.

[0407] 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 a user to input a question via an input device; means for transmitting the question from the input device to the data processing device; means for receiving the question and analyzing it using natural language processing; means for searching for related behavioral data based on the analysis results; generation AI means for performing data analysis based on the search results and generating a proposal; means for transmitting the proposal to the user's input device; means for displaying the proposal on the user's input device; means for analyzing the question using an emotion engine and extracting emotion information; and means for optimizing the generated proposal by integrating the emotion information. This enables the generation of advanced proposals that take user emotions into consideration.

[0408] An "input device" is a device used by a user to input a question, and includes a microphone, keyboard, smartphone, tablet, or other electronic device.

[0409] "Data Processing Unit" refers to the server or cloud computing platform that receives, analyzes and processes queries submitted by users.

[0410] "Natural language processing" is a technology that formalizes input user questions and understands the content of the questions by performing text analysis and keyword extraction.

[0411] "Behavioral data" includes the user's past behavioral history, access history, and other related data, and is data that is searched according to the content of the question.

[0412] "Generative AI" is an artificial intelligence technology that uses machine learning models to analyze behavioral data and emotional information to generate optimal suggestions.

[0413] The "emotion engine" is a system that analyzes the user's emotional state from their questions and behavior, and extracts emotional information such as "relief," "confusion," and "excitement."

[0414] "Suggestion" refers to the optimal answer or recommended action output by the generative AI based on the user's question and emotional information.

[0415] "Data analysis" refers to the process of discovering hidden patterns and trends based on behavioral data and emotional information, and generating optimal suggestions based on the questions asked.

[0416] "Optimization" means that the content of the proposal is adjusted based on the extracted emotional information according to the emotional state of the user, and the most appropriate proposal is provided.

[0417] This invention is a system that uses an emotion engine to recognize emotions in response to user questions and uses generative AI to provide optimal suggestions.

[0418] System Overview

[0419] The system involves a procedure in which a user inputs a question via an input device (e.g., a microphone or smartphone), and the question is sent to a data processing device (e.g., a cloud server). The server analyzes the question using natural language processing (NLP), searches for relevant behavioral data, and performs sentiment analysis using an emotion engine. Based on this, a generative AI generates appropriate suggestions, which are finally sent to the user's input device and displayed.

[0420] Hardware and software used

[0421] Input device: The device the user uses to input a question. Examples include a microphone or a smartphone.

[0422] Data Processing Unit: A server or cloud computing platform that receives, analyzes, and processes user-submitted queries. An example is Amazon Web Services (AWS) EC2.

[0423] Natural Language Processing (NLP) module: A technology that uses the Google Cloud Natural Language API to formalize input user questions and perform text analysis and keyword extraction.

[0424] Emotion engine: A system that uses IBM Watson Tone Analyzer to analyze the user's emotional state from their questions and actions.

[0425] Generative AI: An artificial intelligence technology that implements machine learning models using OpenAI GPT-3.5 to analyze data and emotional information and generate optimal suggestions.

[0426] Specific explanation of the process

[0427] 1. User Question Input: The user uses an input device to enter a question verbally or as text. For example, a question might be, "Is this person safe to grant access?"

[0428] 2. Sending a question: The input device sends a question to the data processing device. The sending method is mainly an HTTP request.

[0429] 3. Question analysis and emotion recognition: When the server receives a question, it analyzes it using a natural language processing module. At the same time, it uses an emotion engine to extract emotional information contained in the question. Emotions such as "worry," "confusion," and "relief" are identified.

[0430] 4. Searching for related data and integrating emotional information: Based on the analysis results, the server searches for related information from the behavior database and integrates emotional information for analysis. This allows the server to consider suggestions that are appropriate for the user's emotions.

[0431] 5. Proposal generation by generative AI: Generative AI analyzes behavioral data and emotional information to generate optimal suggestions. Specific suggestions such as "There are no problems with this person's past visit history, so please allow access" can be obtained.

[0432] 6. Sending and displaying suggestions: The server sends the generated suggestions to the input device and displays them on the user's device. The user can review the displayed suggestions and take appropriate action.

[0433] Examples of concrete examples and prompts

[0434] As a specific example of use, consider the case where a user asks the following question in a security situation:

[0435] (Example of a prompt)

[0436] A visitor is standing at the front door. On-site staff are asking, "Is this person safe to grant access?" The staff is in an emotional state of "worried." Review past visit history and alarm records to generate optimal suggestions.

[0437] Such prompts allow the server to analyze the situation and generate and display optimal suggestions.

[0438] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0439] Step 1:

[0440] The user enters a question using an input device. The input device accepts voice or text input and formats the question as digital data. At this point, the entered data is captured as "voice data" or "text data."

[0441] Step 2:

[0442] The terminal sends the entered question as an HTTP request to the data processing device. The input here is captured "voice data" or "text data," which is used as the payload of the HTTP request. The sent data is stored on the server.

[0443] Step 3:

[0444] The server receives the question and analyzes it using a natural language processing (NLP) module. Here, "voice data" or "text data" is received, and the NLP module performs text analysis and keyword extraction. The analyzed "keyword data" and "structured text data" are generated as output.

[0445] Step 4:

[0446] The server searches for related behavioral data based on the analysis results. The input is "keyword data" and "structured text data," and the output is related "behavioral data." The behavioral database is searched to obtain the required information.

[0447] Step 5:

[0448] The server analyzes the question using an emotion engine and extracts emotional information. Here, "structured text data" is input into the emotion engine, which then outputs "emotional information." This emotional information includes emotional states such as "worry," "excitement," and "relief."

[0449] Step 6:

[0450] The server integrates the emotional information and combines it with behavioral data to generate suggestions using generative AI. The inputs are "behavioral data" and "emotional information," and the output is "optimal suggestions." The generative AI model analyzes this data and generates suggestions optimized for the user's emotional state.

[0451] Step 7:

[0452] The server sends the generated proposal to the terminal as an HTTP response. Here, the server creates an HTTP response using the "optimal proposal" as input and sends it to the terminal.

[0453] Step 8:

[0454] The device displays the suggestions on the user's input device. The received "optimal suggestions" are visually presented to the user, who can then check them and take appropriate action.

[0455] In this way, a system is realized that performs specific data processing and data calculation at each processing step and provides optimal suggestions to the user.

[0456] 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.

[0457] 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.

[0458] 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.

[0459] [Second embodiment]

[0460] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0461] 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.

[0462] 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).

[0463] 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.

[0464] 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.

[0465] 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).

[0466] 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.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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."

[0472] This invention relates to a system that enables users to effectively utilize data. In this system, users input questions via a terminal, and a server analyzes the data based on the questions and provides specific suggestions. Below, the program processing of this system is explained in natural language, with specific examples.

[0473] System Overview

[0474] The system itself works by allowing users to ask questions through an interface, and the generative AI responds with appropriate suggestions. The user's device, the server, and the behavioral big database work together.

[0475] Program processing explanation

[0476] User question input

[0477] The user uses the terminal interface to input a question, for example, a question of the form "What is the best menu for opening a new cafe?"

[0478] Submit a Question

[0479] The terminal sends the entered question to the server as an HTTP request.

[0480] Question Analysis

[0481] The server passes the received question to a natural language processing (NLP) module for text analysis, which identifies what the user is looking for and what data is needed. For example, it extracts keywords such as "new cafe" or "best menu" and identifies the problem domain based on those.

[0482] Finding related data

[0483] The server searches for relevant behavioral big data based on the identified problem domain, such as search trends, location data, and customer visitor information by time of day for cafes.

[0484] Data analysis and proposal generation

[0485] The server passes the searched data to the AI ​​generator, which analyzes it. Using machine learning models and statistical analysis methods, the AI ​​generates the most effective suggestions. For example, it might generate a suggestion like, "The most popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. It would be especially effective to strengthen these menu items during weekday lunch hours."

[0486] Submit a proposal

[0487] The server sends the generated proposal to the user's terminal as an HTTP response.

[0488] View Suggestions

[0489] The terminal displays the received suggestions on a user interface, allowing the user to review the suggestions and take specific actions based on them.

[0490] Specific examples

[0491] For example, if a user asks a question about a new smartphone project, the following steps are taken:

[0492] User question input

[0493] The user types, "What market trends should I look for to help me think about new smartphone features?"

[0494] Submit a Question

[0495] The terminal sends a query to the server.

[0496] Question Analysis

[0497] The server uses natural language processing to analyze keywords such as "smartphone" and "market trends."

[0498] Finding related data

[0499] The server searches behavioral big data and extracts market trends such as high-performance cameras, 5G compatibility, and large-capacity batteries.

[0500] Data analysis and proposal generation

[0501] The server uses generative AI to analyze smartphone features that are in high demand in the market and generate proposals, such as "Recent market trends show an increasing demand for high-performance cameras, 5G compatibility, and large-capacity batteries."

[0502] Submit a proposal

[0503] The server transmits the generated proposal to the user's terminal.

[0504] View Suggestions

[0505] The device displays the suggestions to the user, allowing them to incorporate features based on market trends into new products.

[0506] In this way, the system is designed to enable users to effectively utilize the results of data analysis without having specialized knowledge.

[0507] The processing flow will be explained below.

[0508] Step 1:

[0509] A user uses the device interface to input a question, for example, "What is the best menu item for opening a new cafe?"

[0510] Step 2:

[0511] The device sends the entered question to the server as an HTTP request, which is structured as text data.

[0512] Step 3:

[0513] The server passes the received question to a Natural Language Processing (NLP) module, which performs text analysis of the question, identifying key keywords and context, to understand the user's intent and identify the information they need.

[0514] Step 4:

[0515] The server searches for relevant behavioral big data based on the keywords and context analyzed through the NLP module, and generates and executes queries to extract the required datasets from the behavioral big database.

[0516] Step 5:

[0517] The server passes the searched data to the Generative AI, which then uses machine learning algorithms to analyze the data and generate specific suggestions based on the analysis results.

[0518] Step 6:

[0519] The server sends the generated proposal to the user's device as an HTTP response. The response consists of JSON format data containing the proposal content.

[0520] Step 7:

[0521] The device displays the received suggestions on the user interface. It parses the received JSON data and presents it to the user in a visually easy-to-understand format. For example, it might say, "Popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. It would be particularly effective to strengthen these menu items during weekday lunch hours."

[0522] In this way, the system provides appropriate data analysis and suggestions based on user questions throughout all processing steps.

[0523] Example 1

[0524] 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."

[0525] In conventional data utilization systems, it is difficult for users without specialized knowledge to effectively analyze data and obtain specific proposals based on the results. In particular, it is extremely time-consuming and requires many steps to properly analyze a user's question, search for appropriate data based on that analysis, and generate proposals. For this reason, there is a demand for an efficient and easy-to-use data utilization system.

[0526] 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.

[0527] In this invention, the server includes means for a user to input a question via an information processing device, means for transmitting the question from the information processing device to the information processing device, means for receiving the question and analyzing it using natural language processing, means for searching a large amount of related data based on the analysis results, generation AI means for performing data analysis based on the search results and generating a proposal, means for transmitting the generated proposal to the user's information processing device, and means for displaying the proposal on the user's information processing device. This enables a user to quickly obtain effective data analysis and specific proposals based on the results of the analysis, even without specialized knowledge.

[0528] An "information processing device" is a device that allows a user to input a question and transmit the question to a server, and refers to electronic devices such as computers, smartphones, and tablets.

[0529] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, extracting meaning from text data and providing appropriate information.

[0530] "Big data" refers to a huge collection of data related to a user's question, including databases and cloud storage for searching and retrieving specific information.

[0531] "Generative AI" is an artificial intelligence technology that uses machine learning models to analyze data, make predictions, and make suggestions.

[0532] "Data analysis" is the process of analyzing acquired data using statistical methods and machine learning models to derive useful information and suggestions.

[0533] "Suggestions" refer to specific actions or ideas presented to users based on the results of data analysis.

[0534] A "user interface" refers to a display screen or operating means that allows a user to interact with a system through an information processing device, and includes a web browser and a mobile application.

[0535] The present invention relates to a system for enabling users to effectively utilize data. In this system, a user inputs a question via an information processing device, and a server analyzes the data based on the question and provides specific suggestions. The following describes in detail an embodiment of this system.

[0536] System Overview

[0537] The system mainly consists of a user's information processing device, a server, and a large database. A question entered by the user is sent from the information processing device to the server, which analyzes the question, searches for and analyzes appropriate data, and returns the results to the user's information processing device.

[0538] Hardware and software used

[0539] Information processing devices: computers, smartphones, tablets, etc.

[0540] Server: Hardware that includes a database management system (DBMS) and data storage such as cloud storage.

[0541] Software: Natural language processing libraries (e.g., NLTK, spaCy), machine learning libraries (e.g., Scikit Learn, TensorFlow).

[0542] Program processing

[0543] User question input

[0544] The user inputs a question using the interface of the information processing device, for example, a question in the format "What is the best menu for opening a new cafe?"

[0545] Submit a Question

[0546] The device sends the user-entered question to the server as an HTTP POST request, which converts the question into JSON format and sends it to the API endpoint.

[0547] Question Analysis

[0548] The server decodes the received HTTP request and extracts the question. It then uses a natural language processing (NLP) module to analyze the text and extract keywords, such as "new cafe" or "best menu."

[0549] Finding related data

[0550] The server searches a large database based on the analyzed keywords, using a database management system (DBMS) or cloud storage to obtain relevant data (e.g., search trends and customer data related to cafes).

[0551] Data analysis and proposal generation

[0552] The server passes the acquired data to a generative AI model for data analysis. The generative AI model generates optimal suggestions based on machine learning algorithms (using, for example, Scikit Learn or TensorFlow). For example, a suggestion might be generated such as, "Popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. It would be particularly effective to strengthen these menu items during weekday lunch hours."

[0553] Submit a proposal

[0554] The server sends the generated proposal to the user's information processing device as an HTTP response. The proposal content is serialized in JSON format and included in the response body.

[0555] View Suggestions

[0556] The device deserializes the received suggestions and displays them in the user interface: in the browser, by dynamically adding the suggestions to HTML using JavaScript; in the mobile app, by updating a dedicated UI component to display the suggestions.

[0557] Specific operation example

[0558] For example, if a user inputs "Please tell me the market trends that will help me think about new smartphone features," the processing will be carried out in the following steps.

[0559] User question input

[0560] The user types, "What market trends should I look for to help me think about new smartphone features?"

[0561] Submit a Question

[0562] The terminal sends a query to the server.

[0563] Question Analysis

[0564] The server uses a natural language processing module to analyze keywords such as "smartphone" and "market trends" and extract information to search for appropriate data.

[0565] Finding related data

[0566] The server searches a large database based on the analyzed keywords and extracts market trends such as high-performance cameras, 5G compatibility, and large-capacity batteries.

[0567] Data analysis and proposal generation

[0568] The server analyzes the data using a generative AI model and generates optimal recommendations for the user, such as, "Recent market trends show an increasing demand for high-performance cameras, 5G compatibility, and large-capacity batteries."

[0569] Submit a proposal

[0570] The server transmits the generated proposal to the user's information processing device.

[0571] View Suggestions

[0572] The terminal displays the proposals on the user interface, allowing users to check the proposals based on market trends and take specific actions.

[0573] In this way, the system is designed to enable users to effectively utilize the results of data analysis without having specialized knowledge.

[0574] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0575] Step 1: User enters question

[0576] A user uses the interface of a data processing device to input a question, such as "What is the best menu item for opening a new cafe?", into a text field. The input is done via a web form or a text box in a mobile app.

[0577] Input: The user's question text.

[0578] Output: The user's question text.

[0579] Step 2: Send the question to the server

[0580] The device sends the user-entered question to the server as an HTTP POST request, which converts the question into JSON format and sends it to the API endpoint.

[0581] Input: The user's question text.

[0582] Output: The HTTP request sent to the server.

[0583] Step 3: The server receives the query

[0584] The server decrypts the received HTTP request and extracts the question text from the request body.

[0585] Input: HTTP request.

[0586] Output: The extracted question text.

[0587] Step 4: Parse the question

[0588] The server passes the extracted question text to a natural language processing (NLP) module for text analysis, for example, using Python's NLTK or spaCy libraries to extract keywords such as "new cafe" or "best menu."

[0589] Input: Question text.

[0590] Output: Extracted keywords.

[0591] Step 5: Find related data

[0592] The server searches a large database based on the extracted keywords. It uses a database management system (DBMS) or cloud storage to retrieve relevant data (e.g., search trends and customer data related to cafes). It performs searches using SQL queries or NoSQL query languages.

[0593] Input: Keywords.

[0594] Output: The relevant data found.

[0595] Step 6: Conduct data analysis

[0596] The server then passes the acquired data to a generative AI model for data analysis, which then analyzes the data using machine learning algorithms (for example, using Scikit Learn or TensorFlow) to generate optimal recommendations.

[0597] Input: The relevant data found.

[0598] Output: The generated proposals.

[0599] Step 7: Submit your proposal

[0600] The server sends the generated proposal to the user's information processing device as an HTTP response. The proposal content is serialized in JSON format and included in the response body.

[0601] Input: The generated proposals.

[0602] Output: The HTTP response sent to the user device.

[0603] Step 8: View suggestions

[0604] The device deserializes the received suggestions and displays them in the user interface: in the browser, by dynamically adding the suggestions to HTML using JavaScript; in the mobile app, by updating a dedicated UI component to display the suggestions.

[0605] Input: The proposal received as an HTTP response.

[0606] Output: The proposal displayed in the user interface.

[0607] (Application example 1)

[0608] 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."

[0609] On conventional online shopping sites, users often have difficulty choosing products and it can take a long time to find the right one. Furthermore, there is a lack of systems that can efficiently gather the information users need and make optimal recommendations based on that information. This leads to issues such as a poor user experience and a decrease in purchasing motivation.

[0610] 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.

[0611] In this invention, the server includes: means for a user to input a question via a terminal; means for transmitting the question from the terminal to the server; means for receiving the question and analyzing it using natural language processing; means for searching for related behavioral big data based on the analysis results; generation AI means for performing data analysis based on the search results and generating proposals; means for transmitting the generated proposals to the user's terminal; means for displaying the proposals on the user's terminal; and means for searching market trend data and customer review data based on a question about product selection and suggesting optimal products through data analysis using behavioral big data including these. This enables the user to efficiently select appropriate products.

[0612] A "user terminal" is a communications-enabled device that a user uses to enter questions and receive suggestions.

[0613] The "means for inputting a question" is a function of the interface that allows a user to input a question in text format via a terminal.

[0614] The "means for transmitting to the server" is a communication means for transferring the question entered by the user at the terminal to the server.

[0615] The "means for receiving a question and analyzing it using natural language processing" is a function in which the server receives a question sent and analyzes it using natural language processing technology.

[0616] "Means for searching related behavioral big data" refers to a function that searches a database for related behavioral data based on the analysis results.

[0617] "Generative AI means for analyzing data and generating proposals" refers to AI technology that uses machine learning models to analyze behavioral big data and generate specific proposals for users.

[0618] The "means for transmitting the generated proposal to the user's terminal" is a communication means for transferring the proposal generated by the server to the user's terminal.

[0619] The "means for displaying the proposal on the user's terminal" is an interface function that allows the user to check the received proposal on the display screen of the terminal.

[0620] "Market trend data" refers to data that indicates current market demand and trends.

[0621] "Customer review data" refers to data regarding ratings and reviews given by customers who have purchased a product.

[0622] "Behavioral big data" refers to large datasets about user behavior and preferences.

[0623] This invention relates to a system in which a user inputs a question via a terminal, a server analyzes the data in response to the question, and generates a proposal and responds. Below, the configuration and operation of the system will be described along with each processing step.

[0624] System Configuration

[0625] This system consists of a terminal used by users, a server that processes data, and a database that integrates them.

[0626] Device: A device with communication capabilities used by a user, such as a smartphone or tablet.

[0627] Server: Backend system using Node.js and Express.js.

[0628] Natural Language Processing Module: A natural language processing engine built using TensorFlow.js.

[0629] Database: MongoDB is used.

[0630] Generative AI model: OpenAI GPT-4 is used.

[0631] Operation process

[0632] 1. User enters question:

[0633] Users input their questions through a terminal interface, which is easy to use and built with React Native.

[0634] 2. Submit your question:

[0635] The question entered by the user is sent to the server as an HTTP POST request.

[0636] 3. Question Analysis:

[0637] The server receives the question and analyzes it using a natural language processing module (TensorFlow.js), extracting keywords from the question and understanding its meaning.

[0638] 4. Search for relevant data:

[0639] Based on the analysis results, the server retrieves relevant behavioral big data from a MongoDB database, including market trend data and customer review data.

[0640] 5. Data analysis and proposal generation:

[0641] The server passes the analyzed data to a generative AI model (OpenAI GPT-4) to generate optimal proposals. Based on the machine learning model, data analysis is performed on market trends and other data to create specific proposals for users.

[0642] 6. Submitting and Viewing Proposals:

[0643] The generated proposal is sent to the user's device as an HTTP response, where the user can view the proposal in the device interface.

[0644] Specific examples

[0645] For example, if a user enters the question, "What are the best suggestions for choosing a new smartphone model?", the system operates as follows: The server receives the question and analyzes keywords such as "smartphone" and "model selection" through natural language processing. Next, it searches related market trend data and customer review data and generates optimal suggestions using a generative AI model. It provides the user with suggestions such as, "According to the latest market trends, models with high camera performance are popular. The Model X in particular has high ratings, and its battery tends to be large-capacity and long-lasting."

[0646] Example prompts for generative AI models

[0647] What are your best suggestions for choosing a new smartphone model?

[0648] Input data: customer reviews, sales data, rating rankings

[0649] This allows users to quickly and accurately select the most suitable product, improving the quality of the user experience.

[0650] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0651] Step 1:

[0652] The user uses a device such as a smartphone or tablet to input a question through the interface of the online shopping app.

[0653] Input: User question (e.g., "What are your best suggestions for choosing a new smartphone model?")

[0654] Output: The question text entered

[0655] What happens: The user types a question into the text box and taps the "Submit" button.

[0656] Step 2:

[0657] The terminal sends the entered question to the server as an HTTP POST request.

[0658] Input: The question text entered by the user

[0659] Output: HTTP request sent to the server

[0660] How it works: The question text is sent in the body of an HTTP request to the server's API endpoint.

[0661] Step 3:

[0662] The server receives the received question and passes it to the natural language processing (NLP) module for analysis.

[0663] Input: The question text received by the server

[0664] Output: Analysis results (keywords and their semantic information)

[0665] How it works: The server uses TensorFlow.js to analyze the question text and extract keywords and their meanings. For example, keywords such as "smartphone" and "model selection" are extracted.

[0666] Step 4:

[0667] The server searches for relevant behavioral big data based on the analysis results.

[0668] Input: Analysis results (e.g., keywords "smartphone" and "model selection")

[0669] Output: Relevant datasets (market trend data, customer review data, etc.)

[0670] How it works: The server queries MongoDB to find and retrieve data (market trends, customer reviews) that matches the set criteria.

[0671] Step 5:

[0672] The server passes the retrieved data to a generative AI model to generate optimal suggestions.

[0673] Input: Related datasets

[0674] Output: Generated suggestions (e.g., "According to the latest market trends, models with high camera performance are popular. The Model X in particular is highly rated.")

[0675] How it works: The server uses OpenAI GPT-4 to generate suggestions based on the provided dataset, and outputs the suggestions in text format.

[0676] Step 6:

[0677] The server sends the generated proposal to the user's terminal as an HTTP response.

[0678] Input: Generated suggested text

[0679] Output: Suggested text sent to the user's device

[0680] How it works: The server places the generated proposal in the body of an HTTP response and sends it to the user's device.

[0681] Step 7:

[0682] The terminal displays the received proposals on its interface.

[0683] Input: Suggested text received from the server

[0684] Output: The suggestions displayed

[0685] Operation: The user's device displays the received suggested text on the screen for the user to review.

[0686] 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.

[0687] The present invention relates to a system in which a generative AI uses an emotion engine to recognize emotions in response to user questions and make optimal suggestions. Below, the processing of the system's program is explained in natural language, and specific examples based on the claims are also provided.

[0688] System Overview

[0689] In this system, users input questions via their devices, the server performs data analysis and sentiment analysis based on the questions, and the generative AI generates appropriate suggestions and provides them to the user. The system includes the following elements:

[0690] The device where the user enters their question

[0691] A server that identifies problem areas and analyzes related behavioral big data and emotional information

[0692] Emotion Engine

[0693] Generation AI

[0694] An interface that presents suggestions to the user

[0695] Program processing explanation

[0696] User question input

[0697] The user inputs a question using the terminal interface, such as "What is the best menu for opening a new cafe?"

[0698] Submit a Question

[0699] The terminal sends the entered question to the server as an HTTP request.

[0700] Question analysis and emotion recognition

[0701] The server passes the received question to a natural language processing (NLP) module for text analysis and keyword extraction, thereby understanding what the user is asking.

[0702] The server simultaneously analyzes the emotion contained in the question using an emotion engine, determining, for example, whether the entered text indicates an emotional state such as "excitement," "confusion," or "happiness."

[0703] Retrieval of relevant data and integration of emotional information

[0704] The server searches for relevant data from the behavioral big database based on keywords and context derived from NLP analysis.

[0705] The server also incorporates emotional information obtained from the emotion engine into the data analysis. For example, a passionate message can generate a proposal that requires innovation, while a confused message can generate a proposal that requires clarity and a sense of security.

[0706] Data analysis and proposal generation

[0707] The server uses a generative AI to analyze behavioral big data and emotional information to generate suggestions. The generative AI then uses a machine learning model to analyze this data and provide the most appropriate suggestions.

[0708] Submit a proposal

[0709] The server sends the generated proposal to the user's device as an HTTP response. The proposal is structured in JSON format or similar.

[0710] View Suggestions

[0711] The device displays the received suggestions on a user interface, where the suggestions are presented to the user in a visually easy-to-understand format.

[0712] Specific examples

[0713] For example, consider the case where a user asks a question about a new smartphone project.

[0714] User question input

[0715] User: "What market trends are driving new smartphone features?"

[0716] Submit a Question

[0717] Terminal: Send the above question to the server.

[0718] Question analysis and emotion recognition

[0719] Server: Analyzes questions using natural language processing to extract keywords such as "smartphone" and "market trends," and uses an emotion engine to analyze user emotions and detect rising levels of "excitement."

[0720] Retrieval of relevant data and integration of emotional information

[0721] Server: Searches for market trends such as high-performance cameras, 5G compatibility, and large-capacity batteries from behavioral big data. At the same time, it analyzes emotional information and considers innovative proposals based on the user's excitement level.

[0722] Data analysis and proposal generation

[0723] Server: Generative AI analyzes data and emotional information to generate recommendations tailored to the user. For example, it might generate a recommendation like, "The latest market trends demand high-performance cameras, 5G compatibility, and large-capacity batteries. By incorporating these features into your new product, you can increase your competitiveness."

[0724] Submit a proposal

[0725] Server: Sends the generated proposals to the user's device.

[0726] View Suggestions

[0727] On the device: The received suggestions are displayed in the user interface, allowing the user to review the suggestions and take specific actions based on them.

[0728] In this way, the system allows users to receive useful suggestions based on data analysis and sentiment information without requiring specialized knowledge.

[0729] The processing flow will be explained below.

[0730] This invention relates to a system in which a generative AI uses an emotion engine to recognize emotions in response to user questions and make optimal suggestions. The system's processing flow and specific operations are explained in the following steps.

[0731] System processing steps

[0732] Step 1:

[0733] A user uses the device interface to input a question, for example, "What is the best menu item for opening a new cafe?"

[0734] Step 2:

[0735] The device sends the entered question to the server as an HTTP request, which is structured as text data.

[0736] Step 3:

[0737] The server passes the received question to a natural language processing (NLP) module for text analysis and keyword extraction. For example, it extracts keywords such as "cafe," "opening," "optimal," and "menu," and analyzes the context.

[0738] Step 4:

[0739] The server uses an emotion engine to analyze the emotion contained in the question. For example, it identifies emotions such as "excitement" or "anxiety" from the wording. This is done using a sentiment analysis algorithm.

[0740] Step 5:

[0741] The server searches for relevant behavioral big data based on keywords extracted by NLP and emotional information recognized by the emotion engine. For example, it searches for search trends related to "cafes" and "menus" or regional characteristic data based on the user's location information.

[0742] Step 6:

[0743] The server then passes the searched data and sentiment information to the AI ​​generator, which then uses machine learning algorithms to determine, for example, that "latte art cafe latte" and "homemade cinnamon rolls" are popular in the area.

[0744] Step 7:

[0745] The server uses generative AI to generate specific suggestions, taking into account the user's emotional state, such as, "The most popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. In particular, based on your excitement level, we highly recommend you try a new menu item."

[0746] Step 8:

[0747] The server sends the generated proposal to the user's device as an HTTP response, which is typically structured in JSON format.

[0748] Step 9:

[0749] The device displays the received suggestions on the user interface, using graphs, lists, and other formats that are visually easy for the user to understand.

[0750] Specific examples

[0751] For example, if a user asks a question about a new smartphone project:

[0752] Step 1:

[0753] A user types, "What market trends will help me think about new smartphone features?"

[0754] Step 2:

[0755] The terminal sends a question to the server.

[0756] Step 3:

[0757] The server uses NLP to analyze the text and extract keywords such as "smartphone" and "market trends."

[0758] Step 4:

[0759] The server uses an emotion engine to identify emotions such as "excitement" or "expectation" contained in the user's question.

[0760] Step 5:

[0761] The server searches for relevant data from the behavioral big data based on the extracted keywords and emotional information. For example, it searches for trend data such as "high-performance camera," "5G compatible," and "large-capacity battery."

[0762] Step 6:

[0763] The server passes the searched data and sentiment information to the generative AI, which then performs data analysis. For example, based on market trends, it determines that a high-performance camera, 5G compatibility, and a large-capacity battery are important.

[0764] Step 7:

[0765] The server uses generative AI to generate suggestions, such as, "Recent market trends demand high-performance cameras, 5G compatibility, and large-capacity batteries. In particular, based on your excitement level, we strongly recommend that you actively adopt new technologies."

[0766] Step 8:

[0767] The server transmits the generated proposal to the user's terminal.

[0768] Step 9:

[0769] The device displays the received proposals on the user interface, allowing the user to come up with specific project ideas based on the proposals.

[0770] In this way, the system allows users to receive useful suggestions based on data analysis and sentiment information without requiring specialized knowledge.

[0771] Example 2

[0772] 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."

[0773] Conventional systems simply analyze data based on questions entered by users and generate suggestions, making it difficult to fully understand the user's emotions and intentions and provide optimal suggestions. As a result, the suggestions often do not meet the user's needs, resulting in a decrease in user satisfaction.

[0774] 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.

[0775] In this invention, the server includes means for analyzing questions using natural language processing, means for acquiring emotional information using an emotion analysis engine, means for searching for related data based on the analysis results and the emotional information, and means for generating suggestions based on the analysis results and the emotional information using a generation AI, thereby enabling optimal suggestions that take into account the user's emotions and intentions.

[0776] A "user" is an entity that utilizes the system to enter questions and receive suggestions.

[0777] A "terminal" is a computing device or interface through which a user enters a query and communicates with a server.

[0778] A "question" is information or a problem that a user inputs via a terminal.

[0779] A "server" is a computer system that receives user-entered questions and performs analysis and suggestion generation.

[0780] "Natural language processing" is a technology that analyzes questions and extracts keywords and intent from text.

[0781] An "emotion analysis engine" is software or a module for analyzing the emotional information contained in an input question.

[0782] "Relevant data" refers to information required for generating suggestions, retrieved based on natural language processing and sentiment information.

[0783] "Generative AI" is artificial intelligence that uses machine learning models to generate suggestions based on analysis results and emotional information.

[0784] A "suggestion" is an answer or recommendation that the generative AI creates based on the user's question and related data.

[0785] The present invention relates to a system in which a generation AI uses an emotion engine to recognize emotions in response to a user's question and make optimal suggestions. In this system, the user inputs a question via a terminal, a server performs data analysis and emotion analysis based on the question, and the generation AI generates appropriate suggestions and provides them to the user. The system includes the following elements:

[0786] The device where the user enters their question

[0787] A server that identifies problem areas and analyzes related behavioral big data and emotional information

[0788] Emotion Engine

[0789] Generation AI

[0790] An interface that presents suggestions to the user

[0791] User question input

[0792] The user uses the device interface to input a specific question, such as "What is the best menu for opening a new cafe?"

[0793] Submit a Question

[0794] The device sends the entered question as an HTTP request to the server, with the data packaged in JSON format.

[0795] Question analysis and emotion recognition

[0796] The server passes the received question to a natural language processing (NLP) module for text analysis and keyword extraction. This allows it to understand what the user is asking. At the same time, it uses an emotion engine to analyze the emotion contained in the question. For example, it determines whether the input text indicates an emotional state such as "excitement," "confusion," or "joy."

[0797] Retrieval of relevant data and integration of emotional information

[0798] The server searches for relevant data from the behavioral big database based on keywords and context derived from NLP analysis. At the same time, emotional information obtained from the emotion engine is also incorporated into the data analysis. For example, a passionate message will generate a proposal that requires innovation, while a confused message will generate a proposal that requires clarity and a sense of security.

[0799] Data analysis and proposal generation

[0800] The server uses generative AI to analyze behavioral big data and emotional information to generate proposals. Generative AI then uses machine learning models to analyze this data and make the most appropriate proposals. For example, it generates specific proposals such as, "The latest market trends call for high-performance cameras, 5G compatibility, and large-capacity batteries. By incorporating these features into your new product, you can increase your competitiveness."

[0801] Submit a proposal

[0802] The server sends the generated proposal to the user's device as an HTTP response, structured in JSON format.

[0803] View Suggestions

[0804] The device displays the received suggestions in a user interface, where the suggestions are presented to the user in a visually understandable format, such as charts, tables, or text descriptions.

[0805] Specific examples

[0806] For example, consider the case where a user asks a question about a new smartphone project.

[0807] User: "What market trends are driving new smartphone features?"

[0808] Terminal: Package it in JSON format and send an HTTP request to the API endpoint.

[0809] Server: Interprets the received request and performs analysis using the NLP module and emotion engine.

[0810] Server: Obtains relevant market trend data from the behavioral big database and generates proposals using the generative AI model.

[0811] Server: Sends the generated proposal in JSON format to the device.

[0812] Terminal: Proposals are displayed on the user interface, and the user can review the suggestions and take specific action based on them.

[0813] In this way, the system allows users to receive useful suggestions based on data analysis and sentiment information without having to have specialized knowledge.

[0814] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0815] Step 1: User enters question

[0816] The user opens the device interface and inputs a specific question, for example, "What is the best menu for opening a new cafe?" The question entered through the device interface is stored in the device's internal memory.

[0817] Step 2: Triggering a Question to be Submitted

[0818] The user clicks the send button, which triggers the sending of the entered question to the server. This causes the question data to be formatted into an HTTP request format on the terminal. The input is the user's click, and the output is the question data packaged in JSON format.

[0819] Step 3: Sending an HTTP request

[0820] The terminal sends question data packaged in JSON format to the server. The input is the packaged question data, and the output is an HTTP request to the server.

[0821] Step 4: Receiving the request

[0822] The server receives an HTTP request sent from a terminal. The input is the question data sent from the terminal, and the output is the temporary storage of the question data in the server.

[0823] Step 5: Passing to the Natural Language Processing (NLP) module

[0824] The server passes the question to a natural language processing (NLP) module, which tokenizes the text, tags it with parts of speech, and extracts keywords. The input is the question data, and the output is the tokenized text and extracted keywords.

[0825] Step 6: Sentiment analysis using a sentiment analysis engine

[0826] The server passes the text and keywords obtained from the NLP analysis to an emotion analysis engine to estimate the emotional state. The input is the NLP analysis result, and the output is an emotion tag such as "excitement," "confusion," or "joy."

[0827] Step 7: Generate Database Queries

[0828] The server generates a query to search the behavioral big database based on the keywords and emotion information obtained from the NLP module. The input is the keywords and emotion information, and the output is the database query.

[0829] Step 8: Database Search

[0830] The server uses the generated query to search for relevant data from the behavioral big database. The input is the database query, and the output is a relevant dataset, which may contain, for example, information about cafe menus or market trends.

[0831] Step 9: Proposal generation by generative AI

[0832] The server passes the acquired data and emotional information to the generative AI model to generate recommendations. The input is the relevant dataset and emotional information, and the output is a specific recommendation to the user. For example, a specific recommendation such as "According to the latest market trends, high-performance cameras, 5G compatibility, and large-capacity batteries are required" may be generated.

[0833] Step 10: Formatting the Proposal Data

[0834] The server structures the generated proposal in JSON format and packages it as an HTTP response. The input is the generated proposal and the output is structured data in JSON format.

[0835] Step 11: Send HTTP response

[0836] The server sends formatted proposal data to the user's device. The input is the proposal data in JSON format, and the output is an HTTP response sent to the device.

[0837] Step 12: Receiving Proposal Data

[0838] The terminal receives the proposed data sent from the server as an HTTP response. The input is the proposed data from the server, and the output is the data stored in the terminal.

[0839] Step 13: Display in the User Interface

[0840] The device parses the received suggestion data and displays it on the user interface. The suggestion content is presented in a visually easy-to-understand format. The input is the received suggestion data, and the output is the display on the user interface. The user can check the suggestion content and decide on a specific action based on it.

[0841] (Application example 2)

[0842] 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."

[0843] Conventional systems typically respond to user questions by simply analyzing or searching for answers, making it difficult to provide suggestions that take into account the emotional state of the questioner. Furthermore, particularly in the security field, there is a need for systems that can appropriately recognize emotions such as tension and anxiety among on-site staff and provide sophisticated suggestions. The present invention aims to solve these problems and provide a system that generates suggestions optimized for the user's emotions.

[0844] 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 a user to input a question via an input device; means for transmitting the question from the input device to the data processing device; means for receiving the question and analyzing it using natural language processing; means for searching for related behavioral data based on the analysis results; generation AI means for performing data analysis based on the search results and generating a proposal; means for transmitting the proposal to the user's input device; means for displaying the proposal on the user's input device; means for analyzing the question using an emotion engine and extracting emotion information; and means for optimizing the generated proposal by integrating the emotion information. This enables the generation of advanced proposals that take user emotions into consideration.

[0845] An "input device" is a device used by a user to input a question, and includes a microphone, keyboard, smartphone, tablet, or other electronic device.

[0846] "Data Processing Unit" refers to the server or cloud computing platform that receives, analyzes and processes queries submitted by users.

[0847] "Natural language processing" is a technology that formalizes input user questions and understands the content of the questions by performing text analysis and keyword extraction.

[0848] "Behavioral data" includes the user's past behavioral history, access history, and other related data, and is data that is searched according to the content of the question.

[0849] "Generative AI" is an artificial intelligence technology that uses machine learning models to analyze behavioral data and emotional information to generate optimal suggestions.

[0850] The "emotion engine" is a system that analyzes the user's emotional state from their questions and behavior, and extracts emotional information such as "relief," "confusion," and "excitement."

[0851] "Suggestion" refers to the optimal answer or recommended action output by the generative AI based on the user's question and emotional information.

[0852] "Data analysis" refers to the process of discovering hidden patterns and trends based on behavioral data and emotional information, and generating optimal suggestions based on the questions asked.

[0853] "Optimization" means that the content of the proposal is adjusted based on the extracted emotional information according to the emotional state of the user, and the most appropriate proposal is provided.

[0854] This invention is a system that uses an emotion engine to recognize emotions in response to user questions and uses generative AI to provide optimal suggestions.

[0855] System Overview

[0856] The system involves a procedure in which a user inputs a question via an input device (e.g., a microphone or smartphone), and the question is sent to a data processing device (e.g., a cloud server). The server analyzes the question using natural language processing (NLP), searches for relevant behavioral data, and performs sentiment analysis using an emotion engine. Based on this, a generative AI generates appropriate suggestions, which are finally sent to the user's input device and displayed.

[0857] Hardware and software used

[0858] Input device: The device the user uses to input a question. Examples include a microphone or a smartphone.

[0859] Data Processing Unit: A server or cloud computing platform that receives, analyzes, and processes user-submitted queries. An example is Amazon Web Services (AWS) EC2.

[0860] Natural Language Processing (NLP) module: A technology that uses the Google Cloud Natural Language API to formalize input user questions and perform text analysis and keyword extraction.

[0861] Emotion engine: A system that uses IBM Watson Tone Analyzer to analyze the user's emotional state from their questions and actions.

[0862] Generative AI: An artificial intelligence technology that implements machine learning models using OpenAI GPT-3.5 to analyze data and emotional information and generate optimal suggestions.

[0863] Specific explanation of the process

[0864] 1. User Question Input: The user uses an input device to enter a question verbally or as text. For example, a question might be, "Is this person safe to grant access?"

[0865] 2. Sending a question: The input device sends a question to the data processing device. The sending method is mainly an HTTP request.

[0866] 3. Question analysis and emotion recognition: When the server receives a question, it analyzes it using a natural language processing module. At the same time, it uses an emotion engine to extract emotional information contained in the question. Emotions such as "worry," "confusion," and "relief" are identified.

[0867] 4. Searching for related data and integrating emotional information: Based on the analysis results, the server searches for related information from the behavior database and integrates emotional information for analysis. This allows the server to consider suggestions that are appropriate for the user's emotions.

[0868] 5. Proposal generation by generative AI: Generative AI analyzes behavioral data and emotional information to generate optimal suggestions. Specific suggestions such as "There are no problems with this person's past visit history, so please allow access" can be obtained.

[0869] 6. Sending and displaying suggestions: The server sends the generated suggestions to the input device and displays them on the user's device. The user can review the displayed suggestions and take appropriate action.

[0870] Examples of concrete examples and prompts

[0871] As a specific example of use, consider the case where a user asks the following question in a security situation:

[0872] (Example of a prompt)

[0873] A visitor is standing at the front door. On-site staff are asking, "Is this person safe to grant access?" The staff is in an emotional state of "worried." Review past visit history and alarm records to generate optimal suggestions.

[0874] Such prompts allow the server to analyze the situation and generate and display optimal suggestions.

[0875] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0876] Step 1:

[0877] The user enters a question using an input device. The input device accepts voice or text input and formats the question as digital data. At this point, the entered data is captured as "voice data" or "text data."

[0878] Step 2:

[0879] The terminal sends the entered question as an HTTP request to the data processing device. The input here is captured "voice data" or "text data," which is used as the payload of the HTTP request. The sent data is stored on the server.

[0880] Step 3:

[0881] The server receives the question and analyzes it using a natural language processing (NLP) module. Here, "voice data" or "text data" is received, and the NLP module performs text analysis and keyword extraction. The analyzed "keyword data" and "structured text data" are generated as output.

[0882] Step 4:

[0883] The server searches for related behavioral data based on the analysis results. The input is "keyword data" and "structured text data," and the output is related "behavioral data." The behavioral database is searched to obtain the required information.

[0884] Step 5:

[0885] The server analyzes the question using an emotion engine and extracts emotional information. Here, "structured text data" is input into the emotion engine, which then outputs "emotional information." This emotional information includes emotional states such as "worry," "excitement," and "relief."

[0886] Step 6:

[0887] The server integrates the emotional information and combines it with behavioral data to generate suggestions using generative AI. The inputs are "behavioral data" and "emotional information," and the output is "optimal suggestions." The generative AI model analyzes this data and generates suggestions optimized for the user's emotional state.

[0888] Step 7:

[0889] The server sends the generated proposal to the terminal as an HTTP response. Here, the server creates an HTTP response using the "optimal proposal" as input and sends it to the terminal.

[0890] Step 8:

[0891] The device displays the suggestions on the user's input device. The received "optimal suggestions" are visually presented to the user, who can then check them and take appropriate action.

[0892] In this way, a system is realized that performs specific data processing and data calculation at each processing step and provides optimal suggestions to the user.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] [Third embodiment]

[0897] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0898] 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.

[0899] 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).

[0900] 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.

[0901] 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.

[0902] 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).

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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."

[0909] This invention relates to a system that enables users to effectively utilize data. In this system, users input questions via a terminal, and a server analyzes the data based on the questions and provides specific suggestions. Below, the program processing of this system is explained in natural language, with specific examples.

[0910] System Overview

[0911] The system itself works by allowing users to ask questions through an interface, and the generative AI responds with appropriate suggestions. The user's device, the server, and the behavioral big database work together.

[0912] Program processing explanation

[0913] User question input

[0914] The user uses the terminal interface to input a question, for example, a question of the form "What is the best menu for opening a new cafe?"

[0915] Submit a Question

[0916] The terminal sends the entered question to the server as an HTTP request.

[0917] Question Analysis

[0918] The server passes the received question to a natural language processing (NLP) module for text analysis, which identifies what the user is looking for and what data is needed. For example, it extracts keywords such as "new cafe" or "best menu" and identifies the problem domain based on those.

[0919] Finding related data

[0920] The server searches for relevant behavioral big data based on the identified problem domain, such as search trends, location data, and customer visitor information by time of day for cafes.

[0921] Data analysis and proposal generation

[0922] The server passes the searched data to the AI ​​generator, which analyzes it. Using machine learning models and statistical analysis methods, the AI ​​generates the most effective suggestions. For example, it might generate a suggestion like, "The most popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. It would be especially effective to strengthen these menu items during weekday lunch hours."

[0923] Submit a proposal

[0924] The server sends the generated proposal to the user's terminal as an HTTP response.

[0925] View Suggestions

[0926] The terminal displays the received suggestions on a user interface, allowing the user to review the suggestions and take specific actions based on them.

[0927] Specific examples

[0928] For example, if a user asks a question about a new smartphone project, the following steps are taken:

[0929] User question input

[0930] The user types, "What market trends should I look for to help me think about new smartphone features?"

[0931] Submit a Question

[0932] The terminal sends a query to the server.

[0933] Question Analysis

[0934] The server uses natural language processing to analyze keywords such as "smartphone" and "market trends."

[0935] Finding related data

[0936] The server searches behavioral big data and extracts market trends such as high-performance cameras, 5G compatibility, and large-capacity batteries.

[0937] Data analysis and proposal generation

[0938] The server uses generative AI to analyze smartphone features that are in high demand in the market and generate proposals, such as "Recent market trends show an increasing demand for high-performance cameras, 5G compatibility, and large-capacity batteries."

[0939] Submit a proposal

[0940] The server transmits the generated proposal to the user's terminal.

[0941] View Suggestions

[0942] The device displays the suggestions to the user, allowing them to incorporate features based on market trends into new products.

[0943] In this way, the system is designed to enable users to effectively utilize the results of data analysis without having specialized knowledge.

[0944] The processing flow will be explained below.

[0945] Step 1:

[0946] A user uses the device interface to input a question, for example, "What is the best menu item for opening a new cafe?"

[0947] Step 2:

[0948] The device sends the entered question to the server as an HTTP request, which is structured as text data.

[0949] Step 3:

[0950] The server passes the received question to a Natural Language Processing (NLP) module, which performs text analysis of the question, identifying key keywords and context, to understand the user's intent and identify the information they need.

[0951] Step 4:

[0952] The server searches for relevant behavioral big data based on the keywords and context analyzed through the NLP module, and generates and executes queries to extract the required datasets from the behavioral big database.

[0953] Step 5:

[0954] The server passes the searched data to the Generative AI, which then uses machine learning algorithms to analyze the data and generate specific suggestions based on the analysis results.

[0955] Step 6:

[0956] The server sends the generated proposal to the user's device as an HTTP response. The response consists of JSON format data containing the proposal content.

[0957] Step 7:

[0958] The device displays the received suggestions on the user interface. It parses the received JSON data and presents it to the user in a visually easy-to-understand format. For example, it might say, "Popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. It would be particularly effective to strengthen these menu items during weekday lunch hours."

[0959] In this way, the system provides appropriate data analysis and suggestions based on user questions throughout all processing steps.

[0960] Example 1

[0961] 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."

[0962] In conventional data utilization systems, it is difficult for users without specialized knowledge to effectively analyze data and obtain specific proposals based on the results. In particular, it is extremely time-consuming and requires many steps to properly analyze a user's question, search for appropriate data based on that analysis, and generate proposals. For this reason, there is a demand for an efficient and easy-to-use data utilization system.

[0963] 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.

[0964] In this invention, the server includes means for a user to input a question via an information processing device, means for transmitting the question from the information processing device to the information processing device, means for receiving the question and analyzing it using natural language processing, means for searching a large amount of related data based on the analysis results, generation AI means for performing data analysis based on the search results and generating a proposal, means for transmitting the generated proposal to the user's information processing device, and means for displaying the proposal on the user's information processing device. This enables a user to quickly obtain effective data analysis and specific proposals based on the results of the analysis, even without specialized knowledge.

[0965] An "information processing device" is a device that allows a user to input a question and transmit the question to a server, and refers to electronic devices such as computers, smartphones, and tablets.

[0966] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, extracting meaning from text data and providing appropriate information.

[0967] "Big data" refers to a huge collection of data related to a user's question, including databases and cloud storage for searching and retrieving specific information.

[0968] "Generative AI" is an artificial intelligence technology that uses machine learning models to analyze data, make predictions, and make suggestions.

[0969] "Data analysis" is the process of analyzing acquired data using statistical methods and machine learning models to derive useful information and suggestions.

[0970] "Suggestions" refer to specific actions or ideas presented to users based on the results of data analysis.

[0971] A "user interface" refers to a display screen or operating means that allows a user to interact with a system through an information processing device, and includes a web browser and a mobile application.

[0972] The present invention relates to a system for enabling users to effectively utilize data. In this system, a user inputs a question via an information processing device, and a server analyzes the data based on the question and provides specific suggestions. The following describes in detail an embodiment of this system.

[0973] System Overview

[0974] The system mainly consists of a user's information processing device, a server, and a large database. A question entered by the user is sent from the information processing device to the server, which analyzes the question, searches for and analyzes appropriate data, and returns the results to the user's information processing device.

[0975] Hardware and software used

[0976] Information processing devices: computers, smartphones, tablets, etc.

[0977] Server: Hardware that includes a database management system (DBMS) and data storage such as cloud storage.

[0978] Software: Natural language processing libraries (e.g., NLTK, spaCy), machine learning libraries (e.g., Scikit Learn, TensorFlow).

[0979] Program processing

[0980] User question input

[0981] The user inputs a question using the interface of the information processing device, for example, a question in the format "What is the best menu for opening a new cafe?"

[0982] Submit a Question

[0983] The device sends the user-entered question to the server as an HTTP POST request, which converts the question into JSON format and sends it to the API endpoint.

[0984] Question Analysis

[0985] The server decodes the received HTTP request and extracts the question. It then uses a natural language processing (NLP) module to analyze the text and extract keywords, such as "new cafe" or "best menu."

[0986] Finding related data

[0987] The server searches a large database based on the analyzed keywords, using a database management system (DBMS) or cloud storage to obtain relevant data (e.g., search trends and customer data related to cafes).

[0988] Data analysis and proposal generation

[0989] The server passes the acquired data to a generative AI model for data analysis. The generative AI model generates optimal suggestions based on machine learning algorithms (using, for example, Scikit Learn or TensorFlow). For example, a suggestion might be generated such as, "Popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. It would be particularly effective to strengthen these menu items during weekday lunch hours."

[0990] Submit a proposal

[0991] The server sends the generated proposal to the user's information processing device as an HTTP response. The proposal content is serialized in JSON format and included in the response body.

[0992] View Suggestions

[0993] The device deserializes the received suggestions and displays them in the user interface: in the browser, by dynamically adding the suggestions to HTML using JavaScript; in the mobile app, by updating a dedicated UI component to display the suggestions.

[0994] Specific operation example

[0995] For example, if a user inputs "Please tell me the market trends that will help me think about new smartphone features," the processing will be carried out in the following steps.

[0996] User question input

[0997] The user types, "What market trends should I look for to help me think about new smartphone features?"

[0998] Submit a Question

[0999] The terminal sends a query to the server.

[1000] Question Analysis

[1001] The server uses a natural language processing module to analyze keywords such as "smartphone" and "market trends" and extract information to search for appropriate data.

[1002] Finding related data

[1003] The server searches a large database based on the analyzed keywords and extracts market trends such as high-performance cameras, 5G compatibility, and large-capacity batteries.

[1004] Data analysis and proposal generation

[1005] The server analyzes the data using a generative AI model and generates optimal recommendations for the user, such as, "Recent market trends show an increasing demand for high-performance cameras, 5G compatibility, and large-capacity batteries."

[1006] Submit a proposal

[1007] The server transmits the generated proposal to the user's information processing device.

[1008] View Suggestions

[1009] The terminal displays the proposals on the user interface, allowing users to check the proposals based on market trends and take specific actions.

[1010] In this way, the system is designed to enable users to effectively utilize the results of data analysis without having specialized knowledge.

[1011] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1012] Step 1: User enters question

[1013] A user uses the interface of a data processing device to input a question, such as "What is the best menu item for opening a new cafe?", into a text field. The input is done via a web form or a text box in a mobile app.

[1014] Input: The user's question text.

[1015] Output: The user's question text.

[1016] Step 2: Send the question to the server

[1017] The device sends the user-entered question to the server as an HTTP POST request, which converts the question into JSON format and sends it to the API endpoint.

[1018] Input: The user's question text.

[1019] Output: The HTTP request sent to the server.

[1020] Step 3: The server receives the query

[1021] The server decrypts the received HTTP request and extracts the question text from the request body.

[1022] Input: HTTP request.

[1023] Output: The extracted question text.

[1024] Step 4: Parse the question

[1025] The server passes the extracted question text to a natural language processing (NLP) module for text analysis, for example, using Python's NLTK or spaCy libraries to extract keywords such as "new cafe" or "best menu."

[1026] Input: Question text.

[1027] Output: Extracted keywords.

[1028] Step 5: Find related data

[1029] The server searches a large database based on the extracted keywords. It uses a database management system (DBMS) or cloud storage to retrieve relevant data (e.g., search trends and customer data related to cafes). It performs searches using SQL queries or NoSQL query languages.

[1030] Input: Keywords.

[1031] Output: The relevant data found.

[1032] Step 6: Conduct data analysis

[1033] The server then passes the acquired data to a generative AI model for data analysis, which then analyzes the data using machine learning algorithms (for example, using Scikit Learn or TensorFlow) to generate optimal recommendations.

[1034] Input: The relevant data found.

[1035] Output: The generated proposals.

[1036] Step 7: Submit your proposal

[1037] The server sends the generated proposal to the user's information processing device as an HTTP response. The proposal content is serialized in JSON format and included in the response body.

[1038] Input: The generated proposals.

[1039] Output: The HTTP response sent to the user device.

[1040] Step 8: View suggestions

[1041] The device deserializes the received suggestions and displays them in the user interface: in the browser, by dynamically adding the suggestions to HTML using JavaScript; in the mobile app, by updating a dedicated UI component to display the suggestions.

[1042] Input: The proposal received as an HTTP response.

[1043] Output: The proposal displayed in the user interface.

[1044] (Application example 1)

[1045] 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."

[1046] On conventional online shopping sites, users often have difficulty choosing products and it can take a long time to find the right one. Furthermore, there is a lack of systems that can efficiently gather the information users need and make optimal recommendations based on that information. This leads to issues such as a poor user experience and a decrease in purchasing motivation.

[1047] 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.

[1048] In this invention, the server includes: means for a user to input a question via a terminal; means for transmitting the question from the terminal to the server; means for receiving the question and analyzing it using natural language processing; means for searching for related behavioral big data based on the analysis results; generation AI means for performing data analysis based on the search results and generating proposals; means for transmitting the generated proposals to the user's terminal; means for displaying the proposals on the user's terminal; and means for searching market trend data and customer review data based on a question about product selection and suggesting optimal products through data analysis using behavioral big data including these. This enables the user to efficiently select appropriate products.

[1049] A "user terminal" is a communications-enabled device that a user uses to enter questions and receive suggestions.

[1050] The "means for inputting a question" is a function of the interface that allows a user to input a question in text format via a terminal.

[1051] The "means for transmitting to the server" is a communication means for transferring the question entered by the user at the terminal to the server.

[1052] The "means for receiving a question and analyzing it using natural language processing" is a function in which the server receives a question sent and analyzes it using natural language processing technology.

[1053] "Means for searching related behavioral big data" refers to a function that searches a database for related behavioral data based on the analysis results.

[1054] "Generative AI means for analyzing data and generating proposals" refers to AI technology that uses machine learning models to analyze behavioral big data and generate specific proposals for users.

[1055] The "means for transmitting the generated proposal to the user's terminal" is a communication means for transferring the proposal generated by the server to the user's terminal.

[1056] The "means for displaying the proposal on the user's terminal" is an interface function that allows the user to check the received proposal on the display screen of the terminal.

[1057] "Market trend data" refers to data that indicates current market demand and trends.

[1058] "Customer review data" refers to data regarding ratings and reviews given by customers who have purchased a product.

[1059] "Behavioral big data" refers to large datasets about user behavior and preferences.

[1060] This invention relates to a system in which a user inputs a question via a terminal, a server analyzes the data in response to the question, and generates a proposal and responds. Below, the configuration and operation of the system will be described along with each processing step.

[1061] System Configuration

[1062] This system consists of a terminal used by users, a server that processes data, and a database that integrates them.

[1063] Device: A device with communication capabilities used by a user, such as a smartphone or tablet.

[1064] Server: Backend system using Node.js and Express.js.

[1065] Natural Language Processing Module: A natural language processing engine built using TensorFlow.js.

[1066] Database: MongoDB is used.

[1067] Generative AI model: OpenAI GPT-4 is used.

[1068] Operation process

[1069] 1. User enters question:

[1070] Users input their questions through a terminal interface, which is easy to use and built with React Native.

[1071] 2. Submit your question:

[1072] The question entered by the user is sent to the server as an HTTP POST request.

[1073] 3. Question Analysis:

[1074] The server receives the question and analyzes it using a natural language processing module (TensorFlow.js), extracting keywords from the question and understanding its meaning.

[1075] 4. Search for relevant data:

[1076] Based on the analysis results, the server retrieves relevant behavioral big data from a MongoDB database, including market trend data and customer review data.

[1077] 5. Data analysis and proposal generation:

[1078] The server passes the analyzed data to a generative AI model (OpenAI GPT-4) to generate optimal proposals. Based on the machine learning model, data analysis is performed on market trends and other data to create specific proposals for users.

[1079] 6. Submitting and Viewing Proposals:

[1080] The generated proposal is sent to the user's device as an HTTP response, where the user can view the proposal in the device interface.

[1081] Specific examples

[1082] For example, if a user enters the question, "What are the best suggestions for choosing a new smartphone model?", the system operates as follows: The server receives the question and analyzes keywords such as "smartphone" and "model selection" through natural language processing. Next, it searches related market trend data and customer review data and generates optimal suggestions using a generative AI model. It provides the user with suggestions such as, "According to the latest market trends, models with high camera performance are popular. The Model X in particular has high ratings, and its battery tends to be large-capacity and long-lasting."

[1083] Example prompts for generative AI models

[1084] What are your best suggestions for choosing a new smartphone model?

[1085] Input data: customer reviews, sales data, rating rankings

[1086] This allows users to quickly and accurately select the most suitable product, improving the quality of the user experience.

[1087] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1088] Step 1:

[1089] The user uses a device such as a smartphone or tablet to input a question through the interface of the online shopping app.

[1090] Input: User question (e.g., "What are your best suggestions for choosing a new smartphone model?")

[1091] Output: The question text entered

[1092] What happens: The user types a question into the text box and taps the "Submit" button.

[1093] Step 2:

[1094] The terminal sends the entered question to the server as an HTTP POST request.

[1095] Input: The question text entered by the user

[1096] Output: HTTP request sent to the server

[1097] How it works: The question text is sent in the body of an HTTP request to the server's API endpoint.

[1098] Step 3:

[1099] The server receives the received question and passes it to the natural language processing (NLP) module for analysis.

[1100] Input: The question text received by the server

[1101] Output: Analysis results (keywords and their semantic information)

[1102] How it works: The server uses TensorFlow.js to analyze the question text and extract keywords and their meanings. For example, keywords such as "smartphone" and "model selection" are extracted.

[1103] Step 4:

[1104] The server searches for relevant behavioral big data based on the analysis results.

[1105] Input: Analysis results (e.g., keywords "smartphone" and "model selection")

[1106] Output: Relevant datasets (market trend data, customer review data, etc.)

[1107] How it works: The server queries MongoDB to find and retrieve data (market trends, customer reviews) that matches the set criteria.

[1108] Step 5:

[1109] The server passes the retrieved data to a generative AI model to generate optimal suggestions.

[1110] Input: Related datasets

[1111] Output: Generated suggestions (e.g., "According to the latest market trends, models with high camera performance are popular. The Model X in particular is highly rated.")

[1112] How it works: The server uses OpenAI GPT-4 to generate suggestions based on the provided dataset, and outputs the suggestions in text format.

[1113] Step 6:

[1114] The server sends the generated proposal to the user's terminal as an HTTP response.

[1115] Input: Generated suggested text

[1116] Output: Suggested text sent to the user's device

[1117] How it works: The server places the generated proposal in the body of an HTTP response and sends it to the user's device.

[1118] Step 7:

[1119] The terminal displays the received proposals on its interface.

[1120] Input: Suggested text received from the server

[1121] Output: The suggestions displayed

[1122] Operation: The user's device displays the received suggested text on the screen for the user to review.

[1123] 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.

[1124] The present invention relates to a system in which a generative AI uses an emotion engine to recognize emotions in response to user questions and make optimal suggestions. Below, the processing of the system's program is explained in natural language, and specific examples based on the claims are also provided.

[1125] System Overview

[1126] In this system, users input questions via their devices, the server performs data analysis and sentiment analysis based on the questions, and the generative AI generates appropriate suggestions and provides them to the user. The system includes the following elements:

[1127] The device where the user enters their question

[1128] A server that identifies problem areas and analyzes related behavioral big data and emotional information

[1129] Emotion Engine

[1130] Generation AI

[1131] An interface that presents suggestions to the user

[1132] Program processing explanation

[1133] User question input

[1134] The user inputs a question using the terminal interface, such as "What is the best menu for opening a new cafe?"

[1135] Submit a Question

[1136] The terminal sends the entered question to the server as an HTTP request.

[1137] Question analysis and emotion recognition

[1138] The server passes the received question to a natural language processing (NLP) module for text analysis and keyword extraction, thereby understanding what the user is asking.

[1139] The server simultaneously analyzes the emotion contained in the question using an emotion engine, determining, for example, whether the entered text indicates an emotional state such as "excitement," "confusion," or "happiness."

[1140] Retrieval of relevant data and integration of emotional information

[1141] The server searches for relevant data from the behavioral big database based on keywords and context derived from NLP analysis.

[1142] The server also incorporates emotional information obtained from the emotion engine into the data analysis. For example, a passionate message can generate a proposal that requires innovation, while a confused message can generate a proposal that requires clarity and a sense of security.

[1143] Data analysis and proposal generation

[1144] The server uses a generative AI to analyze behavioral big data and emotional information to generate suggestions. The generative AI then uses a machine learning model to analyze this data and provide the most appropriate suggestions.

[1145] Submit a proposal

[1146] The server sends the generated proposal to the user's device as an HTTP response. The proposal is structured in JSON format or similar.

[1147] View Suggestions

[1148] The device displays the received suggestions on a user interface, where the suggestions are presented to the user in a visually easy-to-understand format.

[1149] Specific examples

[1150] For example, consider the case where a user asks a question about a new smartphone project.

[1151] User question input

[1152] User: "What market trends are driving new smartphone features?"

[1153] Submit a Question

[1154] Terminal: Send the above question to the server.

[1155] Question analysis and emotion recognition

[1156] Server: Analyzes questions using natural language processing to extract keywords such as "smartphone" and "market trends," and uses an emotion engine to analyze user emotions and detect rising levels of "excitement."

[1157] Retrieval of relevant data and integration of emotional information

[1158] Server: Searches for market trends such as high-performance cameras, 5G compatibility, and large-capacity batteries from behavioral big data. At the same time, it analyzes emotional information and considers innovative proposals based on the user's excitement level.

[1159] Data analysis and proposal generation

[1160] Server: Generative AI analyzes data and emotional information to generate recommendations tailored to the user. For example, it might generate a recommendation like, "The latest market trends demand high-performance cameras, 5G compatibility, and large-capacity batteries. By incorporating these features into your new product, you can increase your competitiveness."

[1161] Submit a proposal

[1162] Server: Sends the generated proposals to the user's device.

[1163] View Suggestions

[1164] On the device: The received suggestions are displayed in the user interface, allowing the user to review the suggestions and take specific actions based on them.

[1165] In this way, the system allows users to receive useful suggestions based on data analysis and sentiment information without requiring specialized knowledge.

[1166] The processing flow will be explained below.

[1167] This invention relates to a system in which a generative AI uses an emotion engine to recognize emotions in response to user questions and make optimal suggestions. The system's processing flow and specific operations are explained in the following steps.

[1168] System processing steps

[1169] Step 1:

[1170] A user uses the device interface to input a question, for example, "What is the best menu item for opening a new cafe?"

[1171] Step 2:

[1172] The device sends the entered question to the server as an HTTP request, which is structured as text data.

[1173] Step 3:

[1174] The server passes the received question to a natural language processing (NLP) module for text analysis and keyword extraction. For example, it extracts keywords such as "cafe," "opening," "optimal," and "menu," and analyzes the context.

[1175] Step 4:

[1176] The server uses an emotion engine to analyze the emotion contained in the question. For example, it identifies emotions such as "excitement" or "anxiety" from the wording. This is done using a sentiment analysis algorithm.

[1177] Step 5:

[1178] The server searches for relevant behavioral big data based on keywords extracted by NLP and emotional information recognized by the emotion engine. For example, it searches for search trends related to "cafes" and "menus" or regional characteristic data based on the user's location information.

[1179] Step 6:

[1180] The server then passes the searched data and sentiment information to the AI ​​generator, which then uses machine learning algorithms to determine, for example, that "latte art cafe latte" and "homemade cinnamon rolls" are popular in the area.

[1181] Step 7:

[1182] The server uses generative AI to generate specific suggestions, taking into account the user's emotional state, such as, "The most popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. In particular, based on your excitement level, we highly recommend you try a new menu item."

[1183] Step 8:

[1184] The server sends the generated proposal to the user's device as an HTTP response, which is typically structured in JSON format.

[1185] Step 9:

[1186] The device displays the received suggestions on the user interface, using graphs, lists, and other formats that are visually easy for the user to understand.

[1187] Specific examples

[1188] For example, if a user asks a question about a new smartphone project:

[1189] Step 1:

[1190] A user types, "What market trends will help me think about new smartphone features?"

[1191] Step 2:

[1192] The terminal sends a question to the server.

[1193] Step 3:

[1194] The server uses NLP to analyze the text and extract keywords such as "smartphone" and "market trends."

[1195] Step 4:

[1196] The server uses an emotion engine to identify emotions such as "excitement" or "expectation" contained in the user's question.

[1197] Step 5:

[1198] The server searches for relevant data from the behavioral big data based on the extracted keywords and emotional information. For example, it searches for trend data such as "high-performance camera," "5G compatible," and "large-capacity battery."

[1199] Step 6:

[1200] The server passes the searched data and sentiment information to the generative AI, which then performs data analysis. For example, based on market trends, it determines that a high-performance camera, 5G compatibility, and a large-capacity battery are important.

[1201] Step 7:

[1202] The server uses generative AI to generate suggestions, such as, "Recent market trends demand high-performance cameras, 5G compatibility, and large-capacity batteries. In particular, based on your excitement level, we strongly recommend that you actively adopt new technologies."

[1203] Step 8:

[1204] The server transmits the generated proposal to the user's terminal.

[1205] Step 9:

[1206] The device displays the received proposals on the user interface, allowing the user to come up with specific project ideas based on the proposals.

[1207] In this way, the system allows users to receive useful suggestions based on data analysis and sentiment information without requiring specialized knowledge.

[1208] Example 2

[1209] 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."

[1210] Conventional systems simply analyze data based on questions entered by users and generate suggestions, making it difficult to fully understand the user's emotions and intentions and provide optimal suggestions. As a result, the suggestions often do not meet the user's needs, resulting in a decrease in user satisfaction.

[1211] 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.

[1212] In this invention, the server includes means for analyzing questions using natural language processing, means for acquiring emotional information using an emotion analysis engine, means for searching for related data based on the analysis results and the emotional information, and means for generating suggestions based on the analysis results and the emotional information using a generation AI, thereby enabling optimal suggestions that take into account the user's emotions and intentions.

[1213] A "user" is an entity that utilizes the system to enter questions and receive suggestions.

[1214] A "terminal" is a computing device or interface through which a user enters a query and communicates with a server.

[1215] A "question" is information or a problem that a user inputs via a terminal.

[1216] A "server" is a computer system that receives user-entered questions and performs analysis and suggestion generation.

[1217] "Natural language processing" is a technology that analyzes questions and extracts keywords and intent from text.

[1218] An "emotion analysis engine" is software or a module for analyzing the emotional information contained in an input question.

[1219] "Relevant data" refers to information required for generating suggestions, retrieved based on natural language processing and sentiment information.

[1220] "Generative AI" is artificial intelligence that uses machine learning models to generate suggestions based on analysis results and emotional information.

[1221] A "suggestion" is an answer or recommendation that the generative AI creates based on the user's question and related data.

[1222] The present invention relates to a system in which a generation AI uses an emotion engine to recognize emotions in response to a user's question and make optimal suggestions. In this system, the user inputs a question via a terminal, a server performs data analysis and emotion analysis based on the question, and the generation AI generates appropriate suggestions and provides them to the user. The system includes the following elements:

[1223] The device where the user enters their question

[1224] A server that identifies problem areas and analyzes related behavioral big data and emotional information

[1225] Emotion Engine

[1226] Generation AI

[1227] An interface that presents suggestions to the user

[1228] User question input

[1229] The user uses the device interface to input a specific question, such as "What is the best menu for opening a new cafe?"

[1230] Submit a Question

[1231] The device sends the entered question as an HTTP request to the server, with the data packaged in JSON format.

[1232] Question analysis and emotion recognition

[1233] The server passes the received question to a natural language processing (NLP) module for text analysis and keyword extraction. This allows it to understand what the user is asking. At the same time, it uses an emotion engine to analyze the emotion contained in the question. For example, it determines whether the input text indicates an emotional state such as "excitement," "confusion," or "joy."

[1234] Retrieval of relevant data and integration of emotional information

[1235] The server searches for relevant data from the behavioral big database based on keywords and context derived from NLP analysis. At the same time, emotional information obtained from the emotion engine is also incorporated into the data analysis. For example, a passionate message will generate a proposal that requires innovation, while a confused message will generate a proposal that requires clarity and a sense of security.

[1236] Data analysis and proposal generation

[1237] The server uses generative AI to analyze behavioral big data and emotional information to generate proposals. Generative AI then uses machine learning models to analyze this data and make the most appropriate proposals. For example, it generates specific proposals such as, "The latest market trends call for high-performance cameras, 5G compatibility, and large-capacity batteries. By incorporating these features into your new product, you can increase your competitiveness."

[1238] Submit a proposal

[1239] The server sends the generated proposal to the user's device as an HTTP response, structured in JSON format.

[1240] View Suggestions

[1241] The device displays the received suggestions in a user interface, where the suggestions are presented to the user in a visually understandable format, such as charts, tables, or text descriptions.

[1242] Specific examples

[1243] For example, consider the case where a user asks a question about a new smartphone project.

[1244] User: "What market trends are driving new smartphone features?"

[1245] Terminal: Package it in JSON format and send an HTTP request to the API endpoint.

[1246] Server: Interprets the received request and performs analysis using the NLP module and emotion engine.

[1247] Server: Obtains relevant market trend data from the behavioral big database and generates proposals using the generative AI model.

[1248] Server: Sends the generated proposal in JSON format to the device.

[1249] Terminal: Proposals are displayed on the user interface, and the user can review the suggestions and take specific action based on them.

[1250] In this way, the system allows users to receive useful suggestions based on data analysis and sentiment information without having to have specialized knowledge.

[1251] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1252] Step 1: User enters question

[1253] The user opens the device interface and inputs a specific question, for example, "What is the best menu for opening a new cafe?" The question entered through the device interface is stored in the device's internal memory.

[1254] Step 2: Triggering a Question to be Submitted

[1255] The user clicks the send button, which triggers the sending of the entered question to the server. This causes the question data to be formatted into an HTTP request format on the terminal. The input is the user's click, and the output is the question data packaged in JSON format.

[1256] Step 3: Sending an HTTP request

[1257] The terminal sends question data packaged in JSON format to the server. The input is the packaged question data, and the output is an HTTP request to the server.

[1258] Step 4: Receiving the request

[1259] The server receives an HTTP request sent from a terminal. The input is the question data sent from the terminal, and the output is the temporary storage of the question data in the server.

[1260] Step 5: Passing to the Natural Language Processing (NLP) module

[1261] The server passes the question to a natural language processing (NLP) module, which tokenizes the text, tags it with parts of speech, and extracts keywords. The input is the question data, and the output is the tokenized text and extracted keywords.

[1262] Step 6: Sentiment analysis using a sentiment analysis engine

[1263] The server passes the text and keywords obtained from the NLP analysis to an emotion analysis engine to estimate the emotional state. The input is the NLP analysis result, and the output is an emotion tag such as "excitement," "confusion," or "joy."

[1264] Step 7: Generate Database Queries

[1265] The server generates a query to search the behavioral big database based on the keywords and emotion information obtained from the NLP module. The input is the keywords and emotion information, and the output is the database query.

[1266] Step 8: Database Search

[1267] The server uses the generated query to search for relevant data from the behavioral big database. The input is the database query, and the output is a relevant dataset, which may contain, for example, information about cafe menus or market trends.

[1268] Step 9: Proposal generation by generative AI

[1269] The server passes the acquired data and emotional information to the generative AI model to generate recommendations. The input is the relevant dataset and emotional information, and the output is a specific recommendation to the user. For example, a specific recommendation such as "According to the latest market trends, high-performance cameras, 5G compatibility, and large-capacity batteries are required" may be generated.

[1270] Step 10: Formatting the Proposal Data

[1271] The server structures the generated proposal in JSON format and packages it as an HTTP response. The input is the generated proposal and the output is structured data in JSON format.

[1272] Step 11: Send HTTP response

[1273] The server sends formatted proposal data to the user's device. The input is the proposal data in JSON format, and the output is an HTTP response sent to the device.

[1274] Step 12: Receiving Proposal Data

[1275] The terminal receives the proposed data sent from the server as an HTTP response. The input is the proposed data from the server, and the output is the data stored in the terminal.

[1276] Step 13: Display in the User Interface

[1277] The device parses the received suggestion data and displays it on the user interface. The suggestion content is presented in a visually easy-to-understand format. The input is the received suggestion data, and the output is the display on the user interface. The user can check the suggestion content and decide on a specific action based on it.

[1278] (Application example 2)

[1279] 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."

[1280] Conventional systems typically respond to user questions by simply analyzing or searching for answers, making it difficult to provide suggestions that take into account the emotional state of the questioner. Furthermore, particularly in the security field, there is a need for systems that can appropriately recognize emotions such as tension and anxiety among on-site staff and provide sophisticated suggestions. The present invention aims to solve these problems and provide a system that generates suggestions optimized for the user's emotions.

[1281] 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 a user to input a question via an input device; means for transmitting the question from the input device to the data processing device; means for receiving the question and analyzing it using natural language processing; means for searching for related behavioral data based on the analysis results; generation AI means for performing data analysis based on the search results and generating a proposal; means for transmitting the proposal to the user's input device; means for displaying the proposal on the user's input device; means for analyzing the question using an emotion engine and extracting emotion information; and means for optimizing the generated proposal by integrating the emotion information. This enables the generation of advanced proposals that take user emotions into consideration.

[1282] An "input device" is a device used by a user to input a question, and includes a microphone, keyboard, smartphone, tablet, or other electronic device.

[1283] "Data Processing Unit" refers to the server or cloud computing platform that receives, analyzes and processes queries submitted by users.

[1284] "Natural language processing" is a technology that formalizes input user questions and understands the content of the questions by performing text analysis and keyword extraction.

[1285] "Behavioral data" includes the user's past behavioral history, access history, and other related data, and is data that is searched according to the content of the question.

[1286] "Generative AI" is an artificial intelligence technology that uses machine learning models to analyze behavioral data and emotional information to generate optimal suggestions.

[1287] The "emotion engine" is a system that analyzes the user's emotional state from their questions and behavior, and extracts emotional information such as "relief," "confusion," and "excitement."

[1288] "Suggestion" refers to the optimal answer or recommended action output by the generative AI based on the user's question and emotional information.

[1289] "Data analysis" refers to the process of discovering hidden patterns and trends based on behavioral data and emotional information, and generating optimal suggestions based on the questions asked.

[1290] "Optimization" means that the content of the proposal is adjusted based on the extracted emotional information according to the emotional state of the user, and the most appropriate proposal is provided.

[1291] This invention is a system that uses an emotion engine to recognize emotions in response to user questions and uses generative AI to provide optimal suggestions.

[1292] System Overview

[1293] The system involves a procedure in which a user inputs a question via an input device (e.g., a microphone or smartphone), and the question is sent to a data processing device (e.g., a cloud server). The server analyzes the question using natural language processing (NLP), searches for relevant behavioral data, and performs sentiment analysis using an emotion engine. Based on this, a generative AI generates appropriate suggestions, which are finally sent to the user's input device and displayed.

[1294] Hardware and software used

[1295] Input device: The device the user uses to input a question. Examples include a microphone or a smartphone.

[1296] Data Processing Unit: A server or cloud computing platform that receives, analyzes, and processes user-submitted queries. An example is Amazon Web Services (AWS) EC2.

[1297] Natural Language Processing (NLP) module: A technology that uses the Google Cloud Natural Language API to formalize input user questions and perform text analysis and keyword extraction.

[1298] Emotion engine: A system that uses IBM Watson Tone Analyzer to analyze the user's emotional state from their questions and actions.

[1299] Generative AI: An artificial intelligence technology that implements machine learning models using OpenAI GPT-3.5 to analyze data and emotional information and generate optimal suggestions.

[1300] Specific explanation of the process

[1301] 1. User Question Input: The user uses an input device to enter a question verbally or as text. For example, a question might be, "Is this person safe to grant access?"

[1302] 2. Sending a question: The input device sends a question to the data processing device. The sending method is mainly an HTTP request.

[1303] 3. Question analysis and emotion recognition: When the server receives a question, it analyzes it using a natural language processing module. At the same time, it uses an emotion engine to extract emotional information contained in the question. Emotions such as "worry," "confusion," and "relief" are identified.

[1304] 4. Searching for related data and integrating emotional information: Based on the analysis results, the server searches for related information from the behavior database and integrates emotional information for analysis. This allows the server to consider suggestions that are appropriate for the user's emotions.

[1305] 5. Proposal generation by generative AI: Generative AI analyzes behavioral data and emotional information to generate optimal suggestions. Specific suggestions such as "There are no problems with this person's past visit history, so please allow access" can be obtained.

[1306] 6. Sending and displaying suggestions: The server sends the generated suggestions to the input device and displays them on the user's device. The user can review the displayed suggestions and take appropriate action.

[1307] Examples of concrete examples and prompts

[1308] As a specific example of use, consider the case where a user asks the following question in a security situation:

[1309] (Example of a prompt)

[1310] A visitor is standing at the front door. On-site staff are asking, "Is this person safe to grant access?" The staff is in an emotional state of "worried." Review past visit history and alarm records to generate optimal suggestions.

[1311] Such prompts allow the server to analyze the situation and generate and display optimal suggestions.

[1312] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1313] Step 1:

[1314] The user enters a question using an input device. The input device accepts voice or text input and formats the question as digital data. At this point, the entered data is captured as "voice data" or "text data."

[1315] Step 2:

[1316] The terminal sends the entered question as an HTTP request to the data processing device. The input here is captured "voice data" or "text data," which is used as the payload of the HTTP request. The sent data is stored on the server.

[1317] Step 3:

[1318] The server receives the question and analyzes it using a natural language processing (NLP) module. Here, "voice data" or "text data" is received, and the NLP module performs text analysis and keyword extraction. The analyzed "keyword data" and "structured text data" are generated as output.

[1319] Step 4:

[1320] The server searches for related behavioral data based on the analysis results. The input is "keyword data" and "structured text data," and the output is related "behavioral data." The behavioral database is searched to obtain the required information.

[1321] Step 5:

[1322] The server analyzes the question using an emotion engine and extracts emotional information. Here, "structured text data" is input into the emotion engine, which then outputs "emotional information." This emotional information includes emotional states such as "worry," "excitement," and "relief."

[1323] Step 6:

[1324] The server integrates the emotional information and combines it with behavioral data to generate suggestions using generative AI. The inputs are "behavioral data" and "emotional information," and the output is "optimal suggestions." The generative AI model analyzes this data and generates suggestions optimized for the user's emotional state.

[1325] Step 7:

[1326] The server sends the generated proposal to the terminal as an HTTP response. Here, the server creates an HTTP response using the "optimal proposal" as input and sends it to the terminal.

[1327] Step 8:

[1328] The device displays the suggestions on the user's input device. The received "optimal suggestions" are visually presented to the user, who can then check them and take appropriate action.

[1329] In this way, a system is realized that performs specific data processing and data calculation at each processing step and provides optimal suggestions to the user.

[1330] 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.

[1331] 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.

[1332] 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.

[1333] [Fourth embodiment]

[1334] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1335] 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.

[1336] 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).

[1337] 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.

[1338] 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.

[1339] 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).

[1340] 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.

[1341] 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.

[1342] 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.

[1343] 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.

[1344] 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.

[1345] 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.

[1346] 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."

[1347] This invention relates to a system that enables users to effectively utilize data. In this system, users input questions via a terminal, and a server analyzes the data based on the questions and provides specific suggestions. Below, the program processing of this system is explained in natural language, with specific examples.

[1348] System Overview

[1349] The system itself works by allowing users to ask questions through an interface, and the generative AI responds with appropriate suggestions. The user's device, the server, and the behavioral big database work together.

[1350] Program processing explanation

[1351] User question input

[1352] The user uses the terminal interface to input a question, for example, a question of the form "What is the best menu for opening a new cafe?"

[1353] Submit a Question

[1354] The terminal sends the entered question to the server as an HTTP request.

[1355] Question Analysis

[1356] The server passes the received question to a natural language processing (NLP) module for text analysis, which identifies what the user is looking for and what data is needed. For example, it extracts keywords such as "new cafe" or "best menu" and identifies the problem domain based on those.

[1357] Finding related data

[1358] The server searches for relevant behavioral big data based on the identified problem domain, such as search trends, location data, and customer visitor information by time of day for cafes.

[1359] Data analysis and proposal generation

[1360] The server passes the searched data to the AI ​​generator, which analyzes it. Using machine learning models and statistical analysis methods, the AI ​​generates the most effective suggestions. For example, it might generate a suggestion like, "The most popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. It would be especially effective to strengthen these menu items during weekday lunch hours."

[1361] Submit a proposal

[1362] The server sends the generated proposal to the user's terminal as an HTTP response.

[1363] View Suggestions

[1364] The terminal displays the received suggestions on a user interface, allowing the user to review the suggestions and take specific actions based on them.

[1365] Specific examples

[1366] For example, if a user asks a question about a new smartphone project, the following steps are taken:

[1367] User question input

[1368] The user types, "What market trends should I look for to help me think about new smartphone features?"

[1369] Submit a Question

[1370] The terminal sends a query to the server.

[1371] Question Analysis

[1372] The server uses natural language processing to analyze keywords such as "smartphone" and "market trends."

[1373] Finding related data

[1374] The server searches behavioral big data and extracts market trends such as high-performance cameras, 5G compatibility, and large-capacity batteries.

[1375] Data analysis and proposal generation

[1376] The server uses generative AI to analyze smartphone features that are in high demand in the market and generate proposals, such as "Recent market trends show an increasing demand for high-performance cameras, 5G compatibility, and large-capacity batteries."

[1377] Submit a proposal

[1378] The server transmits the generated proposal to the user's terminal.

[1379] View Suggestions

[1380] The device displays the suggestions to the user, allowing them to incorporate features based on market trends into new products.

[1381] In this way, the system is designed to enable users to effectively utilize the results of data analysis without having specialized knowledge.

[1382] The processing flow will be explained below.

[1383] Step 1:

[1384] A user uses the device interface to input a question, for example, "What is the best menu item for opening a new cafe?"

[1385] Step 2:

[1386] The device sends the entered question to the server as an HTTP request, which is structured as text data.

[1387] Step 3:

[1388] The server passes the received question to a Natural Language Processing (NLP) module, which performs text analysis of the question, identifying key keywords and context, to understand the user's intent and identify the information they need.

[1389] Step 4:

[1390] The server searches for relevant behavioral big data based on the keywords and context analyzed through the NLP module, and generates and executes queries to extract the required datasets from the behavioral big database.

[1391] Step 5:

[1392] The server passes the searched data to the Generative AI, which then uses machine learning algorithms to analyze the data and generate specific suggestions based on the analysis results.

[1393] Step 6:

[1394] The server sends the generated proposal to the user's device as an HTTP response. The response consists of JSON format data containing the proposal content.

[1395] Step 7:

[1396] The device displays the received suggestions on the user interface. It parses the received JSON data and presents it to the user in a visually easy-to-understand format. For example, it might say, "Popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. It would be particularly effective to strengthen these menu items during weekday lunch hours."

[1397] In this way, the system provides appropriate data analysis and suggestions based on user questions throughout all processing steps.

[1398] Example 1

[1399] 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."

[1400] In conventional data utilization systems, it is difficult for users without specialized knowledge to effectively analyze data and obtain specific proposals based on the results. In particular, it is extremely time-consuming and requires many steps to properly analyze a user's question, search for appropriate data based on that analysis, and generate proposals. For this reason, there is a demand for an efficient and easy-to-use data utilization system.

[1401] 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.

[1402] In this invention, the server includes means for a user to input a question via an information processing device, means for transmitting the question from the information processing device to the information processing device, means for receiving the question and analyzing it using natural language processing, means for searching a large amount of related data based on the analysis results, generation AI means for performing data analysis based on the search results and generating a proposal, means for transmitting the generated proposal to the user's information processing device, and means for displaying the proposal on the user's information processing device. This enables a user to quickly obtain effective data analysis and specific proposals based on the results of the analysis, even without specialized knowledge.

[1403] An "information processing device" is a device that allows a user to input a question and transmit the question to a server, and refers to electronic devices such as computers, smartphones, and tablets.

[1404] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, extracting meaning from text data and providing appropriate information.

[1405] "Big data" refers to a huge collection of data related to a user's question, including databases and cloud storage for searching and retrieving specific information.

[1406] "Generative AI" is an artificial intelligence technology that uses machine learning models to analyze data, make predictions, and make suggestions.

[1407] "Data analysis" is the process of analyzing acquired data using statistical methods and machine learning models to derive useful information and suggestions.

[1408] "Suggestions" refer to specific actions or ideas presented to users based on the results of data analysis.

[1409] A "user interface" refers to a display screen or operating means that allows a user to interact with a system through an information processing device, and includes a web browser and a mobile application.

[1410] The present invention relates to a system for enabling users to effectively utilize data. In this system, a user inputs a question via an information processing device, and a server analyzes the data based on the question and provides specific suggestions. The following describes in detail an embodiment of this system.

[1411] System Overview

[1412] The system mainly consists of a user's information processing device, a server, and a large database. A question entered by the user is sent from the information processing device to the server, which analyzes the question, searches for and analyzes appropriate data, and returns the results to the user's information processing device.

[1413] Hardware and software used

[1414] Information processing devices: computers, smartphones, tablets, etc.

[1415] Server: Hardware that includes a database management system (DBMS) and data storage such as cloud storage.

[1416] Software: Natural language processing libraries (e.g., NLTK, spaCy), machine learning libraries (e.g., Scikit Learn, TensorFlow).

[1417] Program processing

[1418] User question input

[1419] The user inputs a question using the interface of the information processing device, for example, a question in the format "What is the best menu for opening a new cafe?"

[1420] Submit a Question

[1421] The device sends the user-entered question to the server as an HTTP POST request, which converts the question into JSON format and sends it to the API endpoint.

[1422] Question Analysis

[1423] The server decodes the received HTTP request and extracts the question. It then uses a natural language processing (NLP) module to analyze the text and extract keywords, such as "new cafe" or "best menu."

[1424] Finding related data

[1425] The server searches a large database based on the analyzed keywords, using a database management system (DBMS) or cloud storage to obtain relevant data (e.g., search trends and customer data related to cafes).

[1426] Data analysis and proposal generation

[1427] The server passes the acquired data to a generative AI model for data analysis. The generative AI model generates optimal suggestions based on machine learning algorithms (using, for example, Scikit Learn or TensorFlow). For example, a suggestion might be generated such as, "Popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. It would be particularly effective to strengthen these menu items during weekday lunch hours."

[1428] Submit a proposal

[1429] The server sends the generated proposal to the user's information processing device as an HTTP response. The proposal content is serialized in JSON format and included in the response body.

[1430] View Suggestions

[1431] The device deserializes the received suggestions and displays them in the user interface: in the browser, by dynamically adding the suggestions to HTML using JavaScript; in the mobile app, by updating a dedicated UI component to display the suggestions.

[1432] Specific operation example

[1433] For example, if a user inputs "Please tell me the market trends that will help me think about new smartphone features," the processing will be carried out in the following steps.

[1434] User question input

[1435] The user types, "What market trends should I look for to help me think about new smartphone features?"

[1436] Submit a Question

[1437] The terminal sends a query to the server.

[1438] Question Analysis

[1439] The server uses a natural language processing module to analyze keywords such as "smartphone" and "market trends" and extract information to search for appropriate data.

[1440] Finding related data

[1441] The server searches a large database based on the analyzed keywords and extracts market trends such as high-performance cameras, 5G compatibility, and large-capacity batteries.

[1442] Data analysis and proposal generation

[1443] The server analyzes the data using a generative AI model and generates optimal recommendations for the user, such as, "Recent market trends show an increasing demand for high-performance cameras, 5G compatibility, and large-capacity batteries."

[1444] Submit a proposal

[1445] The server transmits the generated proposal to the user's information processing device.

[1446] View Suggestions

[1447] The terminal displays the proposals on the user interface, allowing users to check the proposals based on market trends and take specific actions.

[1448] In this way, the system is designed to enable users to effectively utilize the results of data analysis without having specialized knowledge.

[1449] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1450] Step 1: User enters question

[1451] A user uses the interface of a data processing device to input a question, such as "What is the best menu item for opening a new cafe?", into a text field. The input is done via a web form or a text box in a mobile app.

[1452] Input: The user's question text.

[1453] Output: The user's question text.

[1454] Step 2: Send the question to the server

[1455] The device sends the user-entered question to the server as an HTTP POST request, which converts the question into JSON format and sends it to the API endpoint.

[1456] Input: The user's question text.

[1457] Output: The HTTP request sent to the server.

[1458] Step 3: The server receives the query

[1459] The server decrypts the received HTTP request and extracts the question text from the request body.

[1460] Input: HTTP request.

[1461] Output: The extracted question text.

[1462] Step 4: Parse the question

[1463] The server passes the extracted question text to a natural language processing (NLP) module for text analysis, for example, using Python's NLTK or spaCy libraries to extract keywords such as "new cafe" or "best menu."

[1464] Input: Question text.

[1465] Output: Extracted keywords.

[1466] Step 5: Find related data

[1467] The server searches a large database based on the extracted keywords. It uses a database management system (DBMS) or cloud storage to retrieve relevant data (e.g., search trends and customer data related to cafes). It performs searches using SQL queries or NoSQL query languages.

[1468] Input: Keywords.

[1469] Output: The relevant data found.

[1470] Step 6: Conduct data analysis

[1471] The server then passes the acquired data to a generative AI model for data analysis, which then analyzes the data using machine learning algorithms (for example, using Scikit Learn or TensorFlow) to generate optimal recommendations.

[1472] Input: The relevant data found.

[1473] Output: The generated proposals.

[1474] Step 7: Submit your proposal

[1475] The server sends the generated proposal to the user's information processing device as an HTTP response. The proposal content is serialized in JSON format and included in the response body.

[1476] Input: The generated proposals.

[1477] Output: The HTTP response sent to the user device.

[1478] Step 8: View suggestions

[1479] The device deserializes the received suggestions and displays them in the user interface: in the browser, by dynamically adding the suggestions to HTML using JavaScript; in the mobile app, by updating a dedicated UI component to display the suggestions.

[1480] Input: The proposal received as an HTTP response.

[1481] Output: The proposal displayed in the user interface.

[1482] (Application example 1)

[1483] 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."

[1484] On conventional online shopping sites, users often have difficulty choosing products and it can take a long time to find the right one. Furthermore, there is a lack of systems that can efficiently gather the information users need and make optimal recommendations based on that information. This leads to issues such as a poor user experience and a decrease in purchasing motivation.

[1485] 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.

[1486] In this invention, the server includes: means for a user to input a question via a terminal; means for transmitting the question from the terminal to the server; means for receiving the question and analyzing it using natural language processing; means for searching for related behavioral big data based on the analysis results; generation AI means for performing data analysis based on the search results and generating proposals; means for transmitting the generated proposals to the user's terminal; means for displaying the proposals on the user's terminal; and means for searching market trend data and customer review data based on a question about product selection and suggesting optimal products through data analysis using behavioral big data including these. This enables the user to efficiently select appropriate products.

[1487] A "user terminal" is a communications-enabled device that a user uses to enter questions and receive suggestions.

[1488] The "means for inputting a question" is a function of the interface that allows a user to input a question in text format via a terminal.

[1489] The "means for transmitting to the server" is a communication means for transferring the question entered by the user at the terminal to the server.

[1490] The "means for receiving a question and analyzing it using natural language processing" is a function in which the server receives a question sent and analyzes it using natural language processing technology.

[1491] "Means for searching related behavioral big data" refers to a function that searches a database for related behavioral data based on the analysis results.

[1492] "Generative AI means for analyzing data and generating proposals" refers to AI technology that uses machine learning models to analyze behavioral big data and generate specific proposals for users.

[1493] The "means for transmitting the generated proposal to the user's terminal" is a communication means for transferring the proposal generated by the server to the user's terminal.

[1494] The "means for displaying the proposal on the user's terminal" is an interface function that allows the user to check the received proposal on the display screen of the terminal.

[1495] "Market trend data" refers to data that indicates current market demand and trends.

[1496] "Customer review data" refers to data regarding ratings and reviews given by customers who have purchased a product.

[1497] "Behavioral big data" refers to large datasets about user behavior and preferences.

[1498] This invention relates to a system in which a user inputs a question via a terminal, a server analyzes the data in response to the question, and generates a proposal and responds. Below, the configuration and operation of the system will be described along with each processing step.

[1499] System Configuration

[1500] This system consists of a terminal used by users, a server that processes data, and a database that integrates them.

[1501] Device: A device with communication capabilities used by a user, such as a smartphone or tablet.

[1502] Server: Backend system using Node.js and Express.js.

[1503] Natural Language Processing Module: A natural language processing engine built using TensorFlow.js.

[1504] Database: MongoDB is used.

[1505] Generative AI model: OpenAI GPT-4 is used.

[1506] Operation process

[1507] 1. User enters question:

[1508] Users input their questions through a terminal interface, which is easy to use and built with React Native.

[1509] 2. Submit your question:

[1510] The question entered by the user is sent to the server as an HTTP POST request.

[1511] 3. Question Analysis:

[1512] The server receives the question and analyzes it using a natural language processing module (TensorFlow.js), extracting keywords from the question and understanding its meaning.

[1513] 4. Search for relevant data:

[1514] Based on the analysis results, the server retrieves relevant behavioral big data from a MongoDB database, including market trend data and customer review data.

[1515] 5. Data analysis and proposal generation:

[1516] The server passes the analyzed data to a generative AI model (OpenAI GPT-4) to generate optimal proposals. Based on the machine learning model, data analysis is performed on market trends and other data to create specific proposals for users.

[1517] 6. Submitting and Viewing Proposals:

[1518] The generated proposal is sent to the user's device as an HTTP response, where the user can view the proposal in the device interface.

[1519] Specific examples

[1520] For example, if a user enters the question, "What are the best suggestions for choosing a new smartphone model?", the system operates as follows: The server receives the question and analyzes keywords such as "smartphone" and "model selection" through natural language processing. Next, it searches related market trend data and customer review data and generates optimal suggestions using a generative AI model. It provides the user with suggestions such as, "According to the latest market trends, models with high camera performance are popular. The Model X in particular has high ratings, and its battery tends to be large-capacity and long-lasting."

[1521] Example prompts for generative AI models

[1522] What are your best suggestions for choosing a new smartphone model?

[1523] Input data: customer reviews, sales data, rating rankings

[1524] This allows users to quickly and accurately select the most suitable product, improving the quality of the user experience.

[1525] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1526] Step 1:

[1527] The user uses a device such as a smartphone or tablet to input a question through the interface of the online shopping app.

[1528] Input: User question (e.g., "What are your best suggestions for choosing a new smartphone model?")

[1529] Output: The question text entered

[1530] What happens: The user types a question into the text box and taps the "Submit" button.

[1531] Step 2:

[1532] The terminal sends the entered question to the server as an HTTP POST request.

[1533] Input: The question text entered by the user

[1534] Output: HTTP request sent to the server

[1535] How it works: The question text is sent in the body of an HTTP request to the server's API endpoint.

[1536] Step 3:

[1537] The server receives the received question and passes it to the natural language processing (NLP) module for analysis.

[1538] Input: The question text received by the server

[1539] Output: Analysis results (keywords and their semantic information)

[1540] How it works: The server uses TensorFlow.js to analyze the question text and extract keywords and their meanings. For example, keywords such as "smartphone" and "model selection" are extracted.

[1541] Step 4:

[1542] The server searches for relevant behavioral big data based on the analysis results.

[1543] Input: Analysis results (e.g., keywords "smartphone" and "model selection")

[1544] Output: Relevant datasets (market trend data, customer review data, etc.)

[1545] How it works: The server queries MongoDB to find and retrieve data (market trends, customer reviews) that matches the set criteria.

[1546] Step 5:

[1547] The server passes the retrieved data to a generative AI model to generate optimal suggestions.

[1548] Input: Related datasets

[1549] Output: Generated suggestions (e.g., "According to the latest market trends, models with high camera performance are popular. The Model X in particular is highly rated.")

[1550] How it works: The server uses OpenAI GPT-4 to generate suggestions based on the provided dataset, and outputs the suggestions in text format.

[1551] Step 6:

[1552] The server sends the generated proposal to the user's terminal as an HTTP response.

[1553] Input: Generated suggested text

[1554] Output: Suggested text sent to the user's device

[1555] How it works: The server places the generated proposal in the body of an HTTP response and sends it to the user's device.

[1556] Step 7:

[1557] The terminal displays the received proposals on its interface.

[1558] Input: Suggested text received from the server

[1559] Output: The suggestions displayed

[1560] Operation: The user's device displays the received suggested text on the screen for the user to review.

[1561] 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.

[1562] The present invention relates to a system in which a generative AI uses an emotion engine to recognize emotions in response to user questions and make optimal suggestions. Below, the processing of the system's program is explained in natural language, and specific examples based on the claims are also provided.

[1563] System Overview

[1564] In this system, users input questions via their devices, the server performs data analysis and sentiment analysis based on the questions, and the generative AI generates appropriate suggestions and provides them to the user. The system includes the following elements:

[1565] The device where the user enters their question

[1566] A server that identifies problem areas and analyzes related behavioral big data and emotional information

[1567] Emotion Engine

[1568] Generation AI

[1569] An interface that presents suggestions to the user

[1570] Program processing explanation

[1571] User question input

[1572] The user inputs a question using the terminal interface, such as "What is the best menu for opening a new cafe?"

[1573] Submit a Question

[1574] The terminal sends the entered question to the server as an HTTP request.

[1575] Question analysis and emotion recognition

[1576] The server passes the received question to a natural language processing (NLP) module for text analysis and keyword extraction, thereby understanding what the user is asking.

[1577] The server simultaneously analyzes the emotion contained in the question using an emotion engine, determining, for example, whether the entered text indicates an emotional state such as "excitement," "confusion," or "happiness."

[1578] Retrieval of relevant data and integration of emotional information

[1579] The server searches for relevant data from the behavioral big database based on keywords and context derived from NLP analysis.

[1580] The server also incorporates emotional information obtained from the emotion engine into the data analysis. For example, a passionate message can generate a proposal that requires innovation, while a confused message can generate a proposal that requires clarity and a sense of security.

[1581] Data analysis and proposal generation

[1582] The server uses a generative AI to analyze behavioral big data and emotional information to generate suggestions. The generative AI then uses a machine learning model to analyze this data and provide the most appropriate suggestions.

[1583] Submit a proposal

[1584] The server sends the generated proposal to the user's device as an HTTP response. The proposal is structured in JSON format or similar.

[1585] View Suggestions

[1586] The device displays the received suggestions on a user interface, where the suggestions are presented to the user in a visually easy-to-understand format.

[1587] Specific examples

[1588] For example, consider the case where a user asks a question about a new smartphone project.

[1589] User question input

[1590] User: "What market trends are driving new smartphone features?"

[1591] Submit a Question

[1592] Terminal: Send the above question to the server.

[1593] Question analysis and emotion recognition

[1594] Server: Analyzes questions using natural language processing to extract keywords such as "smartphone" and "market trends," and uses an emotion engine to analyze user emotions and detect rising levels of "excitement."

[1595] Retrieval of relevant data and integration of emotional information

[1596] Server: Searches for market trends such as high-performance cameras, 5G compatibility, and large-capacity batteries from behavioral big data. At the same time, it analyzes emotional information and considers innovative proposals based on the user's excitement level.

[1597] Data analysis and proposal generation

[1598] Server: Generative AI analyzes data and emotional information to generate recommendations tailored to the user. For example, it might generate a recommendation like, "The latest market trends demand high-performance cameras, 5G compatibility, and large-capacity batteries. By incorporating these features into your new product, you can increase your competitiveness."

[1599] Submit a proposal

[1600] Server: Sends the generated proposals to the user's device.

[1601] View Suggestions

[1602] On the device: The received suggestions are displayed in the user interface, allowing the user to review the suggestions and take specific actions based on them.

[1603] In this way, the system allows users to receive useful suggestions based on data analysis and sentiment information without requiring specialized knowledge.

[1604] The processing flow will be explained below.

[1605] This invention relates to a system in which a generative AI uses an emotion engine to recognize emotions in response to user questions and make optimal suggestions. The system's processing flow and specific operations are explained in the following steps.

[1606] System processing steps

[1607] Step 1:

[1608] A user uses the device interface to input a question, for example, "What is the best menu item for opening a new cafe?"

[1609] Step 2:

[1610] The device sends the entered question to the server as an HTTP request, which is structured as text data.

[1611] Step 3:

[1612] The server passes the received question to a natural language processing (NLP) module for text analysis and keyword extraction. For example, it extracts keywords such as "cafe," "opening," "optimal," and "menu," and analyzes the context.

[1613] Step 4:

[1614] The server uses an emotion engine to analyze the emotion contained in the question. For example, it identifies emotions such as "excitement" or "anxiety" from the wording. This is done using a sentiment analysis algorithm.

[1615] Step 5:

[1616] The server searches for relevant behavioral big data based on keywords extracted by NLP and emotional information recognized by the emotion engine. For example, it searches for search trends related to "cafes" and "menus" or regional characteristic data based on the user's location information.

[1617] Step 6:

[1618] The server then passes the searched data and sentiment information to the AI ​​generator, which then uses machine learning algorithms to determine, for example, that "latte art cafe latte" and "homemade cinnamon rolls" are popular in the area.

[1619] Step 7:

[1620] The server uses generative AI to generate specific suggestions, taking into account the user's emotional state, such as, "The most popular menu items in the area are latte art cafe lattes and homemade cinnamon rolls. In particular, based on your excitement level, we highly recommend you try a new menu item."

[1621] Step 8:

[1622] The server sends the generated proposal to the user's device as an HTTP response, which is typically structured in JSON format.

[1623] Step 9:

[1624] The device displays the received suggestions on the user interface, using graphs, lists, and other formats that are visually easy for the user to understand.

[1625] Specific examples

[1626] For example, if a user asks a question about a new smartphone project:

[1627] Step 1:

[1628] A user types, "What market trends will help me think about new smartphone features?"

[1629] Step 2:

[1630] The terminal sends a question to the server.

[1631] Step 3:

[1632] The server uses NLP to analyze the text and extract keywords such as "smartphone" and "market trends."

[1633] Step 4:

[1634] The server uses an emotion engine to identify emotions such as "excitement" or "expectation" contained in the user's question.

[1635] Step 5:

[1636] The server searches for relevant data from the behavioral big data based on the extracted keywords and emotional information. For example, it searches for trend data such as "high-performance camera," "5G compatible," and "large-capacity battery."

[1637] Step 6:

[1638] The server passes the searched data and sentiment information to the generative AI, which then performs data analysis. For example, based on market trends, it determines that a high-performance camera, 5G compatibility, and a large-capacity battery are important.

[1639] Step 7:

[1640] The server uses generative AI to generate suggestions, such as, "Recent market trends demand high-performance cameras, 5G compatibility, and large-capacity batteries. In particular, based on your excitement level, we strongly recommend that you actively adopt new technologies."

[1641] Step 8:

[1642] The server transmits the generated proposal to the user's terminal.

[1643] Step 9:

[1644] The device displays the received proposals on the user interface, allowing the user to come up with specific project ideas based on the proposals.

[1645] In this way, the system allows users to receive useful suggestions based on data analysis and sentiment information without requiring specialized knowledge.

[1646] Example 2

[1647] 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."

[1648] Conventional systems simply analyze data based on questions entered by users and generate suggestions, making it difficult to fully understand the user's emotions and intentions and provide optimal suggestions. As a result, the suggestions often do not meet the user's needs, resulting in a decrease in user satisfaction.

[1649] 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.

[1650] In this invention, the server includes means for analyzing questions using natural language processing, means for acquiring emotional information using an emotion analysis engine, means for searching for related data based on the analysis results and the emotional information, and means for generating suggestions based on the analysis results and the emotional information using a generation AI, thereby enabling optimal suggestions that take into account the user's emotions and intentions.

[1651] A "user" is an entity that utilizes the system to enter questions and receive suggestions.

[1652] A "terminal" is a computing device or interface through which a user enters a query and communicates with a server.

[1653] A "question" is information or a problem that a user inputs via a terminal.

[1654] A "server" is a computer system that receives user-entered questions and performs analysis and suggestion generation.

[1655] "Natural language processing" is a technology that analyzes questions and extracts keywords and intent from text.

[1656] An "emotion analysis engine" is software or a module for analyzing the emotional information contained in an input question.

[1657] "Relevant data" refers to information required for generating suggestions, retrieved based on natural language processing and sentiment information.

[1658] "Generative AI" is artificial intelligence that uses machine learning models to generate suggestions based on analysis results and emotional information.

[1659] A "suggestion" is an answer or recommendation that the generative AI creates based on the user's question and related data.

[1660] The present invention relates to a system in which a generation AI uses an emotion engine to recognize emotions in response to a user's question and make optimal suggestions. In this system, the user inputs a question via a terminal, a server performs data analysis and emotion analysis based on the question, and the generation AI generates appropriate suggestions and provides them to the user. The system includes the following elements:

[1661] The device where the user enters their question

[1662] A server that identifies problem areas and analyzes related behavioral big data and emotional information

[1663] Emotion Engine

[1664] Generation AI

[1665] An interface that presents suggestions to the user

[1666] User question input

[1667] The user uses the device interface to input a specific question, such as "What is the best menu for opening a new cafe?"

[1668] Submit a Question

[1669] The device sends the entered question as an HTTP request to the server, with the data packaged in JSON format.

[1670] Question analysis and emotion recognition

[1671] The server passes the received question to a natural language processing (NLP) module for text analysis and keyword extraction. This allows it to understand what the user is asking. At the same time, it uses an emotion engine to analyze the emotion contained in the question. For example, it determines whether the input text indicates an emotional state such as "excitement," "confusion," or "joy."

[1672] Retrieval of relevant data and integration of emotional information

[1673] The server searches for relevant data from the behavioral big database based on keywords and context derived from NLP analysis. At the same time, emotional information obtained from the emotion engine is also incorporated into the data analysis. For example, a passionate message will generate a proposal that requires innovation, while a confused message will generate a proposal that requires clarity and a sense of security.

[1674] Data analysis and proposal generation

[1675] The server uses generative AI to analyze behavioral big data and emotional information to generate proposals. Generative AI then uses machine learning models to analyze this data and make the most appropriate proposals. For example, it generates specific proposals such as, "The latest market trends call for high-performance cameras, 5G compatibility, and large-capacity batteries. By incorporating these features into your new product, you can increase your competitiveness."

[1676] Submit a proposal

[1677] The server sends the generated proposal to the user's device as an HTTP response, structured in JSON format.

[1678] View Suggestions

[1679] The device displays the received suggestions in a user interface, where the suggestions are presented to the user in a visually understandable format, such as charts, tables, or text descriptions.

[1680] Specific examples

[1681] For example, consider the case where a user asks a question about a new smartphone project.

[1682] User: "What market trends are driving new smartphone features?"

[1683] Terminal: Package it in JSON format and send an HTTP request to the API endpoint.

[1684] Server: Interprets the received request and performs analysis using the NLP module and emotion engine.

[1685] Server: Obtains relevant market trend data from the behavioral big database and generates proposals using the generative AI model.

[1686] Server: Sends the generated proposal in JSON format to the device.

[1687] Terminal: Proposals are displayed on the user interface, and the user can review the suggestions and take specific action based on them.

[1688] In this way, the system allows users to receive useful suggestions based on data analysis and sentiment information without having to have specialized knowledge.

[1689] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1690] Step 1: User enters question

[1691] The user opens the device interface and inputs a specific question, for example, "What is the best menu for opening a new cafe?" The question entered through the device interface is stored in the device's internal memory.

[1692] Step 2: Triggering a Question to be Submitted

[1693] The user clicks the send button, which triggers the sending of the entered question to the server. This causes the question data to be formatted into an HTTP request format on the terminal. The input is the user's click, and the output is the question data packaged in JSON format.

[1694] Step 3: Sending an HTTP request

[1695] The terminal sends question data packaged in JSON format to the server. The input is the packaged question data, and the output is an HTTP request to the server.

[1696] Step 4: Receiving the request

[1697] The server receives an HTTP request sent from a terminal. The input is the question data sent from the terminal, and the output is the temporary storage of the question data in the server.

[1698] Step 5: Passing to the Natural Language Processing (NLP) module

[1699] The server passes the question to a natural language processing (NLP) module, which tokenizes the text, tags it with parts of speech, and extracts keywords. The input is the question data, and the output is the tokenized text and extracted keywords.

[1700] Step 6: Sentiment analysis using a sentiment analysis engine

[1701] The server passes the text and keywords obtained from the NLP analysis to an emotion analysis engine to estimate the emotional state. The input is the NLP analysis result, and the output is an emotion tag such as "excitement," "confusion," or "joy."

[1702] Step 7: Generate Database Queries

[1703] The server generates a query to search the behavioral big database based on the keywords and emotion information obtained from the NLP module. The input is the keywords and emotion information, and the output is the database query.

[1704] Step 8: Database Search

[1705] The server uses the generated query to search for relevant data from the behavioral big database. The input is the database query, and the output is a relevant dataset, which may contain, for example, information about cafe menus or market trends.

[1706] Step 9: Proposal generation by generative AI

[1707] The server passes the acquired data and emotional information to the generative AI model to generate recommendations. The input is the relevant dataset and emotional information, and the output is a specific recommendation to the user. For example, a specific recommendation such as "According to the latest market trends, high-performance cameras, 5G compatibility, and large-capacity batteries are required" may be generated.

[1708] Step 10: Formatting the Proposal Data

[1709] The server structures the generated proposal in JSON format and packages it as an HTTP response. The input is the generated proposal and the output is structured data in JSON format.

[1710] Step 11: Send HTTP response

[1711] The server sends formatted proposal data to the user's device. The input is the proposal data in JSON format, and the output is an HTTP response sent to the device.

[1712] Step 12: Receiving Proposal Data

[1713] The terminal receives the proposed data sent from the server as an HTTP response. The input is the proposed data from the server, and the output is the data stored in the terminal.

[1714] Step 13: Display in the User Interface

[1715] The device parses the received suggestion data and displays it on the user interface. The suggestion content is presented in a visually easy-to-understand format. The input is the received suggestion data, and the output is the display on the user interface. The user can check the suggestion content and decide on a specific action based on it.

[1716] (Application example 2)

[1717] 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."

[1718] Conventional systems typically respond to user questions by simply analyzing or searching for answers, making it difficult to provide suggestions that take into account the emotional state of the questioner. Furthermore, particularly in the security field, there is a need for systems that can appropriately recognize emotions such as tension and anxiety among on-site staff and provide sophisticated suggestions. The present invention aims to solve these problems and provide a system that generates suggestions optimized for the user's emotions.

[1719] 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 a user to input a question via an input device; means for transmitting the question from the input device to the data processing device; means for receiving the question and analyzing it using natural language processing; means for searching for related behavioral data based on the analysis results; generation AI means for performing data analysis based on the search results and generating a proposal; means for transmitting the proposal to the user's input device; means for displaying the proposal on the user's input device; means for analyzing the question using an emotion engine and extracting emotion information; and means for optimizing the generated proposal by integrating the emotion information. This enables the generation of advanced proposals that take user emotions into consideration.

[1720] An "input device" is a device used by a user to input a question, and includes a microphone, keyboard, smartphone, tablet, or other electronic device.

[1721] "Data Processing Unit" refers to the server or cloud computing platform that receives, analyzes and processes queries submitted by users.

[1722] "Natural language processing" is a technology that formalizes input user questions and understands the content of the questions by performing text analysis and keyword extraction.

[1723] "Behavioral data" includes the user's past behavioral history, access history, and other related data, and is data that is searched according to the content of the question.

[1724] "Generative AI" is an artificial intelligence technology that uses machine learning models to analyze behavioral data and emotional information to generate optimal suggestions.

[1725] The "emotion engine" is a system that analyzes the user's emotional state from their questions and behavior, and extracts emotional information such as "relief," "confusion," and "excitement."

[1726] "Suggestion" refers to the optimal answer or recommended action output by the generative AI based on the user's question and emotional information.

[1727] "Data analysis" refers to the process of discovering hidden patterns and trends based on behavioral data and emotional information, and generating optimal suggestions based on the questions asked.

[1728] "Optimization" means that the content of the proposal is adjusted based on the extracted emotional information according to the emotional state of the user, and the most appropriate proposal is provided.

[1729] This invention is a system that uses an emotion engine to recognize emotions in response to user questions and uses generative AI to provide optimal suggestions.

[1730] System Overview

[1731] The system involves a procedure in which a user inputs a question via an input device (e.g., a microphone or smartphone), and the question is sent to a data processing device (e.g., a cloud server). The server analyzes the question using natural language processing (NLP), searches for relevant behavioral data, and performs sentiment analysis using an emotion engine. Based on this, a generative AI generates appropriate suggestions, which are finally sent to the user's input device and displayed.

[1732] Hardware and software used

[1733] Input device: The device the user uses to input a question. Examples include a microphone or a smartphone.

[1734] Data Processing Unit: A server or cloud computing platform that receives, analyzes, and processes user-submitted queries. An example is Amazon Web Services (AWS) EC2.

[1735] Natural Language Processing (NLP) module: A technology that uses the Google Cloud Natural Language API to formalize input user questions and perform text analysis and keyword extraction.

[1736] Emotion engine: A system that uses IBM Watson Tone Analyzer to analyze the user's emotional state from their questions and actions.

[1737] Generative AI: An artificial intelligence technology that implements machine learning models using OpenAI GPT-3.5 to analyze data and emotional information and generate optimal suggestions.

[1738] Specific explanation of the process

[1739] 1. User Question Input: The user uses an input device to enter a question verbally or as text. For example, a question might be, "Is this person safe to grant access?"

[1740] 2. Sending a question: The input device sends a question to the data processing device. The sending method is mainly an HTTP request.

[1741] 3. Question analysis and emotion recognition: When the server receives a question, it analyzes it using a natural language processing module. At the same time, it uses an emotion engine to extract emotional information contained in the question. Emotions such as "worry," "confusion," and "relief" are identified.

[1742] 4. Searching for related data and integrating emotional information: Based on the analysis results, the server searches for related information from the behavior database and integrates emotional information for analysis. This allows the server to consider suggestions that are appropriate for the user's emotions.

[1743] 5. Proposal generation by generative AI: Generative AI analyzes behavioral data and emotional information to generate optimal suggestions. Specific suggestions such as "There are no problems with this person's past visit history, so please allow access" can be obtained.

[1744] 6. Sending and displaying suggestions: The server sends the generated suggestions to the input device and displays them on the user's device. The user can review the displayed suggestions and take appropriate action.

[1745] Examples of concrete examples and prompts

[1746] As a specific example of use, consider the case where a user asks the following question in a security situation:

[1747] (Example of a prompt)

[1748] A visitor is standing at the front door. On-site staff are asking, "Is this person safe to grant access?" The staff is in an emotional state of "worried." Review past visit history and alarm records to generate optimal suggestions.

[1749] Such prompts allow the server to analyze the situation and generate and display optimal suggestions.

[1750] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1751] Step 1:

[1752] The user enters a question using an input device. The input device accepts voice or text input and formats the question as digital data. At this point, the entered data is captured as "voice data" or "text data."

[1753] Step 2:

[1754] The terminal sends the entered question as an HTTP request to the data processing device. The input here is captured "voice data" or "text data," which is used as the payload of the HTTP request. The sent data is stored on the server.

[1755] Step 3:

[1756] The server receives the question and analyzes it using a natural language processing (NLP) module. Here, "voice data" or "text data" is received, and the NLP module performs text analysis and keyword extraction. The analyzed "keyword data" and "structured text data" are generated as output.

[1757] Step 4:

[1758] The server searches for related behavioral data based on the analysis results. The input is "keyword data" and "structured text data," and the output is related "behavioral data." The behavioral database is searched to obtain the required information.

[1759] Step 5:

[1760] The server analyzes the question using an emotion engine and extracts emotional information. Here, "structured text data" is input into the emotion engine, which then outputs "emotional information." This emotional information includes emotional states such as "worry," "excitement," and "relief."

[1761] Step 6:

[1762] The server integrates the emotional information and combines it with behavioral data to generate suggestions using generative AI. The inputs are "behavioral data" and "emotional information," and the output is "optimal suggestions." The generative AI model analyzes this data and generates suggestions optimized for the user's emotional state.

[1763] Step 7:

[1764] The server sends the generated proposal to the terminal as an HTTP response. Here, the server creates an HTTP response using the "optimal proposal" as input and sends it to the terminal.

[1765] Step 8:

[1766] The device displays the suggestions on the user's input device. The received "optimal suggestions" are visually presented to the user, who can then check them and take appropriate action.

[1767] In this way, a system is realized that performs specific data processing and data calculation at each processing step and provides optimal suggestions to the user.

[1768] 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.

[1769] 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.

[1770] 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 robot 414.

[1771] 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.

[1772] FIG. 9 illustrates 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 behaviors 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.

[1773] 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.

[1774] 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).

[1775] 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.

[1776] 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."

[1777] 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.

[1778] 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).

[1779] 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.

[1780] 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.

[1781] 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.

[1782] 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.

[1783] 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.

[1784] 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.

[1785] 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.

[1786] 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.

[1787] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1788] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1789] The following is further disclosed regarding the above embodiment.

[1790] (Claim 1)

[1791] a means for a user to input a question via a terminal;

[1792] means for transmitting a question from the terminal to a server;

[1793] means for receiving the query and analyzing it using natural language processing;

[1794] A means for searching for related behavioral big data based on the analysis results;

[1795] A generation AI means for performing data analysis based on the search results and generating a proposal;

[1796] means for transmitting the generated proposal to a user's terminal;

[1797] means for displaying said proposal on a user's terminal;

[1798] A system including:

[1799] (Claim 2)

[1800] 2. The system according to claim 1, wherein the natural language processing means performs text analysis and keyword extraction.

[1801] (Claim 3)

[1802] The system of claim 1, wherein the generating AI means performs data analysis using a machine learning model.

[1803] "Example 1"

[1804] (Claim 1)

[1805] A means for a user to input a question via an information processing device;

[1806] means for transmitting a question from the information processing device to the information processing device;

[1807] means for receiving the query and analyzing it using natural language processing;

[1808] a means for searching a large amount of related data based on the analysis results;

[1809] A generation AI means for performing data analysis based on the search results and generating a proposal;

[1810] means for transmitting the generated proposal to a user's information processing device;

[1811] means for displaying the proposal on a user's information processing device;

[1812] A system including:

[1813] (Claim 2)

[1814] 2. The system according to claim 1, wherein the natural language processing means performs text analysis and keyword extraction.

[1815] (Claim 3)

[1816] The system of claim 1, wherein the generating AI means performs data analysis using a machine learning model.

[1817] "Application Example 1"

[1818] (Claim 1)

[1819] a means for a user to input a question via a terminal;

[1820] means for transmitting a question from the terminal to a server;

[1821] means for receiving the query and analyzing it using natural language processing;

[1822] A means for searching for related behavioral big data based on the analysis results;

[1823] A generation AI means for performing data analysis based on the search results and generating a proposal;

[1824] means for transmitting the generated proposal to a user's terminal;

[1825] means for displaying said proposal on a user's terminal;

[1826] A method for searching market trend data and customer review data based on questions about product selection, and proposing optimal products through data analysis using behavioral big data including these.

[1827] A system including:

[1828] (Claim 2)

[1829] 2. The system according to claim 1, wherein the natural language processing means performs text analysis and keyword extraction.

[1830] (Claim 3)

[1831] The system of claim 1, wherein the generating AI means performs data analysis using a machine learning model.

[1832] "Example 2: Combining Emotion Engines"

[1833] (Claim 1)

[1834] a means for a user to input a question via a terminal;

[1835] means for transmitting a question from the terminal to a server;

[1836] means for receiving the query and analyzing it using natural language processing;

[1837] means for searching for related data based on the analysis result and emotion information obtained by an emotion analysis engine;

[1838] A generation AI means for performing data analysis based on the search results and emotion information to generate a proposal;

[1839] means for transmitting the generated proposal to a user's terminal;

[1840] means for displaying said proposal on a user's terminal;

[1841] A system including:

[1842] (Claim 2)

[1843] 2. The system according to claim 1, wherein the natural language processing means performs text analysis and keyword extraction.

[1844] (Claim 3)

[1845] The system of claim 1, wherein the generating AI means performs data analysis using a machine learning model.

[1846] (Claim 4)

[1847] 2. The system of claim 1, wherein the sentiment analysis engine detects an emotional state and incorporates the results into generating suggestions.

[1848] "Application example 2 when combining emotion engines"

[1849] (Claim 1)

[1850] means for a user to input a question via an input device;

[1851] means for transmitting a query from said input device to a data processing device;

[1852] means for receiving the query and analyzing it using natural language processing;

[1853] a means for searching for related behavioral data based on the analysis results;

[1854] A generation AI means for performing data analysis based on the search results and generating a proposal;

[1855] means for transmitting the suggestions to a user input device;

[1856] means for displaying said suggestions on a user's input device;

[1857] means for analyzing the question using an emotion engine and extracting emotion information;

[1858] means for optimizing the generated suggestions by integrating the emotion information;

[1859] A system including:

[1860] (Claim 2)

[1861] 2. The system of claim 1, wherein the natural language processing means performs text analysis and keyword extraction and uses an emotion engine.

[1862] (Claim 3)

[1863] The system according to claim 1, characterized in that the generating AI means performs data analysis using a machine learning model and integrates emotional information to optimize the proposal content. [Explanation of symbols]

[1864] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for a user to input a question via a terminal; means for transmitting a question from the terminal to a server; means for receiving the query and analyzing it using natural language processing; A means for searching for related behavioral big data based on the analysis results; A generation AI means for performing data analysis based on the search results and generating a proposal; means for transmitting the generated proposal to a user's terminal; means for displaying said proposal on a user's terminal; A system including:

2. 2. The system according to claim 1, wherein the natural language processing means performs text analysis and keyword extraction.

3. The system of claim 1, wherein the generating AI means performs data analysis using a machine learning model.

Images