system

Abstract

We provide the system. [Solution] A natural language processing means for analyzing the received inquiry information, A search means for searching for related information based on the analyzed query information, A generation means that generates an answer using the information obtained by the search means, A display means for displaying the generated response on a user interface, A system including a learning means for accumulating the aforementioned inquiry information and response information and updating it as learning data.

Description

Technical Field

[0004] , , , ,

[0005] , , , ,

[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, and includes 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In many current office operations, it is difficult to quickly obtain the information necessary for the business, resulting in the problem of wasting precious time. In addition, the accumulation of knowledge based on past inquiries is not sufficient, and it is necessary to spend a lot of time creating answers to the same questions. For this reason, there is a problem that salespersons cannot concentrate on sales activities, which are their original tasks.

Means for Solving the Problems

[0005] To address this challenge, we propose a system that quickly analyzes received inquiry information and retrieves relevant information from both databases and external sources. This system uses natural language processing technology to analyze inquiries, generate optimal answers, and present them to the user. Furthermore, by accumulating the exchanged information and using it as training data for an AI agent, the accuracy of the answers can be improved. This streamlines administrative tasks and provides an environment where sales activities can be focused.

[0006] "Reception" refers to the process by which a device receives information or data transmitted from an external source.

[0007] "Inquiry information" refers to the content of questions or requests that users make in order to obtain specific information.

[0008] "Analysis" is the process of structuring received information and examining it in detail to understand its meaning and intent.

[0009] "Natural language processing" refers to the technologies and methods used to process and understand human language using machines.

[0010] "Searching" is the process of finding specific information from a database or information source.

[0011] "Related information" refers to necessary information identified as being related to the inquiry.

[0012] "Generation" is the process of constructing new data or information.

[0013] "Generative means" refers to the mechanisms and methods used to create new data and information by combining them.

[0014] A "user interface" is a device or screen that allows a user to manipulate information and view the results of those actions.

[0015] "Accumulation" refers to the process of gathering and storing information and data.

[0016] "Learning data" is a set of data used by a machine learning algorithm to recognize patterns.

[0017] "AI agent" is an artificial intelligence program designed to operate autonomously and achieve specific goals.

Brief Explanation of Drawings

[0018] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It 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

[0019] 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.

[0020] First, the language used in the following description will be explained.

[0021] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of 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.

[0022] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0023] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0024] 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).

[0025] 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."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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".

[0039] This invention relates to a method for providing an automated response system utilizing an AI agent. This system significantly improves the efficiency of administrative tasks and helps sales representatives concentrate on sales activities.

[0040] The server is equipped with a natural language processing engine capable of analyzing received query information. This engine receives queries sent by users, analyzes their content, and extracts keywords and intent. Based on this analysis, it searches for relevant information from the FAQ database and external databases.

[0041] The terminal provides an interface for users to make inquiries. Through this interface, users can input questions in text format and send them to the server. The server generates a corresponding answer and sends it to the terminal. The terminal displays the received answer to the user, allowing the user to obtain the necessary information immediately.

[0042] For example, if a user asks their device, "What is the date of the next meeting?", the server processes this information through a natural language processing engine and extracts the keywords "meeting" and "date". Based on this, the server refers to internal calendar information and external schedule management databases to generate a specific answer such as, "The next meeting is next Wednesday at 2pm." The server then returns this answer to the device and displays it to the user. In this way, the user can quickly obtain the information they need.

[0043] Furthermore, the server stores the question-and-answer exchanges in a database, which is used to improve the accuracy of generating answers to future questions. This streamlines the response to each inquiry and increases the overall speed of operations.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The terminal retrieves the inquiry information entered by the user and prepares to send this input data to the server.

[0047] Step 2:

[0048] The user uses the terminal interface to enter specific questions and clicks the "Submit" button to send the inquiry information to the server.

[0049] Step 3:

[0050] The server passes the received query information to a natural language processing engine, which analyzes the query content and extracts key keywords and context.

[0051] Step 4:

[0052] The server searches the FAQ database based on keywords and context obtained from the analysis and retrieves appropriate answer candidates. At the same time, it retrieves additional information from external databases and APIs as needed.

[0053] Step 5:

[0054] The server integrates search results and related information to generate the best possible answer. If an answer cannot be generated, it constructs content that presents relevant information and alternative solutions.

[0055] Step 6:

[0056] The server sends the generated response to the terminal. The terminal displays the response to the user through its user interface, allowing for immediate reference.

[0057] Step 7:

[0058] The server stores data on inquiries and their responses, and uses this data to train the AI ​​agent, aiming to improve the accuracy of future responses.

[0059] (Example 1)

[0060] 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."

[0061] Existing automated response systems sometimes lack the ability to provide appropriate and timely answers to a wide range of user inquiries. Furthermore, they lack efficient data accumulation and learning methods for improving the accuracy of their responses. Therefore, system improvements are needed to enhance operational efficiency.

[0062] 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.

[0063] In this invention, the server includes a natural language processing means for analyzing received inquiry information, a search means for searching for related information, a generation means for generating an answer using the acquired information, and an improvement means for accumulating information to improve the accuracy of future answers based on past inquiries and answers. This makes it possible to improve the accuracy and speed of answers to user inquiries and increase operational efficiency.

[0064] "Natural language processing means" refers to technologies for analyzing received inquiry information and extracting keywords and intent.

[0065] A "search method" is a technique for retrieving relevant information from internal or external sources based on analyzed query information.

[0066] "Generation method" refers to a method of generating an appropriate response to a user's inquiry based on the acquired relevant information.

[0067] "Display means" refers to the technology that displays the response content sent from the server through a user interface used by the user.

[0068] A "learning tool" is a system that accumulates inquiry and response information and updates and manages the data in order to improve the accuracy of future responses.

[0069] "Analysis methods" refer to the process of analyzing information in order to extract important keywords and intentions from inquiry information.

[0070] "Improvement measures" refer to technologies that analyze past inquiries and responses and use that analysis to improve the accuracy and processing efficiency of future responses.

[0071] This invention provides an automated response system utilizing artificial intelligence. The system mainly consists of a server, a terminal, and user interaction.

[0072] server

[0073] The server plays a central role in processing received inquiry information. The server is equipped with a natural language processing engine for parsing text data. Specifically, it can use open-source natural language processing libraries such as spaCy or BERT. In addition, based on the parsed information, the server retrieves relevant information from FAQ databases and external databases using search mechanisms. A generation mechanism generates answers based on the obtained data and sends them to the terminal via the user interface.

[0074] terminal

[0075] The terminal provides an interface for users to submit inquiries. The terminal's user interface is built using web technologies such as React and Vue.js, allowing users to input questions in text format. The terminal then sends the entered information to the server. The response received from the server is displayed on the terminal's screen and presented in a format easily understandable to the user.

[0076] User

[0077] Users interact with the system via a terminal. Entering a question triggers rapid analysis and response generation by the server. For example, if a user enters "What is the current stock status?", the server consults its internal database and generates a specific response such as "There are 10 in stock," which is then displayed on the terminal.

[0078] Examples of prompts for the generative AI model include questions such as, "Please tell me the date of the next meeting," or "What's the weather like today?"

[0079] This allows users to quickly obtain the information they need and improve work efficiency. The system also stores past inquiries and responses in a database, helping to improve the accuracy of future responses.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The terminal receives inquiry information entered by the user. The user enters the question in text format through the terminal's interface. For example, "Please tell me the date of the next meeting." The entered information is sent to the server in a data format such as JSON.

[0083] Step 2:

[0084] The server receives the query information sent from the terminal. Next, it uses a natural language processing engine to analyze the query content and extract keywords and intent. Here, spaCy or BERT is used to analyze the text. For example, keywords such as "meeting" and "schedule" are extracted.

[0085] Step 3:

[0086] The server uses search methods based on the analyzed information. The server searches internal databases and external information sources to retrieve relevant data. During this process, it makes specific API calls to extract the necessary information. For example, it might retrieve meeting schedules from its internal calendar system.

[0087] Step 4:

[0088] The server uses generation tools to create appropriate responses based on the acquired data. The generated responses are formatted in a grammatically correct manner. For example, a response such as "The next meeting is next Tuesday at 2pm" might be generated.

[0089] Step 5:

[0090] The server sends the generated response to the terminal. The response data is transmitted using standard communication protocols.

[0091] Step 6:

[0092] The terminal displays the response received from the server on the user interface. The user can then review this and obtain the necessary information. The screen might display output such as, "The next meeting is next Tuesday at 2 PM."

[0093] Step 7:

[0094] The server stores the content of inquiries and responses in a database. This data is used for machine learning and forms the basis for improving the accuracy and efficiency of future responses.

[0095] (Application Example 1)

[0096] 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."

[0097] Electronic payment services require prompt and accurate responses to customer inquiries. However, manual responses are time-consuming and labor-intensive, and also carry the risk of human error. Furthermore, while utilizing past inquiry history and service usage history is necessary to improve the consistency and accuracy of responses, there is a lack of efficient mechanisms for doing so. Therefore, improving customer satisfaction and operational efficiency are key challenges.

[0098] 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.

[0099] In this invention, the server includes natural language processing means for analyzing received inquiry information, search means for searching for related information, and generation means for generating natural-sounding text using a generation AI model. This enables rapid and accurate automated responses to customer inquiries in electronic payment services.

[0100] "Natural language processing means" refers to methods that analyze text-based inquiry information received from users and extract keywords and intent.

[0101] A "search method" is a technique for obtaining relevant information from internal or external databases based on analyzed query information.

[0102] A "generation method" is a technique that generates an answer based on acquired information and communicates that answer to the user.

[0103] "Display means" refers to a method of displaying the generated response on a user interface, making it easy for the user to obtain the information.

[0104] A "learning method" is a technique that involves accumulating inquiry and response information and using it as training data for an AI agent.

[0105] A "generative AI model" is a model of generative artificial intelligence designed to generate natural-sounding responses.

[0106] "Reference means" refers to methods for obtaining necessary information based on service usage history and other past data.

[0107] This invention is a system that provides rapid and accurate automated responses to customer inquiries in electronic payment services. The server achieves this function using multiple means.

[0108] First, when a user's inquiry is sent from the terminal to the server, the server uses a natural language processing engine to analyze the received text information. Examples of natural language processing engines used here include Google® Cloud Natural Language and SpaCy. Through this analysis, keywords and the user's intent are extracted from the inquiry.

[0109] Next, the server searches for relevant data based on the extracted information. In addition to its internal database, it can also access external databases via an API. This ensures that the most suitable information is retrieved.

[0110] The acquired information is used by a generation method to generate a natural-sounding response using a generative AI model. This generative AI model can utilize OpenAI's GPT-3®, among others. The generated response is then formatted to be easily understood by the user.

[0111] Finally, the server sends this generated response to the terminal, where it is displayed on the user interface accessed by the user. The user can quickly obtain the necessary information, and the inquiry is resolved smoothly.

[0112] Furthermore, this system is equipped with both reference and learning mechanisms, allowing for the referencing of information based on service usage history and the improvement of response accuracy through training of AI agents using past inquiry information. As a result, the system continuously improves its performance and continues to provide more accurate responses.

[0113] For example, when a user asks, "What is my payment amount for this month?", the server searches the database for relevant information based on the analyzed keywords such as "payment amount" and "this month," and presents the user with a generated response such as, "Your payment amount for this month is 20,000 yen." An example of a prompt in this case would be, "Generate a natural response to tell the user their credit card payment amount for this month."

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] User inquiries

[0117] The user enters and submits inquiry information in text format via their terminal. The entered inquiry information is then sent to the server.

[0118] Step 2:

[0119] Analysis using natural language processing

[0120] The server passes the received query information to a natural language processing engine (e.g., Google Cloud Natural Language). This engine extracts keywords and intent from the query's text data. The analyzed keywords are then returned to the server as output.

[0121] Step 3:

[0122] Search for related information

[0123] The server searches for relevant information from databases and external APIs based on the analyzed keywords. During this process, it retrieves payment and usage history data related to the inquiry. The necessary information is then obtained as output.

[0124] Step 4:

[0125] Generating natural answers

[0126] The server inputs the acquired information into a generation AI model (e.g., OpenAI GPT-3). Using prompts, it generates a response in natural language. In this generation process, the information obtained as input is used, and a response message to the user is generated as output.

[0127] Step 5:

[0128] Display the answer

[0129] The server sends the generated response to the terminal. The terminal displays this response in the user interface. The user can immediately verify the information.

[0130] Step 6:

[0131] Record of inquiries and responses

[0132] The server stores query information and the corresponding answers in a database. This data is used as training data to improve the accuracy of future queries.

[0133] 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.

[0134] This invention is an advanced automated response system using an AI agent, which improves the quality of responses by incorporating an emotion engine that analyzes the user's emotions. This system analyzes inquiries received from users, understands the user's emotions, and provides appropriate responses accordingly.

[0135] The server first processes the received query information using a natural language processing engine. This analysis extracts keywords and intent from the query content and searches for related information. It also uses an emotion engine to analyze the emotions in the text entered by the user and estimate the user's emotional state.

[0136] The terminal not only provides an interface for users to input and submit inquiries, but also manages the responses displayed to the user. The responses generated by the server in response to inquiries are adjusted to the user's emotions and are carefully crafted to be more appropriate.

[0137] For example, if a user asks a terminal, "This system isn't working properly at all, can you do something about it?", the server analyzes this question using natural language processing and extracts keywords related to the system's operation. Furthermore, the emotion engine recognizes emotions such as dissatisfaction or frustration from the user's wording. Based on this, the server not only provides a technical answer but also generates a response that takes the user's emotions into consideration, such as, "We apologize for the inconvenience. Could you please tell us in more detail what kind of support you need to resolve the issue?"

[0138] Another important aspect of this system is that it accumulates data obtained through sentiment analysis and uses it as training data for the AI ​​agent, further improving the quality of emotional responses to future inquiries. This is expected to lead to more refined responses to users and increased user satisfaction.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The user enters a query into the terminal interface and prepares to send it to the server.

[0142] Step 2:

[0143] The terminal sends the inquiry information entered by the user to the server as string data.

[0144] Step 3:

[0145] The server passes the received query information to a natural language processing engine, which performs analysis to extract keywords and intent.

[0146] Step 4:

[0147] Simultaneously, the server uses an emotion engine to analyze the emotions in the user's input and evaluate the emotional tone.

[0148] Step 5:

[0149] Based on the analyzed keywords and the user's emotional state, the server searches for relevant information from FAQ databases and external sources.

[0150] Step 6:

[0151] The server integrates search results and sentiment information to generate appropriate responses that take the user's emotions into consideration.

[0152] Step 7:

[0153] The generated response is sent from the server to the terminal and displayed to the user. The terminal displays this information clearly on its interface.

[0154] Step 8:

[0155] The server stores all data from user interactions and uses it as training data for future AI agents. This data also includes analyzed sentiment information.

[0156] (Example 2)

[0157] 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."

[0158] In modern information processing systems, improving the quality of responses to user inquiries is a crucial challenge. In particular, if responses are generated uniformly without regard to the user's emotional state, user satisfaction may decrease, potentially impairing the system's usefulness. This invention aims to achieve more responsive and satisfying interactions by appropriately analyzing user emotions and generating responses accordingly.

[0159] 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.

[0160] In this invention, the server includes a language processing means for analyzing received inquiry information, an emotion analysis means for analyzing the user's emotions, and an adjustment means for adjusting the generated response according to the user's emotional state. This makes it possible to generate a more appropriate response that takes the user's emotions into account and improve the user experience.

[0161] "Method of verbalization" refers to a method of converting received data into a usable format, analyzing its contents, and extracting necessary information.

[0162] "Search methods" refer to the process of detecting data from relevant information sources based on analyzed information and collecting necessary information.

[0163] "Creation method" refers to a method for generating an appropriate response to provide to the user based on acquired data.

[0164] "Emotion analysis means" refers to a technology that analyzes a user's input data to understand their emotions and estimate their emotional state.

[0165] A "display mechanism" is a system that presents the generated response on an interface for the user to use.

[0166] "Adjustment means" refers to the process of appropriately modifying the response content generated according to the user's emotional state and improving its quality.

[0167] "Training methods" refer to the process of using collected data to train a system and improve the accuracy and suitability of its responses.

[0168] To implement this invention, it is necessary to construct an advanced automated response system. This system consists of a server, a terminal, and a user. The server processes user inquiries using multiple modules, including a natural language processing engine and an sentiment analysis engine. Specifically, natural language processing tools such as Python's NLTK and spaCy, and common API services for sentiment analysis are available.

[0169] The terminal provides an intuitive interface for users to input and submit inquiries. The terminal also displays the responses received from the server to the user.

[0170] Users can make inquiries through this system and check the responses using the terminal interface. The server analyzes the user's emotions and provides a way to improve the quality of responses by using a generative AI model to generate appropriate responses based on those emotions.

[0171] For example, when a user asks "Tell me about this feature" from their device, the server processes the inquiry using natural language processing to extract key keywords and search for relevant information. The sentiment analysis engine determines the user's emotions from their question and adjusts the response to an appropriate tone based on the result. For instance, a prompt such as "Please answer gently and clearly" can be used to have the generative AI model generate an appropriate response.

[0172] By building this system, users will be able to receive more flexible and emotionally sensitive responses, thereby improving the user experience.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The user enters and submits their inquiry through their device. This input is natural language text, such as "Please tell me about this feature." The device then sends this text data to the server.

[0176] Step 2:

[0177] The server processes the received query text into a natural language processing engine. The input is the text data of the user's query, which is then analyzed to extract keywords and intent. Specifically, it uses libraries such as Python's NLTK or spaCy to perform text analysis and obtains structured data as output.

[0178] Step 3:

[0179] The server uses the information obtained from the parsed text to search relevant information sources and databases. In this step, additional information is retrieved from external sources using keywords extracted from the query. The output is a dataset containing the information necessary to generate the answer.

[0180] Step 4:

[0181] The server performs sentiment analysis on the user's input text. The input is natural language text, and the sentiment analysis engine is used to estimate the emotional state. The output is metadata indicating the user's emotional state, which is used when generating responses.

[0182] Step 5:

[0183] The server generates appropriate responses using a generative AI model. In this process, responses are generated using prompts based on the information and emotional state obtained in the previous step. For example, a prompt such as "Please answer gently and clearly" is input to the model, and it outputs a human-friendly response.

[0184] Step 6:

[0185] The server uses adjustment mechanisms to optimize the generated response according to the user's emotions. This process ensures that the output response has the most appropriate tone and content for the user.

[0186] Step 7:

[0187] The server sends the final response to the terminal. The terminal receives this and displays it in the user interface. The user reviews the provided response to resolve any questions or determine the next course of action.

[0188] Step 8:

[0189] The server stores inquiry information, sentiment state, and response information, updating it as training data. In this step, this data is saved to a database and used as training data for the model. This further improves the quality of responses in subsequent interactions.

[0190] (Application Example 2)

[0191] 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 device 14 will be referred to as the "terminal."

[0192] Improving the quality of responses to user inquiries is a crucial challenge in communication technology. In particular, there is a need for systems that can consider the user's emotions when providing explanations and solutions. However, many conventional automated response systems lack emotion recognition capabilities, potentially reducing user satisfaction. Therefore, there is a need to develop automated response systems that take emotions into account.

[0193] 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.

[0194] In this invention, the server includes data processing means for analyzing received inquiry information, information retrieval means for searching for related information based on the analyzed inquiry information, content generation means for generating a response using the information obtained by the information retrieval means, and emotion adaptation means for analyzing and adjusting the emotions of the generated response. This makes it possible to provide an appropriate and humane response that is in line with the user's emotional state.

[0195] "Data processing means" refers to the technology used to analyze received inquiry information and understand its content.

[0196] An "information retrieval method" is a method for efficiently searching for relevant information from external or internal sources based on analyzed query information.

[0197] "Content generation methods" refer to the process of using acquired information to generate appropriate answers and explanations.

[0198] "Emotional adaptation techniques" are technologies that analyze the user's emotions in response to a generated answer and adjust the answer content accordingly.

[0199] "Information presentation means" refers to methods and devices for effectively displaying adjusted responses to the user.

[0200] A "learning tool" is a system that accumulates past inquiry and response information and uses it to learn in order to improve the accuracy of future responses.

[0201] An "automated response system" is a system that has the function of automatically generating and providing responses to inquiries.

[0202] This automated response system is designed for efficient interaction between the user and the server. The server first analyzes the inquiry information received from the user using data processing tools. This process utilizes a natural language processing engine (e.g., spaCy) to extract important information from the inquiry. Simultaneously, information retrieval tools (e.g., external database access via API) search for relevant information based on the analyzed data.

[0203] Next, the server uses content generation means to generate appropriate responses based on the acquired information, utilizing a generative AI model (e.g., OpenAI GPT). At this time, sentiment adaptation means are used to analyze the user's emotions towards the generated response and adjust the response to the optimal format according to those emotions. For sentiment analysis, a sentiment analysis library (e.g., TextBlob) can be used.

[0204] The terminal displays a finalized response to the user based on the information presented. The system is designed to be easy for users to understand and to allow for quick responses. In addition, the server can accumulate past inquiry and response information through learning mechanisms, and use this data to improve the response accuracy of the AI ​​model. This continuous learning is expected to improve the quality of responses to future inquiries.

[0205] For example, when a user inquires with concern, asking "Why hasn't my payment been approved?", it's possible to immediately identify their concern and provide a tailored response such as: "We will do our best to alleviate your concerns. Please wait a moment while we investigate and address the issue." In this case, the prompt to the generating AI model would be something like, "Based on the user's message, create a kind and considerate response that takes their emotions into account. The user is feeling anxious because their payment hasn't been approved."

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] The user enters their inquiry through their device and sends it to the server. The entered inquiry is recorded as text data. The user is also encouraged to enter sentences written in natural language, including their emotions.

[0209] Step 2:

[0210] The server analyzes the received query using data processing tools. In this step, a natural language processing engine (e.g., spaCy) is used to extract keywords and intent from the text data. The extracted data is then used as input for subsequent information retrieval steps.

[0211] Step 3:

[0212] The server uses information retrieval tools based on the extracted keywords to search for relevant information. In this step, necessary information is retrieved from an external database via an API. This information becomes the output data used for the next content generation.

[0213] Step 4:

[0214] The server generates responses from information obtained using content generation methods. Using a generative AI model (e.g., OpenAI GPT), it creates natural and appropriate responses based on the submitted keywords and search information. These generated responses are then used as input for the next sentiment adaptation.

[0215] Step 5:

[0216] The server uses a sentiment analysis library (e.g., TextBlob) to analyze the user's emotions. It then applies the user's emotion information to the generated responses and adjusts them. The adjusted responses are output for informational purposes, resulting in user-friendly content.

[0217] Step 6:

[0218] The device displays the adjusted response to the user through an information presentation mechanism. The user reviews the response and decides on the next action. The displayed response is easy for the user to understand and guides them toward problem solving.

[0219] Step 7:

[0220] The server stores all query information and generated responses using a learning mechanism. This data is used as training data for an AI model, helping to improve the accuracy of responses to future queries.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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".

[0237] This invention relates to a method for providing an automated response system utilizing an AI agent. This system significantly improves the efficiency of administrative tasks and helps sales representatives concentrate on sales activities.

[0238] The server is equipped with a natural language processing engine capable of analyzing received query information. This engine receives queries sent by users, analyzes their content, and extracts keywords and intent. Based on this analysis, it searches for relevant information from the FAQ database and external databases.

[0239] The terminal provides an interface for users to make inquiries. Through this interface, users can input questions in text format and send them to the server. The server generates a corresponding answer and sends it to the terminal. The terminal displays the received answer to the user, allowing the user to obtain the necessary information immediately.

[0240] For example, if a user asks their device, "What is the date of the next meeting?", the server processes this information through a natural language processing engine and extracts the keywords "meeting" and "date". Based on this, the server refers to internal calendar information and external schedule management databases to generate a specific answer such as, "The next meeting is next Wednesday at 2pm." The server then returns this answer to the device and displays it to the user. In this way, the user can quickly obtain the information they need.

[0241] Furthermore, the server stores the question-and-answer exchanges in a database, which is used to improve the accuracy of generating answers to future questions. This streamlines the response to each inquiry and increases the overall speed of operations.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The terminal retrieves the inquiry information entered by the user and prepares to send this input data to the server.

[0245] Step 2:

[0246] The user uses the terminal interface to enter specific questions and clicks the "Submit" button to send the inquiry information to the server.

[0247] Step 3:

[0248] The server passes the received query information to a natural language processing engine, which analyzes the query content and extracts key keywords and context.

[0249] Step 4:

[0250] The server searches the FAQ database based on keywords and context obtained from the analysis and retrieves appropriate answer candidates. At the same time, it retrieves additional information from external databases and APIs as needed.

[0251] Step 5:

[0252] The server integrates search results and related information to generate the best possible answer. If an answer cannot be generated, it constructs content that presents relevant information and alternative solutions.

[0253] Step 6:

[0254] The server sends the generated response to the terminal. The terminal displays the response to the user through its user interface, allowing for immediate reference.

[0255] Step 7:

[0256] The server stores data on inquiries and their responses, and uses this data to train the AI ​​agent, aiming to improve the accuracy of future responses.

[0257] (Example 1)

[0258] 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."

[0259] Existing automated response systems sometimes lack the ability to provide appropriate and timely answers to a wide range of user inquiries. Furthermore, they lack efficient data accumulation and learning methods for improving the accuracy of their responses. Therefore, system improvements are needed to enhance operational efficiency.

[0260] 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.

[0261] In this invention, the server includes a natural language processing means for analyzing received inquiry information, a search means for searching for related information, a generation means for generating an answer using the acquired information, and an improvement means for accumulating information to improve the accuracy of future answers based on past inquiries and answers. This makes it possible to improve the accuracy and speed of answers to user inquiries and increase operational efficiency.

[0262] "Natural language processing means" refers to technologies for analyzing received inquiry information and extracting keywords and intent.

[0263] A "search method" is a technique for retrieving relevant information from internal or external sources based on analyzed query information.

[0264] "Generation method" refers to a method of generating an appropriate response to a user's inquiry based on the acquired relevant information.

[0265] "Display means" refers to the technology that displays the response content sent from the server through a user interface used by the user.

[0266] A "learning tool" is a system that accumulates inquiry and response information and updates and manages the data in order to improve the accuracy of future responses.

[0267] "Analysis methods" refer to the process of analyzing information in order to extract important keywords and intentions from inquiry information.

[0268] "Improvement measures" refer to technologies that analyze past inquiries and responses and use that analysis to improve the accuracy and processing efficiency of future responses.

[0269] This invention provides an automated response system utilizing artificial intelligence. The system mainly consists of a server, a terminal, and user interaction.

[0270] server

[0271] The server plays a central role in processing received inquiry information. The server is equipped with a natural language processing engine for parsing text data. Specifically, it can use open-source natural language processing libraries such as spaCy or BERT. In addition, based on the parsed information, the server retrieves relevant information from FAQ databases and external databases using search mechanisms. A generation mechanism generates answers based on the obtained data and sends them to the terminal via the user interface.

[0272] terminal

[0273] The terminal provides an interface for users to submit inquiries. The terminal's user interface is built using web technologies such as React and Vue.js, allowing users to input questions in text format. The terminal then sends the entered information to the server. The response received from the server is displayed on the terminal's screen and presented in a format easily understandable to the user.

[0274] User

[0275] Users interact with the system via a terminal. Entering a question triggers rapid analysis and response generation by the server. For example, if a user enters "What is the current stock status?", the server consults its internal database and generates a specific response such as "There are 10 in stock," which is then displayed on the terminal.

[0276] Examples of prompts for the generative AI model include questions such as, "Please tell me the date of the next meeting," or "What's the weather like today?"

[0277] As a result, the user can quickly obtain the necessary information and improve the efficiency of their work. This system also accumulates past inquiries and responses in a database to support improving the accuracy of future responses.

[0278] The flow of the specific process in Example 1 will be described using FIG. 11.

[0279] Step 1:

[0280] The terminal receives the inquiry information input by the user. The user inputs a question in text form through the terminal interface. For example, it is in the form of "Please tell me the schedule of the next meeting." The input information is sent to the server in a data format such as JSON.

[0281] Step 2:

[0282] The server receives the inquiry information sent from the terminal. Next, using a natural language processing engine, it analyzes the inquiry content and extracts keywords and intentions. Here, text analysis is performed using spaCy or BERT. For example, keywords such as "meeting" and "schedule" are extracted.

[0283] Step 3:

[0284] The server uses search means based on the analyzed information. The server searches its internal database or external information sources to obtain relevant data. At this time, specific API calls are made to retrieve the necessary information. For example, the schedule of the meeting is obtained from the internal calendar system.

[0285] Step 4:

[0286] The server utilizes generation means based on the acquired data to generate an appropriate answer. The generated answer is formatted in a grammatically correct form. For example, an answer such as "The next meeting is at 2 pm on Tuesday next week" is generated.

[0287] Step 5:

[0288] The server transmits the generated answer to the terminal. The answer data is transmitted using a normal communication protocol.

[0289] Step 6:

[0290] The terminal displays the answer received from the server on the user interface. The user can check this and obtain the necessary information. For example, an output such as "The next meeting is at 2:00 pm on Tuesday next week" is displayed on the screen.

[0291] Step 7:

[0292] The server accumulates the contents of the inquiry and the answer in the database. This data is used for machine learning and serves as a basis for improving the accuracy and efficiency of future answers.

[0293] (Application Example 1)

[0294] 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".

[0295] In electronic payment services, it is required to respond quickly and accurately to customer inquiries. However, manual handling requires a lot of time and effort, and there is also a risk of human error. In addition, in order to improve the consistency and accuracy of answers, it is necessary to utilize past inquiry histories and service usage histories, but there is a lack of a mechanism to do this efficiently. For this reason, improving customer satisfaction and operational efficiency has become an issue.

[0296] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0297] In this invention, the server includes natural language processing means for analyzing received inquiry information, search means for searching for related information, and generation means for generating natural-sounding text using a generation AI model. This enables rapid and accurate automated responses to customer inquiries in electronic payment services.

[0298] "Natural language processing means" refers to methods that analyze text-based inquiry information received from users and extract keywords and intent.

[0299] A "search method" is a technique for obtaining relevant information from internal or external databases based on analyzed query information.

[0300] A "generation method" is a technique that generates an answer based on acquired information and communicates that answer to the user.

[0301] "Display means" refers to a method of displaying the generated response on a user interface, making it easy for the user to obtain the information.

[0302] A "learning method" is a technique that involves accumulating inquiry and response information and using it as training data for an AI agent.

[0303] A "generative AI model" is a model of generative artificial intelligence designed to generate natural-sounding responses.

[0304] "Reference means" refers to methods for obtaining necessary information based on service usage history and other past data.

[0305] This invention is a system that provides rapid and accurate automated responses to customer inquiries in electronic payment services. The server achieves this function using multiple means.

[0306] First, when an inquiry from a user is sent from a terminal to a server, the server analyzes the received text information using a natural language processing engine. Examples of natural language processing engines used here include Google Cloud Natural Language and SpaCy. Through this analysis, keywords and the user's intention are extracted from the inquiry.

[0307] Next, based on the extracted information, the server searches for relevant data. As search means, in addition to an internal database, it is possible to utilize an external database through an API. In this way, the most suitable information is obtained.

[0308] The obtained information is generated as a natural sentence answer using a generative AI model by a generation means. As the generative AI model here, GPT-3 of OpenAI etc. can be utilized. The generated answer is arranged in a form that is easy for the user to understand.

[0309] Finally, the server sends this generated answer to the terminal and it is displayed on the user interface that the user accesses. The user can quickly obtain the necessary information and the inquiry is smoothly resolved.

[0310] Also, this system has a reference means and a learning means, and it is possible to refer to information based on the service usage history and improve the answer accuracy by training an AI agent using past inquiry information. As a result, the system continuously improves its performance and continues to provide more accurate responses.

[0311] As a specific example, when a user makes an inquiry such as "Tell me the payment amount for this month", based on the analyzed keywords such as "payment amount" and "this month", the server searches for the corresponding information from the database and presents the user with a generated answer such as "The payment amount for this month is 20,000 yen". An example of a prompt sentence in this case is "Please generate a natural answer to convey the payment amount for this month of the credit card to the user."

[0312] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0313] Step 1:

[0314] User inquiries

[0315] The user enters and submits inquiry information in text format via their terminal. The entered inquiry information is then sent to the server.

[0316] Step 2:

[0317] Analysis using natural language processing

[0318] The server passes the received query information to a natural language processing engine (e.g., Google Cloud Natural Language). This engine extracts keywords and intent from the query's text data. The analyzed keywords are then returned to the server as output.

[0319] Step 3:

[0320] Search for related information

[0321] The server searches for relevant information from databases and external APIs based on the analyzed keywords. During this process, it retrieves payment and usage history data related to the inquiry. The necessary information is then obtained as output.

[0322] Step 4:

[0323] Generating natural answers

[0324] The server inputs the acquired information into a generation AI model (e.g., OpenAI GPT-3). Using prompts, it generates a response in natural language. In this generation process, the information obtained as input is used, and a response message to the user is generated as output.

[0325] Step 5:

[0326] Display the answer

[0327] The server sends the generated response to the terminal. The terminal displays this response in the user interface. The user can immediately verify the information.

[0328] Step 6:

[0329] Record of inquiries and responses

[0330] The server stores query information and the corresponding answers in a database. This data is used as training data to improve the accuracy of future queries.

[0331] 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.

[0332] This invention is an advanced automated response system using an AI agent, which improves the quality of responses by incorporating an emotion engine that analyzes the user's emotions. This system analyzes inquiries received from users, understands the user's emotions, and provides appropriate responses accordingly.

[0333] The server first processes the received query information using a natural language processing engine. This analysis extracts keywords and intent from the query content and searches for related information. It also uses an emotion engine to analyze the emotions in the text entered by the user and estimate the user's emotional state.

[0334] The terminal not only provides an interface for users to input and submit inquiries, but also manages the responses displayed to the user. The responses generated by the server in response to inquiries are adjusted to the user's emotions and are carefully crafted to be more appropriate.

[0335] For example, if a user asks a terminal, "This system isn't working properly at all, can you do something about it?", the server analyzes this question using natural language processing and extracts keywords related to the system's operation. Furthermore, the emotion engine recognizes emotions such as dissatisfaction or frustration from the user's wording. Based on this, the server not only provides a technical answer but also generates a response that takes the user's emotions into consideration, such as, "We apologize for the inconvenience. Could you please tell us in more detail what kind of support you need to resolve the issue?"

[0336] Another important aspect of this system is that it accumulates data obtained through sentiment analysis and uses it as training data for the AI ​​agent, further improving the quality of emotional responses to future inquiries. This is expected to lead to more refined responses to users and increased user satisfaction.

[0337] The following describes the processing flow.

[0338] Step 1:

[0339] The user enters a query into the terminal interface and prepares to send it to the server.

[0340] Step 2:

[0341] The terminal sends the inquiry information entered by the user to the server as string data.

[0342] Step 3:

[0343] The server passes the received query information to a natural language processing engine, which performs analysis to extract keywords and intent.

[0344] Step 4:

[0345] Simultaneously, the server uses an emotion engine to analyze the emotions in the user's input and evaluate the emotional tone.

[0346] Step 5:

[0347] Based on the analyzed keywords and the user's emotional state, the server searches for relevant information from FAQ databases and external sources.

[0348] Step 6:

[0349] The server integrates search results and sentiment information to generate appropriate responses that take the user's emotions into consideration.

[0350] Step 7:

[0351] The generated response is sent from the server to the terminal and displayed to the user. The terminal displays this information clearly on its interface.

[0352] Step 8:

[0353] The server stores all data from user interactions and uses it as training data for future AI agents. This data also includes analyzed sentiment information.

[0354] (Example 2)

[0355] 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".

[0356] In modern information processing systems, improving the quality of responses to user inquiries is a crucial challenge. In particular, if responses are generated uniformly without regard to the user's emotional state, user satisfaction may decrease, potentially impairing the system's usefulness. This invention aims to achieve more responsive and satisfying interactions by appropriately analyzing user emotions and generating responses accordingly.

[0357] 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.

[0358] In this invention, the server includes a language processing means for analyzing received inquiry information, an emotion analysis means for analyzing the user's emotions, and an adjustment means for adjusting the generated response according to the user's emotional state. This makes it possible to generate a more appropriate response that takes the user's emotions into account and improve the user experience.

[0359] "Method of verbalization" refers to a method of converting received data into a usable format, analyzing its contents, and extracting necessary information.

[0360] "Search methods" refer to the process of detecting data from relevant information sources based on analyzed information and collecting necessary information.

[0361] "Creation method" refers to a method for generating an appropriate response to provide to the user based on acquired data.

[0362] "Emotion analysis means" refers to a technology that analyzes a user's input data to understand their emotions and estimate their emotional state.

[0363] A "display mechanism" is a system that presents the generated response on an interface for the user to use.

[0364] "Adjustment means" refers to the process of appropriately modifying the response content generated according to the user's emotional state and improving its quality.

[0365] "Training methods" refer to the process of using collected data to train a system and improve the accuracy and suitability of its responses.

[0366] To implement this invention, it is necessary to construct an advanced automated response system. This system consists of a server, a terminal, and a user. The server processes user inquiries using multiple modules, including a natural language processing engine and an sentiment analysis engine. Specifically, natural language processing tools such as Python's NLTK and spaCy, and common API services for sentiment analysis are available.

[0367] The terminal provides an intuitive interface for users to input and submit inquiries. The terminal also displays the responses received from the server to the user.

[0368] Users can make inquiries through this system and check the responses using the terminal interface. The server analyzes the user's emotions and provides a way to improve the quality of responses by using a generative AI model to generate appropriate responses based on those emotions.

[0369] For example, when a user asks "Tell me about this feature" from their device, the server processes the inquiry using natural language processing to extract key keywords and search for relevant information. The sentiment analysis engine determines the user's emotions from their question and adjusts the response to an appropriate tone based on the result. For instance, a prompt such as "Please answer gently and clearly" can be used to have the generative AI model generate an appropriate response.

[0370] By building this system, users will be able to receive more flexible and emotionally sensitive responses, thereby improving the user experience.

[0371] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0372] Step 1:

[0373] The user enters and submits their inquiry through their device. This input is natural language text, such as "Please tell me about this feature." The device then sends this text data to the server.

[0374] Step 2:

[0375] The server processes the received query text into a natural language processing engine. The input is the text data of the user's query, which is then analyzed to extract keywords and intent. Specifically, it uses libraries such as Python's NLTK or spaCy to perform text analysis and obtains structured data as output.

[0376] Step 3:

[0377] The server uses the information obtained from the parsed text to search relevant information sources and databases. In this step, additional information is retrieved from external sources using keywords extracted from the query. The output is a dataset containing the information necessary to generate the answer.

[0378] Step 4:

[0379] The server performs sentiment analysis on the user's input text. The input is natural language text, and the sentiment analysis engine is used to estimate the emotional state. The output is metadata indicating the user's emotional state, which is used when generating responses.

[0380] Step 5:

[0381] The server generates appropriate responses using a generative AI model. In this process, responses are generated using prompts based on the information and emotional state obtained in the previous step. For example, a prompt such as "Please answer gently and clearly" is input to the model, and it outputs a human-friendly response.

[0382] Step 6:

[0383] The server uses adjustment mechanisms to optimize the generated response according to the user's emotions. This process ensures that the output response has the most appropriate tone and content for the user.

[0384] Step 7:

[0385] The server sends the final response to the terminal. The terminal receives this and displays it in the user interface. The user reviews the provided response to resolve any questions or determine the next course of action.

[0386] Step 8:

[0387] The server stores inquiry information, sentiment state, and response information, updating it as training data. In this step, this data is saved to a database and used as training data for the model. This further improves the quality of responses in subsequent interactions.

[0388] (Application Example 2)

[0389] 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."

[0390] Improving the quality of responses to user inquiries is a crucial challenge in communication technology. In particular, there is a need for systems that can consider the user's emotions when providing explanations and solutions. However, many conventional automated response systems lack emotion recognition capabilities, potentially reducing user satisfaction. Therefore, there is a need to develop automated response systems that take emotions into account.

[0391] 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.

[0392] In this invention, the server includes data processing means for analyzing received inquiry information, information retrieval means for searching for related information based on the analyzed inquiry information, content generation means for generating a response using the information obtained by the information retrieval means, and emotion adaptation means for analyzing and adjusting the emotions of the generated response. This makes it possible to provide an appropriate and humane response that is in line with the user's emotional state.

[0393] "Data processing means" refers to the technology used to analyze received inquiry information and understand its content.

[0394] An "information retrieval method" is a method for efficiently searching for relevant information from external or internal sources based on analyzed query information.

[0395] "Content generation methods" refer to the process of using acquired information to generate appropriate answers and explanations.

[0396] "Emotional adaptation techniques" are technologies that analyze the user's emotions in response to a generated answer and adjust the answer content accordingly.

[0397] "Information presentation means" refers to methods and devices for effectively displaying adjusted responses to the user.

[0398] A "learning tool" is a system that accumulates past inquiry and response information and uses it to learn in order to improve the accuracy of future responses.

[0399] An "automated response system" is a system that has the function of automatically generating and providing responses to inquiries.

[0400] This automated response system is designed for efficient interaction between the user and the server. The server first analyzes the inquiry information received from the user using data processing tools. This process utilizes a natural language processing engine (e.g., spaCy) to extract important information from the inquiry. Simultaneously, information retrieval tools (e.g., external database access via API) search for relevant information based on the analyzed data.

[0401] Next, the server uses content generation means to generate appropriate responses based on the acquired information, utilizing a generative AI model (e.g., OpenAI GPT). At this time, sentiment adaptation means are used to analyze the user's emotions towards the generated response and adjust the response to the optimal format according to those emotions. For sentiment analysis, a sentiment analysis library (e.g., TextBlob) can be used.

[0402] The terminal displays a finalized response to the user based on the information presented. The system is designed to be easy for users to understand and to allow for quick responses. In addition, the server can accumulate past inquiry and response information through learning mechanisms, and use this data to improve the response accuracy of the AI ​​model. This continuous learning is expected to improve the quality of responses to future inquiries.

[0403] For example, when a user inquires with concern, asking "Why hasn't my payment been approved?", it's possible to immediately identify their concern and provide a tailored response such as: "We will do our best to alleviate your concerns. Please wait a moment while we investigate and address the issue." In this case, the prompt to the generating AI model would be something like, "Based on the user's message, create a kind and considerate response that takes their emotions into account. The user is feeling anxious because their payment hasn't been approved."

[0404] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0405] Step 1:

[0406] The user enters their inquiry through their device and sends it to the server. The entered inquiry is recorded as text data. The user is also encouraged to enter sentences written in natural language, including their emotions.

[0407] Step 2:

[0408] The server analyzes the received query using data processing tools. In this step, a natural language processing engine (e.g., spaCy) is used to extract keywords and intent from the text data. The extracted data is then used as input for subsequent information retrieval steps.

[0409] Step 3:

[0410] The server uses information retrieval tools based on the extracted keywords to search for relevant information. In this step, necessary information is retrieved from an external database via an API. This information becomes the output data used for the next content generation.

[0411] Step 4:

[0412] The server generates responses from information obtained using content generation methods. Using a generative AI model (e.g., OpenAI GPT), it creates natural and appropriate responses based on the submitted keywords and search information. These generated responses are then used as input for the next sentiment adaptation.

[0413] Step 5:

[0414] The server uses a sentiment analysis library (e.g., TextBlob) to analyze the user's emotions. It then applies the user's emotion information to the generated responses and adjusts them. The adjusted responses are output for informational purposes, resulting in user-friendly content.

[0415] Step 6:

[0416] The device displays the adjusted response to the user through an information presentation mechanism. The user reviews the response and decides on the next action. The displayed response is easy for the user to understand and guides them toward problem solving.

[0417] Step 7:

[0418] The server stores all query information and generated responses using a learning mechanism. This data is used as training data for an AI model, helping to improve the accuracy of responses to future queries.

[0419] 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.

[0420] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0421] 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.

[0422] [Third Embodiment]

[0423] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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).

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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".

[0435] This invention relates to a method for providing an automated response system utilizing an AI agent. This system significantly improves the efficiency of administrative tasks and helps sales representatives concentrate on sales activities.

[0436] The server is equipped with a natural language processing engine capable of analyzing received query information. This engine receives queries sent by users, analyzes their content, and extracts keywords and intent. Based on this analysis, it searches for relevant information from the FAQ database and external databases.

[0437] The terminal provides an interface for users to make inquiries. Through this interface, users can input questions in text format and send them to the server. The server generates a corresponding answer and sends it to the terminal. The terminal displays the received answer to the user, allowing the user to obtain the necessary information immediately.

[0438] For example, if a user asks their device, "What is the date of the next meeting?", the server processes this information through a natural language processing engine and extracts the keywords "meeting" and "date". Based on this, the server refers to internal calendar information and external schedule management databases to generate a specific answer such as, "The next meeting is next Wednesday at 2pm." The server then returns this answer to the device and displays it to the user. In this way, the user can quickly obtain the information they need.

[0439] Furthermore, the server stores the question-and-answer exchanges in a database, which is used to improve the accuracy of generating answers to future questions. This streamlines the response to each inquiry and increases the overall speed of operations.

[0440] The following describes the processing flow.

[0441] Step 1:

[0442] The terminal retrieves the inquiry information entered by the user and prepares to send this input data to the server.

[0443] Step 2:

[0444] The user uses the terminal interface to enter specific questions and clicks the "Submit" button to send the inquiry information to the server.

[0445] Step 3:

[0446] The server passes the received query information to a natural language processing engine, which analyzes the query content and extracts key keywords and context.

[0447] Step 4:

[0448] The server searches the FAQ database based on keywords and context obtained from the analysis and retrieves appropriate answer candidates. At the same time, it retrieves additional information from external databases and APIs as needed.

[0449] Step 5:

[0450] The server integrates search results and related information to generate the best possible answer. If an answer cannot be generated, it constructs content that presents relevant information and alternative solutions.

[0451] Step 6:

[0452] The server sends the generated response to the terminal. The terminal displays the response to the user through its user interface, allowing for immediate reference.

[0453] Step 7:

[0454] The server stores data on inquiries and their responses, and uses this data to train the AI ​​agent, aiming to improve the accuracy of future responses.

[0455] (Example 1)

[0456] 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."

[0457] Existing automated response systems sometimes lack the ability to provide appropriate and timely answers to a wide range of user inquiries. Furthermore, they lack efficient data accumulation and learning methods for improving the accuracy of their responses. Therefore, system improvements are needed to enhance operational efficiency.

[0458] 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.

[0459] In this invention, the server includes a natural language processing means for analyzing received inquiry information, a search means for searching for related information, a generation means for generating an answer using the acquired information, and an improvement means for accumulating information to improve the accuracy of future answers based on past inquiries and answers. This makes it possible to improve the accuracy and speed of answers to user inquiries and increase operational efficiency.

[0460] "Natural language processing means" refers to technologies for analyzing received inquiry information and extracting keywords and intent.

[0461] A "search method" is a technique for retrieving relevant information from internal or external sources based on analyzed query information.

[0462] "Generation method" refers to a method of generating an appropriate response to a user's inquiry based on the acquired relevant information.

[0463] "Display means" refers to the technology that displays the response content sent from the server through a user interface used by the user.

[0464] A "learning tool" is a system that accumulates inquiry and response information and updates and manages the data in order to improve the accuracy of future responses.

[0465] "Analysis methods" refer to the process of analyzing information in order to extract important keywords and intentions from inquiry information.

[0466] "Improvement measures" refer to technologies that analyze past inquiries and responses and use that analysis to improve the accuracy and processing efficiency of future responses.

[0467] This invention provides an automated response system utilizing artificial intelligence. The system mainly consists of a server, a terminal, and user interaction.

[0468] server

[0469] The server plays a central role in processing received inquiry information. The server is equipped with a natural language processing engine for parsing text data. Specifically, it can use open-source natural language processing libraries such as spaCy or BERT. In addition, based on the parsed information, the server retrieves relevant information from FAQ databases and external databases using search mechanisms. A generation mechanism generates answers based on the obtained data and sends them to the terminal via the user interface.

[0470] terminal

[0471] The terminal provides an interface for users to submit inquiries. The terminal's user interface is built using web technologies such as React and Vue.js, allowing users to input questions in text format. The terminal then sends the entered information to the server. The response received from the server is displayed on the terminal's screen and presented in a format easily understandable to the user.

[0472] User

[0473] Users interact with the system via a terminal. Entering a question triggers rapid analysis and response generation by the server. For example, if a user enters "What is the current stock status?", the server consults its internal database and generates a specific response such as "There are 10 in stock," which is then displayed on the terminal.

[0474] Examples of prompts for the generative AI model include questions such as, "Please tell me the date of the next meeting," or "What's the weather like today?"

[0475] This allows users to quickly obtain the information they need and improve work efficiency. The system also stores past inquiries and responses in a database, helping to improve the accuracy of future responses.

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] The terminal receives inquiry information entered by the user. The user enters the question in text format through the terminal's interface. For example, "Please tell me the date of the next meeting." The entered information is sent to the server in a data format such as JSON.

[0479] Step 2:

[0480] The server receives the query information sent from the terminal. Next, it uses a natural language processing engine to analyze the query content and extract keywords and intent. Here, spaCy or BERT is used to analyze the text. For example, keywords such as "meeting" and "schedule" are extracted.

[0481] Step 3:

[0482] The server uses search methods based on the analyzed information. The server searches internal databases and external information sources to retrieve relevant data. During this process, it makes specific API calls to extract the necessary information. For example, it might retrieve meeting schedules from its internal calendar system.

[0483] Step 4:

[0484] The server uses generation tools to create appropriate responses based on the acquired data. The generated responses are formatted in a grammatically correct manner. For example, a response such as "The next meeting is next Tuesday at 2pm" might be generated.

[0485] Step 5:

[0486] The server sends the generated response to the terminal. The response data is transmitted using standard communication protocols.

[0487] Step 6:

[0488] The terminal displays the response received from the server on the user interface. The user can then review this and obtain the necessary information. The screen might display output such as, "The next meeting is next Tuesday at 2 PM."

[0489] Step 7:

[0490] The server stores the content of inquiries and responses in a database. This data is used for machine learning and forms the basis for improving the accuracy and efficiency of future responses.

[0491] (Application Example 1)

[0492] 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."

[0493] Electronic payment services require prompt and accurate responses to customer inquiries. However, manual responses are time-consuming and labor-intensive, and also carry the risk of human error. Furthermore, while utilizing past inquiry history and service usage history is necessary to improve the consistency and accuracy of responses, there is a lack of efficient mechanisms for doing so. Therefore, improving customer satisfaction and operational efficiency are key challenges.

[0494] 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.

[0495] In this invention, the server includes natural language processing means for analyzing received inquiry information, search means for searching for related information, and generation means for generating natural-sounding text using a generation AI model. This enables rapid and accurate automated responses to customer inquiries in electronic payment services.

[0496] "Natural language processing means" refers to methods that analyze text-based inquiry information received from users and extract keywords and intent.

[0497] A "search method" is a technique for obtaining relevant information from internal or external databases based on analyzed query information.

[0498] A "generation method" is a technique that generates an answer based on acquired information and communicates that answer to the user.

[0499] "Display means" refers to a method of displaying the generated response on a user interface, making it easy for the user to obtain the information.

[0500] A "learning method" is a technique that involves accumulating inquiry and response information and using it as training data for an AI agent.

[0501] A "generative AI model" is a model of generative artificial intelligence designed to generate natural-sounding responses.

[0502] "Reference means" refers to methods for obtaining necessary information based on service usage history and other past data.

[0503] This invention is a system that provides rapid and accurate automated responses to customer inquiries in electronic payment services. The server achieves this function using multiple means.

[0504] First, when a user's inquiry is sent from the terminal to the server, the server uses a natural language processing engine to analyze the received text information. Examples of natural language processing engines used here include Google Cloud Natural Language and SpaCy. Through this analysis, keywords and the user's intent are extracted from the inquiry.

[0505] Next, the server searches for relevant data based on the extracted information. In addition to its internal database, it can also access external databases via an API. This ensures that the most suitable information is retrieved.

[0506] The acquired information is used to generate a natural-sounding response using a generative AI model. OpenAI's GPT-3, for example, can be used as the generative AI model. This generated response is then formatted to be easily understood by the user.

[0507] Finally, the server sends this generated response to the terminal, where it is displayed on the user interface accessed by the user. The user can quickly obtain the necessary information, and the inquiry is resolved smoothly.

[0508] Furthermore, this system is equipped with both reference and learning mechanisms, allowing for the referencing of information based on service usage history and the improvement of response accuracy through training of AI agents using past inquiry information. As a result, the system continuously improves its performance and continues to provide more accurate responses.

[0509] For example, when a user asks, "What is my payment amount for this month?", the server searches the database for relevant information based on the analyzed keywords such as "payment amount" and "this month," and presents the user with a generated response such as, "Your payment amount for this month is 20,000 yen." An example of a prompt in this case would be, "Generate a natural response to tell the user their credit card payment amount for this month."

[0510] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0511] Step 1:

[0512] User inquiries

[0513] The user enters and submits inquiry information in text format via their terminal. The entered inquiry information is then sent to the server.

[0514] Step 2:

[0515] Analysis using natural language processing

[0516] The server passes the received query information to a natural language processing engine (e.g., Google Cloud Natural Language). This engine extracts keywords and intent from the query's text data. The analyzed keywords are then returned to the server as output.

[0517] Step 3:

[0518] Search for related information

[0519] The server searches for relevant information from databases and external APIs based on the analyzed keywords. During this process, it retrieves payment and usage history data related to the inquiry. The necessary information is then obtained as output.

[0520] Step 4:

[0521] Generating natural answers

[0522] The server inputs the acquired information into a generation AI model (e.g., OpenAI GPT-3). Using prompts, it generates a response in natural language. In this generation process, the information obtained as input is used, and a response message to the user is generated as output.

[0523] Step 5:

[0524] Display the answer

[0525] The server sends the generated response to the terminal. The terminal displays this response in the user interface. The user can immediately verify the information.

[0526] Step 6:

[0527] Record of inquiries and responses

[0528] The server stores query information and the corresponding answers in a database. This data is used as training data to improve the accuracy of future queries.

[0529] 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.

[0530] This invention is an advanced automated response system using an AI agent, which improves the quality of responses by incorporating an emotion engine that analyzes the user's emotions. This system analyzes inquiries received from users, understands the user's emotions, and provides appropriate responses accordingly.

[0531] The server first processes the received query information using a natural language processing engine. This analysis extracts keywords and intent from the query content and searches for related information. It also uses an emotion engine to analyze the emotions in the text entered by the user and estimate the user's emotional state.

[0532] The terminal not only provides an interface for users to input and submit inquiries, but also manages the responses displayed to the user. The responses generated by the server in response to inquiries are adjusted to the user's emotions and are carefully crafted to be more appropriate.

[0533] For example, if a user asks a terminal, "This system isn't working properly at all, can you do something about it?", the server analyzes this question using natural language processing and extracts keywords related to the system's operation. Furthermore, the emotion engine recognizes emotions such as dissatisfaction or frustration from the user's wording. Based on this, the server not only provides a technical answer but also generates a response that takes the user's emotions into consideration, such as, "We apologize for the inconvenience. Could you please tell us in more detail what kind of support you need to resolve the issue?"

[0534] Another important aspect of this system is that it accumulates data obtained through sentiment analysis and uses it as training data for the AI ​​agent, further improving the quality of emotional responses to future inquiries. This is expected to lead to more refined responses to users and increased user satisfaction.

[0535] The following describes the processing flow.

[0536] Step 1:

[0537] The user enters a query into the terminal interface and prepares to send it to the server.

[0538] Step 2:

[0539] The terminal sends the inquiry information entered by the user to the server as string data.

[0540] Step 3:

[0541] The server passes the received query information to a natural language processing engine, which performs analysis to extract keywords and intent.

[0542] Step 4:

[0543] Simultaneously, the server uses an emotion engine to analyze the emotions in the user's input and evaluate the emotional tone.

[0544] Step 5:

[0545] Based on the analyzed keywords and the user's emotional state, the server searches for relevant information from FAQ databases and external sources.

[0546] Step 6:

[0547] The server integrates search results and sentiment information to generate appropriate responses that take the user's emotions into consideration.

[0548] Step 7:

[0549] The generated response is sent from the server to the terminal and displayed to the user. The terminal displays this information clearly on its interface.

[0550] Step 8:

[0551] The server stores all data from user interactions and uses it as training data for future AI agents. This data also includes analyzed sentiment information.

[0552] (Example 2)

[0553] 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."

[0554] In modern information processing systems, improving the quality of responses to user inquiries is a crucial challenge. In particular, if responses are generated uniformly without regard to the user's emotional state, user satisfaction may decrease, potentially impairing the system's usefulness. This invention aims to achieve more responsive and satisfying interactions by appropriately analyzing user emotions and generating responses accordingly.

[0555] 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.

[0556] In this invention, the server includes a language processing means for analyzing received inquiry information, an emotion analysis means for analyzing the user's emotions, and an adjustment means for adjusting the generated response according to the user's emotional state. This makes it possible to generate a more appropriate response that takes the user's emotions into account and improve the user experience.

[0557] "Method of verbalization" refers to a method of converting received data into a usable format, analyzing its contents, and extracting necessary information.

[0558] "Search methods" refer to the process of detecting data from relevant information sources based on analyzed information and collecting necessary information.

[0559] "Creation method" refers to a method for generating an appropriate response to provide to the user based on acquired data.

[0560] "Emotion analysis means" refers to a technology that analyzes a user's input data to understand their emotions and estimate their emotional state.

[0561] A "display mechanism" is a system that presents the generated response on an interface for the user to use.

[0562] "Adjustment means" refers to the process of appropriately modifying the response content generated according to the user's emotional state and improving its quality.

[0563] "Training methods" refer to the process of using collected data to train a system and improve the accuracy and suitability of its responses.

[0564] To implement this invention, it is necessary to construct an advanced automated response system. This system consists of a server, a terminal, and a user. The server processes user inquiries using multiple modules, including a natural language processing engine and an sentiment analysis engine. Specifically, natural language processing tools such as Python's NLTK and spaCy, and common API services for sentiment analysis are available.

[0565] The terminal provides an intuitive interface for users to input and submit inquiries. The terminal also displays the responses received from the server to the user.

[0566] Users can make inquiries through this system and check the responses using the terminal interface. The server analyzes the user's emotions and provides a way to improve the quality of responses by using a generative AI model to generate appropriate responses based on those emotions.

[0567] For example, when a user asks "Tell me about this feature" from their device, the server processes the inquiry using natural language processing to extract key keywords and search for relevant information. The sentiment analysis engine determines the user's emotions from their question and adjusts the response to an appropriate tone based on the result. For instance, a prompt such as "Please answer gently and clearly" can be used to have the generative AI model generate an appropriate response.

[0568] By building this system, users will be able to receive more flexible and emotionally sensitive responses, thereby improving the user experience.

[0569] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0570] Step 1:

[0571] The user enters and submits their inquiry through their device. This input is natural language text, such as "Please tell me about this feature." The device then sends this text data to the server.

[0572] Step 2:

[0573] The server processes the received query text into a natural language processing engine. The input is the text data of the user's query, which is then analyzed to extract keywords and intent. Specifically, it uses libraries such as Python's NLTK or spaCy to perform text analysis and obtains structured data as output.

[0574] Step 3:

[0575] The server uses the information obtained from the parsed text to search relevant information sources and databases. In this step, additional information is retrieved from external sources using keywords extracted from the query. The output is a dataset containing the information necessary to generate the answer.

[0576] Step 4:

[0577] The server performs sentiment analysis on the user's input text. The input is natural language text, and the sentiment analysis engine is used to estimate the emotional state. The output is metadata indicating the user's emotional state, which is used when generating responses.

[0578] Step 5:

[0579] The server generates appropriate responses using a generative AI model. In this process, responses are generated using prompts based on the information and emotional state obtained in the previous step. For example, a prompt such as "Please answer gently and clearly" is input to the model, and it outputs a human-friendly response.

[0580] Step 6:

[0581] The server uses adjustment mechanisms to optimize the generated response according to the user's emotions. This process ensures that the output response has the most appropriate tone and content for the user.

[0582] Step 7:

[0583] The server sends the final response to the terminal. The terminal receives this and displays it in the user interface. The user reviews the provided response to resolve any questions or determine the next course of action.

[0584] Step 8:

[0585] The server stores inquiry information, sentiment state, and response information, updating it as training data. In this step, this data is saved to a database and used as training data for the model. This further improves the quality of responses in subsequent interactions.

[0586] (Application Example 2)

[0587] 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."

[0588] Improving the quality of responses to user inquiries is a crucial challenge in communication technology. In particular, there is a need for systems that can consider the user's emotions when providing explanations and solutions. However, many conventional automated response systems lack emotion recognition capabilities, potentially reducing user satisfaction. Therefore, there is a need to develop automated response systems that take emotions into account.

[0589] 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.

[0590] In this invention, the server includes data processing means for analyzing received inquiry information, information retrieval means for searching for related information based on the analyzed inquiry information, content generation means for generating a response using the information obtained by the information retrieval means, and emotion adaptation means for analyzing and adjusting the emotions of the generated response. This makes it possible to provide an appropriate and humane response that is in line with the user's emotional state.

[0591] "Data processing means" refers to the technology used to analyze received inquiry information and understand its content.

[0592] An "information retrieval method" is a method for efficiently searching for relevant information from external or internal sources based on analyzed query information.

[0593] "Content generation methods" refer to the process of using acquired information to generate appropriate answers and explanations.

[0594] "Emotional adaptation techniques" are technologies that analyze the user's emotions in response to a generated answer and adjust the answer content accordingly.

[0595] "Information presentation means" refers to methods and devices for effectively displaying adjusted responses to the user.

[0596] A "learning tool" is a system that accumulates past inquiry and response information and uses it to learn in order to improve the accuracy of future responses.

[0597] An "automated response system" is a system that has the function of automatically generating and providing responses to inquiries.

[0598] This automated response system is designed for efficient interaction between the user and the server. The server first analyzes the inquiry information received from the user using data processing tools. This process utilizes a natural language processing engine (e.g., spaCy) to extract important information from the inquiry. Simultaneously, information retrieval tools (e.g., external database access via API) search for relevant information based on the analyzed data.

[0599] Next, the server uses content generation means to generate appropriate responses based on the acquired information, utilizing a generative AI model (e.g., OpenAI GPT). At this time, sentiment adaptation means are used to analyze the user's emotions towards the generated response and adjust the response to the optimal format according to those emotions. For sentiment analysis, a sentiment analysis library (e.g., TextBlob) can be used.

[0600] The terminal displays a finalized response to the user based on the information presented. The system is designed to be easy for users to understand and to allow for quick responses. In addition, the server can accumulate past inquiry and response information through learning mechanisms, and use this data to improve the response accuracy of the AI ​​model. This continuous learning is expected to improve the quality of responses to future inquiries.

[0601] For example, when a user inquires with concern, asking "Why hasn't my payment been approved?", it's possible to immediately identify their concern and provide a tailored response such as: "We will do our best to alleviate your concerns. Please wait a moment while we investigate and address the issue." In this case, the prompt to the generating AI model would be something like, "Based on the user's message, create a kind and considerate response that takes their emotions into account. The user is feeling anxious because their payment hasn't been approved."

[0602] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0603] Step 1:

[0604] The user enters their inquiry through their device and sends it to the server. The entered inquiry is recorded as text data. The user is also encouraged to enter sentences written in natural language, including their emotions.

[0605] Step 2:

[0606] The server analyzes the received query using data processing tools. In this step, a natural language processing engine (e.g., spaCy) is used to extract keywords and intent from the text data. The extracted data is then used as input for subsequent information retrieval steps.

[0607] Step 3:

[0608] The server uses information retrieval tools based on the extracted keywords to search for relevant information. In this step, necessary information is retrieved from an external database via an API. This information becomes the output data used for the next content generation.

[0609] Step 4:

[0610] The server generates responses from information obtained using content generation methods. Using a generative AI model (e.g., OpenAI GPT), it creates natural and appropriate responses based on the submitted keywords and search information. These generated responses are then used as input for the next sentiment adaptation.

[0611] Step 5:

[0612] The server uses a sentiment analysis library (e.g., TextBlob) to analyze the user's emotions. It then applies the user's emotion information to the generated responses and adjusts them. The adjusted responses are output for informational purposes, resulting in user-friendly content.

[0613] Step 6:

[0614] The device displays the adjusted response to the user through an information presentation mechanism. The user reviews the response and decides on the next action. The displayed response is easy for the user to understand and guides them toward problem solving.

[0615] Step 7:

[0616] The server stores all query information and generated responses using a learning mechanism. This data is used as training data for an AI model, helping to improve the accuracy of responses to future queries.

[0617] 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.

[0618] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0619] 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.

[0620] [Fourth Embodiment]

[0621] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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.

[0626] 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).

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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".

[0634] This invention relates to a method for providing an automated response system utilizing an AI agent. This system significantly improves the efficiency of administrative tasks and helps sales representatives concentrate on sales activities.

[0635] The server is equipped with a natural language processing engine capable of analyzing received query information. This engine receives queries sent by users, analyzes their content, and extracts keywords and intent. Based on this analysis, it searches for relevant information from the FAQ database and external databases.

[0636] The terminal provides an interface for users to make inquiries. Through this interface, users can input questions in text format and send them to the server. The server generates a corresponding answer and sends it to the terminal. The terminal displays the received answer to the user, allowing the user to obtain the necessary information immediately.

[0637] For example, if a user asks their device, "What is the date of the next meeting?", the server processes this information through a natural language processing engine and extracts the keywords "meeting" and "date". Based on this, the server refers to internal calendar information and external schedule management databases to generate a specific answer such as, "The next meeting is next Wednesday at 2pm." The server then returns this answer to the device and displays it to the user. In this way, the user can quickly obtain the information they need.

[0638] Furthermore, the server stores the question-and-answer exchanges in a database, which is used to improve the accuracy of generating answers to future questions. This streamlines the response to each inquiry and increases the overall speed of operations.

[0639] The following describes the processing flow.

[0640] Step 1:

[0641] The terminal retrieves the inquiry information entered by the user and prepares to send this input data to the server.

[0642] Step 2:

[0643] The user uses the terminal interface to enter specific questions and clicks the "Submit" button to send the inquiry information to the server.

[0644] Step 3:

[0645] The server passes the received query information to a natural language processing engine, which analyzes the query content and extracts key keywords and context.

[0646] Step 4:

[0647] The server searches the FAQ database based on keywords and context obtained from the analysis and retrieves appropriate answer candidates. At the same time, it retrieves additional information from external databases and APIs as needed.

[0648] Step 5:

[0649] The server integrates search results and related information to generate the best possible answer. If an answer cannot be generated, it constructs content that presents relevant information and alternative solutions.

[0650] Step 6:

[0651] The server sends the generated response to the terminal. The terminal displays the response to the user through its user interface, allowing for immediate reference.

[0652] Step 7:

[0653] The server stores data on inquiries and their responses, and uses this data to train the AI ​​agent, aiming to improve the accuracy of future responses.

[0654] (Example 1)

[0655] 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".

[0656] Existing automated response systems sometimes lack the ability to provide appropriate and timely answers to a wide range of user inquiries. Furthermore, they lack efficient data accumulation and learning methods for improving the accuracy of their responses. Therefore, system improvements are needed to enhance operational efficiency.

[0657] 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.

[0658] In this invention, the server includes a natural language processing means for analyzing received inquiry information, a search means for searching for related information, a generation means for generating an answer using the acquired information, and an improvement means for accumulating information to improve the accuracy of future answers based on past inquiries and answers. This makes it possible to improve the accuracy and speed of answers to user inquiries and increase operational efficiency.

[0659] "Natural language processing means" refers to technologies for analyzing received inquiry information and extracting keywords and intent.

[0660] A "search method" is a technique for retrieving relevant information from internal or external sources based on analyzed query information.

[0661] "Generation method" refers to a method of generating an appropriate response to a user's inquiry based on the acquired relevant information.

[0662] "Display means" refers to the technology that displays the response content sent from the server through a user interface used by the user.

[0663] A "learning tool" is a system that accumulates inquiry and response information and updates and manages the data in order to improve the accuracy of future responses.

[0664] "Analysis methods" refer to the process of analyzing information in order to extract important keywords and intentions from inquiry information.

[0665] "Improvement measures" refer to technologies that analyze past inquiries and responses and use that analysis to improve the accuracy and processing efficiency of future responses.

[0666] This invention provides an automated response system utilizing artificial intelligence. The system mainly consists of a server, a terminal, and user interaction.

[0667] server

[0668] The server plays a central role in processing received inquiry information. The server is equipped with a natural language processing engine for parsing text data. Specifically, it can use open-source natural language processing libraries such as spaCy or BERT. In addition, based on the parsed information, the server retrieves relevant information from FAQ databases and external databases using search mechanisms. A generation mechanism generates answers based on the obtained data and sends them to the terminal via the user interface.

[0669] terminal

[0670] The terminal provides an interface for users to submit inquiries. The terminal's user interface is built using web technologies such as React and Vue.js, allowing users to input questions in text format. The terminal then sends the entered information to the server. The response received from the server is displayed on the terminal's screen and presented in a format easily understandable to the user.

[0671] User

[0672] Users interact with the system via a terminal. Entering a question triggers rapid analysis and response generation by the server. For example, if a user enters "What is the current stock status?", the server consults its internal database and generates a specific response such as "There are 10 in stock," which is then displayed on the terminal.

[0673] Examples of prompts for the generative AI model include questions such as, "Please tell me the date of the next meeting," or "What's the weather like today?"

[0674] This allows users to quickly obtain the information they need and improve work efficiency. The system also stores past inquiries and responses in a database, helping to improve the accuracy of future responses.

[0675] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0676] Step 1:

[0677] The terminal receives inquiry information entered by the user. The user enters the question in text format through the terminal's interface. For example, "Please tell me the date of the next meeting." The entered information is sent to the server in a data format such as JSON.

[0678] Step 2:

[0679] The server receives the query information sent from the terminal. Next, it uses a natural language processing engine to analyze the query content and extract keywords and intent. Here, spaCy or BERT is used to analyze the text. For example, keywords such as "meeting" and "schedule" are extracted.

[0680] Step 3:

[0681] The server uses search methods based on the analyzed information. The server searches internal databases and external information sources to retrieve relevant data. During this process, it makes specific API calls to extract the necessary information. For example, it might retrieve meeting schedules from its internal calendar system.

[0682] Step 4:

[0683] The server uses generation tools to create appropriate responses based on the acquired data. The generated responses are formatted in a grammatically correct manner. For example, a response such as "The next meeting is next Tuesday at 2pm" might be generated.

[0684] Step 5:

[0685] The server sends the generated response to the terminal. The response data is transmitted using standard communication protocols.

[0686] Step 6:

[0687] The terminal displays the response received from the server on the user interface. The user can then review this and obtain the necessary information. The screen might display output such as, "The next meeting is next Tuesday at 2 PM."

[0688] Step 7:

[0689] The server stores the content of inquiries and responses in a database. This data is used for machine learning and forms the basis for improving the accuracy and efficiency of future responses.

[0690] (Application Example 1)

[0691] 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".

[0692] Electronic payment services require prompt and accurate responses to customer inquiries. However, manual responses are time-consuming and labor-intensive, and also carry the risk of human error. Furthermore, while utilizing past inquiry history and service usage history is necessary to improve the consistency and accuracy of responses, there is a lack of efficient mechanisms for doing so. Therefore, improving customer satisfaction and operational efficiency are key challenges.

[0693] 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.

[0694] In this invention, the server includes natural language processing means for analyzing received inquiry information, search means for searching for related information, and generation means for generating natural-sounding text using a generation AI model. This enables rapid and accurate automated responses to customer inquiries in electronic payment services.

[0695] "Natural language processing means" refers to methods that analyze text-based inquiry information received from users and extract keywords and intent.

[0696] A "search method" is a technique for obtaining relevant information from internal or external databases based on analyzed query information.

[0697] A "generation method" is a technique that generates an answer based on acquired information and communicates that answer to the user.

[0698] "Display means" refers to a method of displaying the generated response on a user interface, making it easy for the user to obtain the information.

[0699] A "learning method" is a technique that involves accumulating inquiry and response information and using it as training data for an AI agent.

[0700] A "generative AI model" is a model of generative artificial intelligence designed to generate natural-sounding responses.

[0701] "Reference means" refers to methods for obtaining necessary information based on service usage history and other past data.

[0702] This invention is a system that provides rapid and accurate automated responses to customer inquiries in electronic payment services. The server achieves this function using multiple means.

[0703] First, when a user's inquiry is sent from the terminal to the server, the server uses a natural language processing engine to analyze the received text information. Examples of natural language processing engines used here include Google Cloud Natural Language and SpaCy. Through this analysis, keywords and the user's intent are extracted from the inquiry.

[0704] Next, the server searches for relevant data based on the extracted information. In addition to its internal database, it can also access external databases via an API. This ensures that the most suitable information is retrieved.

[0705] The acquired information is used to generate a natural-sounding response using a generative AI model. OpenAI's GPT-3, for example, can be used as the generative AI model. This generated response is then formatted to be easily understood by the user.

[0706] Finally, the server sends this generated response to the terminal, where it is displayed on the user interface accessed by the user. The user can quickly obtain the necessary information, and the inquiry is resolved smoothly.

[0707] Furthermore, this system is equipped with both reference and learning mechanisms, allowing for the referencing of information based on service usage history and the improvement of response accuracy through training of AI agents using past inquiry information. As a result, the system continuously improves its performance and continues to provide more accurate responses.

[0708] For example, when a user asks, "What is my payment amount for this month?", the server searches the database for relevant information based on the analyzed keywords such as "payment amount" and "this month," and presents the user with a generated response such as, "Your payment amount for this month is 20,000 yen." An example of a prompt in this case would be, "Generate a natural response to tell the user their credit card payment amount for this month."

[0709] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0710] Step 1:

[0711] User inquiries

[0712] The user enters and submits inquiry information in text format via their terminal. The entered inquiry information is then sent to the server.

[0713] Step 2:

[0714] Analysis using natural language processing

[0715] The server passes the received query information to a natural language processing engine (e.g., Google Cloud Natural Language). This engine extracts keywords and intent from the query's text data. The analyzed keywords are then returned to the server as output.

[0716] Step 3:

[0717] Search for related information

[0718] The server searches for relevant information from databases and external APIs based on the analyzed keywords. During this process, it retrieves payment and usage history data related to the inquiry. The necessary information is then obtained as output.

[0719] Step 4:

[0720] Generating natural answers

[0721] The server inputs the acquired information into a generation AI model (e.g., OpenAI GPT-3). Using prompts, it generates a response in natural language. In this generation process, the information obtained as input is used, and a response message to the user is generated as output.

[0722] Step 5:

[0723] Display the answer

[0724] The server sends the generated response to the terminal. The terminal displays this response in the user interface. The user can immediately verify the information.

[0725] Step 6:

[0726] Record of inquiries and responses

[0727] The server stores query information and the corresponding answers in a database. This data is used as training data to improve the accuracy of future queries.

[0728] 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.

[0729] This invention is an advanced automated response system using an AI agent, which improves the quality of responses by incorporating an emotion engine that analyzes the user's emotions. This system analyzes inquiries received from users, understands the user's emotions, and provides appropriate responses accordingly.

[0730] The server first processes the received query information using a natural language processing engine. This analysis extracts keywords and intent from the query content and searches for related information. It also uses an emotion engine to analyze the emotions in the text entered by the user and estimate the user's emotional state.

[0731] The terminal not only provides an interface for users to input and submit inquiries, but also manages the responses displayed to the user. The responses generated by the server in response to inquiries are adjusted to the user's emotions and are carefully crafted to be more appropriate.

[0732] For example, if a user asks a terminal, "This system isn't working properly at all, can you do something about it?", the server analyzes this question using natural language processing and extracts keywords related to the system's operation. Furthermore, the emotion engine recognizes emotions such as dissatisfaction or frustration from the user's wording. Based on this, the server not only provides a technical answer but also generates a response that takes the user's emotions into consideration, such as, "We apologize for the inconvenience. Could you please tell us in more detail what kind of support you need to resolve the issue?"

[0733] Another important aspect of this system is that it accumulates data obtained through sentiment analysis and uses it as training data for the AI ​​agent, further improving the quality of emotional responses to future inquiries. This is expected to lead to more refined responses to users and increased user satisfaction.

[0734] The following describes the processing flow.

[0735] Step 1:

[0736] The user enters a query into the terminal interface and prepares to send it to the server.

[0737] Step 2:

[0738] The terminal sends the inquiry information entered by the user to the server as string data.

[0739] Step 3:

[0740] The server passes the received query information to a natural language processing engine, which performs analysis to extract keywords and intent.

[0741] Step 4:

[0742] Simultaneously, the server uses an emotion engine to analyze the emotions in the user's input and evaluate the emotional tone.

[0743] Step 5:

[0744] Based on the analyzed keywords and the user's emotional state, the server searches for relevant information from FAQ databases and external sources.

[0745] Step 6:

[0746] The server integrates search results and sentiment information to generate appropriate responses that take the user's emotions into consideration.

[0747] Step 7:

[0748] The generated response is sent from the server to the terminal and displayed to the user. The terminal displays this information clearly on its interface.

[0749] Step 8:

[0750] The server stores all data from user interactions and uses it as training data for future AI agents. This data also includes analyzed sentiment information.

[0751] (Example 2)

[0752] 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".

[0753] In modern information processing systems, improving the quality of responses to user inquiries is a crucial challenge. In particular, if responses are generated uniformly without regard to the user's emotional state, user satisfaction may decrease, potentially impairing the system's usefulness. This invention aims to achieve more responsive and satisfying interactions by appropriately analyzing user emotions and generating responses accordingly.

[0754] 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.

[0755] In this invention, the server includes a language processing means for analyzing received inquiry information, an emotion analysis means for analyzing the user's emotions, and an adjustment means for adjusting the generated response according to the user's emotional state. This makes it possible to generate a more appropriate response that takes the user's emotions into account and improve the user experience.

[0756] "Method of verbalization" refers to a method of converting received data into a usable format, analyzing its contents, and extracting necessary information.

[0757] "Search methods" refer to the process of detecting data from relevant information sources based on analyzed information and collecting necessary information.

[0758] "Creation method" refers to a method for generating an appropriate response to provide to the user based on acquired data.

[0759] "Emotion analysis means" refers to a technology that analyzes a user's input data to understand their emotions and estimate their emotional state.

[0760] A "display mechanism" is a system that presents the generated response on an interface for the user to use.

[0761] "Adjustment means" refers to the process of appropriately modifying the response content generated according to the user's emotional state and improving its quality.

[0762] "Training methods" refer to the process of using collected data to train a system and improve the accuracy and suitability of its responses.

[0763] To implement this invention, it is necessary to construct an advanced automated response system. This system consists of a server, a terminal, and a user. The server processes user inquiries using multiple modules, including a natural language processing engine and an sentiment analysis engine. Specifically, natural language processing tools such as Python's NLTK and spaCy, and common API services for sentiment analysis are available.

[0764] The terminal provides an intuitive interface for users to input and submit inquiries. The terminal also displays the responses received from the server to the user.

[0765] Users can make inquiries through this system and check the responses using the terminal interface. The server analyzes the user's emotions and provides a way to improve the quality of responses by using a generative AI model to generate appropriate responses based on those emotions.

[0766] For example, when a user asks "Tell me about this feature" from their device, the server processes the inquiry using natural language processing to extract key keywords and search for relevant information. The sentiment analysis engine determines the user's emotions from their question and adjusts the response to an appropriate tone based on the result. For instance, a prompt such as "Please answer gently and clearly" can be used to have the generative AI model generate an appropriate response.

[0767] By building this system, users will be able to receive more flexible and emotionally sensitive responses, thereby improving the user experience.

[0768] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0769] Step 1:

[0770] The user enters and submits their inquiry through their device. This input is natural language text, such as "Please tell me about this feature." The device then sends this text data to the server.

[0771] Step 2:

[0772] The server processes the received query text into a natural language processing engine. The input is the text data of the user's query, which is then analyzed to extract keywords and intent. Specifically, it uses libraries such as Python's NLTK or spaCy to perform text analysis and obtains structured data as output.

[0773] Step 3:

[0774] The server uses the information obtained from the parsed text to search relevant information sources and databases. In this step, additional information is retrieved from external sources using keywords extracted from the query. The output is a dataset containing the information necessary to generate the answer.

[0775] Step 4:

[0776] The server performs sentiment analysis on the user's input text. The input is natural language text, and the sentiment analysis engine is used to estimate the emotional state. The output is metadata indicating the user's emotional state, which is used when generating responses.

[0777] Step 5:

[0778] The server generates appropriate responses using a generative AI model. In this process, responses are generated using prompts based on the information and emotional state obtained in the previous step. For example, a prompt such as "Please answer gently and clearly" is input to the model, and it outputs a human-friendly response.

[0779] Step 6:

[0780] The server uses adjustment mechanisms to optimize the generated response according to the user's emotions. This process ensures that the output response has the most appropriate tone and content for the user.

[0781] Step 7:

[0782] The server sends the final response to the terminal. The terminal receives this and displays it in the user interface. The user reviews the provided response to resolve any questions or determine the next course of action.

[0783] Step 8:

[0784] The server stores inquiry information, sentiment state, and response information, updating it as training data. In this step, this data is saved to a database and used as training data for the model. This further improves the quality of responses in subsequent interactions.

[0785] (Application Example 2)

[0786] 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".

[0787] Improving the quality of responses to user inquiries is a crucial challenge in communication technology. In particular, there is a need for systems that can consider the user's emotions when providing explanations and solutions. However, many conventional automated response systems lack emotion recognition capabilities, potentially reducing user satisfaction. Therefore, there is a need to develop automated response systems that take emotions into account.

[0788] 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.

[0789] In this invention, the server includes data processing means for analyzing received inquiry information, information retrieval means for searching for related information based on the analyzed inquiry information, content generation means for generating a response using the information obtained by the information retrieval means, and emotion adaptation means for analyzing and adjusting the emotions of the generated response. This makes it possible to provide an appropriate and humane response that is in line with the user's emotional state.

[0790] "Data processing means" refers to the technology used to analyze received inquiry information and understand its content.

[0791] An "information retrieval method" is a method for efficiently searching for relevant information from external or internal sources based on analyzed query information.

[0792] "Content generation methods" refer to the process of using acquired information to generate appropriate answers and explanations.

[0793] "Emotional adaptation techniques" are technologies that analyze the user's emotions in response to a generated answer and adjust the answer content accordingly.

[0794] "Information presentation means" refers to methods and devices for effectively displaying adjusted responses to the user.

[0795] A "learning tool" is a system that accumulates past inquiry and response information and uses it to learn in order to improve the accuracy of future responses.

[0796] An "automated response system" is a system that has the function of automatically generating and providing responses to inquiries.

[0797] This automated response system is designed for efficient interaction between the user and the server. The server first analyzes the inquiry information received from the user using data processing tools. This process utilizes a natural language processing engine (e.g., spaCy) to extract important information from the inquiry. Simultaneously, information retrieval tools (e.g., external database access via API) search for relevant information based on the analyzed data.

[0798] Next, the server uses content generation means to generate appropriate responses based on the acquired information, utilizing a generative AI model (e.g., OpenAI GPT). At this time, sentiment adaptation means are used to analyze the user's emotions towards the generated response and adjust the response to the optimal format according to those emotions. For sentiment analysis, a sentiment analysis library (e.g., TextBlob) can be used.

[0799] The terminal displays a finalized response to the user based on the information presented. The system is designed to be easy for users to understand and to allow for quick responses. In addition, the server can accumulate past inquiry and response information through learning mechanisms, and use this data to improve the response accuracy of the AI ​​model. This continuous learning is expected to improve the quality of responses to future inquiries.

[0800] For example, when a user inquires with concern, asking "Why hasn't my payment been approved?", it's possible to immediately identify their concern and provide a tailored response such as: "We will do our best to alleviate your concerns. Please wait a moment while we investigate and address the issue." In this case, the prompt to the generating AI model would be something like, "Based on the user's message, create a kind and considerate response that takes their emotions into account. The user is feeling anxious because their payment hasn't been approved."

[0801] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0802] Step 1:

[0803] The user enters their inquiry through their device and sends it to the server. The entered inquiry is recorded as text data. The user is also encouraged to enter sentences written in natural language, including their emotions.

[0804] Step 2:

[0805] The server analyzes the received query using data processing tools. In this step, a natural language processing engine (e.g., spaCy) is used to extract keywords and intent from the text data. The extracted data is then used as input for subsequent information retrieval steps.

[0806] Step 3:

[0807] The server uses information retrieval tools based on the extracted keywords to search for relevant information. In this step, necessary information is retrieved from an external database via an API. This information becomes the output data used for the next content generation.

[0808] Step 4:

[0809] The server generates responses from information obtained using content generation methods. Using a generative AI model (e.g., OpenAI GPT), it creates natural and appropriate responses based on the submitted keywords and search information. These generated responses are then used as input for the next sentiment adaptation.

[0810] Step 5:

[0811] The server uses a sentiment analysis library (e.g., TextBlob) to analyze the user's emotions. It then applies the user's emotion information to the generated responses and adjusts them. The adjusted responses are output for informational purposes, resulting in user-friendly content.

[0812] Step 6:

[0813] The device displays the adjusted response to the user through an information presentation mechanism. The user reviews the response and decides on the next action. The displayed response is easy for the user to understand and guides them toward problem solving.

[0814] Step 7:

[0815] The server stores all query information and generated responses using a learning mechanism. This data is used as training data for an AI model, helping to improve the accuracy of responses to future queries.

[0816] 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.

[0817] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0818] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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."

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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 memory.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] The following is further disclosed regarding the embodiments described above.

[0838] (Claim 1)

[0839] A natural language processing means for analyzing the received inquiry information,

[0840] A search means for searching for related information based on the analyzed query information,

[0841] A generation means that generates an answer using the information obtained by the search means,

[0842] A display means for displaying the generated response on a user interface,

[0843] A system including a learning means for accumulating the aforementioned inquiry information and response information and updating it as learning data.

[0844] (Claim 2)

[0845] The system according to claim 1, wherein the search means is configured to obtain additional information from an external database or API.

[0846] (Claim 3)

[0847] The system according to claim 1, wherein the learning means is configured to train an AI agent based on past inquiry and answer information to improve the accuracy of the answers.

[0848] "Example 1"

[0849] (Claim 1)

[0850] A natural language processing means for analyzing the received inquiry information,

[0851] A search means for searching for related information based on the analyzed query information,

[0852] A generation means that generates an answer using the information obtained by the search means,

[0853] A display means that transmits and displays the generated response to a user interface,

[0854] A learning means for accumulating the aforementioned inquiry information and response information and updating it as data for machine learning,

[0855] During the aforementioned analysis process, an analysis means is used to extract keywords and intent of the inquiry,

[0856] A system that includes improvement mechanisms for accumulating information based on past inquiries and answers to improve the accuracy of future answers.

[0857] (Claim 2)

[0858] The system according to claim 1, wherein the search means is configured to obtain additional information from an external information source or an application programming interface.

[0859] (Claim 3)

[0860] The system according to claim 1, wherein the learning means is configured to train a knowledge base based on past inquiry and answer information to improve the accuracy of responses.

[0861] "Application Example 1"

[0862] (Claim 1)

[0863] A natural language processing means for analyzing the received inquiry information,

[0864] A search means for searching for related information based on the analyzed query information,

[0865] A generation means that generates an answer using the information obtained by the search means,

[0866] A display means for displaying the generated response on a user interface,

[0867] A learning means that stores the aforementioned inquiry information and response information and updates it as learning data,

[0868] A generation method that generates natural-sounding text using a generative AI model,

[0869] A means of obtaining information by referring to the service usage history,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, wherein the search means is configured to obtain additional information from an external database or a communication protocol.

[0873] (Claim 3)

[0874] The system according to claim 1, wherein the learning means is configured to train an intelligent agent based on past inquiry and response information to improve the accuracy of responses.

[0875] "Example 2 of combining an emotion engine"

[0876] (Claim 1)

[0877] A language processing method for analyzing received inquiry information,

[0878] A search means for searching for related information based on the analyzed query information,

[0879] A creation means that generates an answer using the information obtained by the search means,

[0880] A means of analyzing user emotions,

[0881] A display means for displaying the generated response on a user interface,

[0882] An adjustment mechanism that adjusts the response generated according to the user's emotional state,

[0883] A system including a training method for accumulating the aforementioned inquiry information, emotional state, and response information, and updating them as learning data.

[0884] (Claim 2)

[0885] The system according to claim 1, wherein the search means is configured to acquire additional information from an external information source or a communication protocol.

[0886] (Claim 3)

[0887] The system according to claim 1, wherein the training means is configured to train an information agent based on past inquiry information, emotional state and response information to improve the suitability of the response.

[0888] "Application example 2 when combining with an emotional engine"

[0889] (Claim 1)

[0890] A data processing means for analyzing received inquiry information,

[0891] Information retrieval means for searching for related information based on the analyzed query information,

[0892] Content generation means that generates a response using the information obtained by the information retrieval means,

[0893] An emotional adaptation means for analyzing and adjusting emotions in the generated response,

[0894] A presentation means that displays the adjusted response using an information presentation means,

[0895] An automated response system including a learning means for accumulating the aforementioned inquiry information and response information and updating it as learning information.

[0896] (Claim 2)

[0897] The automated response system according to claim 1, wherein the information retrieval means is configured to acquire additional information from an external information source.

[0898] (Claim 3)

[0899] The automated response system according to claim 1, wherein the learning means is configured to train a digital agent based on past inquiry and response information to improve the accuracy of its responses. [Explanation of symbols]

[0900] 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

1. A natural language processing means for analyzing the received inquiry information, A search means for searching for related information based on the analyzed query information, A generation means that generates an answer using the information obtained by the search means, A display means for displaying the generated response on a user interface, A system including a learning means for accumulating the aforementioned inquiry information and response information and updating it as learning data.

2. The system according to claim 1, wherein the search means is configured to obtain additional information from an external database or API.

3. The system according to claim 1, wherein the learning means is configured to train an AI agent based on past inquiry and answer information to improve the accuracy of the answers.

Images