system

Abstract

We provide the system. [Solution] A means of receiving inquiries from users, A means of analyzing received inquiries using natural language processing technology, A means for searching a pre-prepared query response database based on the analysis results, A means for generating a response to a user inquiry based on search results, A means for sending the generated response to the user, A system that includes this.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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 Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In consumer agency business, inquiry response requires time and effort, which is a factor increasing the burden on sales staff. It is required to respond quickly and accurately to frequently received inquiries, but the current manual response has limitations and may lead to a decrease in customer satisfaction. Furthermore, since there is no system in place to handle inquiries received outside normal business hours, it is difficult to respond at night or on holidays. Amid such problems, it is necessary to efficiently and continuously handle inquiry responses, reduce the workload of sales staff, and meet customer expectations. 【Means for Solving the Problems】 【0005】 This invention provides a system that automatically receives user inquiries and analyzes them using natural language processing technology. By analyzing the received inquiries, the system understands the user's intent and generates appropriate responses based on a pre-prepared inquiry response database. Furthermore, by immediately sending the automatically generated responses to the users, 24 / 7 support is possible. The inquiry response database also includes multiple pre-configured inquiry categories, enabling rapid responses. Keyword extraction is performed during the inquiry analysis process to identify the user's intent and context, resulting in more accurate automated responses. This system reduces the burden on sales representatives and enables efficient customer service. 【0006】 A "user" is an individual or organization that uses the system to make inquiries. 【0007】 An "inquiry" refers to a question or request made by a user to obtain information about a product or service. 【0008】 "Means of receiving data" refers to the function by which the system takes in inquiries sent by users as data. 【0009】 "Natural language processing technology" is a general term for technologies that enable computers to analyze and understand human language. 【0010】 "Means of analysis" refers to the function that performs the process of understanding received text information and grasping its meaning and intent. 【0011】 A "user inquiry response database" is a collection of data containing pre-prepared answers to user inquiries. 【0012】 "Searching methods" refer to functions for extracting appropriate information from the database based on the analysis results. 【0013】 "Means for generating responses" refers to a function that constructs and outputs an appropriate answer to an inquiry. 【0014】 "Means of transmission" refers to the function that sends the generated response to the user's device. 【0015】 Keyword extraction is the process of selecting important words and phrases from a document or text. [Brief explanation of the drawing] 【0016】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined. 【Mode for Carrying Out the Invention】 【0017】 Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0018】 First, the terms used in the following description will be explained. 【0019】 In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0020】 In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0021】 In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes. 【0022】 In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0023】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0024】 [First Embodiment] 【0025】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0026】 As shown in Figure 1, the 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 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0028】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0029】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. 【0031】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54. 【0032】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0033】 As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30. 【0034】 The storage 32 stores the data generation model 58 and the 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 processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0036】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0037】 This invention provides an automated response system for responding quickly and efficiently to user inquiries. This system mainly includes a server, a user terminal, and an inquiry response database. 【0038】 Users submit inquiries through a chat interface from their device. This interface is intuitive and user-friendly, allowing users to input questions in text format. The device sends the entered inquiry to the server. The server receives this text information and prepares it for analysis. 【0039】 The server analyzes the received text data using a natural language processing (NLP) engine. This allows it to understand the user's intent and the subject of their inquiry, and extract relevant keywords. For example, if a user asks, "Tell me about the latest plans," the server recognizes important keywords such as "latest" and "plans." 【0040】 Next, the server searches the query response database based on these analysis results. This database contains past queries and their optimal responses, organized by category. For example, for queries related to "plans," the database entry would be in the format of "The latest information on the XX plan is XX." 【0041】 The server identifies the most appropriate response from the search results and generates a response for the user based on that. This response is programmed to be expressed in natural language that is easy for the user to understand. The generated response is sent from the server to the user's terminal and displayed on the chat interface. This allows the user to get an answer to their inquiry immediately. 【0042】 This system enables 24 / 7 / 365 support regardless of time or day of the week, ensuring prompt service delivery without compromising user satisfaction, even when sales representatives are unavailable. Furthermore, this implementation aims to free sales representatives from the simple task of handling inquiries, allowing them to focus on more advanced work. 【0043】 The following describes the processing flow. 【0044】 Step 1: 【0045】 Users enter their inquiries in text format through their own devices. These inquiries are conducted using a chat interface. 【0046】 Step 2: 【0047】 The terminal converts the text entered by the user into data packets and sends them to the server using a communication protocol. 【0048】 Step 3: 【0049】 The server receives data packets from the terminal and decodes the text data to analyze the query content. 【0050】 Step 4: 【0051】 The server uses a natural language processing (NLP) engine to analyze the received text and extract the user's intent and key keywords. This analysis identifies the category and purpose of the inquiry. 【0052】 Step 5: 【0053】 The server searches the query response database according to the analysis results. Based on the extracted keywords and categories, it searches the database for the most relevant answers. 【0054】 Step 6: 【0055】 The server generates a natural language response tailored to the user based on information retrieved from the database. This response is then adjusted to have an easily understandable sentence structure. 【0056】 Step 7: 【0057】 The server converts the generated response into a data packet and sends it to the user's terminal. 【0058】 Step 8: 【0059】 The terminal decodes the received data packets and displays the response on the user interface. This allows the user to instantly see the answer to their question. 【0060】 (Example 1) 【0061】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0062】 Currently, many inquiry handling systems are required to respond to user inquiries quickly and accurately, but they have limitations when it comes to complex inquiries that cannot be handled by conventional rule-based approaches. Furthermore, it is difficult to consistently provide responses of the same quality regardless of the time of day or day of the week. In addition, existing systems have insufficient understanding of inquiry content, and more advanced natural language processing capabilities are needed to improve user satisfaction. 【0063】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0064】 In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries using natural language processing technology, and means for searching a pre-prepared inquiry response database based on the analysis results. This enables sophisticated and flexible responses to user inquiries using a generative AI model. 【0065】 A "user" refers to an individual or organization that uses the system to make an inquiry. 【0066】 An "inquiry" is a text-based form containing information or questions that the user wants to know. 【0067】 "Means of receiving" refers to the function that allows a computer system to acquire inquiries sent by users. 【0068】 "Natural language processing technology" refers to the technology used by computers to understand and analyze human language. 【0069】 "Means of analysis" refers to methods for deciphering received inquiries using natural language processing techniques and understanding their meaning. 【0070】 A "query response database" refers to a collection of information in which past queries and their corresponding responses are organized and stored. 【0071】 A "search method" is a function that finds relevant information within a database based on the analysis results. 【0072】 A "generative AI model" is a type of computer program that uses artificial intelligence to generate text in a natural-sounding format. 【0073】 "Means of generating a response" refers to the process of creating an appropriate answer to an inquiry. 【0074】 "Means of transmission" refers to the function that delivers the generated response to the user's device. 【0075】 A "prompt statement" refers to an input statement used to give instructions to a generating AI model. 【0076】 This invention relates to a system for automatically generating responses to user inquiries. This system mainly includes a server, a user terminal, and an inquiry response database. 【0077】 Users submit inquiries through the chat interface on their device. The chat interface is designed to be intuitive and easy to use, allowing users to easily input questions in text format. The submitted inquiry is then sent from the device to the server. 【0078】 The server analyzes the received text data using a natural language processing (NLP) engine. This NLP engine is used to understand the user's intent and the subject of the inquiry, and to extract relevant keywords. For example, if a user asks, "Please tell me the latest product information," the server will extract keywords such as "latest" and "product information." 【0079】 Next, the server searches the query response database based on these analysis results. This database stores past queries and their optimal responses, organized by category. For example, for queries related to "product information," the database contains an appropriate entry such as "The current latest product is XX." 【0080】 The server uses a generative AI model to generate an appropriate response based on the search results. This response is expressed in natural language that is easy for the user to understand. The generative AI model used here is optimized according to the user's intent and context. 【0081】 The generated response is sent from the server to the user's terminal and displayed on the chat interface. This allows the user to quickly obtain information regarding their inquiry. For example, a prompt could be instructed to the AI ​​model to "analyze the user's inquiry 'Please provide the latest product information' and generate a relevant response." As a result of this prompt, a response is generated and displayed. 【0082】 This embodiment allows users to consistently receive high-quality responses regardless of time or location, thus improving user satisfaction with the system. Furthermore, the server's automated response management optimizes human resources. 【0083】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0084】 Step 1: 【0085】 The user enters their inquiry in text format through the chat interface on their device. The user's question text is generated as input data. This input is sent to the server by the user's device. 【0086】 Step 2: 【0087】 The server receives text data sent from the terminal. To process the received data, the server first performs preprocessing, such as converting character codes and removing unnecessary information. This results in clean data for analysis. 【0088】 Step 3: 【0089】 The server uses a natural language processing (NLP) engine to analyze clean text data. The input is pre-processed data, and the output extracts keywords and topics that indicate the user's intent and interests. For example, from the input "Please tell me the latest product information," keywords such as "latest" and "product information" will be output. 【0090】 Step 4: 【0091】 The server searches the query response database based on the analysis results. In this process, relevant information is identified from the database based on keywords. The input is the keywords from the analysis results, and the output is the relevant response candidates. 【0092】 Step 5: 【0093】 The server uses a generative AI model to generate user-facing responses based on response candidates retrieved from a database. In this process, prompt text is provided to the generative AI model, resulting in the generation of natural and easily understandable sentences. The input consists of response candidates and prompt text, and the output is a final response to be presented to the user. 【0094】 Step 6: 【0095】 The server sends the generated response to the user's terminal. The terminal displays this response on the chat interface. The input here is the response from the server, and the output is the final display presented to the user. This allows the user to quickly confirm the answer. 【0096】 (Application Example 1) 【0097】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0098】 In modern e-commerce, it is necessary to respond quickly and accurately to inquiries from a large number of users. However, conventional methods make it difficult to adequately respond to detailed inquiries about a wide variety of products, leading to decreased customer satisfaction and increased support costs. The present invention aims to solve these problems and provide a means to provide efficient and highly accurate responses. 【0099】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0100】 In this invention, the server includes a medium for receiving user inquiries, a medium for analyzing the received inquiries using natural language processing technology, a medium for searching a pre-prepared inquiry response data structure based on the analysis results, a medium for generating a response to the user's inquiry based on the search results, a medium for sending the generated response to the user, and a medium for using an artificial intelligence model for providing product information on a shopping platform to retrieve relevant information from a database. This enables the server to always respond to customer inquiries with optimized content, improving customer satisfaction and reducing operating costs. 【0101】 A "medium for receiving user inquiries" refers to a device or software that receives questions or requests for information from users to a system. 【0102】 A "medium analyzed using natural language processing technology" is a device or software that analyzes input text data in order for a server to understand the language that humans normally use. 【0103】 A "medium for searching query response data structures" refers to a device or software that performs the function of searching for a pre-prepared set of response data based on the results of analysis. 【0104】 A "medium for generating responses to user inquiries" refers to a device or software that takes search results into consideration and constructs an appropriate answer for the user. 【0105】 "The medium for sending the generated response to the user" refers to a device or software that has the role of delivering the constructed response to the user. 【0106】 An "artificial intelligence model for providing product information on a shopping platform" is a device or software that utilizes artificial intelligence technology to present product details in an online shopping environment and possesses analytical methods to provide users with the most relevant information. 【0107】 A "medium for retrieving related information from a database" refers to a device or software that retrieves information related to a product or service from its storage location. 【0108】 The system implementing this invention consists of a central server and terminals for receiving user inquiries. The server is equipped with a natural language processing engine, analyzes inquiries, and generates the optimal response based on the analysis results. Specifically, the server uses natural language processing technology to interpret the text data received from the user. In this process, keywords and sentences are extracted from the input inquiry and data is processed to understand the user's intent. 【0109】 The server leverages existing natural language processing technologies, such as Google Cloud Natural Language API. After keyword extraction, the server quickly searches the query-response data structure to identify the most appropriate response. This ensures consistent information delivery, allowing users to quickly obtain the information they need. 【0110】 The terminal used is the user's smartphone or computer, allowing them to make inquiries through an intuitive interface. The generated response is immediately sent to the terminal and displayed on the screen, so the user can obtain information instantly and promotes continuous engagement. 【0111】 For example, if a user asks "What sizes are available for this product?" through a shopping platform application, the system recognizes "size" as a keyword and retrieves relevant information from its database. As a result, it provides a response such as "This product is available in sizes S, M, L, and XL." 【0112】 An example of a prompt using a generative AI model is: "Question: Does this product come in other colors? Answer: Yes, this product comes in blue, red, and green." This demonstrates the ability to generate natural responses that are relevant to the conversation with the user. 【0113】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0114】 Step 1: 【0115】 The user enters their inquiry through a chat interface using their device. Text data is generated as input, and the device sends this data to the server. The output is text data containing the inquiry. 【0116】 Step 2: 【0117】 The server passes the received text data to the natural language processing engine and begins analysis. The input is text data, and natural language processing techniques are used to extract keywords and sentences and understand the user's intent. The output at this stage is data containing the analyzed keywords and intent. Specifically, the Google Cloud Natural Language API is used to interpret the context. 【0118】 Step 3: 【0119】 The server searches a pre-defined query response data structure based on the analysis results. The input is the analysis results data, and relevant information is quickly retrieved from the database. The output is the relevant response data. This process uses database queries to identify the optimal response. 【0120】 Step 4: 【0121】 The server generates responses to user inquiries based on the information it has retrieved. The input is response data, and a generative AI model is used to create natural language responses. The output is the natural language response provided to the user. This includes, for example, the formation of sentences based on prompts using a generative AI model. 【0122】 Step 5: 【0123】 The server sends the generated response to the user's terminal. The input is response data in natural language, and the output is a text message displayed on the terminal's user interface. The specific operation includes a process of sending data back to the terminal via the network. 【0124】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0125】 This invention establishes a system that provides more appropriate and personalized responses to user inquiries by combining an emotion analysis engine that analyzes the user's emotions with an automated response system for user inquiries. This system includes a server, a user terminal, a natural language processing (NLP) engine, an emotion analysis engine, and an inquiry response database. 【0126】 First, the user makes an inquiry via a chat interface. The terminal converts this into digital data and sends it to the server. The server then analyzes the received data using a natural language processing engine to identify the user's intent and topic, which is the same as before. 【0127】 Furthermore, in this invention, the server uses a sentiment analysis engine to identify the emotional nuances contained in the inquiry text. This makes it possible to identify emotions such as joy, anger, and sadness expressed by the user. For example, from the user's inquiry, "I am disappointed with the recent service. Please tell me why," the sentiment analysis engine recognizes "disappointment." 【0128】 The server integrates the results of this sentiment analysis with the results of natural language processing and searches the query response database. As a result, the selected response not only provides information but also takes the user's emotions into consideration. For example, if disappointment is recognized, the response will be generated to provide specific information while also including comfort and apologies. 【0129】 The server then generates an optimal response based on the user's emotions and context, and sends it to the user's terminal. The user can receive this response in real time, and the entire system aims to provide a service that exceeds the user's expectations. 【0130】 This system is expected to increase customer satisfaction and improve trust in and favorability towards the company's services. Furthermore, because the server consistently provides quick and accurate responses that consider the user's emotions and intentions, it creates an environment where sales representatives can focus on complex inquiries. 【0131】 The following describes the processing flow. 【0132】 Step 1: 【0133】 Users access the chat interface using their own devices and enter their inquiries in text format. These inquiries can be specific questions or feedback on their user experience. 【0134】 Step 2: 【0135】 The terminal converts the input text into digital data packets and sends them to the server. This conversion is performed according to the communication protocol, maintaining data integrity. 【0136】 Step 3: 【0137】 The server receives data sent from the terminal and decodes the text content. The received content is then passed to a natural language processing engine, which prepares it for analyzing the user's intent. 【0138】 Step 4: 【0139】 The server uses a natural language processing engine to analyze the text and understand the subject and intent of the query. At this stage, it identifies key keywords and, based on them, determines the response category. 【0140】 Step 5: 【0141】 The server inputs the analyzed text into a sentiment analysis engine to evaluate the user's emotional state. The sentiment analysis engine identifies emotions such as joy, anger, and sadness based on the words and expressions in the text. 【0142】 Step 6: 【0143】 The server combines the results of natural language processing analysis with the results of sentiment analysis and searches a query response database. This database contains responses in an appropriate tone according to the emotion. 【0144】 Step 7: 【0145】 The server adjusts its response to include a tone that is sensitive to the user's emotions when generating the best possible response from search results. For example, if user dissatisfaction is detected, it will add words of comfort. 【0146】 Step 8: 【0147】 The server sends the generated response as a digital data packet to the user's terminal. Transmission is performed quickly while ensuring communication security. 【0148】 Step 9: 【0149】 The terminal receives responses sent from the server and decodes them for display to the user. Users can view the responses in real time on the chat interface. 【0150】 (Example 2) 【0151】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0152】 Traditional automated response systems often generate responses to user inquiries without considering emotional context, potentially leading to decreased customer satisfaction. There is a need to solve this problem and provide more appropriate, personalized responses. 【0153】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0154】 In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries using natural language processing techniques, and means for using sentiment analysis techniques to identify the user's emotions from the analyzed results. This makes it possible to generate responses that take the user's emotions into consideration. 【0155】 A "user" is the entity that makes a query to a system and receives a response. 【0156】 An "inquiry" is information that represents a question or request that a user sends to a system. 【0157】 "Natural language processing technology" is a technology that uses computers to analyze and understand human language. 【0158】 A "data set" is a collection of pre-prepared information and responses that are retrieved based on a query. 【0159】 "Sentiment analysis technology" is a technique for identifying and classifying emotional expressions within text. 【0160】 A "response" is the information or message that a system provides in response to a user's inquiry. 【0161】 This invention is a system that provides an automated response that takes emotions into account in response to a user's inquiry. The system is comprised of a server, a user's terminal, natural language processing technology, sentiment analysis technology, and a set of inquiry response data. 【0162】 First, the user makes a request via their device. The user's device then sends this as digital data to the server. The device typically has an operating system and interface software installed, which makes this data transmission process efficient. 【0163】 The server analyzes the received query data using natural language processing (NLP) techniques. Specifically, it uses open-source NLP libraries or commercial NLP platforms to identify the user's intent and subject matter. Typical tools include natural language models provided by academic institutions and companies. 【0164】 Next, the server applies sentiment analysis technology to identify the emotions contained in the query. This allows it to grasp the emotional nuances expressed by the user. Sentiment analysis uses text analysis tools and APIs to classify the user's emotions into categories such as "joy," "sadness," and "anger." 【0165】 For example, if a user asks, "I'm dissatisfied with the service. Please tell me why," the server can identify the emotion of "dissatisfaction" from this sentence. Based on this, when generating a response, it can include specific information or comforting expressions that correspond to this emotion. 【0166】 As a concrete example of a prompt, we will show the process of inputting "The user is dissatisfied with the quality of service. How should you respond?" into an AI model and having the model generate an appropriate response example. 【0167】 This system aims to improve customer satisfaction by quickly and accurately generating responses that are tailored to the user's emotional state. 【0168】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0169】 Step 1: 【0170】 The user uses a terminal to enter and submit their inquiry. The entered data is in text format and includes specific inquiry details such as, "I am dissatisfied with the service. Please tell me why." The terminal packets this text data and sends it to the server over the network. 【0171】 Step 2: 【0172】 The server receives data sent from the terminal. It stores the received data in a format suitable for text parsing and passes it on to the next process. The output of this process is text data containing the query content. 【0173】 Step 3: 【0174】 The server uses natural language processing techniques to analyze the received text data. The input for this process is text data, and a language model is applied to identify the user's intent and subject matter. For example, a generative AI model is used to extract intents such as "dissatisfaction" or "wanting to know the reason." This analysis result is then passed on to the next stage. 【0175】 Step 4: 【0176】 The server uses sentiment analysis technology to identify emotions from the analyzed text. The input data is the analysis results obtained in step 3. In this process, the sentiment analysis tool is used to classify emotions into categories such as "anxiety" and "dissatisfaction." The identified emotion information is then used in the next process. 【0177】 Step 5: 【0178】 The server searches the database based on the user's intent and emotional information obtained. The input is the information obtained in steps 3 and 4. From the search results, it selects and generates the most appropriate response. For example, it might select a situation-appropriate apology message and problem-solving suggestions from the database. 【0179】 Step 6: 【0180】 The server sends the generated response to the user's terminal. The output is a text message displayed to the user. The user receives this response and can view it in real time. 【0181】 (Application Example 2) 【0182】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal". 【0183】 Traditional automated response systems focus solely on providing information in response to user inquiries, lacking consideration for user emotions. This leads to a poor user experience and, consequently, lower customer satisfaction. There is a need to improve this situation and provide rapid, personalized responses that are based on user emotions. 【0184】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0185】 In this invention, the server includes a device for receiving requests from users, a device for analyzing the received requests using natural language processing technology, and an emotion analysis device for analyzing the emotions contained in the user's requests. This makes it possible to take the user's emotional state into consideration and provide an individualized response. 【0186】 "User requests" are messages or questions that users send to the system to request information or support. 【0187】 A "device" is a set of hardware or software components designed to perform a specific function. 【0188】 "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language, making natural dialogue possible. 【0189】 A "data set" is a structured collection of information that includes pre-prepared information and responses to address various requests. 【0190】 An "emotion analysis device" is a technology or system for identifying and analyzing the emotional elements contained in user requests. 【0191】 A "response adjustment device" is a system that has the function of automatically changing or optimizing response content based on the results of sentiment analysis. 【0192】 To implement this invention, a program is required that runs on the user's terminal and on a server. The program uses natural language processing and sentiment analysis techniques to receive requests from the user and analyze their content. 【0193】 The server first parses the received request using natural language processing techniques, such as the spaCy library, to identify the user's intent. Then, it uses sentiment analysis with the Google Cloud Natural Language API to recognize the emotions contained in the request. This allows the server to extract the emotions the user is expressing (e.g., joy, anger, sadness). 【0194】 Next, the server searches a pre-prepared database based on the analyzed intent and emotional information, and generates a personalized response that takes the user's emotions into account. In generating the response, the most appropriate message corresponding to the emotional state is selected and adjusted into a natural dialogue format using an AI model. 【0195】 The generated response is sent to the user's terminal in real time, allowing the user to feel as if they are interacting with a human operator. This process is expected to improve customer satisfaction. 【0196】 For example, if a user inquires that "a recently ordered item arrived late," the system can provide detailed information on measures to prevent future delays and generate an apology message based on sentiment analysis. 【0197】 An example of a prompt for a generative AI model is: "Based on the user's inquiry, generate a response that takes their emotions into consideration." 【0198】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0199】 Step 1: 【0200】 The terminal takes user requests as text data and sends that data to the server in digital format. Raw text is provided as input to the server. 【0201】 Step 2: 【0202】 The server uses natural language processing techniques (e.g., the spaCy library) to analyze the received text data and identify the user's intent. The input is the user's request text, which is then analyzed to extract keywords related to the subject and intent, resulting in structured intent data as output. 【0203】 Step 3: 【0204】 The server uses the Google Cloud Natural Language API to analyze the sentiment within the text data. The input is the user request text mentioned earlier, and by performing sentiment analysis on it, it obtains numerical data representing emotions such as joy and anger as output. 【0205】 Step 4: 【0206】 The server combines the results of natural language processing (intent data) and sentiment analysis to search a pre-prepared dataset. The input consists of intent data and sentiment data, which are used to search the dataset for the record with the most appropriate response, and the appropriate response data is obtained as output. 【0207】 Step 5: 【0208】 The server uses an AI model to refine the acquired response data and generate natural, conversational responses that take the user's emotions into consideration. It receives response data from the previous step as input and outputs natural language responses appropriate to the emotional state. 【0209】 Step 6: 【0210】 The server sends the final generated response to the terminal in response to the request. The generated response is the input, and the transmission to the terminal is the output. 【0211】 Step 7: 【0212】 The terminal displays the response sent from the server to the user. It receives response data from the server as input and outputs it by displaying it in a format that is easy for the user to understand. 【0213】 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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. 【0214】 Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0215】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14. 【0216】 [Second Embodiment] 【0217】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0218】 As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server. 【0219】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0220】 The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52. 【0221】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0222】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0223】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0224】 Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0225】 The specific processing program 56 is an example of a "program" relating to the technology of this 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. 【0226】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0227】 In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0228】 Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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". 【0229】 This invention provides an automated response system for responding quickly and efficiently to user inquiries. This system mainly includes a server, a user terminal, and an inquiry response database. 【0230】 Users submit inquiries through a chat interface from their device. This interface is intuitive and user-friendly, allowing users to input questions in text format. The device sends the entered inquiry to the server. The server receives this text information and prepares it for analysis. 【0231】 The server analyzes the received text data using a natural language processing (NLP) engine. This allows it to understand the user's intent and the subject of their inquiry, and extract relevant keywords. For example, if a user asks, "Tell me about the latest plans," the server recognizes important keywords such as "latest" and "plans." 【0232】 Next, the server searches the query response database based on these analysis results. This database contains past queries and their optimal responses, organized by category. For example, for queries related to "plans," the database entry would be in the format of "The latest information on the XX plan is XX." 【0233】 The server identifies the most appropriate response from the search results and generates a response for the user based on that. This response is programmed to be expressed in natural language that is easy for the user to understand. The generated response is sent from the server to the user's terminal and displayed on the chat interface. This allows the user to get an answer to their inquiry immediately. 【0234】 This system enables 24 / 7 / 365 support regardless of time or day of the week, ensuring prompt service delivery without compromising user satisfaction, even when sales representatives are unavailable. Furthermore, this implementation aims to free sales representatives from the simple task of handling inquiries, allowing them to focus on more advanced work. 【0235】 The following describes the processing flow. 【0236】 Step 1: 【0237】 Users enter their inquiries in text format through their own devices. These inquiries are conducted using a chat interface. 【0238】 Step 2: 【0239】 The terminal converts the text entered by the user into data packets and sends them to the server using a communication protocol. 【0240】 Step 3: 【0241】 The server receives data packets from the terminal and decodes the text data to analyze the query content. 【0242】 Step 4: 【0243】 The server uses a natural language processing (NLP) engine to analyze the received text and extract the user's intent and key keywords. This analysis identifies the category and purpose of the inquiry. 【0244】 Step 5: 【0245】 The server searches the query response database according to the analysis results. Based on the extracted keywords and categories, it searches the database for the most relevant answers. 【0246】 Step 6: 【0247】 The server generates a natural language response tailored to the user based on information retrieved from the database. This response is then adjusted to have an easily understandable sentence structure. 【0248】 Step 7: 【0249】 The server converts the generated response into a data packet and sends it to the user's terminal. 【0250】 Step 8: 【0251】 The terminal decodes the received data packets and displays the response on the user interface. This allows the user to instantly see the answer to their question. 【0252】 (Example 1) 【0253】 Next, we will describe Example 1. 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." 【0254】 Currently, many inquiry handling systems are required to respond to user inquiries quickly and accurately, but they have limitations when it comes to complex inquiries that cannot be handled by conventional rule-based approaches. Furthermore, it is difficult to consistently provide responses of the same quality regardless of the time of day or day of the week. In addition, existing systems have insufficient understanding of inquiry content, and more advanced natural language processing capabilities are needed to improve user satisfaction. 【0255】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0256】 In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries using natural language processing technology, and means for searching a pre-prepared inquiry response database based on the analysis results. This enables sophisticated and flexible responses to user inquiries using a generative AI model. 【0257】 A "user" refers to an individual or organization that uses the system to make an inquiry. 【0258】 An "inquiry" is a text-based form containing information or questions that the user wants to know. 【0259】 "Means of receiving" refers to the function that allows a computer system to acquire inquiries sent by users. 【0260】 "Natural language processing technology" refers to the technology used by computers to understand and analyze human language. 【0261】 "Means of analysis" refers to methods for deciphering received inquiries using natural language processing techniques and understanding their meaning. 【0262】 A "query response database" refers to a collection of information in which past queries and their corresponding responses are organized and stored. 【0263】 A "search method" is a function that finds relevant information within a database based on the analysis results. 【0264】 A "generative AI model" is a type of computer program that uses artificial intelligence to generate text in a natural-sounding format. 【0265】 "Means of generating a response" refers to the process of creating an appropriate answer to an inquiry. 【0266】 "Means of transmission" refers to the function that delivers the generated response to the user's device. 【0267】 A "prompt statement" refers to an input statement used to give instructions to a generating AI model. 【0268】 This invention relates to a system for automatically generating responses to user inquiries. This system mainly includes a server, a user terminal, and an inquiry response database. 【0269】 Users submit inquiries through the chat interface on their device. The chat interface is designed to be intuitive and easy to use, allowing users to easily input questions in text format. The submitted inquiry is then sent from the device to the server. 【0270】 The server analyzes the received text data using a natural language processing (NLP) engine. This NLP engine is used to understand the user's intent and the subject of the inquiry, and to extract relevant keywords. For example, if a user asks, "Please tell me the latest product information," the server will extract keywords such as "latest" and "product information." 【0271】 Next, the server searches the query response database based on these analysis results. This database stores past queries and their optimal responses, organized by category. For example, for queries related to "product information," the database contains an appropriate entry such as "The current latest product is XX." 【0272】 The server uses a generative AI model to generate an appropriate response based on the search results. This response is expressed in natural language that is easy for the user to understand. The generative AI model used here is optimized according to the user's intent and context. 【0273】 The generated response is sent from the server to the user's terminal and displayed on the chat interface. This allows the user to quickly obtain information regarding their inquiry. For example, a prompt could be instructed to the AI ​​model to "analyze the user's inquiry 'Please provide the latest product information' and generate a relevant response." As a result of this prompt, a response is generated and displayed. 【0274】 This embodiment allows users to consistently receive high-quality responses regardless of time or location, thus improving user satisfaction with the system. Furthermore, the server's automated response management optimizes human resources. 【0275】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0276】 Step 1: 【0277】 The user inputs an inquiry in text format from the chat interface of the terminal. The user's question text is generated as input data. This input is sent by the user's terminal to the server. 【0278】 Step 2: 【0279】 The server receives the text data sent from the terminal. To process the received data, the server first performs preprocessing such as character code conversion and deletion of unnecessary information. As a result, clean data for analysis is output. 【0280】 Step 3: 【0281】 The server analyzes the clean text data using a natural language processing (NLP) engine. The input here is the preprocessed data, and keywords or topics indicating the user's intent and concerns are extracted as output. For example, from an input like "Please tell me the latest product information", keywords such as "latest" and "product information" are output. 【0282】 Step 4: 【0283】 The server searches the inquiry response database based on the analysis results. In this process, relevant information is identified from the database based on the keywords. The input is the keywords of the analysis results, and the output is the relevant response candidates. 【0284】 Step 5: 【0285】 The server uses a generative AI model to generate a response for the user based on the response candidates obtained from the database. At this time, a prompt sentence is provided to the generative AI model, and a natural and easy-to-understand sentence is generated. The input is the response candidates and the prompt sentence, and the final response for presenting to the user is generated as the output. 【0286】 Step 6: 【0287】 The server sends the generated response to the user's terminal. The terminal displays this response on the chat interface. The input here is the response from the server, and the output is the final display content presented to the user. This enables the user to quickly confirm the answer. 【0288】 (Application Example 1) 【0289】 Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal". 【0290】 In modern e-commerce transactions, it is necessary to respond quickly and accurately to inquiries from a large number of users. However, it is difficult to appropriately respond to detailed inquiries regarding a wide variety of products using conventional methods, which causes a decrease in customer satisfaction and an increase in support costs. The purpose of the present invention is to solve these problems and provide a means for providing an efficient and highly accurate response. 【0291】 The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means. 【0292】 In this invention, the server includes a medium for receiving an inquiry from a user, a medium for analyzing the received inquiry using natural language processing technology, a medium for searching a pre-prepared inquiry response data structure based on the analysis result, a medium for generating a response to the user's inquiry based on the search result, a medium for sending the generated response to the user, and a medium for using an artificial intelligence model for providing product information in a shopping platform and obtaining related information from a database. This enables always responding to customer inquiries with optimized content, improving customer satisfaction and reducing operation costs. 【0293】 A "medium for receiving user inquiries" refers to a device or software that receives questions or requests for information from users to a system. 【0294】 A "medium analyzed using natural language processing technology" is a device or software that analyzes input text data in order for a server to understand the language that humans normally use. 【0295】 A "medium for searching query response data structures" refers to a device or software that performs the function of searching for a pre-prepared set of response data based on the results of analysis. 【0296】 A "medium for generating responses to user inquiries" refers to a device or software that takes search results into consideration and constructs an appropriate answer for the user. 【0297】 "The medium for sending the generated response to the user" refers to a device or software that has the role of delivering the constructed response to the user. 【0298】 An "artificial intelligence model for providing product information on a shopping platform" is a device or software that utilizes artificial intelligence technology to present product details in an online shopping environment and possesses analytical methods to provide users with the most relevant information. 【0299】 A "medium for retrieving related information from a database" refers to a device or software that retrieves information related to a product or service from its storage location. 【0300】 The system implementing this invention consists of a central server and terminals for receiving user inquiries. The server is equipped with a natural language processing engine, analyzes inquiries, and generates the optimal response based on the analysis results. Specifically, the server uses natural language processing technology to interpret the text data received from the user. In this process, keywords and sentences are extracted from the input inquiry and data is processed to understand the user's intent. 【0301】 The server leverages existing natural language processing technologies, such as the Google Cloud Natural Language API. After keyword extraction, the server quickly searches the query-response data structure to identify the most appropriate response. This ensures consistent information delivery, allowing users to quickly obtain the information they need. 【0302】 The terminal used is the user's smartphone or computer, allowing them to make inquiries through an intuitive interface. The generated response is immediately sent to the terminal and displayed on the screen, so the user can obtain information instantly and promotes continuous engagement. 【0303】 For example, if a user asks "What sizes are available for this product?" through a shopping platform application, the system recognizes "size" as a keyword and retrieves relevant information from its database. As a result, it provides a response such as "This product is available in sizes S, M, L, and XL." 【0304】 An example of a prompt using a generative AI model is: "Question: Does this product come in other colors? Answer: Yes, this product comes in blue, red, and green." This demonstrates the ability to generate natural responses that are relevant to the conversation with the user. 【0305】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0306】 Step 1: 【0307】 The user uses the terminal to input an inquiry through the chat interface. Text data is generated as the input, and the terminal sends this data to the server. The output is the text data containing the inquiry content. 【0308】 Step 2: 【0309】 The server passes the received text data to the natural language processing engine and starts analysis. The input is the text data. Keywords and sentences are extracted using natural language processing techniques to understand the user's intention. The output at this stage is the data containing the analyzed keywords and intention. As a specific operation, the Google Cloud Natural Language API is used to interpret the context. 【0310】 Step 3: 【0311】 The server searches the pre-prepared inquiry response data structure based on the analysis result. The input is the data of the analysis result, and relevant information is quickly obtained from the database. The output is the relevant response data. In this process, a database query is used to identify the optimal response. 【0312】 Step 4: 【0313】 The server generates a response to the user's inquiry based on the retrieved information. The input is the response data, and a generative AI model is used to create a natural language response. The output is the natural language response to be provided to the user. Here, for example, the operation of forming a sentence based on a prompt sentence using a generative AI model is included. 【0314】 Step 5: 【0315】 The server sends the generated response to the user's terminal. The input is response data in natural language, and the output is a text message displayed on the terminal's user interface. The specific operation includes a process of sending data back to the terminal via the network. 【0316】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0317】 This invention establishes a system that provides more appropriate and personalized responses to user inquiries by combining an emotion analysis engine that analyzes the user's emotions with an automated response system for user inquiries. This system includes a server, a user terminal, a natural language processing (NLP) engine, an emotion analysis engine, and an inquiry response database. 【0318】 First, the user makes an inquiry via a chat interface. The terminal converts this into digital data and sends it to the server. The server then analyzes the received data using a natural language processing engine to identify the user's intent and topic, which is the same as before. 【0319】 Furthermore, in this invention, the server uses a sentiment analysis engine to identify the emotional nuances contained in the inquiry text. This makes it possible to identify emotions such as joy, anger, and sadness expressed by the user. For example, from the user's inquiry, "I am disappointed with the recent service. Please tell me why," the sentiment analysis engine recognizes "disappointment." 【0320】 The server integrates the results of this sentiment analysis with the results of natural language processing and searches the query response database. As a result, the selected response not only provides information but also takes the user's emotions into consideration. For example, if disappointment is recognized, the response will be generated to provide specific information while also including comfort and apologies. 【0321】 The server then generates an optimal response based on the user's emotions and context, and sends it to the user's terminal. The user can receive this response in real time, and the entire system aims to provide a service that exceeds the user's expectations. 【0322】 This system is expected to increase customer satisfaction and improve trust in and favorability towards the company's services. Furthermore, because the server consistently provides quick and accurate responses that consider the user's emotions and intentions, it creates an environment where sales representatives can focus on complex inquiries. 【0323】 The following describes the processing flow. 【0324】 Step 1: 【0325】 Users access the chat interface using their own devices and enter their inquiries in text format. These inquiries can be specific questions or feedback on their user experience. 【0326】 Step 2: 【0327】 The terminal converts the input text into digital data packets and sends them to the server. This conversion is performed according to the communication protocol, maintaining data integrity. 【0328】 Step 3: 【0329】 The server receives data sent from the terminal and decodes the text content. The received content is then passed to a natural language processing engine, which prepares it for analyzing the user's intent. 【0330】 Step 4: 【0331】 The server uses a natural language processing engine to analyze the text and understand the subject and intent of the query. At this stage, it identifies key keywords and, based on them, determines the response category. 【0332】 Step 5: 【0333】 The server inputs the analyzed text into a sentiment analysis engine to evaluate the user's emotional state. The sentiment analysis engine identifies emotions such as joy, anger, and sadness based on the words and expressions in the text. 【0334】 Step 6: 【0335】 The server combines the results of natural language processing analysis with the results of sentiment analysis and searches a query response database. This database contains responses in an appropriate tone according to the emotion. 【0336】 Step 7: 【0337】 The server adjusts its response to include a tone that is sensitive to the user's emotions when generating the best possible response from search results. For example, if user dissatisfaction is detected, it will add words of comfort. 【0338】 Step 8: 【0339】 The server sends the generated response as a digital data packet to the user's terminal. Transmission is performed quickly while ensuring communication security. 【0340】 Step 9: 【0341】 The terminal receives responses sent from the server and decodes them for display to the user. Users can view the responses in real time on the chat interface. 【0342】 (Example 2) 【0343】 Next, we will describe Example 2. 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". 【0344】 Traditional automated response systems often generate responses to user inquiries without considering emotional context, potentially leading to decreased customer satisfaction. There is a need to solve this problem and provide more appropriate, personalized responses. 【0345】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0346】 In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries using natural language processing techniques, and means for using sentiment analysis techniques to identify the user's emotions from the analyzed results. This makes it possible to generate responses that take the user's emotions into consideration. 【0347】 A "user" is the entity that makes a query to a system and receives a response. 【0348】 An "inquiry" is information that represents a question or request that a user sends to a system. 【0349】 "Natural language processing technology" is a technology that uses computers to analyze and understand human language. 【0350】 A "data set" is a collection of pre-prepared information and responses that are retrieved based on a query. 【0351】 "Sentiment analysis technology" is a technique for identifying and classifying emotional expressions within text. 【0352】 A "response" is the information or message that a system provides in response to a user's inquiry. 【0353】 This invention is a system that provides an automated response that takes emotions into account in response to a user's inquiry. The system is comprised of a server, a user's terminal, natural language processing technology, sentiment analysis technology, and a set of inquiry response data. 【0354】 First, the user makes a request via their device. The user's device then sends this as digital data to the server. The device typically has an operating system and interface software installed, which makes this data transmission process efficient. 【0355】 The server analyzes the received query data using natural language processing (NLP) techniques. Specifically, it uses open-source NLP libraries or commercial NLP platforms to identify the user's intent and subject matter. Typical tools include natural language models provided by academic institutions and companies. 【0356】 Next, the server applies sentiment analysis technology to identify the emotions contained in the query. This allows it to grasp the emotional nuances expressed by the user. Sentiment analysis uses text analysis tools and APIs to classify the user's emotions into categories such as "joy," "sadness," and "anger." 【0357】 For example, if a user asks, "I'm dissatisfied with the service. Please tell me why," the server can identify the emotion of "dissatisfaction" from this sentence. Based on this, when generating a response, it can include specific information or comforting expressions that correspond to this emotion. 【0358】 As a concrete example of a prompt, we will show the process of inputting "The user is dissatisfied with the quality of service. How should you respond?" into an AI model and having the model generate an appropriate response example. 【0359】 This system aims to improve customer satisfaction by quickly and accurately generating responses that are tailored to the user's emotional state. 【0360】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0361】 Step 1: 【0362】 The user uses a terminal to enter and submit their inquiry. The entered data is in text format and includes specific inquiry details such as, "I am dissatisfied with the service. Please tell me why." The terminal packets this text data and sends it to the server over the network. 【0363】 Step 2: 【0364】 The server receives data sent from the terminal. It stores the received data in a format suitable for text parsing and passes it on to the next process. The output of this process is text data containing the query content. 【0365】 Step 3: 【0366】 The server uses natural language processing techniques to analyze the received text data. The input for this process is text data, and a language model is applied to identify the user's intent and subject matter. For example, a generative AI model is used to extract intents such as "dissatisfaction" or "wanting to know the reason." This analysis result is then passed on to the next stage. 【0367】 Step 4: 【0368】 The server uses sentiment analysis technology to identify emotions from the analyzed text. The input data is the analysis results obtained in step 3. In this process, the sentiment analysis tool is used to classify emotions into categories such as "anxiety" and "dissatisfaction." The identified emotion information is then used in the next process. 【0369】 Step 5: 【0370】 The server searches the database based on the user's intent and emotional information obtained. The input is the information obtained in steps 3 and 4. From the search results, it selects and generates the most appropriate response. For example, it might select a situation-appropriate apology message and problem-solving suggestions from the database. 【0371】 Step 6: 【0372】 The server sends the generated response to the user's terminal. The output is a text message displayed to the user. The user receives this response and can view it in real time. 【0373】 (Application Example 2) 【0374】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0375】 Traditional automated response systems focus solely on providing information in response to user inquiries, lacking consideration for user emotions. This leads to a poor user experience and, consequently, lower customer satisfaction. There is a need to improve this situation and provide rapid, personalized responses that are based on user emotions. 【0376】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0377】 In this invention, the server includes a device for receiving requests from users, a device for analyzing the received requests using natural language processing technology, and an emotion analysis device for analyzing the emotions contained in the user's requests. This makes it possible to take the user's emotional state into consideration and provide an individualized response. 【0378】 "User requests" are messages or questions that users send to the system to request information or support. 【0379】 A "device" is a set of hardware or software components designed to perform a specific function. 【0380】 "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language, making natural dialogue possible. 【0381】 A "data set" is a structured collection of information that includes pre-prepared information and responses to address various requests. 【0382】 An "emotion analysis device" is a technology or system for identifying and analyzing the emotional elements contained in user requests. 【0383】 A "response adjustment device" is a system that has the function of automatically changing or optimizing response content based on the results of sentiment analysis. 【0384】 To implement this invention, a program is required that runs on the user's terminal and on a server. The program uses natural language processing and sentiment analysis techniques to receive requests from the user and analyze their content. 【0385】 The server first parses the received request using natural language processing techniques, such as the spaCy library, to identify the user's intent. Then, it uses sentiment analysis with the Google Cloud Natural Language API to recognize the emotions contained in the request. This allows the server to extract the emotions the user is expressing (e.g., joy, anger, sadness). 【0386】 Next, the server searches a pre-prepared database based on the analyzed intent and emotional information, and generates a personalized response that takes the user's emotions into account. In generating the response, the most appropriate message corresponding to the emotional state is selected and adjusted into a natural dialogue format using an AI model. 【0387】 The generated response is sent to the user's terminal in real time, allowing the user to feel as if they are interacting with a human operator. This process is expected to improve customer satisfaction. 【0388】 For example, if a user inquires that "a recently ordered item arrived late," the system can provide detailed information on measures to prevent future delays and generate an apology message based on sentiment analysis. 【0389】 An example of a prompt for a generative AI model is: "Based on the user's inquiry, generate a response that takes their emotions into consideration." 【0390】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0391】 Step 1: 【0392】 The terminal takes user requests as text data and sends that data to the server in digital format. Raw text is provided as input to the server. 【0393】 Step 2: 【0394】 The server uses natural language processing techniques (e.g., the spaCy library) to analyze the received text data and identify the user's intent. The input is the user's request text, which is then analyzed to extract keywords related to the subject and intent, resulting in structured intent data as output. 【0395】 Step 3: 【0396】 The server uses the Google Cloud Natural Language API to analyze the sentiment within the text data. The input is the user request text mentioned earlier, and by performing sentiment analysis on it, it obtains numerical data representing emotions such as joy and anger as output. 【0397】 Step 4: 【0398】 The server combines the results of natural language processing (intent data) and sentiment analysis to search a pre-prepared dataset. The input consists of intent data and sentiment data, which are used to search the dataset for the record with the most appropriate response, and the appropriate response data is obtained as output. 【0399】 Step 5: 【0400】 The server uses an AI model to refine the acquired response data and generate natural, conversational responses that take the user's emotions into consideration. It receives response data from the previous step as input and outputs natural language responses appropriate to the emotional state. 【0401】 Step 6: 【0402】 The server sends the final generated response to the terminal in response to the request. The generated response is the input, and the transmission to the terminal is the output. 【0403】 Step 7: 【0404】 The terminal displays the response sent from the server to the user. It receives response data from the server as input and outputs it by displaying it in a format that is easy for the user to understand. 【0405】 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0406】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0407】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214. 【0408】 [Third Embodiment] 【0409】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0410】 As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server. 【0411】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0412】 The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52. 【0413】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0414】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0415】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0416】 Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0417】 The specific processing program 56 is an example of a "program" relating to the technology of this 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. 【0418】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0419】 In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0420】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal". 【0421】 This invention provides an automated response system for responding quickly and efficiently to user inquiries. This system mainly includes a server, a user terminal, and an inquiry response database. 【0422】 Users submit inquiries through a chat interface from their device. This interface is intuitive and user-friendly, allowing users to input questions in text format. The device sends the entered inquiry to the server. The server receives this text information and prepares it for analysis. 【0423】 The server analyzes the received text data using a natural language processing (NLP) engine. This allows it to understand the user's intent and the subject of their inquiry, and extract relevant keywords. For example, if a user asks, "Tell me about the latest plans," the server recognizes important keywords such as "latest" and "plans." 【0424】 Next, the server searches the query response database based on these analysis results. This database contains past queries and their optimal responses, organized by category. For example, for queries related to "plans," the database entry would be in the format of "The latest information on the XX plan is XX." 【0425】 The server identifies the most appropriate response from the search results and generates a response for the user based on that. This response is programmed to be expressed in natural language that is easy for the user to understand. The generated response is sent from the server to the user's terminal and displayed on the chat interface. This allows the user to get an answer to their inquiry immediately. 【0426】 This system enables 24 / 7 / 365 support regardless of time or day of the week, ensuring prompt service delivery without compromising user satisfaction, even when sales representatives are unavailable. Furthermore, this implementation aims to free sales representatives from the simple task of handling inquiries, allowing them to focus on more advanced work. 【0427】 The following describes the processing flow. 【0428】 Step 1: 【0429】 Users enter their inquiries in text format through their own devices. These inquiries are conducted using a chat interface. 【0430】 Step 2: 【0431】 The terminal converts the text entered by the user into data packets and sends them to the server using a communication protocol. 【0432】 Step 3: 【0433】 The server receives data packets from the terminal and decodes the text data to analyze the query content. 【0434】 Step 4: 【0435】 The server uses a natural language processing (NLP) engine to analyze the received text and extract the user's intent and key keywords. This analysis identifies the category and purpose of the inquiry. 【0436】 Step 5: 【0437】 The server searches the query response database according to the analysis results. Based on the extracted keywords and categories, it searches the database for the most relevant answers. 【0438】 Step 6: 【0439】 The server generates a natural language response tailored to the user based on information retrieved from the database. This response is then adjusted to have an easily understandable sentence structure. 【0440】 Step 7: 【0441】 The server converts the generated response into a data packet and sends it to the user's terminal. 【0442】 Step 8: 【0443】 The terminal decodes the received data packets and displays the response on the user interface. This allows the user to instantly see the answer to their question. 【0444】 (Example 1) 【0445】 Next, we will describe Example 1. 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." 【0446】 Currently, many inquiry handling systems are required to respond to user inquiries quickly and accurately, but they have limitations when it comes to complex inquiries that cannot be handled by conventional rule-based approaches. Furthermore, it is difficult to consistently provide responses of the same quality regardless of the time of day or day of the week. In addition, existing systems have insufficient understanding of inquiry content, and more advanced natural language processing capabilities are needed to improve user satisfaction. 【0447】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0448】 In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries using natural language processing technology, and means for searching a pre-prepared inquiry response database based on the analysis results. This enables sophisticated and flexible responses to user inquiries using a generative AI model. 【0449】 A "user" refers to an individual or organization that uses the system to make an inquiry. 【0450】 An "inquiry" is a text-based form containing information or questions that the user wants to know. 【0451】 "Means of receiving" refers to the function that allows a computer system to acquire inquiries sent by users. 【0452】 "Natural language processing technology" refers to the technology used by computers to understand and analyze human language. 【0453】 "Means of analysis" refers to methods for deciphering received inquiries using natural language processing techniques and understanding their meaning. 【0454】 A "query response database" refers to a collection of information in which past queries and their corresponding responses are organized and stored. 【0455】 A "search method" refers to a function that finds relevant information within a database based on the analysis results. 【0456】 A "generative AI model" is a type of computer program that uses artificial intelligence to generate text in a natural-sounding format. 【0457】 "Means of generating a response" refers to the process of creating an appropriate answer to an inquiry. 【0458】 "Means of transmission" refers to the function that delivers the generated response to the user's device. 【0459】 A "prompt statement" refers to an input statement used to give instructions to a generating AI model. 【0460】 This invention relates to a system for automatically generating responses to user inquiries. This system mainly includes a server, a user terminal, and an inquiry response database. 【0461】 Users submit inquiries through the chat interface on their device. The chat interface is designed to be intuitive and easy to use, allowing users to easily input questions in text format. The submitted inquiry is then sent from the device to the server. 【0462】 The server analyzes the received text data using a natural language processing (NLP) engine. This NLP engine is used to understand the user's intent and the subject of the inquiry, and to extract relevant keywords. For example, if a user asks, "Please tell me the latest product information," the server will extract keywords such as "latest" and "product information." 【0463】 Next, the server searches the query response database based on these analysis results. This database stores past queries and their optimal responses, organized by category. For example, for queries related to "product information," the database contains an appropriate entry such as "The current latest product is XX." 【0464】 The server uses a generative AI model to generate an appropriate response based on the search results. This response is expressed in natural language that is easy for the user to understand. The generative AI model used here is optimized according to the user's intent and context. 【0465】 The generated response is sent from the server to the user's terminal and displayed on the chat interface. This allows the user to quickly obtain information regarding their inquiry. For example, a prompt could be instructed to the AI ​​model to "analyze the user's inquiry 'Please provide the latest product information' and generate a relevant response." As a result of this prompt, a response is generated and displayed. 【0466】 This embodiment allows users to consistently receive high-quality responses regardless of time or location, thus improving user satisfaction with the system. Furthermore, the server's automated response management optimizes human resources. 【0467】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0468】 Step 1: 【0469】 The user enters their inquiry in text format through the chat interface on their device. The user's question text is generated as input data. This input is sent to the server by the user's device. 【0470】 Step 2: 【0471】 The server receives text data sent from the terminal. To process the received data, the server first performs preprocessing, such as converting character codes and removing unnecessary information. This results in clean data for analysis. 【0472】 Step 3: 【0473】 The server uses a natural language processing (NLP) engine to analyze clean text data. The input is pre-processed data, and the output extracts keywords and topics that indicate the user's intent and interests. For example, from the input "Please tell me the latest product information," keywords such as "latest" and "product information" will be output. 【0474】 Step 4: 【0475】 The server searches the query response database based on the analysis results. In this process, relevant information is identified from the database based on keywords. The input is the keywords from the analysis results, and the output is the relevant response candidates. 【0476】 Step 5: 【0477】 The server uses a generative AI model to generate user-facing responses based on response candidates retrieved from a database. In this process, prompt text is provided to the generative AI model, resulting in the generation of natural and easily understandable sentences. The input consists of response candidates and prompt text, and the output is a final response to be presented to the user. 【0478】 Step 6: 【0479】 The server sends the generated response to the user's terminal. The terminal displays this response on the chat interface. The input here is the response from the server, and the output is the final display presented to the user. This allows the user to quickly confirm the answer. 【0480】 (Application Example 1) 【0481】 Next, we will explain Application Example 1. In the following explanation, 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." 【0482】 In modern e-commerce, it is necessary to respond quickly and accurately to inquiries from a large number of users. However, conventional methods make it difficult to adequately respond to detailed inquiries about a wide variety of products, leading to decreased customer satisfaction and increased support costs. The present invention aims to solve these problems and provide a means to provide efficient and highly accurate responses. 【0483】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0484】 In this invention, the server includes a medium for receiving user inquiries, a medium for analyzing the received inquiries using natural language processing technology, a medium for searching a pre-prepared inquiry response data structure based on the analysis results, a medium for generating a response to the user's inquiry based on the search results, a medium for sending the generated response to the user, and a medium for using an artificial intelligence model for providing product information on a shopping platform to retrieve relevant information from a database. This enables the server to always respond to customer inquiries with optimized content, improving customer satisfaction and reducing operating costs. 【0485】 A "medium for receiving user inquiries" refers to a device or software that receives questions or requests for information from users to a system. 【0486】 A "medium analyzed using natural language processing technology" is a device or software that analyzes input text data in order for a server to understand the language that humans normally use. 【0487】 A "medium for searching query response data structures" refers to a device or software that performs the function of searching for a pre-prepared set of response data based on the results of analysis. 【0488】 A "medium for generating responses to user inquiries" refers to a device or software that takes search results into consideration and constructs an appropriate answer for the user. 【0489】 "The medium for sending the generated response to the user" refers to a device or software that has the role of delivering the constructed response to the user. 【0490】 An "artificial intelligence model for providing product information on a shopping platform" is a device or software that utilizes artificial intelligence technology to present product details in an online shopping environment and possesses analytical methods to provide users with the most relevant information. 【0491】 A "medium for retrieving related information from a database" refers to a device or software that retrieves information related to a product or service from its storage location. 【0492】 The system implementing this invention consists of a central server and terminals for receiving user inquiries. The server is equipped with a natural language processing engine, analyzes inquiries, and generates the optimal response based on the analysis results. Specifically, the server uses natural language processing technology to interpret the text data received from the user. In this process, keywords and sentences are extracted from the input inquiry and data is processed to understand the user's intent. 【0493】 The server leverages existing natural language processing technologies, such as the Google Cloud Natural Language API. After keyword extraction, the server quickly searches the query-response data structure to identify the most appropriate response. This ensures consistent information delivery, allowing users to quickly obtain the information they need. 【0494】 The terminal used is the user's smartphone or computer, allowing them to make inquiries through an intuitive interface. The generated response is immediately sent to the terminal and displayed on the screen, so the user can obtain information instantly and promotes continuous engagement. 【0495】 For example, if a user asks "What sizes are available for this product?" through a shopping platform application, the system recognizes "size" as a keyword and retrieves relevant information from its database. As a result, it provides a response such as "This product is available in sizes S, M, L, and XL." 【0496】 An example of a prompt using a generative AI model is: "Question: Does this product come in other colors? Answer: Yes, this product comes in blue, red, and green." This demonstrates the ability to generate natural responses that are relevant to the conversation with the user. 【0497】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0498】 Step 1: 【0499】 The user enters their inquiry through a chat interface using their device. Text data is generated as input, and the device sends this data to the server. The output is text data containing the inquiry. 【0500】 Step 2: 【0501】 The server passes the received text data to the natural language processing engine and begins analysis. The input is text data, and natural language processing techniques are used to extract keywords and sentences and understand the user's intent. The output at this stage is data containing the analyzed keywords and intent. Specifically, the Google Cloud Natural Language API is used to interpret the context. 【0502】 Step 3: 【0503】 The server searches a pre-defined query response data structure based on the analysis results. The input is the analysis results data, and relevant information is quickly retrieved from the database. The output is the relevant response data. This process uses database queries to identify the optimal response. 【0504】 Step 4: 【0505】 The server generates responses to user inquiries based on the information it has retrieved. The input is response data, and a generative AI model is used to create natural language responses. The output is the natural language response provided to the user. This includes, for example, the formation of sentences based on prompts using a generative AI model. 【0506】 Step 5: 【0507】 The server sends the generated response to the user's terminal. The input is response data in natural language, and the output is a text message displayed on the terminal's user interface. The specific operation includes a process of sending data back to the terminal via the network. 【0508】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0509】 This invention establishes a system that provides more appropriate and personalized responses to user inquiries by combining an emotion analysis engine that analyzes the user's emotions with an automated response system for user inquiries. This system includes a server, a user terminal, a natural language processing (NLP) engine, an emotion analysis engine, and an inquiry response database. 【0510】 First, the user makes an inquiry via a chat interface. The terminal converts this into digital data and sends it to the server. The server then analyzes the received data using a natural language processing engine to identify the user's intent and topic, which is the same as before. 【0511】 Furthermore, in this invention, the server uses a sentiment analysis engine to identify the emotional nuances contained in the inquiry text. This makes it possible to identify emotions such as joy, anger, and sadness expressed by the user. For example, from the user's inquiry, "I am disappointed with the recent service. Please tell me why," the sentiment analysis engine recognizes "disappointment." 【0512】 The server integrates the results of this sentiment analysis with the results of natural language processing and searches the query response database. As a result, the selected response not only provides information but also takes the user's emotions into consideration. For example, if disappointment is recognized, the response will be generated to provide specific information while also including comfort and apologies. 【0513】 The server then generates an optimal response based on the user's emotions and context, and sends it to the user's terminal. The user can receive this response in real time, and the entire system aims to provide a service that exceeds the user's expectations. 【0514】 This system is expected to increase customer satisfaction and improve trust in and favorability towards the company's services. Furthermore, because the server consistently provides quick and accurate responses that consider the user's emotions and intentions, it creates an environment where sales representatives can focus on complex inquiries. 【0515】 The following describes the processing flow. 【0516】 Step 1: 【0517】 Users access the chat interface using their own devices and enter their inquiries in text format. These inquiries can be specific questions or feedback on their user experience. 【0518】 Step 2: 【0519】 The terminal converts the input text into digital data packets and sends them to the server. This conversion is performed according to the communication protocol, maintaining data integrity. 【0520】 Step 3: 【0521】 The server receives data sent from the terminal and decodes the text content. The received content is then passed to a natural language processing engine, which prepares it for analyzing the user's intent. 【0522】 Step 4: 【0523】 The server uses a natural language processing engine to analyze the text and understand the subject and intent of the query. At this stage, it identifies key keywords and, based on them, determines the response category. 【0524】 Step 5: 【0525】 The server inputs the analyzed text into a sentiment analysis engine to evaluate the user's emotional state. The sentiment analysis engine identifies emotions such as joy, anger, and sadness based on the words and expressions in the text. 【0526】 Step 6: 【0527】 The server combines the results of natural language processing analysis with the results of sentiment analysis and searches a query response database. This database contains responses in an appropriate tone according to the emotion. 【0528】 Step 7: 【0529】 The server adjusts its response to include a tone that is sensitive to the user's emotions when generating the best possible response from search results. For example, if user dissatisfaction is detected, it will add words of comfort. 【0530】 Step 8: 【0531】 The server sends the generated response as a digital data packet to the user's terminal. Transmission is performed quickly while ensuring communication security. 【0532】 Step 9: 【0533】 The terminal receives responses sent from the server and decodes them for display to the user. Users can view the responses in real time on the chat interface. 【0534】 (Example 2) 【0535】 Next, we will describe Example 2. 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." 【0536】 Traditional automated response systems often generate responses to user inquiries without considering emotional context, potentially leading to decreased customer satisfaction. There is a need to solve this problem and provide more appropriate, personalized responses. 【0537】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0538】 In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries using natural language processing techniques, and means for using sentiment analysis techniques to identify the user's emotions from the analyzed results. This makes it possible to generate responses that take the user's emotions into consideration. 【0539】 A "user" is the entity that makes a query to a system and receives a response. 【0540】 An "inquiry" is information that represents a question or request that a user sends to a system. 【0541】 "Natural language processing technology" is a technology that uses computers to analyze and understand human language. 【0542】 A "data set" is a collection of pre-prepared information and responses that are retrieved based on a query. 【0543】 "Sentiment analysis technology" is a technique for identifying and classifying emotional expressions within text. 【0544】 A "response" is the information or message that a system provides in response to a user's inquiry. 【0545】 This invention is a system that provides an automated response that takes emotions into account in response to a user's inquiry. The system is comprised of a server, a user's terminal, natural language processing technology, sentiment analysis technology, and a set of inquiry response data. 【0546】 First, the user makes a request via their device. The user's device then sends this as digital data to the server. The device typically has an operating system and interface software installed, which makes this data transmission process efficient. 【0547】 The server analyzes the received query data using natural language processing (NLP) techniques. Specifically, it uses open-source NLP libraries or commercial NLP platforms to identify the user's intent and subject matter. Typical tools include natural language models provided by academic institutions and companies. 【0548】 Next, the server applies sentiment analysis technology to identify the emotions contained in the query. This allows it to grasp the emotional nuances expressed by the user. Sentiment analysis uses text analysis tools and APIs to classify the user's emotions into categories such as "joy," "sadness," and "anger." 【0549】 For example, if a user asks, "I'm dissatisfied with the service. Please tell me why," the server can identify the emotion of "dissatisfaction" from this sentence. Based on this, when generating a response, it can include specific information or comforting expressions that correspond to this emotion. 【0550】 As a concrete example of a prompt, we will show the process of inputting "The user is dissatisfied with the quality of service. How should you respond?" into an AI model and having the model generate an appropriate response example. 【0551】 This system aims to improve customer satisfaction by quickly and accurately generating responses that are tailored to the user's emotional state. 【0552】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0553】 Step 1: 【0554】 The user uses a terminal to enter and submit their inquiry. The entered data is in text format and includes specific inquiry details such as, "I am dissatisfied with the service. Please tell me why." The terminal packets this text data and sends it to the server over the network. 【0555】 Step 2: 【0556】 The server receives data sent from the terminal. It stores the received data in a format suitable for text parsing and passes it on to the next process. The output of this process is text data containing the query content. 【0557】 Step 3: 【0558】 The server uses natural language processing techniques to analyze the received text data. The input for this process is text data, and a language model is applied to identify the user's intent and subject matter. For example, a generative AI model is used to extract intents such as "dissatisfaction" or "wanting to know the reason." This analysis result is then passed on to the next stage. 【0559】 Step 4: 【0560】 The server uses sentiment analysis technology to identify emotions from the analyzed text. The input data is the analysis results obtained in step 3. In this process, the sentiment analysis tool is used to classify emotions into categories such as "anxiety" and "dissatisfaction." The identified emotion information is then used in the next process. 【0561】 Step 5: 【0562】 The server searches the database based on the user's intent and sentiment information obtained. The input is the information obtained in steps 3 and 4. From the search results, it selects and generates the most appropriate response. For example, it might select an apology message and a problem-solving suggestion that are appropriate for the situation from the database. 【0563】 Step 6: 【0564】 The server sends the generated response to the user's terminal. The output is a text message displayed to the user. The user receives this response and can view it in real time. 【0565】 (Application Example 2) 【0566】 Next, we will explain application example 2. In the following explanation, 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." 【0567】 Traditional automated response systems focus solely on providing information in response to user inquiries, lacking consideration for user emotions. This leads to a poor user experience and, consequently, lower customer satisfaction. There is a need to improve this situation and provide rapid, personalized responses that are based on user emotions. 【0568】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0569】 In this invention, the server includes a device for receiving requests from users, a device for analyzing the received requests using natural language processing technology, and an emotion analysis device for analyzing the emotions contained in the user's requests. This makes it possible to take the user's emotional state into consideration and provide an individualized response. 【0570】 "User requests" are messages or questions that users send to the system to request information or support. 【0571】 A "device" is a set of hardware or software components designed to perform a specific function. 【0572】 "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language, making natural dialogue possible. 【0573】 A "data set" is a structured collection of information that includes pre-prepared information and responses to address various requests. 【0574】 An "emotion analysis device" is a technology or system for identifying and analyzing the emotional elements contained in user requests. 【0575】 A "response adjustment device" is a system that has the function of automatically changing or optimizing response content based on the results of sentiment analysis. 【0576】 To implement this invention, a program is required that runs on the user's terminal and on a server. The program uses natural language processing and sentiment analysis techniques to receive requests from the user and analyze their content. 【0577】 The server first parses the received request using natural language processing techniques, such as the spaCy library, to identify the user's intent. Then, it uses sentiment analysis with the Google Cloud Natural Language API to recognize the emotions contained in the request. This allows the server to extract the emotions the user is expressing (e.g., joy, anger, sadness). 【0578】 Next, the server searches a pre-prepared database based on the analyzed intent and emotional information, and generates a personalized response that takes the user's emotions into account. In generating the response, the most appropriate message corresponding to the emotional state is selected and adjusted into a natural dialogue format using an AI model. 【0579】 The generated response is sent to the user's terminal in real time, allowing the user to feel as if they are interacting with a human operator. This process is expected to improve customer satisfaction. 【0580】 For example, if a user inquires that "a recently ordered item arrived late," the system can provide detailed information on measures to prevent future delays and generate an apology message based on sentiment analysis. 【0581】 An example of a prompt for a generative AI model is: "Based on the user's inquiry, generate a response that takes their emotions into consideration." 【0582】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0583】 Step 1: 【0584】 The terminal takes user requests as text data and sends that data to the server in digital format. Raw text is provided as input to the server. 【0585】 Step 2: 【0586】 The server uses natural language processing techniques (e.g., the spaCy library) to analyze the received text data and identify the user's intent. The input is the user's request text, which is then analyzed to extract keywords related to the subject and intent, resulting in structured intent data as output. 【0587】 Step 3: 【0588】 The server uses the Google Cloud Natural Language API to analyze the sentiment within the text data. The input is the user request text mentioned earlier, and by performing sentiment analysis on it, it obtains numerical data representing emotions such as joy and anger as output. 【0589】 Step 4: 【0590】 The server combines the results of natural language processing (intent data) and sentiment analysis to search a pre-prepared dataset. The input consists of intent data and sentiment data, which are used to search the dataset for the record with the most appropriate response, and the appropriate response data is obtained as output. 【0591】 Step 5: 【0592】 The server uses an AI model to refine the acquired response data and generate natural, conversational responses that take the user's emotions into consideration. It receives response data from the previous step as input and outputs natural language responses appropriate to the emotional state. 【0593】 Step 6: 【0594】 The server sends the final generated response to the terminal in response to the request. The generated response is the input, and the transmission to the terminal is the output. 【0595】 Step 7: 【0596】 The terminal displays the response sent from the server to the user. It receives response data from the server as input and outputs it by displaying it in a format that is easy for the user to understand. 【0597】 The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0598】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0599】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314. 【0600】 [Fourth Embodiment] 【0601】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0602】 As shown in Figure 7, the 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. 【0603】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0604】 The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52. 【0605】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0606】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0607】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0608】 The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes. 【0609】 Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0610】 The specific processing program 56 is an example of a "program" relating to the technology of this 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. 【0611】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0612】 In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0613】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0614】 This invention provides an automated response system for responding quickly and efficiently to user inquiries. This system mainly includes a server, a user terminal, and an inquiry response database. 【0615】 Users submit inquiries through a chat interface from their device. This interface is intuitive and user-friendly, allowing users to input questions in text format. The device sends the entered inquiry to the server. The server receives this text information and prepares it for analysis. 【0616】 The server analyzes the received text data using a natural language processing (NLP) engine. This allows it to understand the user's intent and the subject of their inquiry, and extract relevant keywords. For example, if a user asks, "Tell me about the latest plans," the server recognizes important keywords such as "latest" and "plans." 【0617】 Next, the server searches the query response database based on these analysis results. This database contains past queries and their optimal responses, organized by category. For example, for queries related to "plans," the database entry would be in the format of "The latest information on the XX plan is XX." 【0618】 The server identifies the most appropriate response from the search results and generates a response for the user based on that. This response is programmed to be expressed in natural language that is easy for the user to understand. The generated response is sent from the server to the user's terminal and displayed on the chat interface. This allows the user to get an answer to their inquiry immediately. 【0619】 This system enables 24 / 7 / 365 support regardless of time or day of the week, ensuring prompt service delivery without compromising user satisfaction, even when sales representatives are unavailable. Furthermore, this implementation aims to free sales representatives from the simple task of handling inquiries, allowing them to focus on more advanced work. 【0620】 The following describes the processing flow. 【0621】 Step 1: 【0622】 Users enter their inquiries in text format through their own devices. These inquiries are conducted using a chat interface. 【0623】 Step 2: 【0624】 The terminal converts the text entered by the user into data packets and sends them to the server using a communication protocol. 【0625】 Step 3: 【0626】 The server receives data packets from the terminal and decodes the text data to analyze the query content. 【0627】 Step 4: 【0628】 The server uses a natural language processing (NLP) engine to analyze the received text and extract the user's intent and key keywords. This analysis identifies the category and purpose of the inquiry. 【0629】 Step 5: 【0630】 The server searches the query response database according to the analysis results. Based on the extracted keywords and categories, it searches the database for the most relevant answers. 【0631】 Step 6: 【0632】 The server generates a natural language response tailored to the user based on information retrieved from the database. This response is then adjusted to have an easily understandable sentence structure. 【0633】 Step 7: 【0634】 The server converts the generated response into a data packet and sends it to the user's terminal. 【0635】 Step 8: 【0636】 The terminal decodes the received data packets and displays the response on the user interface. This allows the user to instantly see the answer to their question. 【0637】 (Example 1) 【0638】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0639】 Currently, many inquiry handling systems are required to respond to user inquiries quickly and accurately, but they have limitations when it comes to complex inquiries that cannot be handled by conventional rule-based approaches. Furthermore, it is difficult to consistently provide responses of the same quality regardless of the time of day or day of the week. In addition, existing systems have insufficient understanding of inquiry content, and more advanced natural language processing capabilities are needed to improve user satisfaction. 【0640】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0641】 In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries using natural language processing technology, and means for searching a pre-prepared inquiry response database based on the analysis results. This enables sophisticated and flexible responses to user inquiries using a generative AI model. 【0642】 A "user" refers to an individual or organization that uses the system to make an inquiry. 【0643】 An "inquiry" is a text-based form containing information or questions that the user wants to know. 【0644】 "Means of receiving" refers to the function that allows a computer system to acquire inquiries sent by users. 【0645】 "Natural language processing technology" refers to the technology used by computers to understand and analyze human language. 【0646】 "Means of analysis" refers to methods for deciphering received inquiries using natural language processing techniques and understanding their meaning. 【0647】 A "query response database" refers to a collection of information in which past queries and their corresponding responses are organized and stored. 【0648】 A "search method" refers to a function that finds relevant information within a database based on the analysis results. 【0649】 A "generative AI model" is a type of computer program that uses artificial intelligence to generate text in a natural-sounding format. 【0650】 "Means of generating a response" refers to the process of creating an appropriate answer to an inquiry. 【0651】 "Means of transmission" refers to the function that delivers the generated response to the user's device. 【0652】 A "prompt statement" refers to an input statement used to give instructions to a generating AI model. 【0653】 This invention relates to a system for automatically generating responses to user inquiries. This system mainly includes a server, a user terminal, and an inquiry response database. 【0654】 Users submit inquiries through the chat interface on their device. The chat interface is designed to be intuitive and easy to use, allowing users to easily input questions in text format. The submitted inquiry is then sent from the device to the server. 【0655】 The server analyzes the received text data using a natural language processing (NLP) engine. This NLP engine is used to understand the user's intent and the subject of the inquiry, and to extract relevant keywords. For example, if a user asks, "Please tell me the latest product information," the server will extract keywords such as "latest" and "product information." 【0656】 Next, the server searches the query response database based on these analysis results. This database stores past queries and their optimal responses, organized by category. For example, for queries related to "product information," the database contains an appropriate entry such as "The current latest product is XX." 【0657】 The server uses a generative AI model to generate an appropriate response based on the search results. This response is expressed in natural language that is easy for the user to understand. The generative AI model used here is optimized according to the user's intent and context. 【0658】 The generated response is sent from the server to the user's terminal and displayed on the chat interface. This allows the user to quickly obtain information regarding their inquiry. For example, a prompt could be instructed to the AI ​​model to "analyze the user's inquiry 'Please provide the latest product information' and generate a relevant response." As a result of this prompt, a response is generated and displayed. 【0659】 This embodiment allows users to consistently receive high-quality responses regardless of time or location, thus improving user satisfaction with the system. Furthermore, the server's automated response management optimizes human resources. 【0660】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0661】 Step 1: 【0662】 The user enters their inquiry in text format through the chat interface on their device. The user's question text is generated as input data. This input is sent to the server by the user's device. 【0663】 Step 2: 【0664】 The server receives text data sent from the terminal. To process the received data, the server first performs preprocessing, such as converting character codes and removing unnecessary information. This results in clean data for analysis. 【0665】 Step 3: 【0666】 The server uses a natural language processing (NLP) engine to analyze clean text data. The input is pre-processed data, and the output extracts keywords and topics that indicate the user's intent and interests. For example, from the input "Please tell me the latest product information," keywords such as "latest" and "product information" will be output. 【0667】 Step 4: 【0668】 The server searches the query response database based on the analysis results. In this process, relevant information is identified from the database based on keywords. The input is the keywords from the analysis results, and the output is the relevant response candidates. 【0669】 Step 5: 【0670】 The server uses a generative AI model to generate user-facing responses based on response candidates retrieved from a database. In this process, prompt text is provided to the generative AI model, resulting in the generation of natural and easily understandable sentences. The input consists of response candidates and prompt text, and the output is a final response to be presented to the user. 【0671】 Step 6: 【0672】 The server sends the generated response to the user's terminal. The terminal displays this response on the chat interface. The input here is the response from the server, and the output is the final display presented to the user. This allows the user to quickly confirm the answer. 【0673】 (Application Example 1) 【0674】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0675】 In modern e-commerce, it is necessary to respond quickly and accurately to inquiries from a large number of users. However, conventional methods make it difficult to adequately respond to detailed inquiries about a wide variety of products, leading to decreased customer satisfaction and increased support costs. The present invention aims to solve these problems and provide a means to provide efficient and highly accurate responses. 【0676】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0677】 In this invention, the server includes a medium for receiving user inquiries, a medium for analyzing the received inquiries using natural language processing technology, a medium for searching a pre-prepared inquiry response data structure based on the analysis results, a medium for generating a response to the user's inquiry based on the search results, a medium for sending the generated response to the user, and a medium for using an artificial intelligence model for providing product information on a shopping platform to retrieve relevant information from a database. This enables the server to always respond to customer inquiries with optimized content, improving customer satisfaction and reducing operating costs. 【0678】 A "medium for receiving user inquiries" refers to a device or software that receives questions or requests for information from users to a system. 【0679】 A "medium analyzed using natural language processing technology" is a device or software that analyzes input text data in order for a server to understand the language that humans normally use. 【0680】 A "medium for searching query response data structures" refers to a device or software that performs the function of searching for a pre-prepared set of response data based on the results of analysis. 【0681】 A "medium for generating responses to user inquiries" refers to a device or software that takes search results into consideration and constructs an appropriate answer for the user. 【0682】 "The medium for sending the generated response to the user" refers to a device or software that has the role of delivering the constructed response to the user. 【0683】 An "artificial intelligence model for providing product information on a shopping platform" is a device or software that utilizes artificial intelligence technology to present product details in an online shopping environment and possesses analytical methods to provide users with the most relevant information. 【0684】 A "medium for retrieving related information from a database" refers to a device or software that retrieves information related to a product or service from its storage location. 【0685】 The system implementing this invention consists of a central server and terminals for receiving user inquiries. The server is equipped with a natural language processing engine, analyzes inquiries, and generates the optimal response based on the analysis results. Specifically, the server uses natural language processing technology to interpret the text data received from the user. In this process, keywords and sentences are extracted from the input inquiry and data is processed to understand the user's intent. 【0686】 The server leverages existing natural language processing technologies, such as the Google Cloud Natural Language API. After keyword extraction, the server quickly searches the query-response data structure to identify the most appropriate response. This ensures consistent information delivery, allowing users to quickly obtain the information they need. 【0687】 The terminal used is the user's smartphone or computer, allowing them to make inquiries through an intuitive interface. The generated response is immediately sent to the terminal and displayed on the screen, so the user can obtain information instantly and promotes continuous engagement. 【0688】 For example, if a user asks "What sizes are available for this product?" through a shopping platform application, the system recognizes "size" as a keyword and retrieves relevant information from its database. As a result, it provides a response such as "This product is available in sizes S, M, L, and XL." 【0689】 An example of a prompt using a generative AI model is: "Question: Does this product come in other colors? Answer: Yes, this product comes in blue, red, and green." This demonstrates the ability to generate natural responses that are relevant to the conversation with the user. 【0690】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0691】 Step 1: 【0692】 The user enters their inquiry through a chat interface using their device. Text data is generated as input, and the device sends this data to the server. The output is text data containing the inquiry. 【0693】 Step 2: 【0694】 The server passes the received text data to the natural language processing engine and begins analysis. The input is text data, and natural language processing techniques are used to extract keywords and sentences and understand the user's intent. The output at this stage is data containing the analyzed keywords and intent. Specifically, the Google Cloud Natural Language API is used to interpret the context. 【0695】 Step 3: 【0696】 The server searches a pre-defined query response data structure based on the analysis results. The input is the analysis results data, and relevant information is quickly retrieved from the database. The output is the relevant response data. This process uses database queries to identify the optimal response. 【0697】 Step 4: 【0698】 The server generates responses to user inquiries based on the information it has retrieved. The input is response data, and a generative AI model is used to create natural language responses. The output is the natural language response provided to the user. This includes, for example, the formation of sentences based on prompts using a generative AI model. 【0699】 Step 5: 【0700】 The server sends the generated response to the user's terminal. The input is response data in natural language, and the output is a text message displayed on the terminal's user interface. The specific operation includes a process of sending data back to the terminal via the network. 【0701】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0702】 This invention establishes a system that provides more appropriate and personalized responses to user inquiries by combining an emotion analysis engine that analyzes the user's emotions with an automated response system for user inquiries. This system includes a server, a user terminal, a natural language processing (NLP) engine, an emotion analysis engine, and an inquiry response database. 【0703】 First, the user makes an inquiry via a chat interface. The terminal converts this into digital data and sends it to the server. The server then analyzes the received data using a natural language processing engine to identify the user's intent and topic, which is the same as before. 【0704】 Furthermore, in this invention, the server uses a sentiment analysis engine to identify the emotional nuances contained in the inquiry text. This makes it possible to identify emotions such as joy, anger, and sadness expressed by the user. For example, from the user's inquiry, "I am disappointed with the recent service. Please tell me why," the sentiment analysis engine recognizes "disappointment." 【0705】 The server integrates the results of this sentiment analysis with the results of natural language processing and searches the query response database. As a result, the selected response not only provides information but also takes the user's emotions into consideration. For example, if disappointment is recognized, the response will be generated to provide specific information while also including comfort and apologies. 【0706】 The server then generates an optimal response based on the user's emotions and context, and sends it to the user's terminal. The user can receive this response in real time, and the entire system aims to provide a service that exceeds the user's expectations. 【0707】 This system is expected to increase customer satisfaction and improve trust in and favorability towards the company's services. Furthermore, because the server consistently provides quick and accurate responses that consider the user's emotions and intentions, it creates an environment where sales representatives can focus on complex inquiries. 【0708】 The following describes the processing flow. 【0709】 Step 1: 【0710】 Users access the chat interface using their own devices and enter their inquiries in text format. These inquiries can be specific questions or feedback on their user experience. 【0711】 Step 2: 【0712】 The terminal converts the input text into digital data packets and sends them to the server. This conversion is performed according to the communication protocol, maintaining data integrity. 【0713】 Step 3: 【0714】 The server receives data sent from the terminal and decodes the text content. The received content is then passed to a natural language processing engine, which prepares it for analyzing the user's intent. 【0715】 Step 4: 【0716】 The server uses a natural language processing engine to analyze the text and understand the subject and intent of the query. At this stage, it identifies key keywords and, based on them, determines the response category. 【0717】 Step 5: 【0718】 The server inputs the analyzed text into a sentiment analysis engine to evaluate the user's emotional state. The sentiment analysis engine identifies emotions such as joy, anger, and sadness based on the words and expressions in the text. 【0719】 Step 6: 【0720】 The server combines the results of natural language processing analysis with the results of sentiment analysis and searches a query response database. This database contains responses in an appropriate tone according to the emotion. 【0721】 Step 7: 【0722】 The server adjusts its response to include a tone that is sensitive to the user's emotions when generating the best possible response from search results. For example, if user dissatisfaction is detected, it will add words of comfort. 【0723】 Step 8: 【0724】 The server sends the generated response as a digital data packet to the user's terminal. Transmission is performed quickly while ensuring communication security. 【0725】 Step 9: 【0726】 The terminal receives responses sent from the server and decodes them for display to the user. Users can view the responses in real time on the chat interface. 【0727】 (Example 2) 【0728】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0729】 Traditional automated response systems often generate responses to user inquiries without considering emotional context, potentially leading to decreased customer satisfaction. There is a need to solve this problem and provide more appropriate, personalized responses. 【0730】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0731】 In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries using natural language processing techniques, and means for using sentiment analysis techniques to identify the user's emotions from the analyzed results. This makes it possible to generate responses that take the user's emotions into consideration. 【0732】 A "user" is the entity that makes a query to a system and receives a response. 【0733】 An "inquiry" is information that represents a question or request that a user sends to a system. 【0734】 "Natural language processing technology" is a technology that uses computers to analyze and understand human language. 【0735】 A "data set" is a collection of pre-prepared information and responses that are retrieved based on a query. 【0736】 "Sentiment analysis technology" is a technique for identifying and classifying emotional expressions within text. 【0737】 A "response" is the information or message that a system provides in response to a user's inquiry. 【0738】 This invention is a system that provides an automated response that takes emotions into account in response to a user's inquiry. The system is comprised of a server, a user's terminal, natural language processing technology, sentiment analysis technology, and a set of inquiry response data. 【0739】 First, the user makes a request via their device. The user's device then sends this as digital data to the server. The device typically has an operating system and interface software installed, which makes this data transmission process efficient. 【0740】 The server analyzes the received query data using natural language processing (NLP) techniques. Specifically, it uses open-source NLP libraries or commercial NLP platforms to identify the user's intent and subject matter. Typical tools include natural language models provided by academic institutions and companies. 【0741】 Next, the server applies sentiment analysis technology to identify the emotions contained in the query. This allows it to grasp the emotional nuances expressed by the user. Sentiment analysis uses text analysis tools and APIs to classify the user's emotions into categories such as "joy," "sadness," and "anger." 【0742】 For example, if a user asks, "I'm dissatisfied with the service. Please tell me why," the server can identify the emotion of "dissatisfaction" from this sentence. Based on this, when generating a response, it can include specific information or comforting expressions that correspond to this emotion. 【0743】 As a concrete example of a prompt, we will show the process of inputting "The user is dissatisfied with the quality of service. How should you respond?" into an AI model and having the model generate an appropriate response example. 【0744】 This system aims to improve customer satisfaction by quickly and accurately generating responses that are tailored to the user's emotional state. 【0745】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0746】 Step 1: 【0747】 The user uses a terminal to enter and submit their inquiry. The entered data is in text format and includes specific inquiry details such as, "I am dissatisfied with the service. Please tell me why." The terminal packets this text data and sends it to the server over the network. 【0748】 Step 2: 【0749】 The server receives data sent from the terminal. It stores the received data in a format suitable for text parsing and passes it on to the next process. The output of this process is text data containing the query content. 【0750】 Step 3: 【0751】 The server uses natural language processing techniques to analyze the received text data. The input for this process is text data, and a language model is applied to identify the user's intent and subject matter. For example, a generative AI model is used to extract intents such as "dissatisfaction" or "wanting to know the reason." This analysis result is then passed on to the next stage. 【0752】 Step 4: 【0753】 The server uses sentiment analysis technology to identify emotions from the analyzed text. The input data is the analysis results obtained in step 3. In this process, the sentiment analysis tool is used to classify emotions into categories such as "anxiety" and "dissatisfaction." The identified emotion information is then used in the next process. 【0754】 Step 5: 【0755】 The server searches the database based on the user's intent and sentiment information obtained. The input is the information obtained in steps 3 and 4. From the search results, it selects and generates the most appropriate response. For example, it might select an apology message and a problem-solving suggestion that are appropriate for the situation from the database. 【0756】 Step 6: 【0757】 The server sends the generated response to the user's terminal. The output is a text message displayed to the user. The user receives this response and can view it in real time. 【0758】 (Application Example 2) 【0759】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0760】 Traditional automated response systems focus solely on providing information in response to user inquiries, lacking consideration for user emotions. This leads to a poor user experience and, consequently, lower customer satisfaction. There is a need to improve this situation and provide rapid, personalized responses that are based on user emotions. 【0761】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0762】 In this invention, the server includes a device for receiving requests from users, a device for analyzing the received requests using natural language processing technology, and an emotion analysis device for analyzing the emotions contained in the user's requests. This makes it possible to take the user's emotional state into consideration and provide an individualized response. 【0763】 "User requests" are messages or questions that users send to the system to request information or support. 【0764】 A "device" is a set of hardware or software components designed to perform a specific function. 【0765】 "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language, making natural dialogue possible. 【0766】 A "data set" is a structured collection of information that includes pre-prepared information and responses to address various requests. 【0767】 An "emotion analysis device" is a technology or system for identifying and analyzing the emotional elements contained in user requests. 【0768】 A "response adjustment device" is a system that has the function of automatically changing or optimizing response content based on the results of sentiment analysis. 【0769】 To implement this invention, a program is required that runs on the user's terminal and on a server. The program uses natural language processing and sentiment analysis techniques to receive requests from the user and analyze their content. 【0770】 The server first parses the received request using natural language processing techniques, such as the spaCy library, to identify the user's intent. Then, it uses sentiment analysis with the Google Cloud Natural Language API to recognize the emotions contained in the request. This allows the server to extract the emotions the user is expressing (e.g., joy, anger, sadness). 【0771】 Next, the server searches a pre-prepared database based on the analyzed intent and emotional information, and generates a personalized response that takes the user's emotions into account. In generating the response, the most appropriate message corresponding to the emotional state is selected and adjusted into a natural dialogue format using an AI model. 【0772】 The generated response is sent to the user's terminal in real time, allowing the user to feel as if they are interacting with a human operator. This process is expected to improve customer satisfaction. 【0773】 For example, if a user inquires that "a recently ordered item arrived late," the system can provide detailed information on measures to prevent future delays and generate an apology message based on sentiment analysis. 【0774】 An example of a prompt for a generative AI model is: "Based on the user's inquiry, generate a response that takes their emotions into consideration." 【0775】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0776】 Step 1: 【0777】 The terminal takes user requests as text data and sends that data to the server in digital format. Raw text is provided as input to the server. 【0778】 Step 2: 【0779】 The server uses natural language processing techniques (e.g., the spaCy library) to analyze the received text data and identify the user's intent. The input is the user's request text, which is then analyzed to extract keywords related to the subject and intent, resulting in structured intent data as output. 【0780】 Step 3: 【0781】 The server uses the Google Cloud Natural Language API to analyze the sentiment within the text data. The input is the user request text mentioned earlier, and by performing sentiment analysis on it, it obtains numerical data representing emotions such as joy and anger as output. 【0782】 Step 4: 【0783】 The server combines the results of natural language processing (intent data) and sentiment analysis to search a pre-prepared dataset. The input consists of intent data and sentiment data, which are used to search the dataset for the record with the most appropriate response, and the appropriate response data is obtained as output. 【0784】 Step 5: 【0785】 The server uses an AI model to refine the acquired response data and generate natural, conversational responses that take the user's emotions into consideration. It receives response data from the previous step as input and outputs natural language responses appropriate to the emotional state. 【0786】 Step 6: 【0787】 The server sends the final generated response to the terminal in response to the request. The generated response is the input, and the transmission to the terminal is the output. 【0788】 Step 7: 【0789】 The terminal displays the response sent from the server to the user. It receives response data from the server as input and outputs it by displaying it in a format that is easy for the user to understand. 【0790】 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0791】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0792】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414. 【0793】 Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion. 【0794】 Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together. 【0795】 These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression. 【0796】 The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become. 【0797】 Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant. 【0798】 The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more." 【0799】 The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values. 【0800】 The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format. 【0801】 In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data. 【0802】 In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56. 【0803】 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. 【0804】 Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56. 【0805】 The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using this memory. 【0806】 The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor. 【0807】 Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources. 【0808】 Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose. 【0809】 The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above. 【0810】 All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference. 【0811】 The following is further disclosed regarding the embodiments described above. 【0812】 (Claim 1) 【0813】 A means of receiving inquiries from users, 【0814】 A means of analyzing received inquiries using natural language processing technology, 【0815】 A means for searching a pre-prepared query response database based on the analysis results, 【0816】 A means for generating a response to a user inquiry based on search results, 【0817】 A means for sending the generated response to the user, 【0818】 A system that includes this. 【0819】 (Claim 2) 【0820】 The system according to claim 1, wherein the inquiry response database includes a plurality of pre-configured inquiry categories. 【0821】 (Claim 3) 【0822】 The system according to claim 1, wherein query analysis includes keyword extraction for identifying the user's intent and context. 【0823】 "Example 1" 【0824】 (Claim 1) 【0825】 A means of receiving inquiries from users, 【0826】 A means of analyzing received inquiries using natural language processing technology, 【0827】 A means for searching a pre-prepared query response database based on the analysis results, 【0828】 A means for generating a response to a user inquiry using a generative AI model based on search results, 【0829】 A means for sending the generated response to the user, 【0830】 A system that includes this. 【0831】 (Claim 2) 【0832】 The system according to claim 1, wherein the inquiry response database includes a plurality of pre-configured inquiry categories. 【0833】 (Claim 3) 【0834】 The system according to claim 1, wherein the query analysis includes keyword extraction to identify the user's intent and context, and processing to generate prompt sentences for a generative AI model. 【0835】 "Application Example 1" 【0836】 (Claim 1) 【0837】 The medium through which user inquiries are received, 【0838】 A medium that analyzes received inquiries using natural language processing technology, 【0839】 A medium for searching a pre-prepared query response data structure based on the analysis results, 【0840】 A medium for generating responses to user inquiries based on search results, 【0841】 The medium through which the generated response is sent to the user, 【0842】 Using an artificial intelligence model to provide product information on a shopping platform, and a medium to retrieve relevant information from a database, 【0843】 A system that includes this. 【0844】 (Claim 2) 【0845】 The system according to claim 1, wherein the query response data structure includes a plurality of pre-configured query categories. 【0846】 (Claim 3) 【0847】 The system according to claim 1, wherein query analysis includes word extraction to identify the user's intent and context. 【0848】 "Example 2 of combining an emotion engine" 【0849】 (Claim 1) 【0850】 A means of receiving inquiries from users, 【0851】 A means of analyzing received inquiries using natural language processing technology, 【0852】 A means for searching a pre-prepared data set based on the analysis results, 【0853】 A means of using sentiment analysis technology to identify the user's emotions from the analyzed results, 【0854】 A means for generating a response to a user inquiry based on sentiment analysis results and search results, 【0855】 A means for sending the generated response to the user, 【0856】 A system that includes this. 【0857】 (Claim 2) 【0858】 The system according to claim 1, wherein the query response database includes a plurality of pre-configured query classifications. 【0859】 (Claim 3) 【0860】 The system according to claim 1, wherein query analysis includes feature extraction to identify the user's intent and context. 【0861】 "Application example 2 when combining with an emotional engine" 【0862】 (Claim 1) 【0863】 A device that receives requests from users, 【0864】 A device that analyzes received requests using natural language processing technology, 【0865】 A device that searches a pre-prepared data set based on the analysis results, 【0866】 A device that generates a response to a user's request based on search results, 【0867】 A device that sends the generated response to the user, 【0868】 A sentiment analysis device that analyzes the emotions contained in the user's request, 【0869】 A device that adjusts responses based on the results of emotional analysis, 【0870】 A system that includes this. 【0871】 (Claim 2) 【0872】 The system according to claim 1, wherein the data collection includes a set of pre-configured request categories. 【0873】 (Claim 3) 【0874】 The system according to claim 1, wherein the request analysis includes keyword extraction to identify the user's intent and context, and further customizes the response content based on the user's emotional state. [Explanation of symbols] 【0875】 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] A means of receiving inquiries from users, A means of analyzing received inquiries using natural language processing technology, A means for searching a pre-prepared query response database based on the analysis results, A means for generating a response to a user inquiry based on search results, A means for sending the generated response to the user, A system that includes this. [Claim 2] The system according to claim 1, wherein the inquiry response database includes a plurality of pre-configured inquiry categories. [Claim 3] The system according to claim 1, wherein the query analysis includes keyword extraction for identifying the user's intent and context.

Images