System

Abstract

A system is provided.SOLUTION: The system includes a terminal for a user to input a question, a server for receiving the question transmitted from the terminal, an analysis module for analyzing the received question and extracting a keyword, a database for searching for an optimal generative artificial intelligence based on the extracted keyword, a result integration module for presenting the optimal generative artificial intelligence to the user from a search result, means for transmitting the question to the generative artificial intelligence selected by the user and receiving an answer, and means for transmitting the received answer to the user terminal.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] Conventional internet information search methods require users to find the appropriate information sources and tools themselves, which is time-consuming and labor-intensive. Furthermore, despite rapid developments in generative artificial intelligence, it is not easy for users to find the generative AI bot that best suits their question. Furthermore, while it is expected that generative AI bots in the future will be able to integrate multiple information sources and provide optimal advice, the lack of a portal site to serve as a search entry point for this hinders convenience. Thus, there is a need to provide a means for users to efficiently and accurately gather information and use the appropriate generative AI bot. [Means for solving the problem]

[0005] The present invention provides a system including a terminal for users to input questions, a server for receiving questions sent from the terminal, an analysis module for analyzing the received questions and extracting keywords, a database for searching for the optimal generative AI based on the extracted keywords, a result integration module for presenting the optimal generative AI to the user from the search results, a means for transferring the question to the generative AI selected by the user and receiving the answer, and a means for transmitting the received answer to the user terminal. The present invention enables users to easily find the appropriate generative AI bot and efficiently collect information. Furthermore, by integrating the answers from each generative AI and presenting it as a single unified answer, user convenience can be further improved.

[0006] "User" means any person or entity that utilizes the System to enter questions and obtain information.

[0007] "Terminal" refers to the device used by the user to enter a question, including a PC, smartphone, tablet, etc.

[0008] "Server" means a computer system that processes questions received from users, analyzes them, searches for generative artificial intelligence, synthesizes the results, and transmits answers.

[0009] The "analysis module" is a software component that uses natural language processing technology to analyze questions received from users and extract keywords and the intent of the questions.

[0010] "Keywords" are important words or phrases extracted from a user's question that indicate the intent or content of the question.

[0011] "Generative artificial intelligence" refers to an artificial intelligence system that provides generative answers to user questions in a specific information field or area of ​​expertise.

[0012] A "database" is a data management system that stores information about generative artificial intelligence and allows it to be searched and referenced.

[0013] The "result integration module" is a software component for presenting to the user generative artificial intelligence searched from the database based on the keywords extracted by the analysis module.

[0014] The term "means" refers to a method, module, device or series of processes for realizing a specific function or operation in the present invention.

[0015] An "answer" is the response information provided by generative artificial intelligence in response to a question from a user. [Brief explanation of the drawings]

[0016] [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 illustrating 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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention is a system for users to efficiently and accurately gather information, utilizing generative artificial intelligence as an optimal alternative to traditional internet search methods. This system is realized in a configuration including a user, a terminal, and a server. Specific embodiments of the system and their operation are described below.

[0038] System Overview

[0039] This system analyzes user questions and provides the optimal generative AI for those questions. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a database that searches for the optimal generative AI, and a result integration module that integrates and presents the results.

[0040] How it works

[0041] Enter and submit your question

[0042] The user uses the device to input a question. For example, they enter a question such as "Please tell me about your symptoms of COVID-19" into the portal site's input form and click the submit button. The input question is sent from the device to the server.

[0043] Receiving and parsing questions

[0044] The server receives the question sent by the user. The received question is analyzed by the analysis module, and important keywords are extracted. For example, keywords such as "COVID-19" and "symptoms" are extracted.

[0045] Searching for the best generative AI bot

[0046] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. The database contains the areas of expertise and question types that each generative AI bot can answer. From the search results, a list of suitable candidate generative AI bots is generated.

[0047] Present and select a bot

[0048] The server displays a list of generative AI bots that are optimal for the user. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user then selects the optimal generative AI bot from the presented options.

[0049] Resend your question and get an answer

[0050] The server resends the question to the generative AI bot selected by the user, which generates an answer based on the question from the server and sends the answer back to the server.

[0051] Displaying the results

[0052] The server formats the answer received from the generative AI bot and sends it to the user's device. The final answer is displayed on the user's device. For example, it may show information such as "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[0053] Specific examples

[0054] Example 1: Asking about COVID-19 symptoms

[0055] 1. The user types in the question, "Tell me about your COVID-19 symptoms" and submits it.

[0056] 2. The server receives the question and extracts the keywords "coronavirus" and "symptoms."

[0057] 3. The server searches for the most suitable generative artificial intelligence bot and lists "Medical Bot A" and "Medical Bot B."

[0058] 4. The user selects "Medical Bot A."

[0059] 5. The server sends a question to the selected bot and retrieves the answer.

[0060] 6. The server formats the answer and sends it to the user's device.

[0061] 7. The user's device will display the message, "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[0062] In this way, this system allows users to efficiently collect information and easily find the optimal AI bot. Furthermore, by integrating and presenting information from multiple AI bots, it is possible to further improve user convenience.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] A user accesses the portal site and enters a question into the question input form.

[0066] Specific behavior: A user accesses the portal site using a browser, enters "Tell me about your COVID-19 symptoms" in the text box, and clicks the submit button.

[0067] Step 2:

[0068] The terminal sends a question to the server.

[0069] What happens: The browser sends the user's input to the server as an HTTP request.

[0070] Step 3:

[0071] The server receives the user's query.

[0072] Specific operation: An HTTP request arrives at the server, and the server retrieves the content.

[0073] Step 4:

[0074] A question analysis module on the server analyzes the question.

[0075] What it does: It uses a natural language processing (NLP) engine to extract keywords such as "coronavirus" and "symptoms."

[0076] Step 5:

[0077] The server searches the generative artificial intelligence database.

[0078] Specific operation: Execute SQL queries to find relevant generative AI bots from the database. For example, medical-related bots "Medical Bot A" and "Medical Bot B" are found.

[0079] Step 6:

[0080] The server lists the most suitable generative artificial intelligence bots from the search results.

[0081] Specific behavior: Formats the found generative AI bots into a list and prepares the data to present to the user.

[0082] Step 7:

[0083] The server presents the user with a list of generative artificial intelligence bots.

[0084] Specific operation: The generated list is sent to the user's terminal in HTML or JSON format and displayed in the browser.

[0085] Step 8:

[0086] The user selects the best bot from the generative artificial intelligence bots presented.

[0087] Specific operation: The user clicks the button of the desired generative artificial intelligence bot from the displayed list.

[0088] Step 9:

[0089] The terminal transmits the selection information of the generative artificial intelligence bot selected to the server.

[0090] Specific operation: Send an HTTP request again to convey the selected information to the server.

[0091] Step 10:

[0092] The server resends the question to the selected generative artificial intelligence bot.

[0093] Specific operation: Again using an API call, the question is forwarded to the selected generative AI bot.

[0094] Step 11:

[0095] The server receives the answer from the generative artificial intelligence bot.

[0096] Specific operation: Receives answer data from the generative AI bot as an API response.

[0097] Step 12:

[0098] Formats the response received by the server.

[0099] Specific operation: Converts the received response data into HTML or JSON format for presentation to the user.

[0100] Step 13:

[0101] The server sends the formatted response to the user terminal.

[0102] Specific operation: The generated data is sent to the user's terminal as an HTTP response.

[0103] Step 14:

[0104] The user's device will display the final answer on the screen.

[0105] What it does: The browser processes the data and displays information to the user, such as "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[0106] Example 1

[0107] 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."

[0108] Conventional Internet search methods can make it difficult for users to gather information efficiently and accurately. In particular, they face problems such as not being able to obtain appropriate information for complex questions and difficulty in finding reliable sources. Furthermore, users must integrate information obtained from multiple sources themselves, which is time-consuming.

[0109] 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.

[0110] In this invention, the server includes an input device for a user to input a question, an information processing device for receiving the question sent from the input device, analysis means for analyzing the received question and extracting keywords, a storage device for searching for the optimal generative AI based on the extracted keywords, information integration means for presenting the optimal generative AI to the user from the search results, communication means for transferring the question to the generative AI selected by the user and receiving an answer, and display means for sending the received answer to the user terminal. This allows the user to efficiently and accurately collect information even for complex questions, and by integrating and providing information from multiple information sources, a reliable, unified answer can be obtained.

[0111] A "user" is an entity that uses the system to collect information.

[0112] An "input device" is a device that allows a user to input a question, such as a keyboard or a touchscreen device.

[0113] A "question" is a request for information that a user enters into the system.

[0114] The "information processing device" is a device that receives and analyzes a question sent from an input device. Specifically, this corresponds to a server.

[0115] The "analysis means" is a module for extracting important keywords from received questions. Natural language processing technology is often used.

[0116] "Keywords" are important words extracted from questions by analytical means and are used to identify the content of the question.

[0117] The "storage device" is a device that includes a database for searching for the optimal generative artificial intelligence based on the extracted keywords.

[0118] "Generative AI" is an AI model that generates appropriate answers to user questions. For example, a natural language generation model falls into this category.

[0119] The "information integration means" is a module that presents the user with the most appropriate generative artificial intelligence from the search results.

[0120] "Communication means" refers to the method by which a user transmits a question to a generative AI selected by the user and receives a response. This includes network communication.

[0121] The "display means" is a device for displaying the received response on the user terminal, such as a display or monitor.

[0122] An "information gathering device" refers to the entire system that allows users to input questions and receive answers from generative artificial intelligence based on those questions.

[0123] The system of the present invention is an information collection device that allows users to collect information efficiently and accurately. This device allows users to input a question and obtain an answer from a generative artificial intelligence that is best suited to that question. Specifically, it includes the following components:

[0124] 1. Input Devices:

[0125] This is the device that a user uses to enter a question. For example, this could be a PC, tablet, or smartphone. This allows a user to enter a question such as "Tell me about your COVID-19 symptoms."

[0126] 2. Information processing equipment:

[0127] This is a server for receiving and analyzing questions sent from an input device. The server receives user input as an HTTP request and analyzes the content of the question using an analysis means.

[0128] 3. Analysis method:

[0129] This module analyzes questions and extracts important keywords. Specifically, it uses morphological analysis tools and natural language processing technologies (such as Mecab and SpaCy) to extract keywords such as "COVID-19" and "symptoms" from questions.

[0130] 4. Storage:

[0131] This device has a database for searching for the optimal generative AI based on extracted keywords. This database contains the fields of expertise of each generative AI model and the question formats it can handle.

[0132] 5. Information integration methods:

[0133] This module presents users with the most suitable generative artificial intelligence based on search results, displaying options such as "Medical Bot A" and "Medical Bot B" to the user.

[0134] 6. Means of communication:

[0135] This is a communications infrastructure for forwarding questions to a user-selected generative AI model and receiving answers. It uses network communications to send questions to the API endpoint of the selected generative AI model.

[0136] 7. Display means:

[0137] This is a device that displays the received response on the user's device. For example, it displays "Symptoms of COVID-19 include fever, cough, and difficulty breathing" on the user's device display.

[0138] Specific examples

[0139] Example questions:

[0140] The user types and submits the question, "Tell me about your COVID-19 symptoms." This question is processed in the system as follows:

[0141] 1. The user enters a question into the input device and clicks the submit button.

[0142] 2. The device sends the entered question to the server as an HTTP request.

[0143] 3. The server receives the question and uses analytical tools to extract keywords such as "coronavirus" and "symptoms."

[0144] 4. Based on the extracted keywords, the server searches the database in the storage device and lists the most suitable generative AI models (e.g., "Medical Bot A" and "Medical Bot B").

[0145] 5. The server uses information integration methods to display candidate bots to the user.

[0146] 6. The user selects the best bot (e.g., "Medical Bot A").

[0147] 7. The server forwards the question to the selected generative AI model and receives the answer from the generative AI model.

[0148] 8. The server formats the received response and sends it to the user's device.

[0149] 9. The user device displays the final answer on the display.

[0150] In this way, the information collection device of the present invention allows users to obtain information efficiently and accurately, and is capable of integrating information from multiple sources to provide users with the most reliable and unified answers.

[0151] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0152] Step 1:

[0153] The user enters a question into the input device. For example, they enter "Please tell me about the symptoms of COVID-19" and click the send button. The entered question is sent from the device to the server as an HTTP request. The input is in text format, and the output is in HTTP request format.

[0154] Step 2:

[0155] The server receives an HTTP request sent from the terminal. The server parses the request and extracts the question. During this process, the question is saved as text data on the server. The input is in HTTP request format, and the output is the question in text format.

[0156] Step 3:

[0157] The server's analysis means analyzes the received question text and extracts important keywords. Natural language processing technology (for example, Mecab or SpaCy) is used to analyze the question content and obtain keywords such as "COVID-19" and "symptoms." The data processing performed in this step is text analysis, where the input is the text data of the question and the output is a list of keywords.

[0158] Step 4:

[0159] The server searches a database in the storage device based on the extracted keywords. The database stores the areas of expertise and question formats that each generative AI model can handle. For example, an SQL query can be used to search for generative AI models related to "COVID-19" and "symptoms." The input is a list of keywords, and the output is a list of candidate generative AI models.

[0160] Step 5:

[0161] The server's information integration means presents the optimal generative AI model to the user from the search results. To do this, it generates a list of candidate generative AI models (e.g., "Medical Bot A" and "Medical Bot B") in HTML format and sends it to the user's device as a response for display. The input is a list of generative AI models, and the output is an HTML response.

[0162] Step 6:

[0163] The user selects the best model from the list of generative AI models presented. The user clicks the selection button and sends the selection to the server. The input is the model selected from the list of generative AI models, and the output is the selection information sent to the server again in the form of an HTTP request.

[0164] Step 7:

[0165] The server resubmits the question to the generative AI model selected by the user. It uses network communication to send the question to the endpoint of the selected AI model and receive the answer from the model. The input is the user's question and the endpoint information of the selected generative AI model, and the output is the generated answer.

[0166] Step 8:

[0167] The server formats the answer it receives, formatting the answer in a user-friendly format, generating a final HTML response and sending it to the user's device. The input is the answer from the generative AI model, and the output is an HTML response containing the formatted answer.

[0168] Step 9:

[0169] The user device displays the received HTML response. The final answer is displayed on the screen, allowing the user to confirm the answer to the question. For example, "Symptoms of COVID-19 include fever, cough, and difficulty breathing." The input is the HTML response, and the output is the displayed answer.

[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] Currently, product picking work at logistics centers requires a lot of time and effort from employees, and there is a need for a support system to make the work more efficient. Furthermore, there is a lack of optimization of picking routes and accurate product location information, which leads to a high likelihood of inefficiency and errors. A system that solves these issues and streamlines picking work at logistics centers is needed.

[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 a terminal for a user to input a question, a means for receiving the question sent from the terminal, an analysis module for analyzing the received question and extracting keywords, a database for searching for the optimal generative artificial intelligence based on the extracted keywords, a result integration module for presenting the optimal generative artificial intelligence to the user from the search results, a means for transferring the question to the generative artificial intelligence selected by the user and receiving an answer, a means for transmitting the received answer to the user terminal, and a means for calculating product location information and an optimal route and assisting in pickup work. This allows the user to efficiently obtain product location information and an optimal picking route, enabling efficient picking work at the logistics center.

[0175] A "user" is a person who uses the system to input questions and obtain information.

[0176] A "question" is a statement that a user enters about the information they want to know, and is sent to the server for analysis.

[0177] "Terminal" refers to the device used by the user to enter a question, including a smartphone, computer, tablet, etc.

[0178] A "server" is a computer system that receives queries sent from terminals and performs processes such as analysis, database search, and result integration.

[0179] The "analysis module" is software installed on the server, which has the function of analyzing received questions and extracting important keywords.

[0180] "Keywords" are important words and predicates extracted from questions by the analysis module and used in generative artificial intelligence searches.

[0181] "Generative AI" is AI that generates appropriate answers to user questions, and includes bots specialized in various fields.

[0182] A "database" is a data storage device that stores information about generative artificial intelligence and its specialized fields, and is used for searching.

[0183] The "results integration module" is software that has the function of selecting the most appropriate generative artificial intelligence from database search results and presenting it to the user.

[0184] "Means" refers to devices, modules, programs, etc. for executing specific functions or processes.

[0185] "Product location information" is data indicating the specific storage location of the product within the logistics center.

[0186] The "optimal route" indicates the best route for efficiently picking up multiple items.

[0187] "Pickup work support" is an auxiliary function that allows employees to work efficiently based on the location information of the specified product and the optimal route.

[0188] The present invention relates to a system for allowing a user to input a question and obtain the best answer to that question. The system includes a terminal for the user to input the question, a server that receives the question sent from the terminal, an analysis module that analyzes the received question and extracts keywords, a database that searches for the best generative artificial intelligence based on the extracted keywords, a result integration module that presents the best generative artificial intelligence to the user from the search results, and means for transferring the question to the generative artificial intelligence selected by the user and receiving the answer.

[0189] System Embodiments

[0190] Hardware and software used

[0191] Hardware:

[0192] Devices: Smartphones (e.g. iPhone, Android devices), PCs, tablets

[0193] server

[0194] software:

[0195] Generative AI models (e.g., GPT-4)

[0196] Database (e.g. MySQL)

[0197] Mobile app development frameworks (e.g., React Native)

[0198] Data processing and calculation

[0199] 1. Entering and receiving questions:

[0200] Users input questions using devices such as smartphones or computers, which are then sent to the server.

[0201] The server receives the question sent from the terminal and sends it to the analysis module.

[0202] 2. Question Analysis:

[0203] The analysis module analyzes the received questions using natural language processing (NLP) technology and extracts important keywords.

[0204] 3. Generative AI Search:

[0205] The server searches the database for generative AI based on the extracted keywords, taking into account the AI's field of expertise and the types of questions it can answer.

[0206] From the search results, a candidate list of optimal generative artificial intelligence bots is generated and sent to the result integration module.

[0207] 4. Generative AI Presentation and Selection:

[0208] The result synthesis module presents the user with a list of the best generative artificial intelligence bots.

[0209] The user selects the best generative AI bot from the presented options.

[0210] 5. Resend the question and generate an answer:

[0211] The server resends the question to the generative artificial intelligence bot selected by the user.

[0212] The generative artificial intelligence bot generates an answer based on a question from the server and sends the answer back to the server.

[0213] 6. Formatting and displaying answers:

[0214] The server formats the generated response and transmits it to the user terminal.

[0215] The final answer will be displayed on the user's device.

[0216] Specific examples

[0217] For example, in a distribution center, an employee uses a smartphone to input a question such as, "What is the location and best route to pick up items A, B, and C?" This question is processed as follows:

[0218] 1. The server receives the question, and the analysis module extracts the keywords "Product A," "Product B," "Product C," "Location information," and "Optimal route."

[0219] 2. Based on the extracted keywords, the server searches the database for related generative artificial intelligence bots and lists "Pickup Bot A" and "Root Bot B."

[0220] 3. The user selects "Pickup Bot A."

[0221] 4. The server resends the question to the selected bot, which calculates the location information and optimal route for each item and returns an answer.

[0222] 5. The server formats the answer and displays it on the smartphone. The user receives real-time location information (item A: Section B3, item B: Section A2, item C: Section C1) and the optimal route (section A2 → section B3 → section C1).

[0223] Prompt Sentence Examples

[0224] "Picking list: Product A, Product B, Product C. Please tell me the location of each product and the best pickup route."

[0225] This system will improve the efficiency and accuracy of picking operations at logistics centers, reducing the workload.

[0226] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0227] Step 1:

[0228] The user inputs a question using a device. Specifically, they input a question such as "Please tell me the location information and the best route to pick up items A, B, and C" into a smartphone or PC application and click the send button. This input is sent to the server as text data.

[0229] Step 2:

[0230] The server receives the question sent by the user. As a preprocessing step before passing this question data to the analysis module, it checks that the text data has been received and converts it into the required format (e.g., JSON format).

[0231] Step 3:

[0232] The analysis module analyzes the received question and extracts important keywords. Here, natural language processing (NLP) techniques are used to extract keywords such as "product A," "product B," "product C," "location information," and "optimal route." The input for this step is the user's question text data, and the output is a list of extracted keywords.

[0233] Step 4:

[0234] The server searches a database based on the extracted keywords. The database contains the areas of expertise of each generative AI bot and the types of questions it can answer. The search results provide a list of related generative AI bots, such as "Pickup Bot A" and "Root Bot B." The output of this step is a list of generative AI bots.

[0235] Step 5:

[0236] The server presents the user with the optimal generative AI bot from the search results. This presentation is done by displaying a list of candidate bots on the application screen of a smartphone or computer. The user selects "Pickup Bot A." The input for this step is a list of bots, and the output is the bot selected by the user.

[0237] Step 6:

[0238] The server resends the question to the generative AI bot selected by the user. Here, data including the user's question is sent to the selected bot as a request message. The input of this step is the user's question text and information about the selected bot, and the output is the answer data from the generative AI bot.

[0239] Step 7:

[0240] A generative AI bot generates an answer based on a question from the server and sends the answer back to the server. For example, Pickup Bot A sends back location information such as "Product A: Section B3, Product B: Section A2, Product C: Section C1" and data such as "Optimal route: Section A2 → Section B3 → Section C1" to the server. The input to this step is the question data from the server, and the output is the generated answer data.

[0241] Step 8:

[0242] The server formats the answer received from the generative AI bot and sends it to the user's terminal. Here, the answer data is converted into a format that is easy for the user to understand and presented through the application. The input of this step is the answer data from the generative AI bot, and the output is the formatted answer data.

[0243] Step 9:

[0244] The user device receives the formatted answer sent from the server and displays it on the screen. For example, location information such as "Product A: Section B3, Product B: Section A2, Product C: Section C1" and specific information such as "Optimal route: Section A2 → Section B3 → Section C1" are displayed. The input of this step is the formatted answer data, and the output is the screen information displayed to the user.

[0245] 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.

[0246] The present invention adds an emotion recognition function to a system that allows users to efficiently and accurately collect information, and provides responses according to the user's emotional state. This system is realized by a configuration including a user, a terminal, a server, and an emotion recognition engine. Specific embodiments of the system and their operation are described below.

[0247] System Overview

[0248] This system analyzes user questions, provides the optimal generative AI for the question, and recognizes the user's emotions to adjust the response. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a database that searches for the optimal generative AI, a result integration module that integrates and presents the results, and an emotion engine that recognizes emotions.

[0249] How it works

[0250] Enter and submit your question

[0251] The user uses the device to input a question. For example, they enter a question such as "Please tell me about your symptoms of COVID-19" into the portal site's input form and click the submit button. The input question is sent from the device to the server.

[0252] Receiving and parsing questions

[0253] The server receives the question sent by the user. The received question is analyzed by the analysis module, and important keywords are extracted. For example, keywords such as "COVID-19" and "symptoms" are extracted.

[0254] Searching for the best generative AI bot

[0255] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. The database contains the areas of expertise and question types that each generative AI bot can answer. From the search results, a list of suitable candidate generative AI bots is generated.

[0256] Emotion recognition

[0257] The server uses an emotion engine to recognize the user's emotions, for example, determining whether the user is feeling stressed from the input text.

[0258] Present and select a bot

[0259] The server displays a list of generative AI bots that are optimal for the user. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user then selects the optimal generative AI bot from the presented options.

[0260] Resend your question and get an answer

[0261] The server resends the question to the generative AI bot selected by the user, which generates an answer based on the question from the server and sends the answer back to the server.

[0262] Adjusting responses based on emotions

[0263] The server adjusts the content and expression of the generated response based on the recognition results of the emotion engine, for example, adding more kind language and detailed explanations if the user is feeling stressed.

[0264] Displaying the results

[0265] The server formats the answer received from the generative AI bot and sends it to the user's device. The final answer is displayed on the user's device. For example, it may show information such as "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[0266] Specific examples

[0267] Example 1: Asking about COVID-19 symptoms

[0268] 1. The user types in the question, "Tell me about your COVID-19 symptoms" and submits it.

[0269] 2. The server receives the question and extracts the keywords "coronavirus" and "symptoms."

[0270] 3. The server searches for the most suitable generative artificial intelligence bot and lists "Medical Bot A" and "Medical Bot B."

[0271] 4. The server uses an emotion engine to analyze the user's emotions, for example, to detect whether the user is feeling anxious or stressed. If the user is feeling anxious, the server is configured to add kind words and detailed explanations.

[0272] 5. The user selects "Medical Bot A."

[0273] 6. The server sends a question to the selected bot and retrieves the answer.

[0274] 7. The server adjusts and formats the obtained answer based on the emotion recognition results.

[0275] 8. The user's device will display the message, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, please consult a medical professional immediately."

[0276] In this way, the system allows users to efficiently collect information and receive responses tailored to their emotional state, improving the user experience and providing more appropriate assistance.

[0277] The processing flow will be explained below.

[0278] Step 1:

[0279] A user accesses the portal site and enters a question into the question input form.

[0280] Specific actions: The user opens the portal site in a browser, enters "Please tell me about your coronavirus symptoms" in the text box, and clicks the submit button.

[0281] Step 2:

[0282] The terminal sends a question to the server.

[0283] Specific operation: The question is sent from the terminal to the server as an HTTP request.

[0284] Step 3:

[0285] The server receives the user's query.

[0286] Specific operation: The server receives an HTTP request and passes the contents to the analysis module.

[0287] Step 4:

[0288] A question analysis module on the server analyzes the question.

[0289] What it does: It uses a natural language processing (NLP) engine to extract keywords such as "coronavirus" and "symptoms."

[0290] Step 5:

[0291] The server uses an emotion engine to recognize the user's emotions.

[0292] Specific operation: The emotion engine analyzes the user's emotional state (e.g., anxiety, stress) from the input text.

[0293] Step 6:

[0294] The server searches the generative artificial intelligence database.

[0295] Specific operation: Executes an SQL query based on the extracted keywords to search for medical-related generative artificial intelligence bots.

[0296] Step 7:

[0297] The server lists the most suitable generative artificial intelligence bots from the search results.

[0298] Specific operation: The found generative artificial intelligence bots (e.g., "Medical Bot A" and "Medical Bot B") are formatted into a list and the data is prepared for presentation to the user.

[0299] Step 8:

[0300] The server presents the user with a list of generative artificial intelligence bots.

[0301] Specific operation: Sends the result in HTML or JSON format to the user's device and displays suggestions in the browser.

[0302] Step 9:

[0303] The user selects the best bot from the generative artificial intelligence bots presented.

[0304] Specific operation: The user clicks the button of the desired generative artificial intelligence bot from the list.

[0305] Step 10:

[0306] The terminal transmits the selection information of the generative artificial intelligence bot selected to the server.

[0307] Specific operation: Send an HTTP request again to convey the selected information to the server.

[0308] Step 11:

[0309] The server resends the question to the selected generative artificial intelligence bot.

[0310] What it does: Uses an API call to forward the user's question to a generative AI bot.

[0311] Step 12:

[0312] The server receives the answer from the generative artificial intelligence bot.

[0313] Specific operation: Receives answer data from the generative AI bot as an API response.

[0314] Step 13:

[0315] The server adjusts the content and expression of the response based on the recognized emotion.

[0316] Specific actions: For example, if a user is feeling anxious, add kind words or detailed explanations to the answer.

[0317] Step 14:

[0318] The server formats the adjusted response.

[0319] Specific operation: The adjusted response data is converted into HTML or JSON format and sent to the user's device.

[0320] Step 15:

[0321] The user's device will display the final answer on the screen.

[0322] What it does: It displays the data sent via JavaScript in the browser, informing the user that "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, please seek medical help immediately."

[0323] Example 2

[0324] 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."

[0325] Conventional information gathering systems have difficulty in quickly providing optimal answers to user questions. Furthermore, they are unable to respond according to the user's emotional state, making it difficult to provide sufficient support, especially to users who are feeling stressed or anxious.

[0326] 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.

[0327] In this invention, the server includes a terminal for a user to input a question, a computer for receiving the question sent from the terminal, an analysis module for analyzing the received question and extracting keywords, a storage device for searching for the optimal generative AI based on the extracted keywords, a result integration module for presenting the optimal generative AI to the user from the search results, means for transferring the question to the generative AI selected by the user and receiving an answer, communication means for transmitting the received answer to the user terminal, and an emotion recognition engine for recognizing the user's emotion and adjusting the answer content based on that emotion. This makes it possible to quickly provide the optimal answer to the user's question and also to respond appropriately according to the user's emotional state.

[0328] A "terminal" is a device through which a user inputs a question and sends it to a server.

[0329] The "computer" is a device that receives questions sent by users, analyzes them, and forwards them to the generative artificial intelligence.

[0330] An "analysis module" is software or hardware for analyzing received questions and extracting important keywords.

[0331] A "storage device" is a storage medium such as a database for searching for the optimal generative artificial intelligence based on extracted keywords.

[0332] A "result integration module" is software or hardware for presenting the user with the most appropriate generative artificial intelligence from search results.

[0333] "Communication means" refers to the network interface and communication protocol used to transmit the received response to the user terminal.

[0334] An "emotion recognition engine" is software or hardware that recognizes a user's emotions and adjusts the content of responses based on those emotions.

[0335] "Generative artificial intelligence" refers to algorithms and models that generate answers to user questions.

[0336] "Keywords" are important words or phrases extracted from a user's question that represent the content of that question.

[0337] The present invention adds an emotion recognition function to a system that allows users to collect information efficiently and accurately, and provides responses according to the user's emotional state. This system is realized by a configuration including a user, a terminal, a server, and an emotion recognition engine.

[0338] System Overview

[0339] This system analyzes user questions, provides the optimal generative AI for the question, and recognizes the user's emotions and adjusts the response accordingly. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a storage device that searches for the optimal generative AI, a result integration module that integrates and presents the results, and an emotion engine that recognizes emotions.

[0340] Detailed explanation of operation

[0341] Enter and submit your question

[0342] The user uses the device to enter a question. The user enters "Please tell me about your COVID-19 symptoms" into the portal site's input form and clicks the submit button. The entered question is sent from the device to the server. Specifically, it is sent as an HTTP request.

[0343] Receiving and parsing questions

[0344] The server receives the question sent by the user. The server analyzes the received HTTP request and extracts the question content. The analysis module analyzes the question using natural language processing technology and extracts important keywords. For example, keywords such as "coronavirus" and "symptoms" are extracted. Natural language processing libraries such as NLTK and spaCy are used here.

[0345] Searching for the best generative AI bot

[0346] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. Specifically, it executes an SQL query to list appropriate generative AI bots. The storage device stores the specialty of each generative AI bot (e.g., medicine, education, entertainment, etc.) and the question formats it can answer. For example, "Medical Bot A" and "Medical Bot B" are listed as candidates.

[0347] Emotion recognition

[0348] The server uses an emotion engine to recognize the user's emotions. Specifically, it calls emotion recognition APIs, such as Google Cloud Natural Language API or IBM Watson's emotion analysis service, to extract emotions from the input text. This identifies whether the user is feeling stressed or anxious.

[0349] Present and select a bot

[0350] The server displays a list of generative AI bots that are optimal for the user. Specifically, the list is displayed to the user using HTML and CSS. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user selects the appropriate generative AI bot from the presented options and clicks the select button.

[0351] Resend your question and get an answer

[0352] The server resends the question to the generative AI bot selected by the user. Specifically, it resends the question by sending an API request. The generative AI bot generates an answer based on the question and sends the answer back to the server as an API response. For example, using OpenAI's generative AI model, the answer "Symptoms of COVID-19 include fever, cough, and difficulty breathing" can be obtained.

[0353] Adjusting responses based on emotions

[0354] The server adjusts the content and expressions of the generated answers based on the recognition results of the emotion engine. Specifically, for users who are feeling stressed, it adds kind language and detailed explanations. For example, it adds phrases such as, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[0355] Displaying the results

[0356] The server formats the answer received from the generative AI bot and sends it to the user's device. Specifically, the answer is formatted in HTML and sent as an HTTP response. The final answer is displayed on the user's device. For example, the following information may be displayed: "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[0357] Specific examples

[0358] Example 1: Asking about COVID-19 symptoms

[0359] 1. The user types in the question, "Tell me about your COVID-19 symptoms" and submits it.

[0360] 2. The server receives the question and extracts the keywords "coronavirus" and "symptoms."

[0361] 3. The server searches for the most suitable generative artificial intelligence bot and lists "Medical Bot A" and "Medical Bot B."

[0362] 4. The server uses an emotion engine to analyze the user's emotions, for example, to detect whether the user is feeling anxious or stressed. If the user is feeling anxious, the server is configured to add kind words and detailed explanations.

[0363] 5. The user selects "Medical Bot A."

[0364] 6. The server sends a question to the selected bot and retrieves the answer.

[0365] 7. The server adjusts and formats the obtained answer based on the emotion recognition results.

[0366] 8. The user's device will display the message, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical professional immediately."

[0367] In this way, the system allows users to efficiently collect information and receive responses tailored to their emotional state, improving the user experience and providing more appropriate assistance.

[0368] Prompt Sentence Examples

[0369] "Please tell me what the symptoms of COVID-19 are. I'm very worried."

[0370] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0371] markdown

[0372] Step 1:

[0373] The user uses the device to enter a question. The user enters "Please tell me about your COVID-19 symptoms" into the portal site's input form and clicks the submit button. The entered question is sent from the device to the server. Specifically, it is sent as an HTTP request.

[0374] Input: User-provided question text

[0375] Output: HTTP request to the server

[0376] Step 2:

[0377] The server receives the question sent by the user. The server analyzes the received HTTP request and extracts the question content. The analysis module analyzes the question using natural language processing technology and extracts important keywords. For example, keywords such as "coronavirus" and "symptoms" are extracted. Natural language processing libraries such as NLTK and spaCy are used here.

[0378] Input: Question text included in HTTP request

[0379] Output: Keywords such as "COVID-19" and "symptoms"

[0380] Step 3:

[0381] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. Specifically, it executes an SQL query to list appropriate generative AI bots. The storage device stores the specialty of each generative AI bot (e.g., medicine, education, entertainment, etc.) and the question formats it can answer. For example, "Medical Bot A" and "Medical Bot B" are listed as candidates.

[0382] Input: Extracted keywords

[0383] Output: A list of optimal generative AI bots (e.g., "Medical Bot A" and "Medical Bot B")

[0384] Step 4:

[0385] The server uses an emotion engine to recognize the user's emotions. Specifically, it calls emotion recognition APIs, such as Google Cloud Natural Language API or IBM Watson's emotion analysis service, to extract emotions from the input text. This identifies whether the user is feeling stressed or anxious.

[0386] Input: Question text

[0387] Output: User's emotional state (e.g., stress, anxiety)

[0388] Step 5:

[0389] The server displays a list of generative AI bots that are optimal for the user. Specifically, the list is displayed to the user using HTML and CSS. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user selects the appropriate generative AI bot from the presented options and clicks the select button.

[0390] Input: A list of the best generative AI bots

[0391] Output: User selects bot

[0392] Step 6:

[0393] The server resends the question to the generative AI bot selected by the user. Specifically, it resends the question by sending an API request. The generative AI bot generates an answer based on the question and sends the answer back to the server as an API response. For example, using OpenAI's generative AI model, the answer "Symptoms of COVID-19 include fever, cough, and difficulty breathing" can be obtained.

[0394] Input: User-selected generative AI bot, question text

[0395] Output: Answer from a generative AI bot

[0396] Step 7:

[0397] The server adjusts the content and expressions of the generated answers based on the recognition results of the emotion engine. Specifically, for users who are feeling stressed, it adds kind language and detailed explanations. For example, it adds phrases such as, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[0398] Input: Answers from a generative AI bot, user's emotional state

[0399] Output: Adjusted answer

[0400] Step 8:

[0401] The server formats the answer received from the generative AI bot and sends it to the user's device. Specifically, the answer is formatted in HTML and sent as an HTTP response. The final answer is displayed on the user's device. For example, the following information may be displayed: "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[0402] Input: Adjusted answer content

[0403] Output: The final answer displayed on the user's terminal

[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] In conventional information gathering systems, response systems have been proposed that can respond quickly and appropriately to user questions, but they lack the ability to adjust responses according to the user's emotional state, which prevents them from fully improving the user experience. Furthermore, in security services, it is necessary to provide a higher level of safety by grasping the emotional state of people in the monitored area in real time and responding according to that emotion, but the lack of such a system is an issue.

[0407] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0408] In this invention, the server includes a terminal for a user to input a question, means for receiving the question sent from the terminal, an analysis module for analyzing the received question and extracting keywords, a database for searching for an optimal generative artificial intelligence based on the extracted keywords, a result integration module for presenting the optimal generative artificial intelligence to the user from the search results, means for transferring the question to the generative artificial intelligence selected by the user and receiving a response, means for transmitting the received response to the user terminal, an emotion recognition engine for analyzing and recognizing the emotional states of people in the monitored area, means for selecting and presenting the optimal generative artificial intelligence according to the emotions identified by the emotion recognition engine, and means for adjusting the response generated by the optimal generative artificial intelligence based on the emotion recognition data, thereby providing a response according to the user's emotional state and enabling improved security services.

[0409] A "terminal for users to input questions" is an electronic device used by users to input questions in the form of text, voice input, or the like.

[0410] The "server for receiving questions sent from a terminal" is a network-connected computer system for receiving questions sent by a user from a terminal and for subsequent processing.

[0411] The "analysis module for analyzing received questions and extracting keywords" is a software component that analyzes the content of questions entered by users and extracts important keywords and phrases.

[0412] A "database for searching for the optimal generative artificial intelligence based on extracted keywords" is a database that stores information for searching for the optimal generative artificial intelligence based on keywords extracted by the analysis module.

[0413] The "result integration module for presenting the user with the optimal generative artificial intelligence from the search results" is a software component for integrating the results of a database search and presenting the user with the optimal generative artificial intelligence candidates.

[0414] "Means for transferring a question to a generative artificial intelligence selected by a user and receiving a response" refers to means for sending a user's question to a generative artificial intelligence selected by a user and receiving a response thereto.

[0415] "Means for transmitting the received answer to the user terminal" refers to means for transmitting the answer received from the generative artificial intelligence to the user terminal.

[0416] The "emotion recognition engine for analyzing and recognizing the emotional state of people within a monitored area" is a software component that analyzes and identifies emotions from the facial expressions, voices, etc. of people within a monitored area.

[0417] "Means for selecting and presenting the most appropriate generative artificial intelligence in accordance with the emotions identified by the emotion recognition engine" refers to means for selecting the most appropriate generative artificial intelligence based on the emotion data analyzed by the emotion recognition engine and presenting the result to the user.

[0418] "Means for adjusting responses generated by optimal generative artificial intelligence based on emotion recognition data" refers to means for adjusting responses generated by generative artificial intelligence according to the emotional state of the user.

[0419] This invention adds emotion recognition functionality to a system that allows users to collect information efficiently and accurately, and provides responses that correspond to the user's emotional state. This system is realized by comprising a user terminal, a server, an analysis module, a generative AI database, a result integration module, and an emotion recognition engine.

[0420] System Overview

[0421] This system analyzes a user's question, provides the most suitable generative artificial intelligence for that question, and recognizes the user's emotions and adjusts the response accordingly. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a database that searches for the most suitable generative artificial intelligence, a result integration module that integrates and presents the results, and an emotion recognition engine that recognizes emotions.

[0422] How it works

[0423] Enter and submit your question

[0424] The user inputs a question using the device. For example, they input a question such as "Please tell me about the symptoms of COVID-19" into the device and send it. The input question is sent from the device to the server.

[0425] Receiving and parsing questions

[0426] The server receives the question sent by the user. The received question is analyzed by the analysis module, and important keywords are extracted. For example, keywords such as "COVID-19" and "symptoms" are extracted.

[0427] Searching for the best generative artificial intelligence

[0428] The server searches a database of generative AI based on the extracted keywords. The database contains the fields of expertise and question formats that each generative AI can handle. The search results then produce a list of suitable generative AIs.

[0429] Recognizing and Responding to Emotions

[0430] The server uses an emotion recognition engine to recognize the user's emotions, for example, to determine whether the user is stressed from the input text. The emotion recognition engine analyzes the facial expressions and tone of voice of people in the monitored area.

[0431] Program processing

[0432] The server performs its operations using, among other things, the following software and hardware:

[0433] Hardware: smart glasses, smartphones, cameras

[0434] software:

[0435] EmotionRecognition Module: Face and emotion recognition engine using OpenCV

[0436] AIModelExecutor module: Generative AI model selection and execution engine (e.g., GPT-4, BERT)

[0437] The server acquires real-time video from the camera and analyzes the emotional data using the EmotionRecognition module. The emotion recognition engine identifies people's emotional states based on the analysis results. The AIModelExecutor module then uses this emotional data to select the optimal generative AI and generate a response.

[0438] Specific examples

[0439] Example 1: Security Monitoring Assistant

[0440] Security guards and facility managers use smart glasses or smartphones to monitor the facility and check the emotional state of people in real time. At this time, an emotion recognition engine analyzes the emotional state (e.g., anxiety, anger, stress) of the people being monitored and selects and presents an appropriate response from an optimal generative artificial intelligence database.

[0441] Example prompt sentence:

[0442] "We have noticed an individual in our surveillance area who appears to be unsafe. Please advise our security personnel on how to respond."

[0443] In this way, the present invention provides a response that is tailored to the user's emotional state, thereby improving the user experience and providing improved security services.

[0444] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0445] Step 1:

[0446] A user uses a terminal to input a question. For example, they input "Please tell me about the symptoms of COVID-19" and send it. The input is the text data of the user's question, and the output is the input question being sent from the terminal to the server.

[0447] Step 2:

[0448] The server receives the question sent by the user. The input is the question text data sent from the terminal, and the output is the received data passed to the analysis module.

[0449] Step 3:

[0450] The analysis module analyzes the received question and extracts important keywords. The input is the received question text data, and the output is the analysis results, which are important keywords (e.g., "COVID-19" and "symptoms").

[0451] Step 4:

[0452] The server searches the database for the optimal generative AI based on the extracted important keywords. The input is the important keywords, and the output is a list of candidate generative AIs (e.g., "Medical Bot A" and "Medical Bot B").

[0453] Step 5:

[0454] The server uses an emotion recognition engine to analyze and identify the user's emotion. The input is the text data of the user's question and facial expression recognition data, and the output is the user's emotional state (e.g., stress, anxiety).

[0455] Step 6:

[0456] The server presents the user with a list of optimal generative AIs, and the user selects one. The input is a list of generative AI candidates, and the output is the generative AI selected by the user (e.g., "Medical Bot A").

[0457] Step 7:

[0458] The server forwards the question to the generative artificial intelligence selected by the user and receives an answer from the generative artificial intelligence. The input is the user's question and the identification information of the selected generative artificial intelligence, and the output is the answer data from the generative artificial intelligence (e.g., "Symptoms of COVID-19 include fever, cough, and difficulty breathing").

[0459] Step 8:

[0460] The server adjusts the generated answer content based on the results of the emotion recognition engine. The input is the answer data and emotion recognition results from the generative AI, and the output is the adjusted answer data (e.g., "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately.").

[0461] Step 9:

[0462] The server sends the adjusted answer to the user terminal, which the user confirms. The input is the adjusted answer data, and the output is the final answer information displayed on the user terminal.

[0463] In this way, the present invention provides appropriate information according to the user's emotional state.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] [Second embodiment]

[0468] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0469] 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.

[0470] 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).

[0471] 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.

[0472] 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.

[0473] 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).

[0474] 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.

[0475] 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.

[0476] 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.

[0477] 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.

[0478] 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.

[0479] 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."

[0480] The present invention is a system for users to efficiently and accurately gather information, utilizing generative artificial intelligence as an optimal alternative to traditional internet search methods. This system is realized in a configuration including a user, a terminal, and a server. Specific embodiments of the system and their operation are described below.

[0481] System Overview

[0482] This system analyzes user questions and provides the optimal generative AI for those questions. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a database that searches for the optimal generative AI, and a result integration module that integrates and presents the results.

[0483] How it works

[0484] Enter and submit your question

[0485] The user uses the device to input a question. For example, they enter a question such as "Please tell me about your symptoms of COVID-19" into the portal site's input form and click the submit button. The input question is sent from the device to the server.

[0486] Receiving and parsing questions

[0487] The server receives the question sent by the user. The received question is analyzed by the analysis module, and important keywords are extracted. For example, keywords such as "COVID-19" and "symptoms" are extracted.

[0488] Searching for the best generative AI bot

[0489] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. The database contains the areas of expertise and question types that each generative AI bot can answer. From the search results, a list of suitable candidate generative AI bots is generated.

[0490] Present and select a bot

[0491] The server displays a list of generative AI bots that are optimal for the user. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user then selects the optimal generative AI bot from the presented options.

[0492] Resend your question and get an answer

[0493] The server resends the question to the generative AI bot selected by the user, which generates an answer based on the question from the server and sends the answer back to the server.

[0494] Displaying the results

[0495] The server formats the answer received from the generative AI bot and sends it to the user's device. The final answer is displayed on the user's device. For example, it may show information such as "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[0496] Specific examples

[0497] Example 1: Asking about COVID-19 symptoms

[0498] 1. The user types in the question, "Tell me about your COVID-19 symptoms" and submits it.

[0499] 2. The server receives the question and extracts the keywords "coronavirus" and "symptoms."

[0500] 3. The server searches for the most suitable generative artificial intelligence bot and lists "Medical Bot A" and "Medical Bot B."

[0501] 4. The user selects "Medical Bot A."

[0502] 5. The server sends a question to the selected bot and retrieves the answer.

[0503] 6. The server formats the answer and sends it to the user's device.

[0504] 7. The user's device will display the message, "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[0505] In this way, this system allows users to efficiently collect information and easily find the optimal AI bot. Furthermore, by integrating and presenting information from multiple AI bots, it is possible to further improve user convenience.

[0506] The processing flow will be explained below.

[0507] Step 1:

[0508] A user accesses the portal site and enters a question into the question input form.

[0509] Specific behavior: A user accesses the portal site using a browser, enters "Tell me about your COVID-19 symptoms" in the text box, and clicks the submit button.

[0510] Step 2:

[0511] The terminal sends a question to the server.

[0512] What happens: The browser sends the user's input to the server as an HTTP request.

[0513] Step 3:

[0514] The server receives the user's query.

[0515] Specific operation: An HTTP request arrives at the server, and the server retrieves the content.

[0516] Step 4:

[0517] A question analysis module on the server analyzes the question.

[0518] What it does: It uses a natural language processing (NLP) engine to extract keywords such as "coronavirus" and "symptoms."

[0519] Step 5:

[0520] The server searches the generative artificial intelligence database.

[0521] Specific operation: Execute SQL queries to find relevant generative AI bots from the database. For example, medical-related bots "Medical Bot A" and "Medical Bot B" are found.

[0522] Step 6:

[0523] The server lists the most suitable generative artificial intelligence bots from the search results.

[0524] Specific behavior: Formats the found generative AI bots into a list and prepares the data to present to the user.

[0525] Step 7:

[0526] The server presents the user with a list of generative artificial intelligence bots.

[0527] Specific operation: The generated list is sent to the user's terminal in HTML or JSON format and displayed in the browser.

[0528] Step 8:

[0529] The user selects the best bot from the generative artificial intelligence bots presented.

[0530] Specific operation: The user clicks the button of the desired generative artificial intelligence bot from the displayed list.

[0531] Step 9:

[0532] The terminal transmits the selection information of the generative artificial intelligence bot selected to the server.

[0533] Specific operation: Send an HTTP request again to convey the selected information to the server.

[0534] Step 10:

[0535] The server resends the question to the selected generative artificial intelligence bot.

[0536] Specific operation: Again using an API call, the question is forwarded to the selected generative AI bot.

[0537] Step 11:

[0538] The server receives the answer from the generative artificial intelligence bot.

[0539] Specific operation: Receives answer data from the generative AI bot as an API response.

[0540] Step 12:

[0541] Formats the response received by the server.

[0542] Specific operation: Converts the received response data into HTML or JSON format for presentation to the user.

[0543] Step 13:

[0544] The server sends the formatted response to the user terminal.

[0545] Specific operation: The generated data is sent to the user's terminal as an HTTP response.

[0546] Step 14:

[0547] The user's device will display the final answer on the screen.

[0548] What it does: The browser processes the data and displays information to the user, such as "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[0549] Example 1

[0550] 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."

[0551] Conventional Internet search methods can make it difficult for users to gather information efficiently and accurately. In particular, they face problems such as not being able to obtain appropriate information for complex questions and difficulty in finding reliable sources. Furthermore, users must integrate information obtained from multiple sources themselves, which is time-consuming.

[0552] 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.

[0553] In this invention, the server includes an input device for a user to input a question, an information processing device for receiving the question sent from the input device, analysis means for analyzing the received question and extracting keywords, a storage device for searching for the optimal generative AI based on the extracted keywords, information integration means for presenting the optimal generative AI to the user from the search results, communication means for transferring the question to the generative AI selected by the user and receiving an answer, and display means for sending the received answer to the user terminal. This allows the user to efficiently and accurately collect information even for complex questions, and by integrating and providing information from multiple information sources, a reliable, unified answer can be obtained.

[0554] A "user" is an entity that uses the system to collect information.

[0555] An "input device" is a device that allows a user to input a question, such as a keyboard or a touchscreen device.

[0556] A "question" is a request for information that a user enters into the system.

[0557] The "information processing device" is a device that receives and analyzes a question sent from an input device. Specifically, this corresponds to a server.

[0558] The "analysis means" is a module for extracting important keywords from received questions. Natural language processing technology is often used.

[0559] "Keywords" are important words extracted from questions by analytical means and are used to identify the content of the question.

[0560] The "storage device" is a device that includes a database for searching for the optimal generative artificial intelligence based on the extracted keywords.

[0561] "Generative AI" is an AI model that generates appropriate answers to user questions. For example, a natural language generation model falls into this category.

[0562] The "information integration means" is a module that presents the user with the most appropriate generative artificial intelligence from the search results.

[0563] "Communication means" refers to the method by which a user transmits a question to a generative AI selected by the user and receives a response. This includes network communication.

[0564] The "display means" is a device for displaying the received response on the user terminal, such as a display or monitor.

[0565] An "information gathering device" refers to the entire system that allows users to input questions and receive answers from generative artificial intelligence based on those questions.

[0566] The system of the present invention is an information collection device that allows users to collect information efficiently and accurately. This device allows users to input a question and obtain an answer from a generative artificial intelligence that is best suited to that question. Specifically, it includes the following components:

[0567] 1. Input Devices:

[0568] This is the device that a user uses to enter a question. For example, this could be a PC, tablet, or smartphone. This allows a user to enter a question such as "Tell me about your COVID-19 symptoms."

[0569] 2. Information processing equipment:

[0570] This is a server for receiving and analyzing questions sent from an input device. The server receives user input as an HTTP request and analyzes the content of the question using an analysis means.

[0571] 3. Analysis method:

[0572] This module analyzes questions and extracts important keywords. Specifically, it uses morphological analysis tools and natural language processing technologies (such as Mecab and SpaCy) to extract keywords such as "COVID-19" and "symptoms" from questions.

[0573] 4. Storage:

[0574] This device has a database for searching for the optimal generative AI based on extracted keywords. This database contains the fields of expertise of each generative AI model and the question formats it can handle.

[0575] 5. Information integration methods:

[0576] This module presents users with the most suitable generative artificial intelligence based on search results, displaying options such as "Medical Bot A" and "Medical Bot B" to the user.

[0577] 6. Means of communication:

[0578] This is a communications infrastructure for forwarding questions to a user-selected generative AI model and receiving answers. It uses network communications to send questions to the API endpoint of the selected generative AI model.

[0579] 7. Display means:

[0580] This is a device that displays the received response on the user's device. For example, it displays "Symptoms of COVID-19 include fever, cough, and difficulty breathing" on the user's device display.

[0581] Specific examples

[0582] Example questions:

[0583] The user types and submits the question, "Tell me about your COVID-19 symptoms." This question is processed in the system as follows:

[0584] 1. The user enters a question into the input device and clicks the submit button.

[0585] 2. The device sends the entered question to the server as an HTTP request.

[0586] 3. The server receives the question and uses analytical tools to extract keywords such as "coronavirus" and "symptoms."

[0587] 4. Based on the extracted keywords, the server searches the database in the storage device and lists the most suitable generative AI models (e.g., "Medical Bot A" and "Medical Bot B").

[0588] 5. The server uses information integration methods to display candidate bots to the user.

[0589] 6. The user selects the best bot (e.g., "Medical Bot A").

[0590] 7. The server forwards the question to the selected generative AI model and receives the answer from the generative AI model.

[0591] 8. The server formats the received response and sends it to the user's device.

[0592] 9. The user device displays the final answer on the display.

[0593] In this way, the information collection device of the present invention allows users to obtain information efficiently and accurately, and is capable of integrating information from multiple sources to provide users with the most reliable and unified answers.

[0594] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0595] Step 1:

[0596] The user enters a question into the input device. For example, they enter "Please tell me about the symptoms of COVID-19" and click the send button. The entered question is sent from the device to the server as an HTTP request. The input is in text format, and the output is in HTTP request format.

[0597] Step 2:

[0598] The server receives an HTTP request sent from the terminal. The server parses the request and extracts the question. During this process, the question is saved as text data on the server. The input is in HTTP request format, and the output is the question in text format.

[0599] Step 3:

[0600] The server's analysis means analyzes the received question text and extracts important keywords. Natural language processing technology (for example, Mecab or SpaCy) is used to analyze the question content and obtain keywords such as "COVID-19" and "symptoms." The data processing performed in this step is text analysis, where the input is the text data of the question and the output is a list of keywords.

[0601] Step 4:

[0602] The server searches a database in the storage device based on the extracted keywords. The database stores the areas of expertise and question formats that each generative AI model can handle. For example, an SQL query can be used to search for generative AI models related to "COVID-19" and "symptoms." The input is a list of keywords, and the output is a list of candidate generative AI models.

[0603] Step 5:

[0604] The server's information integration means presents the optimal generative AI model to the user from the search results. To do this, it generates a list of candidate generative AI models (e.g., "Medical Bot A" and "Medical Bot B") in HTML format and sends it to the user's device as a response for display. The input is a list of generative AI models, and the output is an HTML response.

[0605] Step 6:

[0606] The user selects the best model from the list of generative AI models presented. The user clicks the selection button and sends the selection to the server. The input is the model selected from the list of generative AI models, and the output is the selection information sent to the server again in the form of an HTTP request.

[0607] Step 7:

[0608] The server resubmits the question to the generative AI model selected by the user. It uses network communication to send the question to the endpoint of the selected AI model and receive the answer from the model. The input is the user's question and the endpoint information of the selected generative AI model, and the output is the generated answer.

[0609] Step 8:

[0610] The server formats the answer it receives, formatting the answer in a user-friendly format, generating a final HTML response and sending it to the user's device. The input is the answer from the generative AI model, and the output is an HTML response containing the formatted answer.

[0611] Step 9:

[0612] The user device displays the received HTML response. The final answer is displayed on the screen, allowing the user to confirm the answer to the question. For example, "Symptoms of COVID-19 include fever, cough, and difficulty breathing." The input is the HTML response, and the output is the displayed answer.

[0613] (Application example 1)

[0614] 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."

[0615] Currently, product picking work at logistics centers requires a lot of time and effort from employees, and there is a need for a support system to make the work more efficient. Furthermore, there is a lack of optimization of picking routes and accurate product location information, which leads to a high likelihood of inefficiency and errors. A system that solves these issues and streamlines picking work at logistics centers is needed.

[0616] 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.

[0617] In this invention, the server includes a terminal for a user to input a question, a means for receiving the question sent from the terminal, an analysis module for analyzing the received question and extracting keywords, a database for searching for the optimal generative artificial intelligence based on the extracted keywords, a result integration module for presenting the optimal generative artificial intelligence to the user from the search results, a means for transferring the question to the generative artificial intelligence selected by the user and receiving an answer, a means for transmitting the received answer to the user terminal, and a means for calculating product location information and an optimal route and assisting in pickup work. This allows the user to efficiently obtain product location information and an optimal picking route, enabling efficient picking work at the logistics center.

[0618] A "user" is a person who uses the system to input questions and obtain information.

[0619] A "question" is a statement that a user enters about the information they want to know, and is sent to the server for analysis.

[0620] "Terminal" refers to the device used by the user to enter a question, including a smartphone, computer, tablet, etc.

[0621] A "server" is a computer system that receives queries sent from terminals and performs processes such as analysis, database search, and result integration.

[0622] The "analysis module" is software installed on the server, which has the function of analyzing received questions and extracting important keywords.

[0623] "Keywords" are important words and predicates extracted from questions by the analysis module and used in generative artificial intelligence searches.

[0624] "Generative AI" is AI that generates appropriate answers to user questions, and includes bots specialized in various fields.

[0625] A "database" is a data storage device that stores information about generative artificial intelligence and its specialized fields, and is used for searching.

[0626] The "results integration module" is software that has the function of selecting the most appropriate generative artificial intelligence from database search results and presenting it to the user.

[0627] "Means" refers to devices, modules, programs, etc. for executing specific functions or processes.

[0628] "Product location information" is data indicating the specific storage location of the product within the logistics center.

[0629] The "optimal route" indicates the best route for efficiently picking up multiple items.

[0630] "Pickup work support" is an auxiliary function that allows employees to work efficiently based on the location information of the specified product and the optimal route.

[0631] The present invention relates to a system for allowing a user to input a question and obtain the best answer to that question. The system includes a terminal for the user to input the question, a server that receives the question sent from the terminal, an analysis module that analyzes the received question and extracts keywords, a database that searches for the best generative artificial intelligence based on the extracted keywords, a result integration module that presents the best generative artificial intelligence to the user from the search results, and means for transferring the question to the generative artificial intelligence selected by the user and receiving the answer.

[0632] System Embodiments

[0633] Hardware and software used

[0634] Hardware:

[0635] Devices: Smartphones (e.g. iPhone, Android devices), PCs, tablets

[0636] server

[0637] software:

[0638] Generative AI models (e.g., GPT-4)

[0639] Database (e.g. MySQL)

[0640] Mobile app development frameworks (e.g., React Native)

[0641] Data processing and calculation

[0642] 1. Entering and receiving questions:

[0643] Users input questions using devices such as smartphones or computers, which are then sent to the server.

[0644] The server receives the question sent from the terminal and sends it to the analysis module.

[0645] 2. Question Analysis:

[0646] The analysis module analyzes the received questions using natural language processing (NLP) technology and extracts important keywords.

[0647] 3. Generative AI Search:

[0648] The server searches the database for generative AI based on the extracted keywords, taking into account the AI's field of expertise and the types of questions it can answer.

[0649] From the search results, a candidate list of optimal generative artificial intelligence bots is generated and sent to the result integration module.

[0650] 4. Generative AI Presentation and Selection:

[0651] The result synthesis module presents the user with a list of the best generative artificial intelligence bots.

[0652] The user selects the best generative AI bot from the presented options.

[0653] 5. Resend the question and generate an answer:

[0654] The server resends the question to the generative artificial intelligence bot selected by the user.

[0655] The generative artificial intelligence bot generates an answer based on a question from the server and sends the answer back to the server.

[0656] 6. Formatting and displaying answers:

[0657] The server formats the generated response and transmits it to the user terminal.

[0658] The final answer will be displayed on the user's device.

[0659] Specific examples

[0660] For example, in a distribution center, an employee uses a smartphone to input a question such as, "What is the location and best route to pick up items A, B, and C?" This question is processed as follows:

[0661] 1. The server receives the question, and the analysis module extracts the keywords "Product A," "Product B," "Product C," "Location information," and "Optimal route."

[0662] 2. Based on the extracted keywords, the server searches the database for related generative artificial intelligence bots and lists "Pickup Bot A" and "Root Bot B."

[0663] 3. The user selects "Pickup Bot A."

[0664] 4. The server resends the question to the selected bot, which calculates the location information and optimal route for each item and returns an answer.

[0665] 5. The server formats the answer and displays it on the smartphone. The user receives real-time location information (item A: Section B3, item B: Section A2, item C: Section C1) and the optimal route (section A2 → section B3 → section C1).

[0666] Prompt Sentence Examples

[0667] "Picking list: Product A, Product B, Product C. Please tell me the location of each product and the best pickup route."

[0668] This system will improve the efficiency and accuracy of picking operations at logistics centers, reducing the workload.

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

[0670] Step 1:

[0671] The user inputs a question using a device. Specifically, they input a question such as "Please tell me the location information and the best route to pick up items A, B, and C" into a smartphone or PC application and click the send button. This input is sent to the server as text data.

[0672] Step 2:

[0673] The server receives the question sent by the user. As a preprocessing step before passing this question data to the analysis module, it checks that the text data has been received and converts it into the required format (e.g., JSON format).

[0674] Step 3:

[0675] The analysis module analyzes the received question and extracts important keywords. Here, natural language processing (NLP) techniques are used to extract keywords such as "product A," "product B," "product C," "location information," and "optimal route." The input for this step is the user's question text data, and the output is a list of extracted keywords.

[0676] Step 4:

[0677] The server searches a database based on the extracted keywords. The database contains the areas of expertise of each generative AI bot and the types of questions it can answer. The search results provide a list of related generative AI bots, such as "Pickup Bot A" and "Root Bot B." The output of this step is a list of generative AI bots.

[0678] Step 5:

[0679] The server presents the user with the optimal generative AI bot from the search results. This presentation is done by displaying a list of candidate bots on the application screen of a smartphone or computer. The user selects "Pickup Bot A." The input for this step is a list of bots, and the output is the bot selected by the user.

[0680] Step 6:

[0681] The server resends the question to the generative AI bot selected by the user. Here, data including the user's question is sent to the selected bot as a request message. The input of this step is the user's question text and information about the selected bot, and the output is the answer data from the generative AI bot.

[0682] Step 7:

[0683] A generative AI bot generates an answer based on a question from the server and sends the answer back to the server. For example, Pickup Bot A sends back location information such as "Product A: Section B3, Product B: Section A2, Product C: Section C1" and data such as "Optimal route: Section A2 → Section B3 → Section C1" to the server. The input to this step is the question data from the server, and the output is the generated answer data.

[0684] Step 8:

[0685] The server formats the answer received from the generative AI bot and sends it to the user's terminal. Here, the answer data is converted into a format that is easy for the user to understand and presented through the application. The input of this step is the answer data from the generative AI bot, and the output is the formatted answer data.

[0686] Step 9:

[0687] The user device receives the formatted answer sent from the server and displays it on the screen. For example, location information such as "Product A: Section B3, Product B: Section A2, Product C: Section C1" and specific information such as "Optimal route: Section A2 → Section B3 → Section C1" are displayed. The input of this step is the formatted answer data, and the output is the screen information displayed to the user.

[0688] 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.

[0689] The present invention adds an emotion recognition function to a system that allows users to efficiently and accurately collect information, and provides responses according to the user's emotional state. This system is realized by a configuration including a user, a terminal, a server, and an emotion recognition engine. Specific embodiments of the system and their operation are described below.

[0690] System Overview

[0691] This system analyzes user questions, provides the optimal generative AI for the question, and recognizes the user's emotions to adjust the response. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a database that searches for the optimal generative AI, a result integration module that integrates and presents the results, and an emotion engine that recognizes emotions.

[0692] How it works

[0693] Enter and submit your question

[0694] The user uses the device to input a question. For example, they enter a question such as "Please tell me about your symptoms of COVID-19" into the portal site's input form and click the submit button. The input question is sent from the device to the server.

[0695] Receiving and parsing questions

[0696] The server receives the question sent by the user. The received question is analyzed by the analysis module, and important keywords are extracted. For example, keywords such as "COVID-19" and "symptoms" are extracted.

[0697] Searching for the best generative AI bot

[0698] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. The database contains the areas of expertise and question types that each generative AI bot can answer. From the search results, a list of suitable candidate generative AI bots is generated.

[0699] Emotion recognition

[0700] The server uses an emotion engine to recognize the user's emotions, for example, determining whether the user is feeling stressed from the input text.

[0701] Present and select a bot

[0702] The server displays a list of generative AI bots that are optimal for the user. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user then selects the optimal generative AI bot from the presented options.

[0703] Resend your question and get an answer

[0704] The server resends the question to the generative AI bot selected by the user, which generates an answer based on the question from the server and sends the answer back to the server.

[0705] Adjusting responses based on emotions

[0706] The server adjusts the content and expression of the generated response based on the recognition results of the emotion engine, for example, adding more kind language and detailed explanations if the user is feeling stressed.

[0707] Displaying the results

[0708] The server formats the answer received from the generative AI bot and sends it to the user's device. The final answer is displayed on the user's device. For example, it may show information such as "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[0709] Specific examples

[0710] Example 1: Asking about COVID-19 symptoms

[0711] 1. The user types in the question, "Tell me about your COVID-19 symptoms" and submits it.

[0712] 2. The server receives the question and extracts the keywords "coronavirus" and "symptoms."

[0713] 3. The server searches for the most suitable generative artificial intelligence bot and lists "Medical Bot A" and "Medical Bot B."

[0714] 4. The server uses an emotion engine to analyze the user's emotions, for example, to detect whether the user is feeling anxious or stressed. If the user is feeling anxious, the server is configured to add kind words and detailed explanations.

[0715] 5. The user selects "Medical Bot A."

[0716] 6. The server sends a question to the selected bot and retrieves the answer.

[0717] 7. The server adjusts and formats the obtained answer based on the emotion recognition results.

[0718] 8. The user's device will display the message, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, please consult a medical professional immediately."

[0719] In this way, the system allows users to efficiently collect information and receive responses tailored to their emotional state, improving the user experience and providing more appropriate assistance.

[0720] The processing flow will be explained below.

[0721] Step 1:

[0722] A user accesses the portal site and enters a question into the question input form.

[0723] Specific actions: The user opens the portal site in a browser, enters "Please tell me about your coronavirus symptoms" in the text box, and clicks the submit button.

[0724] Step 2:

[0725] The terminal sends a question to the server.

[0726] Specific operation: The question is sent from the terminal to the server as an HTTP request.

[0727] Step 3:

[0728] The server receives the user's query.

[0729] Specific operation: The server receives an HTTP request and passes the contents to the analysis module.

[0730] Step 4:

[0731] A question analysis module on the server analyzes the question.

[0732] What it does: It uses a natural language processing (NLP) engine to extract keywords such as "coronavirus" and "symptoms."

[0733] Step 5:

[0734] The server uses an emotion engine to recognize the user's emotions.

[0735] Specific operation: The emotion engine analyzes the user's emotional state (e.g., anxiety, stress) from the input text.

[0736] Step 6:

[0737] The server searches the generative artificial intelligence database.

[0738] Specific operation: Executes an SQL query based on the extracted keywords to search for medical-related generative artificial intelligence bots.

[0739] Step 7:

[0740] The server lists the most suitable generative artificial intelligence bots from the search results.

[0741] Specific operation: The found generative artificial intelligence bots (e.g., "Medical Bot A" and "Medical Bot B") are formatted into a list and the data is prepared for presentation to the user.

[0742] Step 8:

[0743] The server presents the user with a list of generative artificial intelligence bots.

[0744] Specific operation: Sends the result in HTML or JSON format to the user's device and displays suggestions in the browser.

[0745] Step 9:

[0746] The user selects the best bot from the generative artificial intelligence bots presented.

[0747] Specific operation: The user clicks the button of the desired generative artificial intelligence bot from the list.

[0748] Step 10:

[0749] The terminal transmits the selection information of the generative artificial intelligence bot selected to the server.

[0750] Specific operation: Send an HTTP request again to convey the selected information to the server.

[0751] Step 11:

[0752] The server resends the question to the selected generative artificial intelligence bot.

[0753] What it does: Uses an API call to forward the user's question to a generative AI bot.

[0754] Step 12:

[0755] The server receives the answer from the generative artificial intelligence bot.

[0756] Specific operation: Receives answer data from the generative AI bot as an API response.

[0757] Step 13:

[0758] The server adjusts the content and expression of the response based on the recognized emotion.

[0759] Specific actions: For example, if a user is feeling anxious, add kind words or detailed explanations to the answer.

[0760] Step 14:

[0761] The server formats the adjusted response.

[0762] Specific operation: The adjusted response data is converted into HTML or JSON format and sent to the user's device.

[0763] Step 15:

[0764] The user's device will display the final answer on the screen.

[0765] What it does: It displays the data sent via JavaScript in the browser, informing the user that "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, please seek medical help immediately."

[0766] Example 2

[0767] 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."

[0768] Conventional information gathering systems have difficulty in quickly providing optimal answers to user questions. Furthermore, they are unable to respond according to the user's emotional state, making it difficult to provide sufficient support, especially to users who are feeling stressed or anxious.

[0769] 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.

[0770] In this invention, the server includes a terminal for a user to input a question, a computer for receiving the question sent from the terminal, an analysis module for analyzing the received question and extracting keywords, a storage device for searching for the optimal generative AI based on the extracted keywords, a result integration module for presenting the optimal generative AI to the user from the search results, means for transferring the question to the generative AI selected by the user and receiving an answer, communication means for transmitting the received answer to the user terminal, and an emotion recognition engine for recognizing the user's emotion and adjusting the answer content based on that emotion. This makes it possible to quickly provide the optimal answer to the user's question and also to respond appropriately according to the user's emotional state.

[0771] A "terminal" is a device through which a user inputs a question and sends it to a server.

[0772] The "computer" is a device that receives questions sent by users, analyzes them, and forwards them to the generative artificial intelligence.

[0773] An "analysis module" is software or hardware for analyzing received questions and extracting important keywords.

[0774] A "storage device" is a storage medium such as a database for searching for the optimal generative artificial intelligence based on extracted keywords.

[0775] A "result integration module" is software or hardware for presenting the user with the most appropriate generative artificial intelligence from search results.

[0776] "Communication means" refers to the network interface and communication protocol used to transmit the received response to the user terminal.

[0777] An "emotion recognition engine" is software or hardware that recognizes a user's emotions and adjusts the content of responses based on those emotions.

[0778] "Generative artificial intelligence" refers to algorithms and models that generate answers to user questions.

[0779] "Keywords" are important words or phrases extracted from a user's question that represent the content of that question.

[0780] The present invention adds an emotion recognition function to a system that allows users to collect information efficiently and accurately, and provides responses according to the user's emotional state. This system is realized by a configuration including a user, a terminal, a server, and an emotion recognition engine.

[0781] System Overview

[0782] This system analyzes user questions, provides the optimal generative AI for the question, and recognizes the user's emotions and adjusts the response accordingly. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a storage device that searches for the optimal generative AI, a result integration module that integrates and presents the results, and an emotion engine that recognizes emotions.

[0783] Detailed explanation of operation

[0784] Enter and submit your question

[0785] The user uses the device to enter a question. The user enters "Please tell me about your COVID-19 symptoms" into the portal site's input form and clicks the submit button. The entered question is sent from the device to the server. Specifically, it is sent as an HTTP request.

[0786] Receiving and parsing questions

[0787] The server receives the question sent by the user. The server analyzes the received HTTP request and extracts the question content. The analysis module analyzes the question using natural language processing technology and extracts important keywords. For example, keywords such as "coronavirus" and "symptoms" are extracted. Natural language processing libraries such as NLTK and spaCy are used here.

[0788] Searching for the best generative AI bot

[0789] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. Specifically, it executes an SQL query to list appropriate generative AI bots. The storage device stores the specialty of each generative AI bot (e.g., medicine, education, entertainment, etc.) and the question formats it can answer. For example, "Medical Bot A" and "Medical Bot B" are listed as candidates.

[0790] Emotion recognition

[0791] The server uses an emotion engine to recognize the user's emotions. Specifically, it calls emotion recognition APIs, such as Google Cloud Natural Language API or IBM Watson's emotion analysis service, to extract emotions from the input text. This identifies whether the user is feeling stressed or anxious.

[0792] Present and select a bot

[0793] The server displays a list of generative AI bots that are optimal for the user. Specifically, the list is displayed to the user using HTML and CSS. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user selects the appropriate generative AI bot from the presented options and clicks the select button.

[0794] Resend your question and get an answer

[0795] The server resends the question to the generative AI bot selected by the user. Specifically, it resends the question by sending an API request. The generative AI bot generates an answer based on the question and sends the answer back to the server as an API response. For example, using OpenAI's generative AI model, the answer "Symptoms of COVID-19 include fever, cough, and difficulty breathing" can be obtained.

[0796] Adjusting responses based on emotions

[0797] The server adjusts the content and expressions of the generated answers based on the recognition results of the emotion engine. Specifically, for users who are feeling stressed, it adds kind language and detailed explanations. For example, it adds phrases such as, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[0798] Displaying the results

[0799] The server formats the answer received from the generative AI bot and sends it to the user's device. Specifically, the answer is formatted in HTML and sent as an HTTP response. The final answer is displayed on the user's device. For example, the following information may be displayed: "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[0800] Specific examples

[0801] Example 1: Asking about COVID-19 symptoms

[0802] 1. The user types in the question, "Tell me about your COVID-19 symptoms" and submits it.

[0803] 2. The server receives the question and extracts the keywords "coronavirus" and "symptoms."

[0804] 3. The server searches for the most suitable generative artificial intelligence bot and lists "Medical Bot A" and "Medical Bot B."

[0805] 4. The server uses an emotion engine to analyze the user's emotions, for example, to detect whether the user is feeling anxious or stressed. If the user is feeling anxious, the server is configured to add kind words and detailed explanations.

[0806] 5. The user selects "Medical Bot A."

[0807] 6. The server sends a question to the selected bot and retrieves the answer.

[0808] 7. The server adjusts and formats the obtained answer based on the emotion recognition results.

[0809] 8. The user's device will display the message, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical professional immediately."

[0810] In this way, the system allows users to efficiently collect information and receive responses tailored to their emotional state, improving the user experience and providing more appropriate assistance.

[0811] Prompt Sentence Examples

[0812] "Please tell me what the symptoms of COVID-19 are. I'm very worried."

[0813] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0814] markdown

[0815] Step 1:

[0816] The user uses the device to enter a question. The user enters "Please tell me about your COVID-19 symptoms" into the portal site's input form and clicks the submit button. The entered question is sent from the device to the server. Specifically, it is sent as an HTTP request.

[0817] Input: User-provided question text

[0818] Output: HTTP request to the server

[0819] Step 2:

[0820] The server receives the question sent by the user. The server analyzes the received HTTP request and extracts the question content. The analysis module analyzes the question using natural language processing technology and extracts important keywords. For example, keywords such as "coronavirus" and "symptoms" are extracted. Natural language processing libraries such as NLTK and spaCy are used here.

[0821] Input: Question text included in HTTP request

[0822] Output: Keywords such as "COVID-19" and "symptoms"

[0823] Step 3:

[0824] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. Specifically, it executes an SQL query to list appropriate generative AI bots. The storage device stores the specialty of each generative AI bot (e.g., medicine, education, entertainment, etc.) and the question formats it can answer. For example, "Medical Bot A" and "Medical Bot B" are listed as candidates.

[0825] Input: Extracted keywords

[0826] Output: A list of optimal generative AI bots (e.g., "Medical Bot A" and "Medical Bot B")

[0827] Step 4:

[0828] The server uses an emotion engine to recognize the user's emotions. Specifically, it calls emotion recognition APIs, such as Google Cloud Natural Language API or IBM Watson's emotion analysis service, to extract emotions from the input text. This identifies whether the user is feeling stressed or anxious.

[0829] Input: Question text

[0830] Output: User's emotional state (e.g., stress, anxiety)

[0831] Step 5:

[0832] The server displays a list of generative AI bots that are optimal for the user. Specifically, the list is displayed to the user using HTML and CSS. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user selects the appropriate generative AI bot from the presented options and clicks the select button.

[0833] Input: A list of the best generative AI bots

[0834] Output: User selects bot

[0835] Step 6:

[0836] The server resends the question to the generative AI bot selected by the user. Specifically, it resends the question by sending an API request. The generative AI bot generates an answer based on the question and sends the answer back to the server as an API response. For example, using OpenAI's generative AI model, the answer "Symptoms of COVID-19 include fever, cough, and difficulty breathing" can be obtained.

[0837] Input: User-selected generative AI bot, question text

[0838] Output: Answer from a generative AI bot

[0839] Step 7:

[0840] The server adjusts the content and expressions of the generated answers based on the recognition results of the emotion engine. Specifically, for users who are feeling stressed, it adds kind language and detailed explanations. For example, it adds phrases such as, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[0841] Input: Answers from a generative AI bot, user's emotional state

[0842] Output: Adjusted answer

[0843] Step 8:

[0844] The server formats the answer received from the generative AI bot and sends it to the user's device. Specifically, the answer is formatted in HTML and sent as an HTTP response. The final answer is displayed on the user's device. For example, the following information may be displayed: "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[0845] Input: Adjusted answer content

[0846] Output: The final answer displayed on the user's terminal

[0847] (Application example 2)

[0848] 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."

[0849] In conventional information gathering systems, response systems have been proposed that can respond quickly and appropriately to user questions, but they lack the ability to adjust responses according to the user's emotional state, which prevents them from fully improving the user experience. Furthermore, in security services, it is necessary to provide a higher level of safety by grasping the emotional state of people in the monitored area in real time and responding according to that emotion, but the lack of such a system is an issue.

[0850] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0851] In this invention, the server includes a terminal for a user to input a question, means for receiving the question sent from the terminal, an analysis module for analyzing the received question and extracting keywords, a database for searching for an optimal generative artificial intelligence based on the extracted keywords, a result integration module for presenting the optimal generative artificial intelligence to the user from the search results, means for transferring the question to the generative artificial intelligence selected by the user and receiving a response, means for transmitting the received response to the user terminal, an emotion recognition engine for analyzing and recognizing the emotional states of people in the monitored area, means for selecting and presenting the optimal generative artificial intelligence according to the emotions identified by the emotion recognition engine, and means for adjusting the response generated by the optimal generative artificial intelligence based on the emotion recognition data, thereby providing a response according to the user's emotional state and enabling improved security services.

[0852] A "terminal for users to input questions" is an electronic device used by users to input questions in the form of text, voice input, or the like.

[0853] The "server for receiving questions sent from a terminal" is a network-connected computer system for receiving questions sent by a user from a terminal and for subsequent processing.

[0854] The "analysis module for analyzing received questions and extracting keywords" is a software component that analyzes the content of questions entered by users and extracts important keywords and phrases.

[0855] A "database for searching for the optimal generative artificial intelligence based on extracted keywords" is a database that stores information for searching for the optimal generative artificial intelligence based on keywords extracted by the analysis module.

[0856] The "result integration module for presenting the user with the optimal generative artificial intelligence from the search results" is a software component for integrating the results of a database search and presenting the user with the optimal generative artificial intelligence candidates.

[0857] "Means for transferring a question to a generative artificial intelligence selected by a user and receiving a response" refers to means for sending a user's question to a generative artificial intelligence selected by a user and receiving a response thereto.

[0858] "Means for transmitting the received answer to the user terminal" refers to means for transmitting the answer received from the generative artificial intelligence to the user terminal.

[0859] The "emotion recognition engine for analyzing and recognizing the emotional state of people within a monitored area" is a software component that analyzes and identifies emotions from the facial expressions, voices, etc. of people within a monitored area.

[0860] "Means for selecting and presenting the most appropriate generative artificial intelligence in accordance with the emotions identified by the emotion recognition engine" refers to means for selecting the most appropriate generative artificial intelligence based on the emotion data analyzed by the emotion recognition engine and presenting the result to the user.

[0861] "Means for adjusting responses generated by optimal generative artificial intelligence based on emotion recognition data" refers to means for adjusting responses generated by generative artificial intelligence according to the emotional state of the user.

[0862] This invention adds emotion recognition functionality to a system that allows users to collect information efficiently and accurately, and provides responses that correspond to the user's emotional state. This system is realized by comprising a user terminal, a server, an analysis module, a generative AI database, a result integration module, and an emotion recognition engine.

[0863] System Overview

[0864] This system analyzes a user's question, provides the most suitable generative artificial intelligence for that question, and recognizes the user's emotions and adjusts the response accordingly. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a database that searches for the most suitable generative artificial intelligence, a result integration module that integrates and presents the results, and an emotion recognition engine that recognizes emotions.

[0865] How it works

[0866] Enter and submit your question

[0867] The user inputs a question using the device. For example, they input a question such as "Please tell me about the symptoms of COVID-19" into the device and send it. The input question is sent from the device to the server.

[0868] Receiving and parsing questions

[0869] The server receives the question sent by the user. The received question is analyzed by the analysis module, and important keywords are extracted. For example, keywords such as "COVID-19" and "symptoms" are extracted.

[0870] Searching for the best generative artificial intelligence

[0871] The server searches a database of generative AI based on the extracted keywords. The database contains the fields of expertise and question formats that each generative AI can handle. The search results then produce a list of suitable generative AIs.

[0872] Recognizing and Responding to Emotions

[0873] The server uses an emotion recognition engine to recognize the user's emotions, for example, to determine whether the user is stressed from the input text. The emotion recognition engine analyzes the facial expressions and tone of voice of people in the monitored area.

[0874] Program processing

[0875] The server performs its operations using, among other things, the following software and hardware:

[0876] Hardware: smart glasses, smartphones, cameras

[0877] software:

[0878] EmotionRecognition Module: Face and emotion recognition engine using OpenCV

[0879] AIModelExecutor module: Generative AI model selection and execution engine (e.g., GPT-4, BERT)

[0880] The server acquires real-time video from the camera and analyzes the emotional data using the EmotionRecognition module. The emotion recognition engine identifies people's emotional states based on the analysis results. The AIModelExecutor module then uses this emotional data to select the optimal generative AI and generate a response.

[0881] Specific examples

[0882] Example 1: Security Monitoring Assistant

[0883] Security guards and facility managers use smart glasses or smartphones to monitor the facility and check the emotional state of people in real time. At this time, an emotion recognition engine analyzes the emotional state (e.g., anxiety, anger, stress) of the people being monitored and selects and presents an appropriate response from an optimal generative artificial intelligence database.

[0884] Example prompt sentence:

[0885] "We have noticed an individual in our surveillance area who appears to be unsafe. Please advise our security personnel on how to respond."

[0886] In this way, the present invention provides a response that is tailored to the user's emotional state, thereby improving the user experience and providing improved security services.

[0887] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0888] Step 1:

[0889] A user uses a terminal to input a question. For example, they input "Please tell me about the symptoms of COVID-19" and send it. The input is the text data of the user's question, and the output is the input question being sent from the terminal to the server.

[0890] Step 2:

[0891] The server receives the question sent by the user. The input is the question text data sent from the terminal, and the output is the received data passed to the analysis module.

[0892] Step 3:

[0893] The analysis module analyzes the received question and extracts important keywords. The input is the received question text data, and the output is the analysis results, which are important keywords (e.g., "COVID-19" and "symptoms").

[0894] Step 4:

[0895] The server searches the database for the optimal generative AI based on the extracted important keywords. The input is the important keywords, and the output is a list of candidate generative AIs (e.g., "Medical Bot A" and "Medical Bot B").

[0896] Step 5:

[0897] The server uses an emotion recognition engine to analyze and identify the user's emotion. The input is the text data of the user's question and facial expression recognition data, and the output is the user's emotional state (e.g., stress, anxiety).

[0898] Step 6:

[0899] The server presents the user with a list of optimal generative AIs, and the user selects one. The input is a list of generative AI candidates, and the output is the generative AI selected by the user (e.g., "Medical Bot A").

[0900] Step 7:

[0901] The server forwards the question to the generative artificial intelligence selected by the user and receives an answer from the generative artificial intelligence. The input is the user's question and the identification information of the selected generative artificial intelligence, and the output is the answer data from the generative artificial intelligence (e.g., "Symptoms of COVID-19 include fever, cough, and difficulty breathing").

[0902] Step 8:

[0903] The server adjusts the generated answer content based on the results of the emotion recognition engine. The input is the answer data and emotion recognition results from the generative AI, and the output is the adjusted answer data (e.g., "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately.").

[0904] Step 9:

[0905] The server sends the adjusted answer to the user terminal, which the user confirms. The input is the adjusted answer data, and the output is the final answer information displayed on the user terminal.

[0906] In this way, the present invention provides appropriate information according to the user's emotional state.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] [Third embodiment]

[0911] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0912] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0913] 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).

[0914] 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.

[0915] 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.

[0916] 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).

[0917] 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.

[0918] 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.

[0919] 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.

[0920] 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.

[0921] 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.

[0922] 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."

[0923] The present invention is a system for users to efficiently and accurately gather information, utilizing generative artificial intelligence as an optimal alternative to traditional internet search methods. This system is realized in a configuration including a user, a terminal, and a server. Specific embodiments of the system and their operation are described below.

[0924] System Overview

[0925] This system analyzes user questions and provides the optimal generative AI for those questions. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a database that searches for the optimal generative AI, and a result integration module that integrates and presents the results.

[0926] How it works

[0927] Enter and submit your question

[0928] The user uses the device to input a question. For example, they enter a question such as "Please tell me about your symptoms of COVID-19" into the portal site's input form and click the submit button. The input question is sent from the device to the server.

[0929] Receiving and parsing questions

[0930] The server receives the question sent by the user. The received question is analyzed by the analysis module, and important keywords are extracted. For example, keywords such as "COVID-19" and "symptoms" are extracted.

[0931] Searching for the best generative AI bot

[0932] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. The database contains the areas of expertise and question types that each generative AI bot can answer. From the search results, a list of suitable candidate generative AI bots is generated.

[0933] Present and select a bot

[0934] The server displays a list of generative AI bots that are optimal for the user. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user then selects the optimal generative AI bot from the presented options.

[0935] Resend your question and get an answer

[0936] The server resends the question to the generative AI bot selected by the user, which generates an answer based on the question from the server and sends the answer back to the server.

[0937] Displaying the results

[0938] The server formats the answer received from the generative AI bot and sends it to the user's device. The final answer is displayed on the user's device. For example, it may show information such as "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[0939] Specific examples

[0940] Example 1: Asking about COVID-19 symptoms

[0941] 1. The user types in the question, "Tell me about your COVID-19 symptoms" and submits it.

[0942] 2. The server receives the question and extracts the keywords "coronavirus" and "symptoms."

[0943] 3. The server searches for the most suitable generative artificial intelligence bot and lists "Medical Bot A" and "Medical Bot B."

[0944] 4. The user selects "Medical Bot A."

[0945] 5. The server sends a question to the selected bot and retrieves the answer.

[0946] 6. The server formats the answer and sends it to the user's device.

[0947] 7. The user's device will display the message, "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[0948] In this way, this system allows users to efficiently collect information and easily find the optimal AI bot. Furthermore, by integrating and presenting information from multiple AI bots, it is possible to further improve user convenience.

[0949] The processing flow will be explained below.

[0950] Step 1:

[0951] A user accesses the portal site and enters a question into the question input form.

[0952] Specific behavior: A user accesses the portal site using a browser, enters "Tell me about your COVID-19 symptoms" in the text box, and clicks the submit button.

[0953] Step 2:

[0954] The terminal sends a question to the server.

[0955] What happens: The browser sends the user's input to the server as an HTTP request.

[0956] Step 3:

[0957] The server receives the user's query.

[0958] Specific operation: An HTTP request arrives at the server, and the server retrieves the content.

[0959] Step 4:

[0960] A question analysis module on the server analyzes the question.

[0961] What it does: It uses a natural language processing (NLP) engine to extract keywords such as "coronavirus" and "symptoms."

[0962] Step 5:

[0963] The server searches the generative artificial intelligence database.

[0964] Specific operation: Execute SQL queries to find relevant generative AI bots from the database. For example, medical-related bots "Medical Bot A" and "Medical Bot B" are found.

[0965] Step 6:

[0966] The server lists the most suitable generative artificial intelligence bots from the search results.

[0967] Specific behavior: Formats the found generative AI bots into a list and prepares the data to present to the user.

[0968] Step 7:

[0969] The server presents the user with a list of generative artificial intelligence bots.

[0970] Specific operation: The generated list is sent to the user's terminal in HTML or JSON format and displayed in the browser.

[0971] Step 8:

[0972] The user selects the best bot from the generative artificial intelligence bots presented.

[0973] Specific operation: The user clicks the button of the desired generative artificial intelligence bot from the displayed list.

[0974] Step 9:

[0975] The terminal transmits the selection information of the generative artificial intelligence bot selected to the server.

[0976] Specific operation: Send an HTTP request again to convey the selected information to the server.

[0977] Step 10:

[0978] The server resends the question to the selected generative artificial intelligence bot.

[0979] Specific operation: Again using an API call, the question is forwarded to the selected generative AI bot.

[0980] Step 11:

[0981] The server receives the answer from the generative artificial intelligence bot.

[0982] Specific operation: Receives answer data from the generative AI bot as an API response.

[0983] Step 12:

[0984] Formats the response received by the server.

[0985] Specific operation: Converts the received response data into HTML or JSON format for presentation to the user.

[0986] Step 13:

[0987] The server sends the formatted response to the user terminal.

[0988] Specific operation: The generated data is sent to the user's terminal as an HTTP response.

[0989] Step 14:

[0990] The user's device will display the final answer on the screen.

[0991] What it does: The browser processes the data and displays information to the user, such as "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[0992] Example 1

[0993] 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."

[0994] Conventional Internet search methods can make it difficult for users to gather information efficiently and accurately. In particular, they face problems such as not being able to obtain appropriate information for complex questions and difficulty in finding reliable sources. Furthermore, users must integrate information obtained from multiple sources themselves, which is time-consuming.

[0995] 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.

[0996] In this invention, the server includes an input device for a user to input a question, an information processing device for receiving the question sent from the input device, analysis means for analyzing the received question and extracting keywords, a storage device for searching for the optimal generative AI based on the extracted keywords, information integration means for presenting the optimal generative AI to the user from the search results, communication means for transferring the question to the generative AI selected by the user and receiving an answer, and display means for sending the received answer to the user terminal. This allows the user to efficiently and accurately collect information even for complex questions, and by integrating and providing information from multiple information sources, a reliable, unified answer can be obtained.

[0997] A "user" is an entity that uses the system to collect information.

[0998] An "input device" is a device that allows a user to input a question, such as a keyboard or a touchscreen device.

[0999] A "question" is a request for information that a user enters into the system.

[1000] The "information processing device" is a device that receives and analyzes a question sent from an input device. Specifically, this corresponds to a server.

[1001] The "analysis means" is a module for extracting important keywords from received questions. Natural language processing technology is often used.

[1002] "Keywords" are important words extracted from questions by analytical means and are used to identify the content of the question.

[1003] The "storage device" is a device that includes a database for searching for the optimal generative artificial intelligence based on the extracted keywords.

[1004] "Generative AI" is an AI model that generates appropriate answers to user questions. For example, a natural language generation model falls into this category.

[1005] The "information integration means" is a module that presents the user with the most appropriate generative artificial intelligence from the search results.

[1006] "Communication means" refers to the method by which a user transmits a question to a generative AI selected by the user and receives a response. This includes network communication.

[1007] The "display means" is a device for displaying the received response on the user terminal, such as a display or monitor.

[1008] An "information gathering device" refers to the entire system that allows users to input questions and receive answers from generative artificial intelligence based on those questions.

[1009] The system of the present invention is an information collection device that allows users to collect information efficiently and accurately. This device allows users to input a question and obtain an answer from a generative artificial intelligence that is best suited to that question. Specifically, it includes the following components:

[1010] 1. Input Devices:

[1011] This is the device that a user uses to enter a question. For example, this could be a PC, tablet, or smartphone. This allows a user to enter a question such as "Tell me about your COVID-19 symptoms."

[1012] 2. Information processing equipment:

[1013] This is a server for receiving and analyzing questions sent from an input device. The server receives user input as an HTTP request and analyzes the content of the question using an analysis means.

[1014] 3. Analysis method:

[1015] This module analyzes questions and extracts important keywords. Specifically, it uses morphological analysis tools and natural language processing technologies (such as Mecab and SpaCy) to extract keywords such as "COVID-19" and "symptoms" from questions.

[1016] 4. Storage:

[1017] This device has a database for searching for the optimal generative AI based on extracted keywords. This database contains the fields of expertise of each generative AI model and the question formats it can handle.

[1018] 5. Information integration methods:

[1019] This module presents users with the most suitable generative artificial intelligence based on search results, displaying options such as "Medical Bot A" and "Medical Bot B" to the user.

[1020] 6. Means of communication:

[1021] This is a communications infrastructure for forwarding questions to a user-selected generative AI model and receiving answers. It uses network communications to send questions to the API endpoint of the selected generative AI model.

[1022] 7. Display means:

[1023] This is a device that displays the received response on the user's device. For example, it displays "Symptoms of COVID-19 include fever, cough, and difficulty breathing" on the user's device display.

[1024] Specific examples

[1025] Example questions:

[1026] The user types and submits the question, "Tell me about your COVID-19 symptoms." This question is processed in the system as follows:

[1027] 1. The user enters a question into the input device and clicks the submit button.

[1028] 2. The device sends the entered question to the server as an HTTP request.

[1029] 3. The server receives the question and uses analytical tools to extract keywords such as "coronavirus" and "symptoms."

[1030] 4. Based on the extracted keywords, the server searches the database in the storage device and lists the most suitable generative AI models (e.g., "Medical Bot A" and "Medical Bot B").

[1031] 5. The server uses information integration methods to display candidate bots to the user.

[1032] 6. The user selects the best bot (e.g., "Medical Bot A").

[1033] 7. The server forwards the question to the selected generative AI model and receives the answer from the generative AI model.

[1034] 8. The server formats the received response and sends it to the user's device.

[1035] 9. The user device displays the final answer on the display.

[1036] In this way, the information collection device of the present invention allows users to obtain information efficiently and accurately, and is capable of integrating information from multiple sources to provide users with the most reliable and unified answers.

[1037] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1038] Step 1:

[1039] The user enters a question into the input device. For example, they enter "Please tell me about the symptoms of COVID-19" and click the send button. The entered question is sent from the device to the server as an HTTP request. The input is in text format, and the output is in HTTP request format.

[1040] Step 2:

[1041] The server receives an HTTP request sent from the terminal. The server parses the request and extracts the question. During this process, the question is saved as text data on the server. The input is in HTTP request format, and the output is the question in text format.

[1042] Step 3:

[1043] The server's analysis means analyzes the received question text and extracts important keywords. Natural language processing technology (for example, Mecab or SpaCy) is used to analyze the question content and obtain keywords such as "COVID-19" and "symptoms." The data processing performed in this step is text analysis, where the input is the text data of the question and the output is a list of keywords.

[1044] Step 4:

[1045] The server searches a database in the storage device based on the extracted keywords. The database stores the areas of expertise and question formats that each generative AI model can handle. For example, an SQL query can be used to search for generative AI models related to "COVID-19" and "symptoms." The input is a list of keywords, and the output is a list of candidate generative AI models.

[1046] Step 5:

[1047] The server's information integration means presents the optimal generative AI model to the user from the search results. To do this, it generates a list of candidate generative AI models (e.g., "Medical Bot A" and "Medical Bot B") in HTML format and sends it to the user's device as a response for display. The input is a list of generative AI models, and the output is an HTML response.

[1048] Step 6:

[1049] The user selects the best model from the list of generative AI models presented. The user clicks the selection button and sends the selection to the server. The input is the model selected from the list of generative AI models, and the output is the selection information sent to the server again in the form of an HTTP request.

[1050] Step 7:

[1051] The server resubmits the question to the generative AI model selected by the user. It uses network communication to send the question to the endpoint of the selected AI model and receive the answer from the model. The input is the user's question and the endpoint information of the selected generative AI model, and the output is the generated answer.

[1052] Step 8:

[1053] The server formats the answer it receives, formatting the answer in a user-friendly format, generating a final HTML response and sending it to the user's device. The input is the answer from the generative AI model, and the output is an HTML response containing the formatted answer.

[1054] Step 9:

[1055] The user device displays the received HTML response. The final answer is displayed on the screen, allowing the user to confirm the answer to the question. For example, "Symptoms of COVID-19 include fever, cough, and difficulty breathing." The input is the HTML response, and the output is the displayed answer.

[1056] (Application example 1)

[1057] 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."

[1058] Currently, product picking work at logistics centers requires a lot of time and effort from employees, and there is a need for a support system to make the work more efficient. Furthermore, there is a lack of optimization of picking routes and accurate product location information, which leads to a high likelihood of inefficiency and errors. A system that solves these issues and streamlines picking work at logistics centers is needed.

[1059] 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.

[1060] In this invention, the server includes a terminal for a user to input a question, a means for receiving the question sent from the terminal, an analysis module for analyzing the received question and extracting keywords, a database for searching for the optimal generative artificial intelligence based on the extracted keywords, a result integration module for presenting the optimal generative artificial intelligence to the user from the search results, a means for transferring the question to the generative artificial intelligence selected by the user and receiving an answer, a means for transmitting the received answer to the user terminal, and a means for calculating product location information and an optimal route and assisting in pickup work. This allows the user to efficiently obtain product location information and an optimal picking route, enabling efficient picking work at the logistics center.

[1061] A "user" is a person who uses the system to input questions and obtain information.

[1062] A "question" is a statement that a user enters about the information they want to know, and is sent to the server for analysis.

[1063] "Terminal" refers to the device used by the user to enter a question, including a smartphone, computer, tablet, etc.

[1064] A "server" is a computer system that receives queries sent from terminals and performs processes such as analysis, database search, and result integration.

[1065] The "analysis module" is software installed on the server, which has the function of analyzing received questions and extracting important keywords.

[1066] "Keywords" are important words and predicates extracted from questions by the analysis module and used in generative artificial intelligence searches.

[1067] "Generative AI" is AI that generates appropriate answers to user questions, and includes bots specialized in various fields.

[1068] A "database" is a data storage device that stores information about generative artificial intelligence and its specialized fields, and is used for searching.

[1069] The "results integration module" is software that has the function of selecting the most appropriate generative artificial intelligence from database search results and presenting it to the user.

[1070] "Means" refers to devices, modules, programs, etc. for executing specific functions or processes.

[1071] "Product location information" is data indicating the specific storage location of the product within the logistics center.

[1072] The "optimal route" indicates the best route for efficiently picking up multiple items.

[1073] "Pickup work support" is an auxiliary function that allows employees to work efficiently based on the location information of the specified product and the optimal route.

[1074] The present invention relates to a system for allowing a user to input a question and obtain the best answer to that question. The system includes a terminal for the user to input the question, a server that receives the question sent from the terminal, an analysis module that analyzes the received question and extracts keywords, a database that searches for the best generative artificial intelligence based on the extracted keywords, a result integration module that presents the best generative artificial intelligence to the user from the search results, and means for transferring the question to the generative artificial intelligence selected by the user and receiving the answer.

[1075] System Embodiments

[1076] Hardware and software used

[1077] Hardware:

[1078] Devices: Smartphones (e.g. iPhone, Android devices), PCs, tablets

[1079] server

[1080] software:

[1081] Generative AI models (e.g., GPT-4)

[1082] Database (e.g. MySQL)

[1083] Mobile app development frameworks (e.g., React Native)

[1084] Data processing and calculation

[1085] 1. Entering and receiving questions:

[1086] Users input questions using devices such as smartphones or computers, which are then sent to the server.

[1087] The server receives the question sent from the terminal and sends it to the analysis module.

[1088] 2. Question Analysis:

[1089] The analysis module analyzes the received questions using natural language processing (NLP) technology and extracts important keywords.

[1090] 3. Generative AI Search:

[1091] The server searches the database for generative AI based on the extracted keywords, taking into account the AI's field of expertise and the types of questions it can answer.

[1092] From the search results, a candidate list of optimal generative artificial intelligence bots is generated and sent to the result integration module.

[1093] 4. Generative AI Presentation and Selection:

[1094] The result synthesis module presents the user with a list of the best generative artificial intelligence bots.

[1095] The user selects the best generative AI bot from the presented options.

[1096] 5. Resend the question and generate an answer:

[1097] The server resends the question to the generative artificial intelligence bot selected by the user.

[1098] The generative artificial intelligence bot generates an answer based on a question from the server and sends the answer back to the server.

[1099] 6. Formatting and displaying answers:

[1100] The server formats the generated response and transmits it to the user terminal.

[1101] The final answer will be displayed on the user's device.

[1102] Specific examples

[1103] For example, in a distribution center, an employee uses a smartphone to input a question such as, "What is the location and best route to pick up items A, B, and C?" This question is processed as follows:

[1104] 1. The server receives the question, and the analysis module extracts the keywords "Product A," "Product B," "Product C," "Location information," and "Optimal route."

[1105] 2. Based on the extracted keywords, the server searches the database for related generative artificial intelligence bots and lists "Pickup Bot A" and "Root Bot B."

[1106] 3. The user selects "Pickup Bot A."

[1107] 4. The server resends the question to the selected bot, which calculates the location information and optimal route for each item and returns an answer.

[1108] 5. The server formats the answer and displays it on the smartphone. The user receives real-time location information (item A: Section B3, item B: Section A2, item C: Section C1) and the optimal route (section A2 → section B3 → section C1).

[1109] Prompt Sentence Examples

[1110] "Picking list: Product A, Product B, Product C. Please tell me the location of each product and the best pickup route."

[1111] This system will improve the efficiency and accuracy of picking operations at logistics centers, reducing the workload.

[1112] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1113] Step 1:

[1114] The user inputs a question using a device. Specifically, they input a question such as "Please tell me the location information and the best route to pick up items A, B, and C" into a smartphone or PC application and click the send button. This input is sent to the server as text data.

[1115] Step 2:

[1116] The server receives the question sent by the user. As a preprocessing step before passing this question data to the analysis module, it checks that the text data has been received and converts it into the required format (e.g., JSON format).

[1117] Step 3:

[1118] The analysis module analyzes the received question and extracts important keywords. Here, natural language processing (NLP) techniques are used to extract keywords such as "product A," "product B," "product C," "location information," and "optimal route." The input for this step is the user's question text data, and the output is a list of extracted keywords.

[1119] Step 4:

[1120] The server searches a database based on the extracted keywords. The database contains the areas of expertise of each generative AI bot and the types of questions it can answer. The search results provide a list of related generative AI bots, such as "Pickup Bot A" and "Root Bot B." The output of this step is a list of generative AI bots.

[1121] Step 5:

[1122] The server presents the user with the optimal generative AI bot from the search results. This presentation is done by displaying a list of candidate bots on the application screen of a smartphone or computer. The user selects "Pickup Bot A." The input for this step is a list of bots, and the output is the bot selected by the user.

[1123] Step 6:

[1124] The server resends the question to the generative AI bot selected by the user. Here, data including the user's question is sent to the selected bot as a request message. The input of this step is the user's question text and information about the selected bot, and the output is the answer data from the generative AI bot.

[1125] Step 7:

[1126] A generative AI bot generates an answer based on a question from the server and sends the answer back to the server. For example, Pickup Bot A sends back location information such as "Product A: Section B3, Product B: Section A2, Product C: Section C1" and data such as "Optimal route: Section A2 → Section B3 → Section C1" to the server. The input to this step is the question data from the server, and the output is the generated answer data.

[1127] Step 8:

[1128] The server formats the answer received from the generative AI bot and sends it to the user's terminal. Here, the answer data is converted into a format that is easy for the user to understand and presented through the application. The input of this step is the answer data from the generative AI bot, and the output is the formatted answer data.

[1129] Step 9:

[1130] The user device receives the formatted answer sent from the server and displays it on the screen. For example, location information such as "Product A: Section B3, Product B: Section A2, Product C: Section C1" and specific information such as "Optimal route: Section A2 → Section B3 → Section C1" are displayed. The input of this step is the formatted answer data, and the output is the screen information displayed to the user.

[1131] 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.

[1132] The present invention adds an emotion recognition function to a system that allows users to efficiently and accurately collect information, and provides responses according to the user's emotional state. This system is realized by a configuration including a user, a terminal, a server, and an emotion recognition engine. Specific embodiments of the system and their operation are described below.

[1133] System Overview

[1134] This system analyzes user questions, provides the optimal generative AI for the question, and recognizes the user's emotions to adjust the response. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a database that searches for the optimal generative AI, a result integration module that integrates and presents the results, and an emotion engine that recognizes emotions.

[1135] How it works

[1136] Enter and submit your question

[1137] The user uses the device to input a question. For example, they enter a question such as "Please tell me about your symptoms of COVID-19" into the portal site's input form and click the submit button. The input question is sent from the device to the server.

[1138] Receiving and parsing questions

[1139] The server receives the question sent by the user. The received question is analyzed by the analysis module, and important keywords are extracted. For example, keywords such as "COVID-19" and "symptoms" are extracted.

[1140] Searching for the best generative AI bot

[1141] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. The database contains the areas of expertise and question types that each generative AI bot can answer. From the search results, a list of suitable candidate generative AI bots is generated.

[1142] Emotion recognition

[1143] The server uses an emotion engine to recognize the user's emotions, for example, determining whether the user is feeling stressed from the input text.

[1144] Present and select a bot

[1145] The server displays a list of generative AI bots that are optimal for the user. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user then selects the optimal generative AI bot from the presented options.

[1146] Resend your question and get an answer

[1147] The server resends the question to the generative AI bot selected by the user, which generates an answer based on the question from the server and sends the answer back to the server.

[1148] Adjusting responses based on emotions

[1149] The server adjusts the content and expression of the generated response based on the recognition results of the emotion engine, for example, adding more kind language and detailed explanations if the user is feeling stressed.

[1150] Displaying the results

[1151] The server formats the answer received from the generative AI bot and sends it to the user's device. The final answer is displayed on the user's device. For example, it may show information such as "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[1152] Specific examples

[1153] Example 1: Asking about COVID-19 symptoms

[1154] 1. The user types in the question, "Tell me about your COVID-19 symptoms" and submits it.

[1155] 2. The server receives the question and extracts the keywords "coronavirus" and "symptoms."

[1156] 3. The server searches for the most suitable generative artificial intelligence bot and lists "Medical Bot A" and "Medical Bot B."

[1157] 4. The server uses an emotion engine to analyze the user's emotions, for example, to detect whether the user is feeling anxious or stressed. If the user is feeling anxious, the server is configured to add kind words and detailed explanations.

[1158] 5. The user selects "Medical Bot A."

[1159] 6. The server sends a question to the selected bot and retrieves the answer.

[1160] 7. The server adjusts and formats the obtained answer based on the emotion recognition results.

[1161] 8. The user's device will display the message, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, please consult a medical professional immediately."

[1162] In this way, the system allows users to efficiently collect information and receive responses tailored to their emotional state, improving the user experience and providing more appropriate assistance.

[1163] The processing flow will be explained below.

[1164] Step 1:

[1165] A user accesses the portal site and enters a question into the question input form.

[1166] Specific actions: The user opens the portal site in a browser, enters "Please tell me about your coronavirus symptoms" in the text box, and clicks the submit button.

[1167] Step 2:

[1168] The terminal sends a question to the server.

[1169] Specific operation: The question is sent from the terminal to the server as an HTTP request.

[1170] Step 3:

[1171] The server receives the user's query.

[1172] Specific operation: The server receives an HTTP request and passes the contents to the analysis module.

[1173] Step 4:

[1174] A question analysis module on the server analyzes the question.

[1175] What it does: It uses a natural language processing (NLP) engine to extract keywords such as "coronavirus" and "symptoms."

[1176] Step 5:

[1177] The server uses an emotion engine to recognize the user's emotions.

[1178] Specific operation: The emotion engine analyzes the user's emotional state (e.g., anxiety, stress) from the input text.

[1179] Step 6:

[1180] The server searches the generative artificial intelligence database.

[1181] Specific operation: Executes an SQL query based on the extracted keywords to search for medical-related generative artificial intelligence bots.

[1182] Step 7:

[1183] The server lists the most suitable generative artificial intelligence bots from the search results.

[1184] Specific operation: The found generative artificial intelligence bots (e.g., "Medical Bot A" and "Medical Bot B") are formatted into a list and the data is prepared for presentation to the user.

[1185] Step 8:

[1186] The server presents the user with a list of generative artificial intelligence bots.

[1187] Specific operation: Sends the result in HTML or JSON format to the user's device and displays suggestions in the browser.

[1188] Step 9:

[1189] The user selects the best bot from the generative artificial intelligence bots presented.

[1190] Specific operation: The user clicks the button of the desired generative artificial intelligence bot from the list.

[1191] Step 10:

[1192] The terminal transmits the selection information of the generative artificial intelligence bot selected to the server.

[1193] Specific operation: Send an HTTP request again to convey the selected information to the server.

[1194] Step 11:

[1195] The server resends the question to the selected generative artificial intelligence bot.

[1196] What it does: Uses an API call to forward the user's question to a generative AI bot.

[1197] Step 12:

[1198] The server receives the answer from the generative artificial intelligence bot.

[1199] Specific operation: Receives answer data from the generative AI bot as an API response.

[1200] Step 13:

[1201] The server adjusts the content and expression of the response based on the recognized emotion.

[1202] Specific actions: For example, if a user is feeling anxious, add kind words or detailed explanations to the answer.

[1203] Step 14:

[1204] The server formats the adjusted response.

[1205] Specific operation: The adjusted response data is converted into HTML or JSON format and sent to the user's device.

[1206] Step 15:

[1207] The user's device will display the final answer on the screen.

[1208] What it does: It displays the data sent via JavaScript in the browser, informing the user that "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, please seek medical help immediately."

[1209] Example 2

[1210] 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."

[1211] Conventional information gathering systems have difficulty in quickly providing optimal answers to user questions. Furthermore, they are unable to respond according to the user's emotional state, making it difficult to provide sufficient support, especially to users who are feeling stressed or anxious.

[1212] 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.

[1213] In this invention, the server includes a terminal for a user to input a question, a computer for receiving the question sent from the terminal, an analysis module for analyzing the received question and extracting keywords, a storage device for searching for the optimal generative AI based on the extracted keywords, a result integration module for presenting the optimal generative AI to the user from the search results, means for transferring the question to the generative AI selected by the user and receiving an answer, communication means for transmitting the received answer to the user terminal, and an emotion recognition engine for recognizing the user's emotion and adjusting the answer content based on that emotion. This makes it possible to quickly provide the optimal answer to the user's question and also to respond appropriately according to the user's emotional state.

[1214] A "terminal" is a device through which a user inputs a question and sends it to a server.

[1215] The "computer" is a device that receives questions sent by users, analyzes them, and forwards them to the generative artificial intelligence.

[1216] An "analysis module" is software or hardware for analyzing received questions and extracting important keywords.

[1217] A "storage device" is a storage medium such as a database for searching for the optimal generative artificial intelligence based on extracted keywords.

[1218] A "result integration module" is software or hardware for presenting the user with the most appropriate generative artificial intelligence from search results.

[1219] "Communication means" refers to the network interface and communication protocol used to transmit the received response to the user terminal.

[1220] An "emotion recognition engine" is software or hardware that recognizes a user's emotions and adjusts the content of responses based on those emotions.

[1221] "Generative artificial intelligence" refers to algorithms and models that generate answers to user questions.

[1222] "Keywords" are important words or phrases extracted from a user's question that represent the content of that question.

[1223] The present invention adds an emotion recognition function to a system that allows users to collect information efficiently and accurately, and provides responses according to the user's emotional state. This system is realized by a configuration including a user, a terminal, a server, and an emotion recognition engine.

[1224] System Overview

[1225] This system analyzes user questions, provides the optimal generative AI for the question, and recognizes the user's emotions and adjusts the response accordingly. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a storage device that searches for the optimal generative AI, a result integration module that integrates and presents the results, and an emotion engine that recognizes emotions.

[1226] Detailed explanation of operation

[1227] Enter and submit your question

[1228] The user uses the device to enter a question. The user enters "Please tell me about your COVID-19 symptoms" into the portal site's input form and clicks the submit button. The entered question is sent from the device to the server. Specifically, it is sent as an HTTP request.

[1229] Receiving and parsing questions

[1230] The server receives the question sent by the user. The server analyzes the received HTTP request and extracts the question content. The analysis module analyzes the question using natural language processing technology and extracts important keywords. For example, keywords such as "coronavirus" and "symptoms" are extracted. Natural language processing libraries such as NLTK and spaCy are used here.

[1231] Searching for the best generative AI bot

[1232] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. Specifically, it executes an SQL query to list appropriate generative AI bots. The storage device stores the specialty of each generative AI bot (e.g., medicine, education, entertainment, etc.) and the question formats it can answer. For example, "Medical Bot A" and "Medical Bot B" are listed as candidates.

[1233] Emotion recognition

[1234] The server uses an emotion engine to recognize the user's emotions. Specifically, it calls emotion recognition APIs, such as Google Cloud Natural Language API or IBM Watson's emotion analysis service, to extract emotions from the input text. This identifies whether the user is feeling stressed or anxious.

[1235] Present and select a bot

[1236] The server displays a list of generative AI bots that are optimal for the user. Specifically, the list is displayed to the user using HTML and CSS. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user selects the appropriate generative AI bot from the presented options and clicks the select button.

[1237] Resend your question and get an answer

[1238] The server resends the question to the generative AI bot selected by the user. Specifically, it resends the question by sending an API request. The generative AI bot generates an answer based on the question and sends the answer back to the server as an API response. For example, using OpenAI's generative AI model, the answer "Symptoms of COVID-19 include fever, cough, and difficulty breathing" can be obtained.

[1239] Adjusting responses based on emotions

[1240] The server adjusts the content and expressions of the generated answers based on the recognition results of the emotion engine. Specifically, for users who are feeling stressed, it adds kind language and detailed explanations. For example, it adds phrases such as, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[1241] Displaying the results

[1242] The server formats the answer received from the generative AI bot and sends it to the user's device. Specifically, the answer is formatted in HTML and sent as an HTTP response. The final answer is displayed on the user's device. For example, the following information may be displayed: "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[1243] Specific examples

[1244] Example 1: Asking about COVID-19 symptoms

[1245] 1. The user types in the question, "Tell me about your COVID-19 symptoms" and submits it.

[1246] 2. The server receives the question and extracts the keywords "coronavirus" and "symptoms."

[1247] 3. The server searches for the most suitable generative artificial intelligence bot and lists "Medical Bot A" and "Medical Bot B."

[1248] 4. The server uses an emotion engine to analyze the user's emotions, for example, to detect whether the user is feeling anxious or stressed. If the user is feeling anxious, the server is configured to add kind words and detailed explanations.

[1249] 5. The user selects "Medical Bot A."

[1250] 6. The server sends a question to the selected bot and retrieves the answer.

[1251] 7. The server adjusts and formats the obtained answer based on the emotion recognition results.

[1252] 8. The user's device will display the message, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical professional immediately."

[1253] In this way, the system allows users to efficiently collect information and receive responses tailored to their emotional state, improving the user experience and providing more appropriate assistance.

[1254] Prompt Sentence Examples

[1255] "Please tell me what the symptoms of COVID-19 are. I'm very worried."

[1256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1257] markdown

[1258] Step 1:

[1259] The user uses the device to enter a question. The user enters "Please tell me about your COVID-19 symptoms" into the portal site's input form and clicks the submit button. The entered question is sent from the device to the server. Specifically, it is sent as an HTTP request.

[1260] Input: User-provided question text

[1261] Output: HTTP request to the server

[1262] Step 2:

[1263] The server receives the question sent by the user. The server analyzes the received HTTP request and extracts the question content. The analysis module analyzes the question using natural language processing technology and extracts important keywords. For example, keywords such as "coronavirus" and "symptoms" are extracted. Natural language processing libraries such as NLTK and spaCy are used here.

[1264] Input: Question text included in HTTP request

[1265] Output: Keywords such as "COVID-19" and "symptoms"

[1266] Step 3:

[1267] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. Specifically, it executes an SQL query to list appropriate generative AI bots. The storage device stores the specialty of each generative AI bot (e.g., medicine, education, entertainment, etc.) and the question formats it can answer. For example, "Medical Bot A" and "Medical Bot B" are listed as candidates.

[1268] Input: Extracted keywords

[1269] Output: A list of optimal generative AI bots (e.g., "Medical Bot A" and "Medical Bot B")

[1270] Step 4:

[1271] The server uses an emotion engine to recognize the user's emotions. Specifically, it calls emotion recognition APIs, such as Google Cloud Natural Language API or IBM Watson's emotion analysis service, to extract emotions from the input text. This identifies whether the user is feeling stressed or anxious.

[1272] Input: Question text

[1273] Output: User's emotional state (e.g., stress, anxiety)

[1274] Step 5:

[1275] The server displays a list of generative AI bots that are optimal for the user. Specifically, the list is displayed to the user using HTML and CSS. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user selects the appropriate generative AI bot from the presented options and clicks the select button.

[1276] Input: A list of the best generative AI bots

[1277] Output: User selects bot

[1278] Step 6:

[1279] The server resends the question to the generative AI bot selected by the user. Specifically, it resends the question by sending an API request. The generative AI bot generates an answer based on the question and sends the answer back to the server as an API response. For example, using OpenAI's generative AI model, the answer "Symptoms of COVID-19 include fever, cough, and difficulty breathing" can be obtained.

[1280] Input: User-selected generative AI bot, question text

[1281] Output: Answer from a generative AI bot

[1282] Step 7:

[1283] The server adjusts the content and expressions of the generated answers based on the recognition results of the emotion engine. Specifically, for users who are feeling stressed, it adds kind language and detailed explanations. For example, it adds phrases such as, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[1284] Input: Answers from a generative AI bot, user's emotional state

[1285] Output: Adjusted answer

[1286] Step 8:

[1287] The server formats the answer received from the generative AI bot and sends it to the user's device. Specifically, the answer is formatted in HTML and sent as an HTTP response. The final answer is displayed on the user's device. For example, the following information may be displayed: "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[1288] Input: Adjusted answer content

[1289] Output: The final answer displayed on the user's terminal

[1290] (Application example 2)

[1291] 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."

[1292] In conventional information gathering systems, response systems have been proposed that can respond quickly and appropriately to user questions, but they lack the ability to adjust responses according to the user's emotional state, which prevents them from fully improving the user experience. Furthermore, in security services, it is necessary to provide a higher level of safety by grasping the emotional state of people in the monitored area in real time and responding according to that emotion, but the lack of such a system is an issue.

[1293] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1294] In this invention, the server includes a terminal for a user to input a question, means for receiving the question sent from the terminal, an analysis module for analyzing the received question and extracting keywords, a database for searching for an optimal generative artificial intelligence based on the extracted keywords, a result integration module for presenting the optimal generative artificial intelligence to the user from the search results, means for transferring the question to the generative artificial intelligence selected by the user and receiving a response, means for transmitting the received response to the user terminal, an emotion recognition engine for analyzing and recognizing the emotional states of people in the monitored area, means for selecting and presenting the optimal generative artificial intelligence according to the emotions identified by the emotion recognition engine, and means for adjusting the response generated by the optimal generative artificial intelligence based on the emotion recognition data, thereby providing a response according to the user's emotional state and enabling improved security services.

[1295] A "terminal for users to input questions" is an electronic device used by users to input questions in the form of text, voice input, or the like.

[1296] The "server for receiving questions sent from a terminal" is a network-connected computer system for receiving questions sent by a user from a terminal and for subsequent processing.

[1297] The "analysis module for analyzing received questions and extracting keywords" is a software component that analyzes the content of questions entered by users and extracts important keywords and phrases.

[1298] A "database for searching for the optimal generative artificial intelligence based on extracted keywords" is a database that stores information for searching for the optimal generative artificial intelligence based on keywords extracted by the analysis module.

[1299] The "result integration module for presenting the user with the optimal generative artificial intelligence from the search results" is a software component for integrating the results of a database search and presenting the user with the optimal generative artificial intelligence candidates.

[1300] "Means for transferring a question to a generative artificial intelligence selected by a user and receiving a response" refers to means for sending a user's question to a generative artificial intelligence selected by a user and receiving a response thereto.

[1301] "Means for transmitting the received answer to the user terminal" refers to means for transmitting the answer received from the generative artificial intelligence to the user terminal.

[1302] The "emotion recognition engine for analyzing and recognizing the emotional state of people within a monitored area" is a software component that analyzes and identifies emotions from the facial expressions, voices, etc. of people within a monitored area.

[1303] "Means for selecting and presenting the most appropriate generative artificial intelligence in accordance with the emotions identified by the emotion recognition engine" refers to means for selecting the most appropriate generative artificial intelligence based on the emotion data analyzed by the emotion recognition engine and presenting the result to the user.

[1304] "Means for adjusting responses generated by optimal generative artificial intelligence based on emotion recognition data" refers to means for adjusting responses generated by generative artificial intelligence according to the emotional state of the user.

[1305] This invention adds emotion recognition functionality to a system that allows users to collect information efficiently and accurately, and provides responses that correspond to the user's emotional state. This system is realized by comprising a user terminal, a server, an analysis module, a generative AI database, a result integration module, and an emotion recognition engine.

[1306] System Overview

[1307] This system analyzes a user's question, provides the most suitable generative artificial intelligence for that question, and recognizes the user's emotions and adjusts the response accordingly. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a database that searches for the most suitable generative artificial intelligence, a result integration module that integrates and presents the results, and an emotion recognition engine that recognizes emotions.

[1308] How it works

[1309] Enter and submit your question

[1310] The user inputs a question using the device. For example, they input a question such as "Please tell me about the symptoms of COVID-19" into the device and send it. The input question is sent from the device to the server.

[1311] Receiving and parsing questions

[1312] The server receives the question sent by the user. The received question is analyzed by the analysis module, and important keywords are extracted. For example, keywords such as "COVID-19" and "symptoms" are extracted.

[1313] Searching for the best generative artificial intelligence

[1314] The server searches a database of generative AI based on the extracted keywords. The database contains the fields of expertise and question formats that each generative AI can handle. The search results then produce a list of suitable generative AIs.

[1315] Recognizing and Responding to Emotions

[1316] The server uses an emotion recognition engine to recognize the user's emotions, for example, to determine whether the user is stressed from the input text. The emotion recognition engine analyzes the facial expressions and tone of voice of people in the monitored area.

[1317] Program processing

[1318] The server performs its operations using, among other things, the following software and hardware:

[1319] Hardware: smart glasses, smartphones, cameras

[1320] software:

[1321] EmotionRecognition Module: Face and emotion recognition engine using OpenCV

[1322] AIModelExecutor module: Generative AI model selection and execution engine (e.g., GPT-4, BERT)

[1323] The server acquires real-time video from the camera and analyzes the emotional data using the EmotionRecognition module. The emotion recognition engine identifies people's emotional states based on the analysis results. The AIModelExecutor module then uses this emotional data to select the optimal generative AI and generate a response.

[1324] Specific examples

[1325] Example 1: Security Monitoring Assistant

[1326] Security guards and facility managers use smart glasses or smartphones to monitor the facility and check the emotional state of people in real time. At this time, an emotion recognition engine analyzes the emotional state (e.g., anxiety, anger, stress) of the people being monitored and selects and presents an appropriate response from an optimal generative artificial intelligence database.

[1327] Example prompt sentence:

[1328] "We have noticed an individual in our surveillance area who appears to be unsafe. Please advise our security personnel on how to respond."

[1329] In this way, the present invention provides a response that is tailored to the user's emotional state, thereby improving the user experience and providing improved security services.

[1330] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1331] Step 1:

[1332] A user uses a terminal to input a question. For example, they input "Please tell me about the symptoms of COVID-19" and send it. The input is the text data of the user's question, and the output is the input question being sent from the terminal to the server.

[1333] Step 2:

[1334] The server receives the question sent by the user. The input is the question text data sent from the terminal, and the output is the received data passed to the analysis module.

[1335] Step 3:

[1336] The analysis module analyzes the received question and extracts important keywords. The input is the received question text data, and the output is the analysis results, which are important keywords (e.g., "COVID-19" and "symptoms").

[1337] Step 4:

[1338] The server searches the database for the optimal generative AI based on the extracted important keywords. The input is the important keywords, and the output is a list of candidate generative AIs (e.g., "Medical Bot A" and "Medical Bot B").

[1339] Step 5:

[1340] The server uses an emotion recognition engine to analyze and identify the user's emotion. The input is the text data of the user's question and facial expression recognition data, and the output is the user's emotional state (e.g., stress, anxiety).

[1341] Step 6:

[1342] The server presents the user with a list of optimal generative AIs, and the user selects one. The input is a list of generative AI candidates, and the output is the generative AI selected by the user (e.g., "Medical Bot A").

[1343] Step 7:

[1344] The server forwards the question to the generative artificial intelligence selected by the user and receives an answer from the generative artificial intelligence. The input is the user's question and the identification information of the selected generative artificial intelligence, and the output is the answer data from the generative artificial intelligence (e.g., "Symptoms of COVID-19 include fever, cough, and difficulty breathing").

[1345] Step 8:

[1346] The server adjusts the generated answer content based on the results of the emotion recognition engine. The input is the answer data and emotion recognition results from the generative AI, and the output is the adjusted answer data (e.g., "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately.").

[1347] Step 9:

[1348] The server sends the adjusted answer to the user terminal, which the user confirms. The input is the adjusted answer data, and the output is the final answer information displayed on the user terminal.

[1349] In this way, the present invention provides appropriate information according to the user's emotional state.

[1350] 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.

[1351] 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.

[1352] 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.

[1353] [Fourth embodiment]

[1354] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1355] 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.

[1356] 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).

[1357] 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.

[1358] 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.

[1359] 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).

[1360] 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.

[1361] 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.

[1362] 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.

[1363] 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.

[1364] 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.

[1365] 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.

[1366] 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."

[1367] The present invention is a system for users to efficiently and accurately gather information, utilizing generative artificial intelligence as an optimal alternative to traditional internet search methods. This system is realized in a configuration including a user, a terminal, and a server. Specific embodiments of the system and their operation are described below.

[1368] System Overview

[1369] This system analyzes user questions and provides the optimal generative AI for those questions. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a database that searches for the optimal generative AI, and a result integration module that integrates and presents the results.

[1370] How it works

[1371] Enter and submit your question

[1372] The user uses the device to input a question. For example, they enter a question such as "Please tell me about your symptoms of COVID-19" into the portal site's input form and click the submit button. The input question is sent from the device to the server.

[1373] Receiving and parsing questions

[1374] The server receives the question sent by the user. The received question is analyzed by the analysis module, and important keywords are extracted. For example, keywords such as "COVID-19" and "symptoms" are extracted.

[1375] Searching for the best generative AI bot

[1376] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. The database contains the areas of expertise and question types that each generative AI bot can answer. From the search results, a list of suitable candidate generative AI bots is generated.

[1377] Present and select a bot

[1378] The server displays a list of generative AI bots that are optimal for the user. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user then selects the optimal generative AI bot from the presented options.

[1379] Resend your question and get an answer

[1380] The server resends the question to the generative AI bot selected by the user, which generates an answer based on the question from the server and sends the answer back to the server.

[1381] Displaying the results

[1382] The server formats the answer received from the generative AI bot and sends it to the user's device. The final answer is displayed on the user's device. For example, it may show information such as "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[1383] Specific examples

[1384] Example 1: Asking about COVID-19 symptoms

[1385] 1. The user types in the question, "Tell me about your COVID-19 symptoms" and submits it.

[1386] 2. The server receives the question and extracts the keywords "coronavirus" and "symptoms."

[1387] 3. The server searches for the most suitable generative artificial intelligence bot and lists "Medical Bot A" and "Medical Bot B."

[1388] 4. The user selects "Medical Bot A."

[1389] 5. The server sends a question to the selected bot and retrieves the answer.

[1390] 6. The server formats the answer and sends it to the user's device.

[1391] 7. The user's device will display the message, "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[1392] In this way, this system allows users to efficiently collect information and easily find the optimal AI bot. Furthermore, by integrating and presenting information from multiple AI bots, it is possible to further improve user convenience.

[1393] The processing flow will be explained below.

[1394] Step 1:

[1395] A user accesses the portal site and enters a question into the question input form.

[1396] Specific behavior: A user accesses the portal site using a browser, enters "Tell me about your COVID-19 symptoms" in the text box, and clicks the submit button.

[1397] Step 2:

[1398] The terminal sends a question to the server.

[1399] What happens: The browser sends the user's input to the server as an HTTP request.

[1400] Step 3:

[1401] The server receives the user's query.

[1402] Specific operation: An HTTP request arrives at the server, and the server retrieves the content.

[1403] Step 4:

[1404] A question analysis module on the server analyzes the question.

[1405] What it does: It uses a natural language processing (NLP) engine to extract keywords such as "coronavirus" and "symptoms."

[1406] Step 5:

[1407] The server searches the generative artificial intelligence database.

[1408] Specific operation: Execute SQL queries to find relevant generative AI bots from the database. For example, medical-related bots "Medical Bot A" and "Medical Bot B" are found.

[1409] Step 6:

[1410] The server lists the most suitable generative artificial intelligence bots from the search results.

[1411] Specific behavior: Formats the found generative AI bots into a list and prepares the data to present to the user.

[1412] Step 7:

[1413] The server presents the user with a list of generative artificial intelligence bots.

[1414] Specific operation: The generated list is sent to the user's terminal in HTML or JSON format and displayed in the browser.

[1415] Step 8:

[1416] The user selects the best bot from the generative artificial intelligence bots presented.

[1417] Specific operation: The user clicks the button of the desired generative artificial intelligence bot from the displayed list.

[1418] Step 9:

[1419] The terminal transmits the selection information of the generative artificial intelligence bot selected to the server.

[1420] Specific operation: Send an HTTP request again to convey the selected information to the server.

[1421] Step 10:

[1422] The server resends the question to the selected generative artificial intelligence bot.

[1423] Specific operation: Again using an API call, the question is forwarded to the selected generative AI bot.

[1424] Step 11:

[1425] The server receives the answer from the generative artificial intelligence bot.

[1426] Specific operation: Receives answer data from the generative AI bot as an API response.

[1427] Step 12:

[1428] Formats the response received by the server.

[1429] Specific operation: Converts the received response data into HTML or JSON format for presentation to the user.

[1430] Step 13:

[1431] The server sends the formatted response to the user terminal.

[1432] Specific operation: The generated data is sent to the user's terminal as an HTTP response.

[1433] Step 14:

[1434] The user's device will display the final answer on the screen.

[1435] What it does: The browser processes the data and displays information to the user, such as "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[1436] Example 1

[1437] 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."

[1438] Conventional Internet search methods can make it difficult for users to gather information efficiently and accurately. In particular, they face problems such as not being able to obtain appropriate information for complex questions and difficulty in finding reliable sources. Furthermore, users must integrate information obtained from multiple sources themselves, which is time-consuming.

[1439] 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.

[1440] In this invention, the server includes an input device for a user to input a question, an information processing device for receiving the question sent from the input device, analysis means for analyzing the received question and extracting keywords, a storage device for searching for the optimal generative AI based on the extracted keywords, information integration means for presenting the optimal generative AI to the user from the search results, communication means for transferring the question to the generative AI selected by the user and receiving an answer, and display means for sending the received answer to the user terminal. This allows the user to efficiently and accurately collect information even for complex questions, and by integrating and providing information from multiple information sources, a reliable, unified answer can be obtained.

[1441] A "user" is an entity that uses the system to collect information.

[1442] An "input device" is a device that allows a user to input a question, such as a keyboard or a touchscreen device.

[1443] A "question" is a request for information that a user enters into the system.

[1444] The "information processing device" is a device that receives and analyzes a question sent from an input device. Specifically, this corresponds to a server.

[1445] The "analysis means" is a module for extracting important keywords from received questions. Natural language processing technology is often used.

[1446] "Keywords" are important words extracted from questions by analytical means and are used to identify the content of the question.

[1447] The "storage device" is a device that includes a database for searching for the optimal generative artificial intelligence based on the extracted keywords.

[1448] "Generative AI" is an AI model that generates appropriate answers to user questions. For example, a natural language generation model falls into this category.

[1449] The "information integration means" is a module that presents the user with the most appropriate generative artificial intelligence from the search results.

[1450] "Communication means" refers to the method by which a user transmits a question to a generative AI selected by the user and receives a response. This includes network communication.

[1451] The "display means" is a device for displaying the received response on the user terminal, such as a display or monitor.

[1452] An "information gathering device" refers to the entire system that allows users to input questions and receive answers from generative artificial intelligence based on those questions.

[1453] The system of the present invention is an information collection device that allows users to collect information efficiently and accurately. This device allows users to input a question and obtain an answer from a generative artificial intelligence that is best suited to that question. Specifically, it includes the following components:

[1454] 1. Input Devices:

[1455] This is the device that a user uses to enter a question. For example, this could be a PC, tablet, or smartphone. This allows a user to enter a question such as "Tell me about your COVID-19 symptoms."

[1456] 2. Information processing equipment:

[1457] This is a server for receiving and analyzing questions sent from an input device. The server receives user input as an HTTP request and analyzes the content of the question using an analysis means.

[1458] 3. Analysis method:

[1459] This module analyzes questions and extracts important keywords. Specifically, it uses morphological analysis tools and natural language processing technologies (such as Mecab and SpaCy) to extract keywords such as "COVID-19" and "symptoms" from questions.

[1460] 4. Storage:

[1461] This device has a database for searching for the optimal generative AI based on extracted keywords. This database contains the fields of expertise of each generative AI model and the question formats it can handle.

[1462] 5. Information integration methods:

[1463] This module presents users with the most suitable generative artificial intelligence based on search results, displaying options such as "Medical Bot A" and "Medical Bot B" to the user.

[1464] 6. Means of communication:

[1465] This is a communications infrastructure for forwarding questions to a user-selected generative AI model and receiving answers. It uses network communications to send questions to the API endpoint of the selected generative AI model.

[1466] 7. Display means:

[1467] This is a device that displays the received response on the user's device. For example, it displays "Symptoms of COVID-19 include fever, cough, and difficulty breathing" on the user's device display.

[1468] Specific examples

[1469] Example questions:

[1470] The user types and submits the question, "Tell me about your COVID-19 symptoms." This question is processed in the system as follows:

[1471] 1. The user enters a question into the input device and clicks the submit button.

[1472] 2. The device sends the entered question to the server as an HTTP request.

[1473] 3. The server receives the question and uses analytical tools to extract keywords such as "coronavirus" and "symptoms."

[1474] 4. Based on the extracted keywords, the server searches the database in the storage device and lists the most suitable generative AI models (e.g., "Medical Bot A" and "Medical Bot B").

[1475] 5. The server uses information integration methods to display candidate bots to the user.

[1476] 6. The user selects the best bot (e.g., "Medical Bot A").

[1477] 7. The server forwards the question to the selected generative AI model and receives the answer from the generative AI model.

[1478] 8. The server formats the received response and sends it to the user's device.

[1479] 9. The user device displays the final answer on the display.

[1480] In this way, the information collection device of the present invention allows users to obtain information efficiently and accurately, and is capable of integrating information from multiple sources to provide users with the most reliable and unified answers.

[1481] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1482] Step 1:

[1483] The user enters a question into the input device. For example, they enter "Please tell me about the symptoms of COVID-19" and click the send button. The entered question is sent from the device to the server as an HTTP request. The input is in text format, and the output is in HTTP request format.

[1484] Step 2:

[1485] The server receives an HTTP request sent from the terminal. The server parses the request and extracts the question. During this process, the question is saved as text data on the server. The input is in HTTP request format, and the output is the question in text format.

[1486] Step 3:

[1487] The server's analysis means analyzes the received question text and extracts important keywords. Natural language processing technology (for example, Mecab or SpaCy) is used to analyze the question content and obtain keywords such as "COVID-19" and "symptoms." The data processing performed in this step is text analysis, where the input is the text data of the question and the output is a list of keywords.

[1488] Step 4:

[1489] The server searches a database in the storage device based on the extracted keywords. The database stores the areas of expertise and question formats that each generative AI model can handle. For example, an SQL query can be used to search for generative AI models related to "COVID-19" and "symptoms." The input is a list of keywords, and the output is a list of candidate generative AI models.

[1490] Step 5:

[1491] The server's information integration means presents the optimal generative AI model to the user from the search results. To do this, it generates a list of candidate generative AI models (e.g., "Medical Bot A" and "Medical Bot B") in HTML format and sends it to the user's device as a response for display. The input is a list of generative AI models, and the output is an HTML response.

[1492] Step 6:

[1493] The user selects the best model from the list of generative AI models presented. The user clicks the selection button and sends the selection to the server. The input is the model selected from the list of generative AI models, and the output is the selection information sent to the server again in the form of an HTTP request.

[1494] Step 7:

[1495] The server resubmits the question to the generative AI model selected by the user. It uses network communication to send the question to the endpoint of the selected AI model and receive the answer from the model. The input is the user's question and the endpoint information of the selected generative AI model, and the output is the generated answer.

[1496] Step 8:

[1497] The server formats the answer it receives, formatting the answer in a user-friendly format, generating a final HTML response and sending it to the user's device. The input is the answer from the generative AI model, and the output is an HTML response containing the formatted answer.

[1498] Step 9:

[1499] The user device displays the received HTML response. The final answer is displayed on the screen, allowing the user to confirm the answer to the question. For example, "Symptoms of COVID-19 include fever, cough, and difficulty breathing." The input is the HTML response, and the output is the displayed answer.

[1500] (Application example 1)

[1501] 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."

[1502] Currently, product picking work at logistics centers requires a lot of time and effort from employees, and there is a need for a support system to make the work more efficient. Furthermore, there is a lack of optimization of picking routes and accurate product location information, which leads to a high likelihood of inefficiency and errors. A system that solves these issues and streamlines picking work at logistics centers is needed.

[1503] 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.

[1504] In this invention, the server includes a terminal for a user to input a question, a means for receiving the question sent from the terminal, an analysis module for analyzing the received question and extracting keywords, a database for searching for the optimal generative artificial intelligence based on the extracted keywords, a result integration module for presenting the optimal generative artificial intelligence to the user from the search results, a means for transferring the question to the generative artificial intelligence selected by the user and receiving an answer, a means for transmitting the received answer to the user terminal, and a means for calculating product location information and an optimal route and assisting in pickup work. This allows the user to efficiently obtain product location information and an optimal picking route, enabling efficient picking work at the logistics center.

[1505] A "user" is a person who uses the system to input questions and obtain information.

[1506] A "question" is a statement that a user enters about the information they want to know, and is sent to the server for analysis.

[1507] "Terminal" refers to the device used by the user to enter a question, including a smartphone, computer, tablet, etc.

[1508] A "server" is a computer system that receives queries sent from terminals and performs processes such as analysis, database search, and result integration.

[1509] The "analysis module" is software installed on the server, which has the function of analyzing received questions and extracting important keywords.

[1510] "Keywords" are important words and predicates extracted from questions by the analysis module and used in generative artificial intelligence searches.

[1511] "Generative AI" is AI that generates appropriate answers to user questions, and includes bots specialized in various fields.

[1512] A "database" is a data storage device that stores information about generative artificial intelligence and its specialized fields, and is used for searching.

[1513] The "results integration module" is software that has the function of selecting the most appropriate generative artificial intelligence from database search results and presenting it to the user.

[1514] "Means" refers to devices, modules, programs, etc. for executing specific functions or processes.

[1515] "Product location information" is data indicating the specific storage location of the product within the logistics center.

[1516] The "optimal route" indicates the best route for efficiently picking up multiple items.

[1517] "Pickup work support" is an auxiliary function that allows employees to work efficiently based on the location information of the specified product and the optimal route.

[1518] The present invention relates to a system for allowing a user to input a question and obtain the best answer to that question. The system includes a terminal for the user to input the question, a server that receives the question sent from the terminal, an analysis module that analyzes the received question and extracts keywords, a database that searches for the best generative artificial intelligence based on the extracted keywords, a result integration module that presents the best generative artificial intelligence to the user from the search results, and means for transferring the question to the generative artificial intelligence selected by the user and receiving the answer.

[1519] System Embodiments

[1520] Hardware and software used

[1521] Hardware:

[1522] Devices: Smartphones (e.g. iPhone, Android devices), PCs, tablets

[1523] server

[1524] software:

[1525] Generative AI models (e.g., GPT-4)

[1526] Database (e.g. MySQL)

[1527] Mobile app development frameworks (e.g., React Native)

[1528] Data processing and calculation

[1529] 1. Entering and receiving questions:

[1530] Users input questions using devices such as smartphones or computers, which are then sent to the server.

[1531] The server receives the question sent from the terminal and sends it to the analysis module.

[1532] 2. Question Analysis:

[1533] The analysis module analyzes the received questions using natural language processing (NLP) technology and extracts important keywords.

[1534] 3. Generative AI Search:

[1535] The server searches the database for generative AI based on the extracted keywords, taking into account the AI's field of expertise and the types of questions it can answer.

[1536] From the search results, a candidate list of optimal generative artificial intelligence bots is generated and sent to the result integration module.

[1537] 4. Generative AI Presentation and Selection:

[1538] The result synthesis module presents the user with a list of the best generative artificial intelligence bots.

[1539] The user selects the best generative AI bot from the presented options.

[1540] 5. Resend the question and generate an answer:

[1541] The server resends the question to the generative artificial intelligence bot selected by the user.

[1542] The generative artificial intelligence bot generates an answer based on a question from the server and sends the answer back to the server.

[1543] 6. Formatting and displaying answers:

[1544] The server formats the generated response and transmits it to the user terminal.

[1545] The final answer will be displayed on the user's device.

[1546] Specific examples

[1547] For example, in a distribution center, an employee uses a smartphone to input a question such as, "What is the location and best route to pick up items A, B, and C?" This question is processed as follows:

[1548] 1. The server receives the question, and the analysis module extracts the keywords "Product A," "Product B," "Product C," "Location information," and "Optimal route."

[1549] 2. Based on the extracted keywords, the server searches the database for related generative artificial intelligence bots and lists "Pickup Bot A" and "Root Bot B."

[1550] 3. The user selects "Pickup Bot A."

[1551] 4. The server resends the question to the selected bot, which calculates the location information and optimal route for each item and returns an answer.

[1552] 5. The server formats the answer and displays it on the smartphone. The user receives real-time location information (item A: Section B3, item B: Section A2, item C: Section C1) and the optimal route (section A2 → section B3 → section C1).

[1553] Prompt Sentence Examples

[1554] "Picking list: Product A, Product B, Product C. Please tell me the location of each product and the best pickup route."

[1555] This system will improve the efficiency and accuracy of picking operations at logistics centers, reducing the workload.

[1556] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1557] Step 1:

[1558] The user inputs a question using a device. Specifically, they input a question such as "Please tell me the location information and the best route to pick up items A, B, and C" into a smartphone or PC application and click the send button. This input is sent to the server as text data.

[1559] Step 2:

[1560] The server receives the question sent by the user. As a preprocessing step before passing this question data to the analysis module, it checks that the text data has been received and converts it into the required format (e.g., JSON format).

[1561] Step 3:

[1562] The analysis module analyzes the received question and extracts important keywords. Here, natural language processing (NLP) techniques are used to extract keywords such as "product A," "product B," "product C," "location information," and "optimal route." The input for this step is the user's question text data, and the output is a list of extracted keywords.

[1563] Step 4:

[1564] The server searches a database based on the extracted keywords. The database contains the areas of expertise of each generative AI bot and the types of questions it can answer. The search results provide a list of related generative AI bots, such as "Pickup Bot A" and "Root Bot B." The output of this step is a list of generative AI bots.

[1565] Step 5:

[1566] The server presents the user with the optimal generative AI bot from the search results. This presentation is done by displaying a list of candidate bots on the application screen of a smartphone or computer. The user selects "Pickup Bot A." The input for this step is a list of bots, and the output is the bot selected by the user.

[1567] Step 6:

[1568] The server resends the question to the generative AI bot selected by the user. Here, data including the user's question is sent to the selected bot as a request message. The input of this step is the user's question text and information about the selected bot, and the output is the answer data from the generative AI bot.

[1569] Step 7:

[1570] A generative AI bot generates an answer based on a question from the server and sends the answer back to the server. For example, Pickup Bot A sends back location information such as "Product A: Section B3, Product B: Section A2, Product C: Section C1" and data such as "Optimal route: Section A2 → Section B3 → Section C1" to the server. The input to this step is the question data from the server, and the output is the generated answer data.

[1571] Step 8:

[1572] The server formats the answer received from the generative AI bot and sends it to the user's terminal. Here, the answer data is converted into a format that is easy for the user to understand and presented through the application. The input of this step is the answer data from the generative AI bot, and the output is the formatted answer data.

[1573] Step 9:

[1574] The user device receives the formatted answer sent from the server and displays it on the screen. For example, location information such as "Product A: Section B3, Product B: Section A2, Product C: Section C1" and specific information such as "Optimal route: Section A2 → Section B3 → Section C1" are displayed. The input of this step is the formatted answer data, and the output is the screen information displayed to the user.

[1575] 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.

[1576] The present invention adds an emotion recognition function to a system that allows users to efficiently and accurately collect information, and provides responses according to the user's emotional state. This system is realized by a configuration including a user, a terminal, a server, and an emotion recognition engine. Specific embodiments of the system and their operation are described below.

[1577] System Overview

[1578] This system analyzes user questions, provides the optimal generative AI for the question, and recognizes the user's emotions to adjust the response. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a database that searches for the optimal generative AI, a result integration module that integrates and presents the results, and an emotion engine that recognizes emotions.

[1579] How it works

[1580] Enter and submit your question

[1581] The user uses the device to input a question. For example, they enter a question such as "Please tell me about your symptoms of COVID-19" into the portal site's input form and click the submit button. The input question is sent from the device to the server.

[1582] Receiving and parsing questions

[1583] The server receives the question sent by the user. The received question is analyzed by the analysis module, and important keywords are extracted. For example, keywords such as "COVID-19" and "symptoms" are extracted.

[1584] Searching for the best generative AI bot

[1585] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. The database contains the areas of expertise and question types that each generative AI bot can answer. From the search results, a list of suitable candidate generative AI bots is generated.

[1586] Emotion recognition

[1587] The server uses an emotion engine to recognize the user's emotions, for example, determining whether the user is feeling stressed from the input text.

[1588] Present and select a bot

[1589] The server displays a list of generative AI bots that are optimal for the user. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user then selects the optimal generative AI bot from the presented options.

[1590] Resend your question and get an answer

[1591] The server resends the question to the generative AI bot selected by the user, which generates an answer based on the question from the server and sends the answer back to the server.

[1592] Adjusting responses based on emotions

[1593] The server adjusts the content and expression of the generated response based on the recognition results of the emotion engine, for example, adding more kind language and detailed explanations if the user is feeling stressed.

[1594] Displaying the results

[1595] The server formats the answer received from the generative AI bot and sends it to the user's device. The final answer is displayed on the user's device. For example, it may show information such as "Symptoms of COVID-19 include fever, cough, and difficulty breathing."

[1596] Specific examples

[1597] Example 1: Asking about COVID-19 symptoms

[1598] 1. The user types in the question, "Tell me about your COVID-19 symptoms" and submits it.

[1599] 2. The server receives the question and extracts the keywords "coronavirus" and "symptoms."

[1600] 3. The server searches for the most suitable generative artificial intelligence bot and lists "Medical Bot A" and "Medical Bot B."

[1601] 4. The server uses an emotion engine to analyze the user's emotions, for example, to detect whether the user is feeling anxious or stressed. If the user is feeling anxious, the server is configured to add kind words and detailed explanations.

[1602] 5. The user selects "Medical Bot A."

[1603] 6. The server sends a question to the selected bot and retrieves the answer.

[1604] 7. The server adjusts and formats the obtained answer based on the emotion recognition results.

[1605] 8. The user's device will display the message, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, please consult a medical professional immediately."

[1606] In this way, the system allows users to efficiently collect information and receive responses tailored to their emotional state, improving the user experience and providing more appropriate assistance.

[1607] The processing flow will be explained below.

[1608] Step 1:

[1609] A user accesses the portal site and enters a question into the question input form.

[1610] Specific actions: The user opens the portal site in a browser, enters "Please tell me about your coronavirus symptoms" in the text box, and clicks the submit button.

[1611] Step 2:

[1612] The terminal sends a question to the server.

[1613] Specific operation: The question is sent from the terminal to the server as an HTTP request.

[1614] Step 3:

[1615] The server receives the user's query.

[1616] Specific operation: The server receives an HTTP request and passes the contents to the analysis module.

[1617] Step 4:

[1618] A question analysis module on the server analyzes the question.

[1619] What it does: It uses a natural language processing (NLP) engine to extract keywords such as "coronavirus" and "symptoms."

[1620] Step 5:

[1621] The server uses an emotion engine to recognize the user's emotions.

[1622] Specific operation: The emotion engine analyzes the user's emotional state (e.g., anxiety, stress) from the input text.

[1623] Step 6:

[1624] The server searches the generative artificial intelligence database.

[1625] Specific operation: Executes an SQL query based on the extracted keywords to search for medical-related generative artificial intelligence bots.

[1626] Step 7:

[1627] The server lists the most suitable generative artificial intelligence bots from the search results.

[1628] Specific operation: The found generative artificial intelligence bots (e.g., "Medical Bot A" and "Medical Bot B") are formatted into a list and the data is prepared for presentation to the user.

[1629] Step 8:

[1630] The server presents the user with a list of generative artificial intelligence bots.

[1631] Specific operation: Sends the result in HTML or JSON format to the user's device and displays suggestions in the browser.

[1632] Step 9:

[1633] The user selects the best bot from the generative artificial intelligence bots presented.

[1634] Specific operation: The user clicks the button of the desired generative artificial intelligence bot from the list.

[1635] Step 10:

[1636] The terminal transmits the selection information of the generative artificial intelligence bot selected to the server.

[1637] Specific operation: Send an HTTP request again to convey the selected information to the server.

[1638] Step 11:

[1639] The server resends the question to the selected generative artificial intelligence bot.

[1640] What it does: Uses an API call to forward the user's question to a generative AI bot.

[1641] Step 12:

[1642] The server receives the answer from the generative artificial intelligence bot.

[1643] Specific operation: Receives answer data from the generative AI bot as an API response.

[1644] Step 13:

[1645] The server adjusts the content and expression of the response based on the recognized emotion.

[1646] Specific actions: For example, if a user is feeling anxious, add kind words or detailed explanations to the answer.

[1647] Step 14:

[1648] The server formats the adjusted response.

[1649] Specific operation: The adjusted response data is converted into HTML or JSON format and sent to the user's device.

[1650] Step 15:

[1651] The user's device will display the final answer on the screen.

[1652] What it does: It displays the data sent via JavaScript in the browser, informing the user that "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, please seek medical help immediately."

[1653] Example 2

[1654] 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."

[1655] Conventional information gathering systems have difficulty in quickly providing optimal answers to user questions. Furthermore, they are unable to respond according to the user's emotional state, making it difficult to provide sufficient support, especially to users who are feeling stressed or anxious.

[1656] 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.

[1657] In this invention, the server includes a terminal for a user to input a question, a computer for receiving the question sent from the terminal, an analysis module for analyzing the received question and extracting keywords, a storage device for searching for the optimal generative AI based on the extracted keywords, a result integration module for presenting the optimal generative AI to the user from the search results, means for transferring the question to the generative AI selected by the user and receiving an answer, communication means for transmitting the received answer to the user terminal, and an emotion recognition engine for recognizing the user's emotion and adjusting the answer content based on that emotion. This makes it possible to quickly provide the optimal answer to the user's question and also to respond appropriately according to the user's emotional state.

[1658] A "terminal" is a device through which a user inputs a question and sends it to a server.

[1659] The "computer" is a device that receives questions sent by users, analyzes them, and forwards them to the generative artificial intelligence.

[1660] An "analysis module" is software or hardware for analyzing received questions and extracting important keywords.

[1661] A "storage device" is a storage medium such as a database for searching for the optimal generative artificial intelligence based on extracted keywords.

[1662] A "result integration module" is software or hardware for presenting the user with the most appropriate generative artificial intelligence from search results.

[1663] "Communication means" refers to the network interface and communication protocol used to transmit the received response to the user terminal.

[1664] An "emotion recognition engine" is software or hardware that recognizes a user's emotions and adjusts the content of responses based on those emotions.

[1665] "Generative artificial intelligence" refers to algorithms and models that generate answers to user questions.

[1666] "Keywords" are important words or phrases extracted from a user's question that represent the content of that question.

[1667] The present invention adds an emotion recognition function to a system that allows users to collect information efficiently and accurately, and provides responses according to the user's emotional state. This system is realized by a configuration including a user, a terminal, a server, and an emotion recognition engine.

[1668] System Overview

[1669] This system analyzes user questions, provides the optimal generative AI for the question, and recognizes the user's emotions and adjusts the response accordingly. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a storage device that searches for the optimal generative AI, a result integration module that integrates and presents the results, and an emotion engine that recognizes emotions.

[1670] Detailed explanation of operation

[1671] Enter and submit your question

[1672] The user uses the device to enter a question. The user enters "Please tell me about your COVID-19 symptoms" into the portal site's input form and clicks the submit button. The entered question is sent from the device to the server. Specifically, it is sent as an HTTP request.

[1673] Receiving and parsing questions

[1674] The server receives the question sent by the user. The server analyzes the received HTTP request and extracts the question content. The analysis module analyzes the question using natural language processing technology and extracts important keywords. For example, keywords such as "coronavirus" and "symptoms" are extracted. Natural language processing libraries such as NLTK and spaCy are used here.

[1675] Searching for the best generative AI bot

[1676] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. Specifically, it executes an SQL query to list appropriate generative AI bots. The storage device stores the specialty of each generative AI bot (e.g., medicine, education, entertainment, etc.) and the question formats it can answer. For example, "Medical Bot A" and "Medical Bot B" are listed as candidates.

[1677] Emotion recognition

[1678] The server uses an emotion engine to recognize the user's emotions. Specifically, it calls emotion recognition APIs, such as Google Cloud Natural Language API or IBM Watson's emotion analysis service, to extract emotions from the input text. This identifies whether the user is feeling stressed or anxious.

[1679] Present and select a bot

[1680] The server displays a list of generative AI bots that are optimal for the user. Specifically, the list is displayed to the user using HTML and CSS. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user selects the appropriate generative AI bot from the presented options and clicks the select button.

[1681] Resend your question and get an answer

[1682] The server resends the question to the generative AI bot selected by the user. Specifically, it resends the question by sending an API request. The generative AI bot generates an answer based on the question and sends the answer back to the server as an API response. For example, using OpenAI's generative AI model, the answer "Symptoms of COVID-19 include fever, cough, and difficulty breathing" can be obtained.

[1683] Adjusting responses based on emotions

[1684] The server adjusts the content and expressions of the generated answers based on the recognition results of the emotion engine. Specifically, for users who are feeling stressed, it adds kind language and detailed explanations. For example, it adds phrases such as, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[1685] Displaying the results

[1686] The server formats the answer received from the generative AI bot and sends it to the user's device. Specifically, the answer is formatted in HTML and sent as an HTTP response. The final answer is displayed on the user's device. For example, the following information may be displayed: "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[1687] Specific examples

[1688] Example 1: Asking about COVID-19 symptoms

[1689] 1. The user types in the question, "Tell me about your COVID-19 symptoms" and submits it.

[1690] 2. The server receives the question and extracts the keywords "coronavirus" and "symptoms."

[1691] 3. The server searches for the most suitable generative artificial intelligence bot and lists "Medical Bot A" and "Medical Bot B."

[1692] 4. The server uses an emotion engine to analyze the user's emotions, for example, to detect whether the user is feeling anxious or stressed. If the user is feeling anxious, the server is configured to add kind words and detailed explanations.

[1693] 5. The user selects "Medical Bot A."

[1694] 6. The server sends a question to the selected bot and retrieves the answer.

[1695] 7. The server adjusts and formats the obtained answer based on the emotion recognition results.

[1696] 8. The user's device will display the message, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical professional immediately."

[1697] In this way, the system allows users to efficiently collect information and receive responses tailored to their emotional state, improving the user experience and providing more appropriate assistance.

[1698] Prompt Sentence Examples

[1699] "Please tell me what the symptoms of COVID-19 are. I'm very worried."

[1700] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1701] markdown

[1702] Step 1:

[1703] The user uses the device to enter a question. The user enters "Please tell me about your COVID-19 symptoms" into the portal site's input form and clicks the submit button. The entered question is sent from the device to the server. Specifically, it is sent as an HTTP request.

[1704] Input: User-provided question text

[1705] Output: HTTP request to the server

[1706] Step 2:

[1707] The server receives the question sent by the user. The server analyzes the received HTTP request and extracts the question content. The analysis module analyzes the question using natural language processing technology and extracts important keywords. For example, keywords such as "coronavirus" and "symptoms" are extracted. Natural language processing libraries such as NLTK and spaCy are used here.

[1708] Input: Question text included in HTTP request

[1709] Output: Keywords such as "COVID-19" and "symptoms"

[1710] Step 3:

[1711] The server searches a database of generative AI bots based on the keywords extracted by the analysis module. Specifically, it executes an SQL query to list appropriate generative AI bots. The storage device stores the specialty of each generative AI bot (e.g., medicine, education, entertainment, etc.) and the question formats it can answer. For example, "Medical Bot A" and "Medical Bot B" are listed as candidates.

[1712] Input: Extracted keywords

[1713] Output: A list of optimal generative AI bots (e.g., "Medical Bot A" and "Medical Bot B")

[1714] Step 4:

[1715] The server uses an emotion engine to recognize the user's emotions. Specifically, it calls emotion recognition APIs, such as Google Cloud Natural Language API or IBM Watson's emotion analysis service, to extract emotions from the input text. This identifies whether the user is feeling stressed or anxious.

[1716] Input: Question text

[1717] Output: User's emotional state (e.g., stress, anxiety)

[1718] Step 5:

[1719] The server displays a list of generative AI bots that are optimal for the user. Specifically, the list is displayed to the user using HTML and CSS. For example, candidates such as "Medical Bot A" and "Medical Bot B" are presented to the user. The user selects the appropriate generative AI bot from the presented options and clicks the select button.

[1720] Input: A list of the best generative AI bots

[1721] Output: User selects bot

[1722] Step 6:

[1723] The server resends the question to the generative AI bot selected by the user. Specifically, it resends the question by sending an API request. The generative AI bot generates an answer based on the question and sends the answer back to the server as an API response. For example, using OpenAI's generative AI model, the answer "Symptoms of COVID-19 include fever, cough, and difficulty breathing" can be obtained.

[1724] Input: User-selected generative AI bot, question text

[1725] Output: Answer from a generative AI bot

[1726] Step 7:

[1727] The server adjusts the content and expressions of the generated answers based on the recognition results of the emotion engine. Specifically, for users who are feeling stressed, it adds kind language and detailed explanations. For example, it adds phrases such as, "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[1728] Input: Answers from a generative AI bot, user's emotional state

[1729] Output: Adjusted answer

[1730] Step 8:

[1731] The server formats the answer received from the generative AI bot and sends it to the user's device. Specifically, the answer is formatted in HTML and sent as an HTTP response. The final answer is displayed on the user's device. For example, the following information may be displayed: "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately."

[1732] Input: Adjusted answer content

[1733] Output: The final answer displayed on the user's terminal

[1734] (Application example 2)

[1735] 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."

[1736] In conventional information gathering systems, response systems have been proposed that can respond quickly and appropriately to user questions, but they lack the ability to adjust responses according to the user's emotional state, which prevents them from fully improving the user experience. Furthermore, in security services, it is necessary to provide a higher level of safety by grasping the emotional state of people in the monitored area in real time and responding according to that emotion, but the lack of such a system is an issue.

[1737] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1738] In this invention, the server includes a terminal for a user to input a question, means for receiving the question sent from the terminal, an analysis module for analyzing the received question and extracting keywords, a database for searching for an optimal generative artificial intelligence based on the extracted keywords, a result integration module for presenting the optimal generative artificial intelligence to the user from the search results, means for transferring the question to the generative artificial intelligence selected by the user and receiving a response, means for transmitting the received response to the user terminal, an emotion recognition engine for analyzing and recognizing the emotional states of people in the monitored area, means for selecting and presenting the optimal generative artificial intelligence according to the emotions identified by the emotion recognition engine, and means for adjusting the response generated by the optimal generative artificial intelligence based on the emotion recognition data, thereby providing a response according to the user's emotional state and enabling improved security services.

[1739] A "terminal for users to input questions" is an electronic device used by users to input questions in the form of text, voice input, or the like.

[1740] The "server for receiving questions sent from a terminal" is a network-connected computer system for receiving questions sent by a user from a terminal and for subsequent processing.

[1741] The "analysis module for analyzing received questions and extracting keywords" is a software component that analyzes the content of questions entered by users and extracts important keywords and phrases.

[1742] A "database for searching for the optimal generative artificial intelligence based on extracted keywords" is a database that stores information for searching for the optimal generative artificial intelligence based on keywords extracted by the analysis module.

[1743] The "result integration module for presenting the user with the optimal generative artificial intelligence from the search results" is a software component for integrating the results of a database search and presenting the user with the optimal generative artificial intelligence candidates.

[1744] "Means for transferring a question to a generative artificial intelligence selected by a user and receiving a response" refers to means for sending a user's question to a generative artificial intelligence selected by a user and receiving a response thereto.

[1745] "Means for transmitting the received answer to the user terminal" refers to means for transmitting the answer received from the generative artificial intelligence to the user terminal.

[1746] The "emotion recognition engine for analyzing and recognizing the emotional state of people within a monitored area" is a software component that analyzes and identifies emotions from the facial expressions, voices, etc. of people within a monitored area.

[1747] "Means for selecting and presenting the most appropriate generative artificial intelligence in accordance with the emotions identified by the emotion recognition engine" refers to means for selecting the most appropriate generative artificial intelligence based on the emotion data analyzed by the emotion recognition engine and presenting the result to the user.

[1748] "Means for adjusting responses generated by optimal generative artificial intelligence based on emotion recognition data" refers to means for adjusting responses generated by generative artificial intelligence according to the emotional state of the user.

[1749] This invention adds emotion recognition functionality to a system that allows users to collect information efficiently and accurately, and provides responses that correspond to the user's emotional state. This system is realized by comprising a user terminal, a server, an analysis module, a generative AI database, a result integration module, and an emotion recognition engine.

[1750] System Overview

[1751] This system analyzes a user's question, provides the most suitable generative artificial intelligence for that question, and recognizes the user's emotions and adjusts the response accordingly. The system includes a terminal where the user inputs the question, a server that receives and processes the question, an analysis module that analyzes the question, a database that searches for the most suitable generative artificial intelligence, a result integration module that integrates and presents the results, and an emotion recognition engine that recognizes emotions.

[1752] How it works

[1753] Enter and submit your question

[1754] The user inputs a question using the device. For example, they input a question such as "Please tell me about the symptoms of COVID-19" into the device and send it. The input question is sent from the device to the server.

[1755] Receiving and parsing questions

[1756] The server receives the question sent by the user. The received question is analyzed by the analysis module, and important keywords are extracted. For example, keywords such as "COVID-19" and "symptoms" are extracted.

[1757] Searching for the best generative artificial intelligence

[1758] The server searches a database of generative AI based on the extracted keywords. The database contains the fields of expertise and question formats that each generative AI can handle. The search results then produce a list of suitable generative AIs.

[1759] Recognizing and Responding to Emotions

[1760] The server uses an emotion recognition engine to recognize the user's emotions, for example, to determine whether the user is stressed from the input text. The emotion recognition engine analyzes the facial expressions and tone of voice of people in the monitored area.

[1761] Program processing

[1762] The server performs its operations using, among other things, the following software and hardware:

[1763] Hardware: smart glasses, smartphones, cameras

[1764] software:

[1765] EmotionRecognition Module: Face and emotion recognition engine using OpenCV

[1766] AIModelExecutor module: Generative AI model selection and execution engine (e.g., GPT-4, BERT)

[1767] The server acquires real-time video from the camera and analyzes the emotional data using the EmotionRecognition module. The emotion recognition engine identifies people's emotional states based on the analysis results. The AIModelExecutor module then uses this emotional data to select the optimal generative AI and generate a response.

[1768] Specific examples

[1769] Example 1: Security Monitoring Assistant

[1770] Security guards and facility managers use smart glasses or smartphones to monitor the facility and check the emotional state of people in real time. At this time, an emotion recognition engine analyzes the emotional state (e.g., anxiety, anger, stress) of the people being monitored and selects and presents an appropriate response from an optimal generative artificial intelligence database.

[1771] Example prompt sentence:

[1772] "We have noticed an individual in our surveillance area who appears to be unsafe. Please advise our security personnel on how to respond."

[1773] In this way, the present invention provides a response that is tailored to the user's emotional state, thereby improving the user experience and providing improved security services.

[1774] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1775] Step 1:

[1776] A user uses a terminal to input a question. For example, they input "Please tell me about the symptoms of COVID-19" and send it. The input is the text data of the user's question, and the output is the input question being sent from the terminal to the server.

[1777] Step 2:

[1778] The server receives the question sent by the user. The input is the question text data sent from the terminal, and the output is the received data passed to the analysis module.

[1779] Step 3:

[1780] The analysis module analyzes the received question and extracts important keywords. The input is the received question text data, and the output is the analysis results, which are important keywords (e.g., "COVID-19" and "symptoms").

[1781] Step 4:

[1782] The server searches the database for the optimal generative AI based on the extracted important keywords. The input is the important keywords, and the output is a list of candidate generative AIs (e.g., "Medical Bot A" and "Medical Bot B").

[1783] Step 5:

[1784] The server uses an emotion recognition engine to analyze and identify the user's emotion. The input is the text data of the user's question and facial expression recognition data, and the output is the user's emotional state (e.g., stress, anxiety).

[1785] Step 6:

[1786] The server presents the user with a list of optimal generative AIs, and the user selects one. The input is a list of generative AI candidates, and the output is the generative AI selected by the user (e.g., "Medical Bot A").

[1787] Step 7:

[1788] The server forwards the question to the generative artificial intelligence selected by the user and receives an answer from the generative artificial intelligence. The input is the user's question and the identification information of the selected generative artificial intelligence, and the output is the answer data from the generative artificial intelligence (e.g., "Symptoms of COVID-19 include fever, cough, and difficulty breathing").

[1789] Step 8:

[1790] The server adjusts the generated answer content based on the results of the emotion recognition engine. The input is the answer data and emotion recognition results from the generative AI, and the output is the adjusted answer data (e.g., "Symptoms of COVID-19 include fever, cough, and difficulty breathing. If you are concerned, consult a medical institution immediately.").

[1791] Step 9:

[1792] The server sends the adjusted answer to the user terminal, which the user confirms. The input is the adjusted answer data, and the output is the final answer information displayed on the user terminal.

[1793] In this way, the present invention provides appropriate information according to the user's emotional state.

[1794] 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.

[1795] 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.

[1796] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1797] 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.

[1798] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1799] 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.

[1800] 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).

[1801] 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.

[1802] 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."

[1803] 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.

[1804] 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).

[1805] 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.

[1806] 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.

[1807] 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.

[1808] 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.

[1809] 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.

[1810] 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.

[1811] 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.

[1812] 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.

[1813] 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.

[1814] 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.

[1815] The following is further disclosed regarding the above embodiment.

[1816] (Claim 1)

[1817] a terminal for users to enter questions;

[1818] a server for receiving queries sent from the terminals;

[1819] an analysis module for analyzing the received questions and extracting keywords;

[1820] A database for searching for the optimal generative artificial intelligence based on extracted keywords;

[1821] a result integration module for presenting the best generative artificial intelligence results to the user from the search results;

[1822] means for forwarding questions to a user-selected generative artificial intelligence and receiving answers;

[1823] means for transmitting the received response to a user terminal;

[1824] A system including:

[1825] (Claim 2)

[1826] 10. The system of claim 1, further comprising means for selecting an optimal generative artificial intelligence based on the type of information and area of ​​expertise that each generative artificial intelligence can provide in response to a received question.

[1827] (Claim 3)

[1828] 10. The system of claim 1, further comprising means for aggregating the answers received from each generative artificial intelligence and presenting them to the user as a single unified answer.

[1829] "Example 1"

[1830] (Claim 1)

[1831] an input device for a user to input a question;

[1832] an information processing device for receiving a question transmitted from an input device;

[1833] an analysis means for analyzing the received question and extracting keywords;

[1834] a storage device for searching for an optimal generative artificial intelligence based on the extracted keywords;

[1835] An information integration method for presenting the optimal generative artificial intelligence to the user from the search results;

[1836] A communication means for transmitting questions to the user-selected generative artificial intelligence and receiving answers;

[1837] display means for transmitting the received response to a user terminal;

[1838] An information gathering device including:

[1839] (Claim 2)

[1840] 2. The information collection device according to claim 1, further comprising means for selecting an optimal generative artificial intelligence based on the type of information and area of ​​expertise that each generative artificial intelligence can provide in response to a received question.

[1841] (Claim 3)

[1842] 10. The information collection device of claim 1, further comprising means for integrating the answers received from each generative artificial intelligence and presenting it to the user as a single unified answer.

[1843] "Application Example 1"

[1844] (Claim 1)

[1845] a terminal for users to enter questions;

[1846] a server for receiving queries sent from the terminals;

[1847] an analysis module for analyzing the received questions and extracting keywords;

[1848] A database for searching for the optimal generative artificial intelligence based on extracted keywords;

[1849] a result integration module for presenting the best generative artificial intelligence results to the user from the search results;

[1850] means for forwarding questions to a user-selected generative artificial intelligence and receiving answers;

[1851] means for transmitting the received response to a user terminal;

[1852] A means to calculate product location information and the optimal route to assist with pickup operations;

[1853] A system including:

[1854] (Claim 2)

[1855] 10. The system of claim 1, further comprising means for selecting an optimal generative artificial intelligence based on the type of info...

Claims

1. a terminal for users to enter questions; a server for receiving queries sent from the terminals; an analysis module for analyzing the received questions and extracting keywords; A database for searching for the optimal generative artificial intelligence based on extracted keywords; a result integration module for presenting the best generative artificial intelligence results to the user from the search results; means for forwarding questions to a user-selected generative artificial intelligence and receiving answers; means for transmitting the received response to a user terminal; A system including:

2. The system of claim 1 , further comprising means for selecting an optimal generative artificial intelligence based on the type of information and area of ​​expertise that each generative artificial intelligence can provide in response to a received question.

3. The system of claim 1 , further comprising means for aggregating the answers received from each generative artificial intelligence and presenting it to the user as a single unified answer.

Images