system

Abstract

We provide the system. [Solution] A means of receiving information input from a user and analyzing the key points of the information using natural language processing, A means for automatically collecting relevant technical documents from external data sources and internal record bases based on the analyzed key points, A means of constructing a virtual simulation under specific environmental conditions and performing related work verification, A method for generating proposed answers using artificial intelligence based on collected materials and the results of work verification, In order to provide the generated draft answers, there is a means by which experts can check the content and make final changes, A means of quickly providing users with the optimal solution in real time through an application installed on a smart device, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional inquiry response system, there is a problem that a large amount of man-hours are required for a person in charge to individually respond to complex technical inquiries and inquiries regarding specifications. In particular, when manual processing such as operation confirmation and collection of technical information is required, the response is significantly delayed, leading to a decrease in customer satisfaction. In addition, due to an increase in the load on the person in charge, there is also a risk of a decrease in the quality of answers.

Means for Solving the Problems

[0005] This invention provides a system that reduces the workload of personnel by automatically analyzing user inquiries and automating the collection of relevant technical information and operational verification. It utilizes an AI agent to analyze the key points of inquiries and collect necessary information from web sources and an internal knowledge base. Furthermore, under specific conditions, it builds a virtual environment for operational verification, and the AI ​​generates a draft answer based on this verification, enabling a rapid and efficient response. In addition, the draft answer is reviewed by personnel and provided to the user as the final answer, guaranteeing the accuracy and quality of the response.

[0006] A "user" is an individual or legal entity that makes an inquiry to the system.

[0007] "Inquiry content" refers to the problems or questions that users are seeking to resolve.

[0008] "Natural language processing" is a technology that enables computers to understand and process human language appropriately.

[0009] "Key points" refer to the essential information and elements necessary for resolving an inquiry, extracted from the content of the inquiry.

[0010] "Technical information" refers to technical knowledge and data that are useful for solving related problems.

[0011] "Web information sources" refer to information and databases that are publicly available on the internet.

[0012] An "internal knowledge base" refers to the knowledge and documents accumulated within a company or organization.

[0013] A "virtual environment" refers to an experimental or test execution environment built on software without using physical hardware.

[0014] "Operational verification" is the act of verifying whether a system or device functions correctly under specified conditions.

[0015] "Artificial intelligence" refers to a computer program or system that mimics human intellectual behavior.

[0016] "Answer draft" refers to a draft answer to a user's inquiry, generated based on the collected information and verification results.

[0017] "Responsible person" refers to the person who operates the system and checks and corrects the answers provided to the user.

[0018] "Specification inquiry" refers to the act of inquiring an external organization about the technical details regarding the functions and performance of specific equipment or software.

Brief Description of Drawings

[0019] [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 multiple emotions are mapped. [Figure 10]Shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the flow of processing of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the flow of processing of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the flow of processing of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the flow of processing of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0023] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] 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).

[0026] 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."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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".

[0040] This invention is an inquiry response system utilizing an AI agent, aiming to respond quickly and efficiently to technical inquiries from users. The system is implemented as follows:

[0041] When a user makes an inquiry using a device, the device sends the inquiry content to the server. The server receives this inquiry and analyzes it using natural language processing technology. This analysis extracts the key points from the inquiry content.

[0042] Subsequently, the server uses an AI agent to collect relevant technical information from external web sources and internal knowledge bases. This information collection is automated, gathering the data necessary to resolve user inquiries.

[0043] Furthermore, if the inquiry meets certain conditions, the server creates a virtual environment. Here, it performs operational checks related to the user's inquiry and obtains accurate information based on the results.

[0044] The server integrates this information, and the AI ​​agent generates a proposed response to the user. This proposed response is sent to the person in charge, who reviews the content and makes revisions as needed.

[0045] Ultimately, the user receives an answer that has been approved by the person in charge. This entire process speeds up inquiry response and reduces the burden on the person in charge.

[0046] For example, if a user inquires about how to configure new network equipment, the server first collects relevant configuration information and verifies its operation in a virtual network environment. Based on the verification results, an AI agent generates a suggested solution with specific configuration steps and provides it to the user. This allows the user to quickly receive accurate and useful configuration information.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The user operates their device, enters a question into the inquiry form, and submits it. The inquiry includes specific technical problems and questions.

[0050] Step 2:

[0051] The server receives the query sent from the terminal. The server saves the query content to the database and prepares it for analysis.

[0052] Step 3:

[0053] The server uses a natural language processing engine to analyze the query content. This analysis extracts the main topics and keywords of the query.

[0054] Step 4:

[0055] The server uses an AI agent to search web information sources and internal knowledge bases based on extracted keywords. It collects relevant technical documents and FAQs.

[0056] Step 5:

[0057] The server creates a virtual environment when certain conditions are met. The server performs operational tests related to the query and records the results.

[0058] Step 6:

[0059] Based on the collected information and the results of operational tests, the server's AI agent generates a suggested answer. This suggested answer details the solution to the inquiry.

[0060] Step 7:

[0061] The generated draft response is sent from the server to the person in charge. The person in charge reviews the draft response, checks its accuracy, and makes corrections if necessary.

[0062] Step 8:

[0063] The final answer is provided to the user from the server. Through the terminal, the user receives the solution and can address the problem.

[0064] (Example 1)

[0065] 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."

[0066] As information technology advances, traditional systems have struggled to respond quickly and accurately to increasingly diverse technical inquiries. Furthermore, manual responses to inquiries place a heavy burden on staff, highlighting the need for more efficient responses. The challenge lies in providing highly accurate and reliable answers in a short timeframe by conducting appropriate information gathering and operational checks based on the content of the inquiry.

[0067] 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.

[0068] In this invention, the server includes means for receiving user inquiries and analyzing the key points of the inquiries using natural language processing, means for automatically collecting relevant information from external information sources and internal knowledge bases based on the analyzed key points, and means for creating a virtual environment according to conditions and performing relevant operational checks. This makes it possible to respond quickly to a wide range of technical inquiries from users, reduce the burden on personnel, and provide highly accurate answers.

[0069] A "user" refers to an individual or organization that makes technical inquiries about the system.

[0070] "Inquiry content" refers to information, including technical questions and requests, that a user sends to the system.

[0071] Natural language processing is a technology for understanding and analyzing human language, and it is used by systems to extract the key points of a query.

[0072] "Key points" refer to the essential information and points raised from the inquiry.

[0073] "Information sources" refer to external and internal databases and knowledge bases that a system accesses to gather relevant information.

[0074] A "knowledge base" refers to a knowledge base managed within a company, a collection of data where technical information is aggregated.

[0075] A "virtual environment" refers to a simulated environment built on software without using actual physical hardware.

[0076] "Operational verification" is the process of testing technical operations related to user inquiries within a virtual environment and evaluating the results.

[0077] A "generative AI model" refers to an artificial intelligence model that generates responses in natural language based on input data.

[0078] A "draft response" refers to the initial response generated by the system as a solution to an inquiry.

[0079] "Responsible party" refers to an individual or team responsible for reviewing the generated draft responses and making final revisions.

[0080] A "prompt sentence" refers to a sentence used to input specific instructions or questions to a generative AI model.

[0081] This invention is an inquiry response system that utilizes an AI agent. Its purpose is to provide quick and accurate responses when users make technical inquiries.

[0082] In the operation of the system, users use a terminal to input technical questions and send the inquiry details to the server. In this process, the terminal used by the user includes personal computers and smartphones.

[0083] The server uses natural language processing techniques to analyze incoming queries. This technique utilizes Python and libraries such as NLTK and spaCy. This allows the server to effectively extract the key points of the query content.

[0084] Based on the analyzed information, the server utilizes an AI agent to collect relevant information. This process involves accessing search engines and internal knowledge bases to gather necessary technical information. Web scraping tools and APIs are used for information gathering, ensuring efficient data collection.

[0085] If a user's inquiry meets certain conditions, the server will create a virtual environment using virtualization technologies such as Docker. This makes it possible to test related technical operations within the virtual environment and verify their operation.

[0086] Based on the collected information and the results of operational checks, the server generates suggested answers using a generative AI model. For example, a general generative AI can be used as a natural language model to form answers in natural language. An example of a prompt used during generation is, "Please tell me the procedure for configuring network equipment."

[0087] The generated draft answers are reviewed by the person in charge and revised as needed. This process ensures that users receive accurate and reliable technical information quickly. For example, if a user asks, "I want to change my Wi-Fi router password," the server checks the relevant procedures and provides the best possible steps.

[0088] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0089] Step 1:

[0090] The user initiates the inquiry by entering a technical question into the terminal. The input concerns problems or settings the user wants to resolve. The terminal sends this input data to the server, which initiates the inquiry processing.

[0091] Step 2:

[0092] The server receives query data from the terminal as input. Next, it analyzes the data using natural language processing techniques. Specifically, it uses the Python NLTK library to extract important keywords and phrases from the text. This process outputs the main points of the query, which are then used for subsequent processing.

[0093] Step 3:

[0094] Based on the analysis results, the server begins collecting relevant information. Using the extracted key points as input, it accesses external information sources and internal knowledge bases. Web scraping tools and APIs are used for information gathering. As output, a set of technical information related to the user's question is generated.

[0095] Step 4:

[0096] The server builds a virtual environment based on the conditions. The input here is a determination of whether the user's inquiry requires operational verification. A virtual environment is created using virtualization technology (e.g., Docker), and operational verification is performed within it. The output is the operational verification result data.

[0097] Step 5:

[0098] The server generates suggested answers using a generative AI model based on the collected information and the results of operational checks. The input includes relevant information and operational check results. The generative AI model (e.g., a natural language model) is used to generate answers in natural language. The output is a suggested answer corresponding to the user's inquiry.

[0099] Step 6:

[0100] The generated draft answers are sent from the server to the person in charge. In this step, the person in charge reviews the generated draft answers as input. The person in charge checks the content of the answers and makes corrections if necessary. Finally, the final answer is prepared based on the review results.

[0101] Step 7:

[0102] The server sends the final response, approved by the person in charge, to the user's terminal. The input here is the revised final response, and the output is the information the user receives on their terminal. This allows the user to review the necessary technical information and use it to solve the problem.

[0103] (Application Example 1)

[0104] 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."

[0105] Electronic payment services require the rapid and accurate resolution of technical problems faced by users. Current systems often require manual responses to user inquiries, which is not only time-consuming but also places a heavy burden on staff. Furthermore, depending on the user's technical skills, understanding their inquiries and providing appropriate solutions can be difficult.

[0106] 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.

[0107] In this invention, the server includes means for receiving information input from a user and analyzing the key points of the information using natural language processing; means for automatically collecting relevant technical documents from external data sources and internal record bases based on the analyzed key points; and means for constructing a virtual simulation under specific environmental conditions and performing relevant work verification. This makes it possible to provide quick and accurate solutions to technical problems faced by users and reduce the burden on personnel.

[0108] A "user" is someone who uses the system to seek technical support or assistance in resolving issues related to electronic payment services.

[0109] "Information input" refers to the act or data that a user provides to a system regarding technical problems or inquiries.

[0110] "Natural language processing" is a technology that enables computers to understand and appropriately analyze human language.

[0111] "Technical documentation" refers to documents and records that include relevant technical information and data and are referenced for problem-solving.

[0112] An "external data source" is a source of information that exists outside the system and is referenced to obtain technical information related to a query.

[0113] An "internal record base" is a database of technical information managed within an organization and used as reference material.

[0114] "Virtual simulation" is a technique that uses computer models that mimic real-world environments to verify and test functionality.

[0115] "Operation verification" is the process of confirming that operations and processes are performed correctly in a virtual environment or a real environment.

[0116] An "expert" is someone who checks the generated solutions and proposed answers and verifies their accuracy.

[0117] A "smart device" is a portable communication device that has the functionality to run applications related to electronic payment services.

[0118] "Real-time" refers to a temporal characteristic where a response to a user's request or action is provided immediately.

[0119] This invention relates to a technical support system for an AI-powered electronic payment service. When a user makes an inquiry via a smart device, the device sends the information to a server. The server analyzes the content of the received inquiry using natural language processing and extracts the key points. Software used for analysis includes NLP libraries (e.g., spaCy and NLTK).

[0120] Based on the analyzed key points, the server automatically collects relevant technical documents from external data sources and internal record bases. Web scraping techniques and API access are used for information gathering. Existing technologies such as Apache® or Nginx can be used for the web server.

[0121] Subsequently, the server will build a virtual simulation environment using Docker as needed and perform related work verification. This environment is used to verify operation using a virtual model corresponding to the user's inquiry.

[0122] Based on the results of the work verification, the AI ​​model generates the optimal answer. The generating AI model utilizes advanced models such as the GPT series. At this stage, the generated answer is not presented as is; it is checked by experts and modified as necessary. The final answer is provided to the user in real time via a smart device.

[0123] For example, when a user asks, "Please tell me how to resolve error code 1234," the system quickly gathers and verifies relevant information and presents a solution. An example of a prompt sentence input to the generating AI model in this case would be, "Please tell me how to resolve error code 1234 that occurs in the electronic payment function."

[0124] In this way, the system provides a solution that can quickly and accurately resolve users' technical problems and improve the convenience of electronic payment services.

[0125] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0126] Step 1:

[0127] The user enters inquiry information using a smart device. This input information is sent to the device as text data in natural language format. The device then prepares to send this data to the server.

[0128] Step 2:

[0129] The server receives query information sent from the terminal. The received data is analyzed using natural language processing software (e.g., spaCy or NLTK) to extract key points. The input is the user's query text, and the output is structured data containing the key points. Keyword extraction and contextual analysis are performed during this analysis process.

[0130] Step 3:

[0131] The server automatically collects relevant technical documents from external data sources and internal record bases based on the analyzed key points. Using web scraping and API access techniques, the input is a list of extracted key points, and the output is a dataset of related technical documents. This process allows for the organized retrieval of relevant information.

[0132] Step 4:

[0133] The server uses Docker to build a virtual simulation environment based on specific environmental conditions requested by the user. The input consists of a technical data dataset and environment configuration information, while the output is the simulation results. System operation is then verified within the constructed virtual environment.

[0134] Step 5:

[0135] The server generates suggested answers using a generative AI model (e.g., the GPT series) based on the work verification results and collected information. The input is the simulation results and a technical document dataset, and the output is the suggested answer for the user. Here, appropriate answers are derived by using prompt statements for the generative AI model.

[0136] Step 6:

[0137] The server generates a draft answer and sends it to an expert. The expert reviews this answer and makes revisions if necessary. The input is the generated draft answer, and the output is the revised final answer. The accuracy of the answer is improved based on the expert's knowledge.

[0138] Step 7:

[0139] The corrected final answer is sent to the user's smart device in real time. The server manages the response notification to the user's device. The input is the final answer, and the output is the notification to the user. This process allows for the rapid and accurate delivery of solutions to the user.

[0140] 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.

[0141] This invention aims to recognize user emotions and personalize responses by combining an emotion engine with an AI agent-based inquiry response system. This system is implemented as follows.

[0142] When a user submits an inquiry from their device, the server receives the inquiry. The server then uses natural language processing techniques to analyze the key points of the inquiry. In addition, it uses an emotion engine to recognize the user's emotional state. This emotion recognition detects emotions such as joy, anxiety, and anger from the user's word choice and the tone of their input.

[0143] Based on the analyzed key points and emotions, the server launches an AI agent optimized for the individual user experience and automatically collects relevant technical information from web sources and internal knowledge bases. Under specific conditions, a virtual environment is created and necessary operational checks are performed. As a result, accurate information is obtained.

[0144] Next, the AI ​​agent generates suggested answers based on the collected information and the results of the operational checks. The tone of the suggested answers is adjusted based on the user's emotional state, as determined by the emotion engine. For example, for a user who is feeling angry, a more calm and empathetic response will be generated.

[0145] The generated draft answers are reviewed by a designated person. The person reviews the answers for technical accuracy and makes revisions as needed. Finally, the server sends the reviewed answers to the user. At this stage, the system automatically determines whether to prioritize the user's request, taking into account their emotional state.

[0146] For example, when receiving an urgent inquiry regarding a network failure, the server can not only provide technical solutions but also use an emotion engine to select kind and helpful language to reduce stress. In this way, the present invention improves the accuracy and quality of inquiry responses and contributes to increased customer satisfaction.

[0147] The following describes the processing flow.

[0148] Step 1:

[0149] The user operates their device to enter a question into the inquiry form and submit it. The inquiry contains specific problems or questions.

[0150] Step 2:

[0151] The server receives the query sent from the terminal. The server saves this query to the database and prepares it for analysis.

[0152] Step 3:

[0153] The server uses natural language processing technology to analyze the query content and extract key keywords and essential points. This analysis identifies the information necessary to resolve the query.

[0154] Step 4:

[0155] The server uses an emotion engine to analyze the user's emotions from the wording of the inquiry. This analysis determines whether the user is experiencing emotions such as anger, joy, or anxiety.

[0156] Step 5:

[0157] The server activates an AI agent that automatically collects relevant technical information from the web and internal knowledge bases based on extracted keywords and sentiments.

[0158] Step 6:

[0159] When certain conditions are met, the server creates a virtual environment and performs operational checks related to the query. This allows the technical problem to be reproduced and the solution to be verified.

[0160] Step 7:

[0161] The server integrates the collected information and the results of operational checks, and the AI ​​agent generates suggested answers. The tone of these suggested answers is adjusted according to the user's emotional state.

[0162] Step 8:

[0163] The generated draft response is sent from the server to the person in charge. The person in charge checks for technical accuracy and emotional considerations and makes revisions as needed.

[0164] Step 9:

[0165] The final answer is provided to the user from the server. Through the device, the user receives the adjusted answer and can proceed with taking steps toward resolving the problem. The customer experience is improved by taking emotions into consideration.

[0166] (Example 2)

[0167] 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 as the "terminal".

[0168] While understanding and appropriately responding to user inquiries is crucial, traditional systems struggled to analyze the key points of inquiries and consider user emotions. Furthermore, processes such as automated information gathering and testing, tone adjustment of responses, and priority determination were not integrated, resulting in challenges regarding response quality and speed. There is a need to solve these problems and provide more personalized and effective responses.

[0169] 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.

[0170] In this invention, the server includes means for receiving inquiry information from a user and analyzing key points using natural language processing, means for automatically collecting digital information from a group of information sources based on the analyzed key points and the user's emotional state, and means for constructing a virtual execution environment and performing operational verification. This makes it possible to quickly collect necessary information and provide highly accurate answers while taking the user's emotions into consideration.

[0171] A "user" refers to an individual or organization that uses the system to make inquiries.

[0172] "Inquiry information" refers to data about questions and requests that users enter or submit through the system.

[0173] "Natural language processing" refers to the technology that enables computers to understand and analyze human language.

[0174] "Key points" refer to the essential information or the core of the problem extracted from the inquiry information.

[0175] "Emotional state" refers to the emotional response and mental state of a user when they make an inquiry.

[0176] "Digital information" refers to any form of electronic data obtained from the set of information sources that a system collects.

[0177] A "collection of information sources" refers to a set of internal or external databases and websites that are referenced to obtain relevant technical information.

[0178] A "virtual execution environment" refers to a virtual space where simulations and tests can be performed on a system that replicates an actual system.

[0179] "Operational verification" is the process of conducting tests in a virtual execution environment under specific scenarios to verify whether the system operates as expected.

[0180] A "draft response" refers to an initial solution or suggestion generated as an answer to a user's inquiry.

[0181] "Tone adjustment" refers to the process of optimizing the expression and wording of generated response suggestions to match the user's emotional state.

[0182] The present invention is a system aimed at providing a rapid and appropriate response to user inquiries. Specific embodiments thereof are described below.

[0183] When a user submits an inquiry via their device, the server receives the inquiry information. Inquiries may include questions about product defects, usage instructions, or technical specifications. The server first extracts the key points of the inquiry using natural language processing techniques. At this stage, a text analysis engine is used to extract keywords and identify intent. Specifically, general text analysis software is used for natural language processing.

[0184] Next, the server uses an emotion engine to analyze the emotional state of the user making the inquiry. The user's linguistic characteristics and text tone are crucial factors in this emotion recognition. The emotion engine detects whether the user is feeling anger or anxiety, and the server utilizes the results.

[0185] Once the analysis is complete, the server collects relevant information from digital sources. These sources include internal knowledge bases and external web databases, and web scraping techniques are used for information gathering. At this stage, if a specific virtual execution environment is required, the server builds it and performs operational verification. By conducting operational tests in this virtual environment, the server verifies whether the proposed solution is effective.

[0186] Based on the collected information, the server uses a generative AI model to create suggested answers. These answers are generated with a tone adjusted by an emotion engine, taking into account the user's emotional state. For example, a user expressing anger will receive a calm and empathetic response.

[0187] The final response is reviewed by a staff member, and any necessary revisions are made. Once the staff member has reviewed the response, it is sent from the server to the user. At this point, the system prioritizes the response based on the user's emotional state, and if a faster response is required, the sending process is optimized according to that metric.

[0188] As a concrete example, the prompt "The user has reported a network problem and is experiencing significant stress. Please create a response that suggests a technical solution while maintaining a reassuring tone" is input to the AI ​​model. In this way, an appropriate response to the user is automatically generated.

[0189] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0190] Step 1:

[0191] The user inputs and submits inquiry information via a terminal. The input data consists of text-based questions and problem descriptions. The terminal uses a communication protocol to transfer this data to the server.

[0192] Step 2:

[0193] The server receives the query information. The received data is recorded as a log and passed to the natural language processing engine. The input here is the text data of the query information, and the output is the extraction of key points. Specifically, the process extracts keywords and important phrases from the text.

[0194] Step 3:

[0195] The server uses an emotion engine to analyze the user's emotional state. The input is the user's inquiry text, and the output is the type of emotion (joy, anxiety, anger, etc.) and its intensity. At this stage, data calculations are performed to calculate an emotion score from the text content.

[0196] Step 4:

[0197] The server automatically collects relevant digital information from databases and external web sources based on the analyzed key points and sentiment data. The input is key points and sentiment data, and the output is the collected technical information. Specifically, it uses APIs and crawling technologies to collect the necessary data.

[0198] Step 5:

[0199] The server will build a virtual execution environment as needed and perform operational verification. The input consists of collected technical data and virtual environment settings, while the output is the test results. Tools and emulators are used in specific scenarios to verify that the system functions correctly.

[0200] Step 6:

[0201] The server uses a generative AI model to create suggested answers based on collected information and emotional states. The input is collected technical information and emotional scores, and the output is the adjusted suggested answer. Here, the generative AI model uses prompts such as "output an answer optimized according to the user's emotions."

[0202] Step 7:

[0203] The generated draft answers are reviewed by the assigned person. The input is the generated draft answer, and the output is the assigned person's proposed revisions or comments. The assigned person performs a specific review to check the technical accuracy and tone of the answer.

[0204] Step 8:

[0205] The server sends the revised, final response to the user. The input consists of the reviewed draft response and the user's inquiry information, while the output is the final response message to the user. This process adjusts the timing and method of sending the response based on the user's sentiment and priorities.

[0206] (Application Example 2)

[0207] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0208] Conventional customer service systems were unable to respond appropriately to users' emotions, and therefore could not adequately improve customer satisfaction. Furthermore, security systems struggled to analyze people's emotions and detect potential threats early on.

[0209] 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.

[0210] In this invention, the server includes means for receiving user inquiries and analyzing the key points of the inquiries using natural language processing; means for automatically collecting relevant technical information from information sources and internal knowledge bases based on the analyzed key points; means for constructing a virtual space under specific conditions and performing relevant behavioral verification; and means for analyzing a person's emotions using a video device and automatically sending a warning to the administrator in specific situations based on the analysis results. This enables inquiry responses that take user emotions into consideration and real-time security improvements.

[0211] "Inquiry details" refer to text information of questions or problem reports that users submit to the system or service.

[0212] "Natural language processing" is the technology that enables computers to understand the language that humans normally use.

[0213] The "key points" refer to the core information that is particularly important within the content of the inquiry.

[0214] "Technical information" refers to specialized knowledge and data related to the content of the inquiry.

[0215] "Information sources" refer to internet resources such as websites and digital repositories from which relevant information can be obtained.

[0216] An "internal knowledge base" refers to the know-how and databases accumulated within an organization.

[0217] A "virtual space" is a simulation environment built on a computer.

[0218] "Behavior verification" is a process to verify that a system or device is functioning correctly.

[0219] "Video equipment" refers to hardware such as cameras used to acquire visual information.

[0220] "Emotional analysis" is the process of identifying a person's emotions from video or text.

[0221] A "warning" is an alert that notifies you of a potential danger or anomaly.

[0222] An "administrator" is a person responsible for the operation and management of a system or service.

[0223] This system is designed for handling inquiries and security analysis. First, the server receives user inquiries and analyzes their key points using natural language processing techniques. Natural language processing libraries such as "NLTK" are suitable software for this purpose.

[0224] Next, the server automatically collects relevant technical information from external sources and internal knowledge bases based on the analyzed key points. Based on the definition of information sources, this includes resources on the internet and internal databases.

[0225] Furthermore, under certain conditions, the server uses software such as "Unity" or "Unreal Engine" to construct a virtual space and verify related behaviors. This allows for a simulation of how the proposed solutions will function in a real-world environment.

[0226] Furthermore, the server performs emotion analysis using video footage acquired by video equipment connected to the terminal. This process utilizes tools such as "OpenCV" and "Emotion-RNN" to identify a person's emotions in real time. For example, if a camera installed as a security measure in a shopping mall detects a person's anxiety, it will warn of potential danger.

[0227] The server distributes appropriately generated response proposals and warnings to the responsible personnel, who can then review the information and make corrections as needed. This entire process, when integrated, makes it possible to provide users with a richer and safer experience.

[0228] An example of a prompt sentence to be input to the generating AI model would be, "Analyze the emotions of people in security camera footage and notify me in real time if a specific emotion is detected."

[0229] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0230] Step 1:

[0231] The server receives the query from the user. It takes text data sent by the user from their terminal as input. Based on this data, the server uses the natural language processing library "NLTK" to analyze the key points of the query. The analysis results in a keyword list that identifies the subject and important points of the query.

[0232] Step 2:

[0233] Based on the analyzed key points, the server accesses information sources and internal knowledge bases to collect relevant technical information. The keywords obtained from the analysis results in Step 1 are used as input. The server queries web resources and databases via APIs, filtering relevant information and organizing the collected data. This ensures that useful information is obtained in response to user inquiries.

[0234] Step 3:

[0235] When certain conditions are met, the server uses Unity or Unreal Engine to construct a virtual space. At this stage, collected technical information and pre-configured simulation scenarios are used as input. The server uses this data to model the virtual environment and perform related behavioral checks. The simulation results are used to verify whether the operating conditions are met.

[0236] Step 4:

[0237] The server performs emotion analysis on a person using video data acquired from a video device. The input is a real-time video stream. The server uses "OpenCV" and "Emotion-RNN" to analyze facial expressions in the video and identify emotions. As a result of this analysis, the type of emotion (e.g., joy, anxiety, anger) and its intensity are output.

[0238] Step 5:

[0239] Based on the analysis results, the server automatically sends a warning to the administrator if a specific emotion is detected. The input includes the user inquiry analysis results and the emotion analysis results. The server compares the warning criteria and, if the threshold requiring notification is met, delivers a warning message to the administrator through the notification system. This output allows the administrator to receive appropriate information for immediate action.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] [Second Embodiment]

[0244] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0245] 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.

[0246] 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).

[0247] 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.

[0248] 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.

[0249] 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).

[0250] 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.

[0251] 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.

[0252] 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.

[0253] 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.

[0254] 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.

[0255] 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".

[0256] This invention is an inquiry response system utilizing an AI agent, aiming to respond quickly and efficiently to technical inquiries from users. The system is implemented as follows:

[0257] When a user makes an inquiry using a device, the device sends the inquiry content to the server. The server receives this inquiry and analyzes it using natural language processing technology. This analysis extracts the key points from the inquiry content.

[0258] Subsequently, the server uses an AI agent to collect relevant technical information from external web sources and internal knowledge bases. This information collection is automated, gathering the data necessary to resolve user inquiries.

[0259] Furthermore, if the inquiry meets certain conditions, the server creates a virtual environment. Here, it performs operational checks related to the user's inquiry and obtains accurate information based on the results.

[0260] The server integrates this information, and the AI ​​agent generates a proposed response to the user. This proposed response is sent to the person in charge, who reviews the content and makes revisions as needed.

[0261] Ultimately, the user receives an answer that has been approved by the person in charge. This entire process speeds up inquiry response and reduces the burden on the person in charge.

[0262] For example, if a user inquires about how to configure new network equipment, the server first collects relevant configuration information and verifies its operation in a virtual network environment. Based on the verification results, an AI agent generates a suggested solution with specific configuration steps and provides it to the user. This allows the user to quickly receive accurate and useful configuration information.

[0263] The following describes the processing flow.

[0264] Step 1:

[0265] The user operates their device, enters a question into the inquiry form, and submits it. The inquiry includes specific technical problems and questions.

[0266] Step 2:

[0267] The server receives the query sent from the terminal. The server saves the query content to the database and prepares it for analysis.

[0268] Step 3:

[0269] The server uses a natural language processing engine to analyze the query content. This analysis extracts the main topics and keywords of the query.

[0270] Step 4:

[0271] The server uses an AI agent to search web information sources and internal knowledge bases based on extracted keywords. It collects relevant technical documents and FAQs.

[0272] Step 5:

[0273] The server creates a virtual environment when certain conditions are met. The server performs operational tests related to the query and records the results.

[0274] Step 6:

[0275] Based on the collected information and the results of operational tests, the server's AI agent generates a suggested answer. This suggested answer details the solution to the inquiry.

[0276] Step 7:

[0277] The generated draft response is sent from the server to the person in charge. The person in charge reviews the draft response, checks its accuracy, and makes corrections if necessary.

[0278] Step 8:

[0279] The final answer is provided to the user from the server. Through the terminal, the user receives the solution and can address the problem.

[0280] (Example 1)

[0281] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0282] With the progress of information technology, it has been difficult for conventional systems to respond quickly and accurately to diversified technical inquiries. Also, when manually answering inquiries, the burden on the person in charge is large, and efficient response is required. There is an issue of providing a highly accurate and reliable answer in a short time by performing appropriate information collection and operation confirmation according to the inquiry content.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0284] In this invention, the server includes means for receiving the inquiry content from the user and analyzing the key points of the inquiry using natural language processing, means for automatically collecting relevant information from external information sources and internal knowledge bases based on the analyzed key points, and means for creating a virtual environment according to conditions and performing relevant operation confirmation. Thereby, it becomes possible to quickly respond to various technical inquiries from the user, reduce the burden on the person in charge, and provide a highly accurate answer.

[0285] The "user" refers to an individual or organization that makes a technical inquiry to the system.

[0286] The "inquiry content" refers to information including technical questions and requests sent by the user to the system.

[0287] "Natural language processing" is a technology for understanding and analyzing human language, and is used by the system to extract the key points of an inquiry.

[0288] The "key points" are those obtained by extracting important information and pointed-out matters from the inquiry content.

[0289] "Information sources" refer to external and internal databases and knowledge bases that a system accesses to gather relevant information.

[0290] A "knowledge base" refers to a knowledge base managed within a company, a collection of data where technical information is aggregated.

[0291] A "virtual environment" refers to a simulated environment built on software without using actual physical hardware.

[0292] "Operational verification" is the process of testing technical operations related to user inquiries within a virtual environment and evaluating the results.

[0293] A "generative AI model" refers to an artificial intelligence model that generates responses in natural language based on input data.

[0294] A "draft response" refers to the initial response generated by the system as a solution to an inquiry.

[0295] "Responsible party" refers to an individual or team responsible for reviewing the generated draft responses and making final revisions.

[0296] A "prompt sentence" refers to a sentence used to input specific instructions or questions to a generative AI model.

[0297] This invention is an inquiry response system that utilizes an AI agent. Its purpose is to provide quick and accurate responses when users make technical inquiries.

[0298] In the operation of the system, users use a terminal to input technical questions and send the inquiry details to the server. In this process, the terminal used by the user includes personal computers and smartphones.

[0299] The server uses natural language processing techniques to analyze incoming queries. This technique utilizes Python and libraries such as NLTK and spaCy. This allows the server to effectively extract the key points of the query content.

[0300] Based on the analyzed information, the server utilizes an AI agent to collect relevant information. This process involves accessing search engines and internal knowledge bases to gather necessary technical information. Web scraping tools and APIs are used for information gathering, ensuring efficient data collection.

[0301] If a user's inquiry meets certain conditions, the server will create a virtual environment using virtualization technologies such as Docker. This makes it possible to test related technical operations within the virtual environment and verify their operation.

[0302] Based on the collected information and the results of operational checks, the server generates suggested answers using a generative AI model. For example, a general generative AI can be used as a natural language model to form answers in natural language. An example of a prompt used during generation is, "Please tell me the procedure for configuring network equipment."

[0303] The generated draft answers are reviewed by the person in charge and revised as needed. This process ensures that users receive accurate and reliable technical information quickly. For example, if a user asks, "I want to change my Wi-Fi router password," the server checks the relevant procedures and provides the best possible steps.

[0304] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0305] Step 1:

[0306] The user inputs a technical question into the terminal and starts an inquiry. What is input is a question regarding the problem the user wants to solve or settings. The terminal sends this input data to the server. Thereby, the inquiry process is started.

[0307] Step 2:

[0308] The server receives the inquiry data received from the terminal as input. Next, it analyzes the data using natural language processing technology. Specifically, it uses the NLTK library in Python to extract important keywords and phrases from the text. Through this process, the key points of the inquiry are output and used for subsequent processing.

[0309] Step 3:

[0310] Based on the analysis result, the server starts collecting relevant information. It uses the key points extracted as input to access external information sources and internal knowledge bases. Web scraping tools and APIs are used for information collection. As output, a set of technical information related to the user's question is generated.

[0311] Step 4:

[0312] [ The server constructs a virtual environment according to the conditions. The input here is a judgment on whether the content of the user's inquiry requires operation verification. Using virtualization technology (e.g., Docker), a virtual environment is created and operation verification is performed within it. As output, the result data of the operation verification is obtained.

[0313] Step 5:

[0314] Based on the collected information and the result of the operation verification, the server uses a generative AI model to generate an answer. The input includes the relevant information and the result of the operation verification. Using a generative AI model (e.g., a natural language model), an answer is generated in natural language. As output, an answer corresponding to the user's inquiry is generated.

[0315] Step 6:

[0316] The generated draft answers are sent from the server to the person in charge. In this step, the person in charge reviews the generated draft answers as input. The person in charge checks the content of the answers and makes corrections if necessary. Finally, the final answer is prepared based on the review results.

[0317] Step 7:

[0318] The server sends the final response, approved by the person in charge, to the user's terminal. The input here is the revised final response, and the output is the information the user receives on their terminal. This allows the user to review the necessary technical information and use it to solve the problem.

[0319] (Application Example 1)

[0320] 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 glasses 214 will be referred to as the "terminal."

[0321] Electronic payment services require the rapid and accurate resolution of technical problems faced by users. Current systems often require manual responses to user inquiries, which is not only time-consuming but also places a heavy burden on staff. Furthermore, depending on the user's technical skills, understanding their inquiries and providing appropriate solutions can be difficult.

[0322] 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.

[0323] In this invention, the server includes means for receiving information input from a user and analyzing the key points of the information using natural language processing; means for automatically collecting relevant technical documents from external data sources and internal record bases based on the analyzed key points; and means for constructing a virtual simulation under specific environmental conditions and performing relevant work verification. This makes it possible to provide quick and accurate solutions to technical problems faced by users and reduce the burden on personnel.

[0324] A "user" is someone who uses the system to seek technical support or assistance in resolving issues related to electronic payment services.

[0325] "Information input" refers to the act or data that a user provides to a system regarding technical problems or inquiries.

[0326] "Natural language processing" is a technology that enables computers to understand and appropriately analyze human language.

[0327] "Technical documentation" refers to documents and records that include relevant technical information and data and are referenced for problem-solving.

[0328] An "external data source" is a source of information that exists outside the system and is referenced to obtain technical information related to a query.

[0329] An "internal record base" is a database of technical information managed within an organization and used as reference material.

[0330] "Virtual simulation" is a technique that uses computer models that mimic real-world environments to verify and test functionality.

[0331] "Operation verification" is the process of confirming that operations and processes are performed correctly in a virtual environment or a real environment.

[0332] An "expert" is someone who checks the generated solutions and proposed answers and verifies their accuracy.

[0333] A "smart device" is a portable communication device that has the functionality to run applications related to electronic payment services.

[0334] "Real-time" refers to a temporal characteristic where a response to a user's request or action is provided immediately.

[0335] This invention relates to a technical support system for an AI-powered electronic payment service. When a user makes an inquiry via a smart device, the device sends the information to a server. The server analyzes the content of the received inquiry using natural language processing and extracts the key points. Software used for analysis includes NLP libraries (e.g., spaCy and NLTK).

[0336] Based on the analyzed key points, the server automatically collects relevant technical documentation from external data sources and internal record bases. Web scraping techniques and API access are used for information gathering. Existing web server technologies such as Apache or Nginx can be used.

[0337] Subsequently, the server will build a virtual simulation environment using Docker as needed and perform related work verification. This environment is used to verify operation using a virtual model corresponding to the user's inquiry.

[0338] Based on the results of the work verification, the AI ​​model generates the optimal answer. The generating AI model utilizes advanced models such as the GPT series. At this stage, the generated answer is not presented as is; it is checked by experts and modified as necessary. The final answer is provided to the user in real time via a smart device.

[0339] For example, when a user asks, "Please tell me how to resolve error code 1234," the system quickly gathers and verifies relevant information and presents a solution. An example of a prompt sentence input to the generating AI model in this case would be, "Please tell me how to resolve error code 1234 that occurs in the electronic payment function."

[0340] In this way, the system provides a solution that can quickly and accurately resolve users' technical problems and improve the convenience of electronic payment services.

[0341] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0342] Step 1:

[0343] The user enters inquiry information using a smart device. This input information is sent to the device as text data in natural language format. The device then prepares to send this data to the server.

[0344] Step 2:

[0345] The server receives query information sent from the terminal. The received data is analyzed using natural language processing software (e.g., spaCy or NLTK) to extract key points. The input is the user's query text, and the output is structured data containing the key points. Keyword extraction and contextual analysis are performed during this analysis process.

[0346] Step 3:

[0347] The server automatically collects relevant technical documents from external data sources and internal record bases based on the analyzed key points. Using web scraping and API access techniques, the input is a list of extracted key points, and the output is a dataset of related technical documents. This process allows for the organized retrieval of relevant information.

[0348] Step 4:

[0349] The server uses Docker to build a virtual simulation environment based on specific environmental conditions requested by the user. The input consists of a technical data dataset and environment configuration information, while the output is the simulation results. System operation is then verified within the constructed virtual environment.

[0350] Step 5:

[0351] The server generates suggested answers using a generative AI model (e.g., the GPT series) based on the work verification results and collected information. The input is the simulation results and a technical document dataset, and the output is the suggested answer for the user. Here, appropriate answers are derived by using prompt statements for the generative AI model.

[0352] Step 6:

[0353] The server generates a draft answer and sends it to an expert. The expert reviews this answer and makes revisions if necessary. The input is the generated draft answer, and the output is the revised final answer. The accuracy of the answer is improved based on the expert's knowledge.

[0354] Step 7:

[0355] The corrected final answer is sent to the user's smart device in real time. The server manages the response notification to the user's device. The input is the final answer, and the output is the notification to the user. This process allows for the rapid and accurate delivery of solutions to the user.

[0356] 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.

[0357] This invention aims to recognize user emotions and personalize responses by combining an emotion engine with an AI agent-based inquiry response system. This system is implemented as follows.

[0358] When a user submits an inquiry from their device, the server receives the inquiry. The server then uses natural language processing techniques to analyze the key points of the inquiry. In addition, it uses an emotion engine to recognize the user's emotional state. This emotion recognition detects emotions such as joy, anxiety, and anger from the user's word choice and the tone of their input.

[0359] Based on the analyzed key points and emotions, the server launches an AI agent optimized for the individual user experience and automatically collects relevant technical information from web sources and internal knowledge bases. Under specific conditions, a virtual environment is created and necessary operational checks are performed. As a result, accurate information is obtained.

[0360] Next, the AI ​​agent generates suggested answers based on the collected information and the results of the operational checks. The tone of the suggested answers is adjusted based on the user's emotional state, as determined by the emotion engine. For example, for a user who is feeling angry, a more calm and empathetic response will be generated.

[0361] The generated draft answers are reviewed by a designated person. The person reviews the answers for technical accuracy and makes revisions as needed. Finally, the server sends the reviewed answers to the user. At this stage, the system automatically determines whether to prioritize the user's request, taking into account their emotional state.

[0362] For example, when receiving an urgent inquiry regarding a network failure, the server can not only provide technical solutions but also use an emotion engine to select kind and helpful language to reduce stress. In this way, the present invention improves the accuracy and quality of inquiry responses and contributes to increased customer satisfaction.

[0363] The following describes the processing flow.

[0364] Step 1:

[0365] The user operates their device to enter a question into the inquiry form and submit it. The inquiry contains specific problems or questions.

[0366] Step 2:

[0367] The server receives the query sent from the terminal. The server saves this query to the database and prepares it for analysis.

[0368] Step 3:

[0369] The server uses natural language processing technology to analyze the query content and extract key keywords and essential points. This analysis identifies the information necessary to resolve the query.

[0370] Step 4:

[0371] The server uses an emotion engine to analyze the user's emotions from the wording of the inquiry. This analysis determines whether the user is experiencing emotions such as anger, joy, or anxiety.

[0372] Step 5:

[0373] The server activates an AI agent that automatically collects relevant technical information from the web and internal knowledge bases based on extracted keywords and sentiments.

[0374] Step 6:

[0375] When certain conditions are met, the server creates a virtual environment and performs operational checks related to the query. This allows the technical problem to be reproduced and the solution to be verified.

[0376] Step 7:

[0377] The server integrates the collected information and the results of operational checks, and the AI ​​agent generates suggested answers. The tone of these suggested answers is adjusted according to the user's emotional state.

[0378] Step 8:

[0379] The generated draft response is sent from the server to the person in charge. The person in charge checks for technical accuracy and emotional considerations and makes revisions as needed.

[0380] Step 9:

[0381] The final answer is provided to the user from the server. Through the device, the user receives the adjusted answer and can proceed with taking steps toward resolving the problem. The customer experience is improved by taking emotions into consideration.

[0382] (Example 2)

[0383] 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".

[0384] While understanding and appropriately responding to user inquiries is crucial, traditional systems struggled to analyze the key points of inquiries and consider user emotions. Furthermore, processes such as automated information gathering and testing, tone adjustment of responses, and priority determination were not integrated, resulting in challenges regarding response quality and speed. There is a need to solve these problems and provide more personalized and effective responses.

[0385] 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.

[0386] In this invention, the server includes means for receiving inquiry information from a user and analyzing key points using natural language processing, means for automatically collecting digital information from a group of information sources based on the analyzed key points and the user's emotional state, and means for constructing a virtual execution environment and performing operational verification. This makes it possible to quickly collect necessary information and provide highly accurate answers while taking the user's emotions into consideration.

[0387] A "user" refers to an individual or organization that uses the system to make inquiries.

[0388] "Inquiry information" refers to data about questions and requests that users enter or submit through the system.

[0389] "Natural language processing" refers to the technology that enables computers to understand and analyze human language.

[0390] "Key points" refer to the essential information or the core of the problem extracted from the inquiry information.

[0391] "Emotional state" refers to the emotional response and mental state of a user when they make an inquiry.

[0392] "Digital information" refers to any form of electronic data obtained from the set of information sources that a system collects.

[0393] A "collection of information sources" refers to a set of internal or external databases and websites that are referenced to obtain relevant technical information.

[0394] A "virtual execution environment" refers to a virtual space where simulations and tests can be performed on a system that replicates an actual system.

[0395] "Operational verification" is the process of conducting tests in a virtual execution environment under specific scenarios to verify whether the system operates as expected.

[0396] A "draft response" refers to an initial solution or suggestion generated as an answer to a user's inquiry.

[0397] "Tone adjustment" refers to the process of optimizing the expression and wording of generated response suggestions to match the user's emotional state.

[0398] The present invention is a system aimed at providing a rapid and appropriate response to user inquiries. Specific embodiments thereof are described below.

[0399] When a user submits an inquiry via their device, the server receives the inquiry information. Inquiries may include questions about product defects, usage instructions, or technical specifications. The server first extracts the key points of the inquiry using natural language processing techniques. At this stage, a text analysis engine is used to extract keywords and identify intent. Specifically, general text analysis software is used for natural language processing.

[0400] Next, the server uses an emotion engine to analyze the emotional state of the user making the inquiry. The user's linguistic characteristics and text tone are crucial factors in this emotion recognition. The emotion engine detects whether the user is feeling anger or anxiety, and the server utilizes the results.

[0401] Once the analysis is complete, the server collects relevant information from digital sources. These sources include internal knowledge bases and external web databases, and web scraping techniques are used for information gathering. At this stage, if a specific virtual execution environment is required, the server builds it and performs operational verification. By conducting operational tests in this virtual environment, the server verifies whether the proposed solution is effective.

[0402] Based on the collected information, the server uses a generative AI model to create suggested answers. These answers are generated with a tone adjusted by an emotion engine, taking into account the user's emotional state. For example, a user expressing anger will receive a calm and empathetic response.

[0403] The final response is reviewed by a staff member, and any necessary revisions are made. Once the staff member has reviewed the response, it is sent from the server to the user. At this point, the system prioritizes the response based on the user's emotional state, and if a faster response is required, the sending process is optimized according to that metric.

[0404] As a concrete example, the prompt "The user has reported a network problem and is experiencing significant stress. Please create a response that suggests a technical solution while maintaining a reassuring tone" is input to the AI ​​model. In this way, an appropriate response to the user is automatically generated.

[0405] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0406] Step 1:

[0407] The user inputs and submits inquiry information via a terminal. The input data consists of text-based questions and problem descriptions. The terminal uses a communication protocol to transfer this data to the server.

[0408] Step 2:

[0409] The server receives the query information. The received data is recorded as a log and passed to the natural language processing engine. The input here is the text data of the query information, and the output is the extraction of key points. Specifically, the process extracts keywords and important phrases from the text.

[0410] Step 3:

[0411] The server uses an emotion engine to analyze the user's emotional state. The input is the user's inquiry text, and the output is the type of emotion (joy, anxiety, anger, etc.) and its intensity. At this stage, data calculations are performed to calculate an emotion score from the text content.

[0412] Step 4:

[0413] The server automatically collects relevant digital information from databases and external web sources based on the analyzed key points and sentiment data. The input is key points and sentiment data, and the output is the collected technical information. Specifically, it uses APIs and crawling technologies to collect the necessary data.

[0414] Step 5:

[0415] The server will build a virtual execution environment as needed and perform operational verification. The input consists of collected technical data and virtual environment settings, while the output is the test results. Tools and emulators are used in specific scenarios to verify that the system functions correctly.

[0416] Step 6:

[0417] The server uses a generative AI model to create suggested answers based on collected information and emotional states. The input is collected technical information and emotional scores, and the output is the adjusted suggested answer. Here, the generative AI model uses prompts such as "output an answer optimized according to the user's emotions."

[0418] Step 7:

[0419] The generated draft answers are reviewed by the assigned person. The input is the generated draft answer, and the output is the assigned person's proposed revisions or comments. The assigned person performs a specific review to check the technical accuracy and tone of the answer.

[0420] Step 8:

[0421] The server sends the revised, final response to the user. The input consists of the reviewed draft response and the user's inquiry information, while the output is the final response message to the user. This process adjusts the timing and method of sending the response based on the user's sentiment and priorities.

[0422] (Application Example 2)

[0423] 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."

[0424] Conventional customer service systems were unable to respond appropriately to users' emotions, and therefore could not adequately improve customer satisfaction. Furthermore, security systems struggled to analyze people's emotions and detect potential threats early on.

[0425] 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.

[0426] In this invention, the server includes means for receiving user inquiries and analyzing the key points of the inquiries using natural language processing; means for automatically collecting relevant technical information from information sources and internal knowledge bases based on the analyzed key points; means for constructing a virtual space under specific conditions and performing relevant behavioral verification; and means for analyzing a person's emotions using a video device and automatically sending a warning to the administrator in specific situations based on the analysis results. This enables inquiry responses that take user emotions into consideration and real-time security improvements.

[0427] "Inquiry details" refer to text information of questions or problem reports that users submit to the system or service.

[0428] "Natural language processing" is the technology that enables computers to understand the language that humans normally use.

[0429] The "key points" refer to the core information that is particularly important within the content of the inquiry.

[0430] "Technical information" refers to specialized knowledge and data related to the content of the inquiry.

[0431] "Information sources" refer to internet resources such as websites and digital repositories from which relevant information can be obtained.

[0432] An "internal knowledge base" refers to the know-how and databases accumulated within an organization.

[0433] A "virtual space" is a simulation environment built on a computer.

[0434] "Behavior verification" is a process to verify that a system or device is functioning correctly.

[0435] "Video equipment" refers to hardware such as cameras used to acquire visual information.

[0436] "Emotional analysis" is the process of identifying a person's emotions from video or text.

[0437] A "warning" is an alert that notifies you of a potential danger or anomaly.

[0438] An "administrator" is a person responsible for the operation and management of a system or service.

[0439] This system is designed for handling inquiries and security analysis. First, the server receives user inquiries and analyzes their key points using natural language processing techniques. Natural language processing libraries such as "NLTK" are suitable software for this purpose.

[0440] Next, the server automatically collects relevant technical information from external sources and internal knowledge bases based on the analyzed key points. Based on the definition of information sources, this includes resources on the internet and internal databases.

[0441] Furthermore, under certain conditions, the server uses software such as "Unity" or "Unreal Engine" to construct a virtual space and verify related behaviors. This allows for a simulation of how the proposed solutions will function in a real-world environment.

[0442] Furthermore, the server performs emotion analysis using video footage acquired by video equipment connected to the terminal. This process utilizes tools such as "OpenCV" and "Emotion-RNN" to identify a person's emotions in real time. For example, if a camera installed as a security measure in a shopping mall detects a person's anxiety, it will warn of potential danger.

[0443] The server distributes appropriately generated response proposals and warnings to the responsible personnel, who can then review the information and make corrections as needed. This entire process, when integrated, makes it possible to provide users with a richer and safer experience.

[0444] An example of a prompt sentence to be input to the generating AI model would be, "Analyze the emotions of people in security camera footage and notify me in real time if a specific emotion is detected."

[0445] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0446] Step 1:

[0447] The server receives the query from the user. It takes text data sent by the user from their terminal as input. Based on this data, the server uses the natural language processing library "NLTK" to analyze the key points of the query. The analysis results in a keyword list that identifies the subject and important points of the query.

[0448] Step 2:

[0449] Based on the analyzed key points, the server accesses information sources and internal knowledge bases to collect relevant technical information. The keywords obtained from the analysis results in Step 1 are used as input. The server queries web resources and databases via APIs, filtering relevant information and organizing the collected data. This ensures that useful information is obtained in response to user inquiries.

[0450] Step 3:

[0451] When certain conditions are met, the server uses Unity or Unreal Engine to construct a virtual space. At this stage, collected technical information and pre-configured simulation scenarios are used as input. The server uses this data to model the virtual environment and perform related behavioral checks. The simulation results are used to verify whether the operating conditions are met.

[0452] Step 4:

[0453] The server performs emotion analysis on a person using video data acquired from a video device. The input is a real-time video stream. The server uses "OpenCV" and "Emotion-RNN" to analyze facial expressions in the video and identify emotions. As a result of this analysis, the type of emotion (e.g., joy, anxiety, anger) and its intensity are output.

[0454] Step 5:

[0455] Based on the analysis results, the server automatically sends a warning to the administrator if a specific emotion is detected. The input includes the user inquiry analysis results and the emotion analysis results. The server compares the warning criteria and, if the threshold requiring notification is met, delivers a warning message to the administrator through the notification system. This output allows the administrator to receive appropriate information for immediate action.

[0456] 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.

[0457] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0458] 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.

[0459] [Third Embodiment]

[0460] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0461] 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.

[0462] 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).

[0463] 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.

[0464] 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.

[0465] 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).

[0466] 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.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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".

[0472] This invention is an inquiry response system utilizing an AI agent, aiming to respond quickly and efficiently to technical inquiries from users. The system is implemented as follows:

[0473] When a user makes an inquiry using a device, the device sends the inquiry content to the server. The server receives this inquiry and analyzes it using natural language processing technology. This analysis extracts the key points from the inquiry content.

[0474] Subsequently, the server uses an AI agent to collect relevant technical information from external web sources and internal knowledge bases. This information collection is automated, gathering the data necessary to resolve user inquiries.

[0475] Furthermore, if the inquiry meets certain conditions, the server creates a virtual environment. Here, it performs operational checks related to the user's inquiry and obtains accurate information based on the results.

[0476] The server integrates this information, and the AI ​​agent generates a proposed response to the user. This proposed response is sent to the person in charge, who reviews the content and makes revisions as needed.

[0477] Ultimately, the user receives an answer that has been approved by the person in charge. This entire process speeds up inquiry response and reduces the burden on the person in charge.

[0478] For example, if a user inquires about how to configure new network equipment, the server first collects relevant configuration information and verifies its operation in a virtual network environment. Based on the verification results, an AI agent generates a suggested solution with specific configuration steps and provides it to the user. This allows the user to quickly receive accurate and useful configuration information.

[0479] The following describes the processing flow.

[0480] Step 1:

[0481] The user operates their device, enters a question into the inquiry form, and submits it. The inquiry includes specific technical problems and questions.

[0482] Step 2:

[0483] The server receives the query sent from the terminal. The server saves the query content to the database and prepares it for analysis.

[0484] Step 3:

[0485] The server uses a natural language processing engine to analyze the query content. This analysis extracts the main topics and keywords of the query.

[0486] Step 4:

[0487] The server uses an AI agent to search web information sources and internal knowledge bases based on extracted keywords. It collects relevant technical documents and FAQs.

[0488] Step 5:

[0489] The server creates a virtual environment when certain conditions are met. The server performs operational tests related to the query and records the results.

[0490] Step 6:

[0491] Based on the collected information and the results of operational tests, the server's AI agent generates a suggested answer. This suggested answer details the solution to the inquiry.

[0492] Step 7:

[0493] The generated draft response is sent from the server to the person in charge. The person in charge reviews the draft response, checks its accuracy, and makes corrections if necessary.

[0494] Step 8:

[0495] The final answer is provided to the user from the server. Through the terminal, the user receives the solution and can address the problem.

[0496] (Example 1)

[0497] 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."

[0498] As information technology advances, traditional systems have struggled to respond quickly and accurately to increasingly diverse technical inquiries. Furthermore, manual responses to inquiries place a heavy burden on staff, highlighting the need for more efficient responses. The challenge lies in providing highly accurate and reliable answers in a short timeframe by conducting appropriate information gathering and operational checks based on the content of the inquiry.

[0499] 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.

[0500] In this invention, the server includes means for receiving user inquiries and analyzing the key points of the inquiries using natural language processing, means for automatically collecting relevant information from external information sources and internal knowledge bases based on the analyzed key points, and means for creating a virtual environment according to conditions and performing relevant operational checks. This makes it possible to respond quickly to a wide range of technical inquiries from users, reduce the burden on personnel, and provide highly accurate answers.

[0501] A "user" refers to an individual or organization that makes technical inquiries about the system.

[0502] "Inquiry content" refers to information, including technical questions and requests, that a user sends to the system.

[0503] Natural language processing is a technology for understanding and analyzing human language, and it is used by systems to extract the key points of a query.

[0504] "Key points" refer to the essential information and points raised from the inquiry.

[0505] "Information sources" refer to external and internal databases and knowledge bases that a system accesses to gather relevant information.

[0506] A "knowledge base" refers to a knowledge base managed within a company, a collection of data where technical information is aggregated.

[0507] A "virtual environment" refers to a simulated environment built on software without using actual physical hardware.

[0508] "Operational verification" is the process of testing technical operations related to user inquiries within a virtual environment and evaluating the results.

[0509] A "generative AI model" refers to an artificial intelligence model that generates responses in natural language based on input data.

[0510] A "draft response" refers to the initial response generated by the system as a solution to an inquiry.

[0511] "Responsible party" refers to an individual or team responsible for reviewing the generated draft responses and making final revisions.

[0512] A "prompt sentence" refers to a sentence used to input specific instructions or questions to a generative AI model.

[0513] This invention is an inquiry response system that utilizes an AI agent. Its purpose is to provide quick and accurate responses when users make technical inquiries.

[0514] In the operation of the system, users use a terminal to input technical questions and send the inquiry details to the server. In this process, the terminal used by the user includes personal computers and smartphones.

[0515] The server uses natural language processing techniques to analyze incoming queries. This technique utilizes Python and libraries such as NLTK and spaCy. This allows the server to effectively extract the key points of the query content.

[0516] Based on the analyzed information, the server utilizes an AI agent to collect relevant information. This process involves accessing search engines and internal knowledge bases to gather necessary technical information. Web scraping tools and APIs are used for information gathering, ensuring efficient data collection.

[0517] If a user's inquiry meets certain conditions, the server will create a virtual environment using virtualization technologies such as Docker. This makes it possible to test related technical operations within the virtual environment and verify their operation.

[0518] Based on the collected information and the results of operational checks, the server generates suggested answers using a generative AI model. For example, a general generative AI can be used as a natural language model to form answers in natural language. An example of a prompt used during generation is, "Please tell me the procedure for configuring network equipment."

[0519] The generated draft answers are reviewed by the person in charge and revised as needed. This process ensures that users receive accurate and reliable technical information quickly. For example, if a user asks, "I want to change my Wi-Fi router password," the server checks the relevant procedures and provides the best possible steps.

[0520] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0521] Step 1:

[0522] The user initiates the inquiry by entering a technical question into the terminal. The input concerns problems or settings the user wants to resolve. The terminal sends this input data to the server, which initiates the inquiry processing.

[0523] Step 2:

[0524] The server receives query data from the terminal as input. Next, it analyzes the data using natural language processing techniques. Specifically, it uses the Python NLTK library to extract important keywords and phrases from the text. This process outputs the main points of the query, which are then used for subsequent processing.

[0525] Step 3:

[0526] Based on the analysis results, the server begins collecting relevant information. Using the extracted key points as input, it accesses external information sources and internal knowledge bases. Web scraping tools and APIs are used for information gathering. As output, a set of technical information related to the user's question is generated.

[0527] Step 4:

[0528] The server builds a virtual environment based on the conditions. The input here is a determination of whether the user's inquiry requires operational verification. A virtual environment is created using virtualization technology (e.g., Docker), and operational verification is performed within it. The output is the operational verification result data.

[0529] Step 5:

[0530] The server generates suggested answers using a generative AI model based on the collected information and the results of operational checks. The input includes relevant information and operational check results. The generative AI model (e.g., a natural language model) is used to generate answers in natural language. The output is a suggested answer corresponding to the user's inquiry.

[0531] Step 6:

[0532] The generated draft answers are sent from the server to the person in charge. In this step, the person in charge reviews the generated draft answers as input. The person in charge checks the content of the answers and makes corrections if necessary. Finally, the final answer is prepared based on the review results.

[0533] Step 7:

[0534] The server sends the final response, approved by the person in charge, to the user's terminal. The input here is the revised final response, and the output is the information the user receives on their terminal. This allows the user to review the necessary technical information and use it to solve the problem.

[0535] (Application Example 1)

[0536] 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."

[0537] Electronic payment services require the rapid and accurate resolution of technical problems faced by users. Current systems often require manual responses to user inquiries, which is not only time-consuming but also places a heavy burden on staff. Furthermore, depending on the user's technical skills, understanding their inquiries and providing appropriate solutions can be difficult.

[0538] 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.

[0539] In this invention, the server includes means for receiving information input from a user and analyzing the key points of the information using natural language processing; means for automatically collecting relevant technical documents from external data sources and internal record bases based on the analyzed key points; and means for constructing a virtual simulation under specific environmental conditions and performing relevant work verification. This makes it possible to provide quick and accurate solutions to technical problems faced by users and reduce the burden on personnel.

[0540] A "user" is someone who uses the system to seek technical support or assistance in resolving issues related to electronic payment services.

[0541] "Information input" refers to the act or data that a user provides to a system regarding technical problems or inquiries.

[0542] "Natural language processing" is a technology that enables computers to understand and appropriately analyze human language.

[0543] "Technical documentation" refers to documents and records that include relevant technical information and data and are referenced for problem-solving.

[0544] An "external data source" is a source of information that exists outside the system and is referenced to obtain technical information related to a query.

[0545] An "internal record base" is a database of technical information managed within an organization and used as reference material.

[0546] "Virtual simulation" is a technique that uses computer models that mimic real-world environments to verify and test functionality.

[0547] "Operation verification" is the process of confirming that operations and processes are performed correctly in a virtual environment or a real environment.

[0548] An "expert" is someone who checks the generated solutions and proposed answers and verifies their accuracy.

[0549] A "smart device" is a portable communication device that has the functionality to run applications related to electronic payment services.

[0550] "Real-time" refers to a temporal characteristic where a response to a user's request or action is provided immediately.

[0551] This invention relates to a technical support system for an AI-powered electronic payment service. When a user makes an inquiry via a smart device, the device sends the information to a server. The server analyzes the content of the received inquiry using natural language processing and extracts the key points. Software used for analysis includes NLP libraries (e.g., spaCy and NLTK).

[0552] Based on the analyzed key points, the server automatically collects relevant technical documentation from external data sources and internal record bases. Web scraping techniques and API access are used for information gathering. Existing web server technologies such as Apache or Nginx can be used.

[0553] Subsequently, the server will build a virtual simulation environment using Docker as needed and perform related work verification. This environment is used to verify operation using a virtual model corresponding to the user's inquiry.

[0554] Based on the results of the work verification, the AI ​​model generates the optimal answer. The generating AI model utilizes advanced models such as the GPT series. At this stage, the generated answer is not presented as is; it is checked by experts and modified as necessary. The final answer is provided to the user in real time via a smart device.

[0555] For example, when a user asks, "Please tell me how to resolve error code 1234," the system quickly gathers and verifies relevant information and presents a solution. An example of a prompt sentence input to the generating AI model in this case would be, "Please tell me how to resolve error code 1234 that occurs in the electronic payment function."

[0556] In this way, the system provides a solution that can quickly and accurately resolve users' technical problems and improve the convenience of electronic payment services.

[0557] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0558] Step 1:

[0559] The user enters inquiry information using a smart device. This input information is sent to the device as text data in natural language format. The device then prepares to send this data to the server.

[0560] Step 2:

[0561] The server receives query information sent from the terminal. The received data is analyzed using natural language processing software (e.g., spaCy or NLTK) to extract key points. The input is the user's query text, and the output is structured data containing the key points. Keyword extraction and contextual analysis are performed during this analysis process.

[0562] Step 3:

[0563] The server automatically collects relevant technical documents from external data sources and internal record bases based on the analyzed key points. Using web scraping and API access techniques, the input is a list of extracted key points, and the output is a dataset of related technical documents. This process allows for the organized retrieval of relevant information.

[0564] Step 4:

[0565] The server uses Docker to build a virtual simulation environment based on specific environmental conditions requested by the user. The input consists of a technical data dataset and environment configuration information, while the output is the simulation results. System operation is then verified within the constructed virtual environment.

[0566] Step 5:

[0567] The server generates suggested answers using a generative AI model (e.g., the GPT series) based on the work verification results and collected information. The input is the simulation results and a technical document dataset, and the output is the suggested answer for the user. Here, appropriate answers are derived by using prompt statements for the generative AI model.

[0568] Step 6:

[0569] The server generates a draft answer and sends it to an expert. The expert reviews this answer and makes revisions if necessary. The input is the generated draft answer, and the output is the revised final answer. The accuracy of the answer is improved based on the expert's knowledge.

[0570] Step 7:

[0571] The corrected final answer is sent to the user's smart device in real time. The server manages the response notification to the user's device. The input is the final answer, and the output is the notification to the user. This process allows for the rapid and accurate delivery of solutions to the user.

[0572] 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.

[0573] This invention aims to recognize user emotions and personalize responses by combining an emotion engine with an AI agent-based inquiry response system. This system is implemented as follows.

[0574] When a user submits an inquiry from their device, the server receives the inquiry. The server then uses natural language processing techniques to analyze the key points of the inquiry. In addition, it uses an emotion engine to recognize the user's emotional state. This emotion recognition detects emotions such as joy, anxiety, and anger from the user's word choice and the tone of their input.

[0575] Based on the analyzed key points and emotions, the server launches an AI agent optimized for the individual user experience and automatically collects relevant technical information from web sources and internal knowledge bases. Under specific conditions, a virtual environment is created and necessary operational checks are performed. As a result, accurate information is obtained.

[0576] Next, the AI ​​agent generates suggested answers based on the collected information and the results of the operational checks. The tone of the suggested answers is adjusted based on the user's emotional state, as determined by the emotion engine. For example, for a user who is feeling angry, a more calm and empathetic response will be generated.

[0577] The generated draft answers are reviewed by a designated person. The person reviews the answers for technical accuracy and makes revisions as needed. Finally, the server sends the reviewed answers to the user. At this stage, the system automatically determines whether to prioritize the user's request, taking into account their emotional state.

[0578] For example, when receiving an urgent inquiry regarding a network failure, the server can not only provide technical solutions but also use an emotion engine to select kind and helpful language to reduce stress. In this way, the present invention improves the accuracy and quality of inquiry responses and contributes to increased customer satisfaction.

[0579] The following describes the processing flow.

[0580] Step 1:

[0581] The user operates their device to enter a question into the inquiry form and submit it. The inquiry contains specific problems or questions.

[0582] Step 2:

[0583] The server receives the query sent from the terminal. The server saves this query to the database and prepares it for analysis.

[0584] Step 3:

[0585] The server uses natural language processing technology to analyze the query content and extract key keywords and essential points. This analysis identifies the information necessary to resolve the query.

[0586] Step 4:

[0587] The server uses an emotion engine to analyze the user's emotions from the wording of the inquiry. This analysis determines whether the user is experiencing emotions such as anger, joy, or anxiety.

[0588] Step 5:

[0589] The server activates an AI agent that automatically collects relevant technical information from the web and internal knowledge bases based on extracted keywords and sentiments.

[0590] Step 6:

[0591] When certain conditions are met, the server creates a virtual environment and performs operational checks related to the query. This allows the technical problem to be reproduced and the solution to be verified.

[0592] Step 7:

[0593] The server integrates the collected information and the results of operational checks, and the AI ​​agent generates suggested answers. The tone of these suggested answers is adjusted according to the user's emotional state.

[0594] Step 8:

[0595] The generated draft response is sent from the server to the person in charge. The person in charge checks for technical accuracy and emotional considerations and makes revisions as needed.

[0596] Step 9:

[0597] The final answer is provided to the user from the server. Through the device, the user receives the adjusted answer and can proceed with taking steps toward resolving the problem. The customer experience is improved by taking emotions into consideration.

[0598] (Example 2)

[0599] 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."

[0600] While understanding and appropriately responding to user inquiries is crucial, traditional systems struggled to analyze the key points of inquiries and consider user emotions. Furthermore, processes such as automated information gathering and testing, tone adjustment of responses, and priority determination were not integrated, resulting in challenges regarding response quality and speed. There is a need to solve these problems and provide more personalized and effective responses.

[0601] 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.

[0602] In this invention, the server includes means for receiving inquiry information from a user and analyzing key points using natural language processing, means for automatically collecting digital information from a group of information sources based on the analyzed key points and the user's emotional state, and means for constructing a virtual execution environment and performing operational verification. This makes it possible to quickly collect necessary information and provide highly accurate answers while taking the user's emotions into consideration.

[0603] A "user" refers to an individual or organization that uses the system to make inquiries.

[0604] "Inquiry information" refers to data about questions and requests that users enter or submit through the system.

[0605] "Natural language processing" refers to the technology that enables computers to understand and analyze human language.

[0606] "Key points" refer to the essential information or the core of the problem extracted from the inquiry information.

[0607] "Emotional state" refers to the emotional response and mental state of a user when they make an inquiry.

[0608] "Digital information" refers to any form of electronic data obtained from the set of information sources that a system collects.

[0609] A "collection of information sources" refers to a set of internal or external databases and websites that are referenced to obtain relevant technical information.

[0610] A "virtual execution environment" refers to a virtual space where simulations and tests can be performed on a system that replicates an actual system.

[0611] "Operational verification" is the process of conducting tests in a virtual execution environment under specific scenarios to verify whether the system operates as expected.

[0612] A "draft response" refers to an initial solution or suggestion generated as an answer to a user's inquiry.

[0613] "Tone adjustment" refers to the process of optimizing the expression and wording of generated response suggestions to match the user's emotional state.

[0614] The present invention is a system aimed at providing a rapid and appropriate response to user inquiries. Specific embodiments thereof are described below.

[0615] When a user submits an inquiry via their device, the server receives the inquiry information. Inquiries may include questions about product defects, usage instructions, or technical specifications. The server first extracts the key points of the inquiry using natural language processing techniques. At this stage, a text analysis engine is used to extract keywords and identify intent. Specifically, general text analysis software is used for natural language processing.

[0616] Next, the server uses an emotion engine to analyze the emotional state of the user making the inquiry. The user's linguistic characteristics and text tone are crucial factors in this emotion recognition. The emotion engine detects whether the user is feeling anger or anxiety, and the server utilizes the results.

[0617] Once the analysis is complete, the server collects relevant information from digital sources. These sources include internal knowledge bases and external web databases, and web scraping techniques are used for information gathering. At this stage, if a specific virtual execution environment is required, the server builds it and performs operational verification. By conducting operational tests in this virtual environment, the server verifies whether the proposed solution is effective.

[0618] Based on the collected information, the server uses a generative AI model to create suggested answers. These answers are generated with a tone adjusted by an emotion engine, taking into account the user's emotional state. For example, a user expressing anger will receive a calm and empathetic response.

[0619] The final response is reviewed by a staff member, and any necessary revisions are made. Once the staff member has reviewed the response, it is sent from the server to the user. At this point, the system prioritizes the response based on the user's emotional state, and if a faster response is required, the sending process is optimized according to that metric.

[0620] As a concrete example, the prompt "The user has reported a network problem and is experiencing significant stress. Please create a response that suggests a technical solution while maintaining a reassuring tone" is input to the AI ​​model. In this way, an appropriate response to the user is automatically generated.

[0621] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0622] Step 1:

[0623] The user inputs and submits inquiry information via a terminal. The input data consists of text-based questions and problem descriptions. The terminal uses a communication protocol to transfer this data to the server.

[0624] Step 2:

[0625] The server receives the query information. The received data is recorded as a log and passed to the natural language processing engine. The input here is the text data of the query information, and the output is the extraction of key points. Specifically, the process extracts keywords and important phrases from the text.

[0626] Step 3:

[0627] The server uses an emotion engine to analyze the user's emotional state. The input is the user's inquiry text, and the output is the type of emotion (joy, anxiety, anger, etc.) and its intensity. At this stage, data calculations are performed to calculate an emotion score from the text content.

[0628] Step 4:

[0629] The server automatically collects relevant digital information from databases and external web sources based on the analyzed key points and sentiment data. The input is key points and sentiment data, and the output is the collected technical information. Specifically, it uses APIs and crawling technologies to collect the necessary data.

[0630] Step 5:

[0631] The server will build a virtual execution environment as needed and perform operational verification. The input consists of collected technical data and virtual environment settings, while the output is the test results. Tools and emulators are used in specific scenarios to verify that the system functions correctly.

[0632] Step 6:

[0633] The server uses a generative AI model to create suggested answers based on collected information and emotional states. The input is collected technical information and emotional scores, and the output is the adjusted suggested answer. Here, the generative AI model uses prompts such as "output an answer optimized according to the user's emotions."

[0634] Step 7:

[0635] The generated draft answers are reviewed by the assigned person. The input is the generated draft answer, and the output is the assigned person's proposed revisions or comments. The assigned person performs a specific review to check the technical accuracy and tone of the answer.

[0636] Step 8:

[0637] The server sends the revised, final response to the user. The input consists of the reviewed draft response and the user's inquiry information, while the output is the final response message to the user. This process adjusts the timing and method of sending the response based on the user's sentiment and priorities.

[0638] (Application Example 2)

[0639] 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."

[0640] Conventional customer service systems were unable to respond appropriately to users' emotions, and therefore could not adequately improve customer satisfaction. Furthermore, security systems struggled to analyze people's emotions and detect potential threats early on.

[0641] 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.

[0642] In this invention, the server includes means for receiving user inquiries and analyzing the key points of the inquiries using natural language processing; means for automatically collecting relevant technical information from information sources and internal knowledge bases based on the analyzed key points; means for constructing a virtual space under specific conditions and performing relevant behavioral verification; and means for analyzing a person's emotions using a video device and automatically sending a warning to the administrator in specific situations based on the analysis results. This enables inquiry responses that take user emotions into consideration and real-time security improvements.

[0643] "Inquiry details" refer to text information of questions or problem reports that users submit to the system or service.

[0644] "Natural language processing" is the technology that enables computers to understand the language that humans normally use.

[0645] The "key points" refer to the core information that is particularly important within the content of the inquiry.

[0646] "Technical information" refers to specialized knowledge and data related to the content of the inquiry.

[0647] "Information sources" refer to internet resources such as websites and digital repositories from which relevant information can be obtained.

[0648] An "internal knowledge base" refers to the know-how and databases accumulated within an organization.

[0649] A "virtual space" is a simulation environment built on a computer.

[0650] "Behavior verification" is a process to verify that a system or device is functioning correctly.

[0651] "Video equipment" refers to hardware such as cameras used to acquire visual information.

[0652] "Emotional analysis" is the process of identifying a person's emotions from video or text.

[0653] A "warning" is an alert that notifies you of a potential danger or anomaly.

[0654] An "administrator" is a person responsible for the operation and management of a system or service.

[0655] This system is designed for handling inquiries and security analysis. First, the server receives user inquiries and analyzes their key points using natural language processing techniques. Natural language processing libraries such as "NLTK" are suitable software for this purpose.

[0656] Next, the server automatically collects relevant technical information from external sources and internal knowledge bases based on the analyzed key points. Based on the definition of information sources, this includes resources on the internet and internal databases.

[0657] Furthermore, under certain conditions, the server uses software such as "Unity" or "Unreal Engine" to construct a virtual space and verify related behaviors. This allows for a simulation of how the proposed solutions will function in a real-world environment.

[0658] Furthermore, the server performs emotion analysis using video footage acquired by video equipment connected to the terminal. This process utilizes tools such as "OpenCV" and "Emotion-RNN" to identify a person's emotions in real time. For example, if a camera installed as a security measure in a shopping mall detects a person's anxiety, it will warn of potential danger.

[0659] The server distributes appropriately generated response proposals and warnings to the responsible personnel, who can then review the information and make corrections as needed. This entire process, when integrated, makes it possible to provide users with a richer and safer experience.

[0660] An example of a prompt sentence to be input to the generating AI model would be, "Analyze the emotions of people in security camera footage and notify me in real time if a specific emotion is detected."

[0661] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0662] Step 1:

[0663] The server receives the query from the user. It takes text data sent by the user from their terminal as input. Based on this data, the server uses the natural language processing library "NLTK" to analyze the key points of the query. The analysis results in a keyword list that identifies the subject and important points of the query.

[0664] Step 2:

[0665] Based on the analyzed key points, the server accesses information sources and internal knowledge bases to collect relevant technical information. The keywords obtained from the analysis results in Step 1 are used as input. The server queries web resources and databases via APIs, filtering relevant information and organizing the collected data. This ensures that useful information is obtained in response to user inquiries.

[0666] Step 3:

[0667] When certain conditions are met, the server uses Unity or Unreal Engine to construct a virtual space. At this stage, collected technical information and pre-configured simulation scenarios are used as input. The server uses this data to model the virtual environment and perform related behavioral checks. The simulation results are used to verify whether the operating conditions are met.

[0668] Step 4:

[0669] The server performs emotion analysis on a person using video data acquired from a video device. The input is a real-time video stream. The server uses "OpenCV" and "Emotion-RNN" to analyze facial expressions in the video and identify emotions. As a result of this analysis, the type of emotion (e.g., joy, anxiety, anger) and its intensity are output.

[0670] Step 5:

[0671] Based on the analysis results, the server automatically sends a warning to the administrator if a specific emotion is detected. The input includes the user inquiry analysis results and the emotion analysis results. The server compares the warning criteria and, if the threshold requiring notification is met, delivers a warning message to the administrator through the notification system. This output allows the administrator to receive appropriate information for immediate action.

[0672] 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.

[0673] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0674] 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.

[0675] [Fourth Embodiment]

[0676] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0677] 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.

[0678] 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).

[0679] 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.

[0680] 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.

[0681] 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).

[0682] 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.

[0683] 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.

[0684] 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.

[0685] 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.

[0686] 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.

[0687] 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.

[0688] 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".

[0689] This invention is an inquiry response system utilizing an AI agent, aiming to respond quickly and efficiently to technical inquiries from users. The system is implemented as follows:

[0690] When a user makes an inquiry using a device, the device sends the inquiry content to the server. The server receives this inquiry and analyzes it using natural language processing technology. This analysis extracts the key points from the inquiry content.

[0691] Subsequently, the server uses an AI agent to collect relevant technical information from external web sources and internal knowledge bases. This information collection is automated, gathering the data necessary to resolve user inquiries.

[0692] Furthermore, if the inquiry meets certain conditions, the server creates a virtual environment. Here, it performs operational checks related to the user's inquiry and obtains accurate information based on the results.

[0693] The server integrates this information, and the AI ​​agent generates a proposed response to the user. This proposed response is sent to the person in charge, who reviews the content and makes revisions as needed.

[0694] Ultimately, the user receives an answer that has been approved by the person in charge. This entire process speeds up inquiry response and reduces the burden on the person in charge.

[0695] For example, if a user inquires about how to configure new network equipment, the server first collects relevant configuration information and verifies its operation in a virtual network environment. Based on the verification results, an AI agent generates a suggested solution with specific configuration steps and provides it to the user. This allows the user to quickly receive accurate and useful configuration information.

[0696] The following describes the processing flow.

[0697] Step 1:

[0698] The user operates their device, enters a question into the inquiry form, and submits it. The inquiry includes specific technical problems and questions.

[0699] Step 2:

[0700] The server receives the query sent from the terminal. The server saves the query content to the database and prepares it for analysis.

[0701] Step 3:

[0702] The server uses a natural language processing engine to analyze the query content. This analysis extracts the main topics and keywords of the query.

[0703] Step 4:

[0704] The server uses an AI agent to search web information sources and internal knowledge bases based on extracted keywords. It collects relevant technical documents and FAQs.

[0705] Step 5:

[0706] The server creates a virtual environment when certain conditions are met. The server performs operational tests related to the query and records the results.

[0707] Step 6:

[0708] Based on the collected information and the results of operational tests, the server's AI agent generates a suggested answer. This suggested answer details the solution to the inquiry.

[0709] Step 7:

[0710] The generated draft response is sent from the server to the person in charge. The person in charge reviews the draft response, checks its accuracy, and makes corrections if necessary.

[0711] Step 8:

[0712] The final answer is provided to the user from the server. Through the terminal, the user receives the solution and can address the problem.

[0713] (Example 1)

[0714] 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".

[0715] As information technology advances, traditional systems have struggled to respond quickly and accurately to increasingly diverse technical inquiries. Furthermore, manual responses to inquiries place a heavy burden on staff, highlighting the need for more efficient responses. The challenge lies in providing highly accurate and reliable answers in a short timeframe by conducting appropriate information gathering and operational checks based on the content of the inquiry.

[0716] 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.

[0717] In this invention, the server includes means for receiving user inquiries and analyzing the key points of the inquiries using natural language processing, means for automatically collecting relevant information from external information sources and internal knowledge bases based on the analyzed key points, and means for creating a virtual environment according to conditions and performing relevant operational checks. This makes it possible to respond quickly to a wide range of technical inquiries from users, reduce the burden on personnel, and provide highly accurate answers.

[0718] A "user" refers to an individual or organization that makes technical inquiries about the system.

[0719] "Inquiry content" refers to information, including technical questions and requests, that a user sends to the system.

[0720] Natural language processing is a technology for understanding and analyzing human language, and it is used by systems to extract the key points of a query.

[0721] "Key points" refer to the essential information and points raised from the inquiry.

[0722] "Information sources" refer to external and internal databases and knowledge bases that a system accesses to gather relevant information.

[0723] A "knowledge base" refers to a knowledge base managed within a company, a collection of data where technical information is aggregated.

[0724] A "virtual environment" refers to a simulated environment built on software without using actual physical hardware.

[0725] "Operational verification" is the process of testing technical operations related to user inquiries within a virtual environment and evaluating the results.

[0726] A "generative AI model" refers to an artificial intelligence model that generates responses in natural language based on input data.

[0727] A "draft response" refers to the initial response generated by the system as a solution to an inquiry.

[0728] "Responsible party" refers to an individual or team responsible for reviewing the generated draft responses and making final revisions.

[0729] A "prompt sentence" refers to a sentence used to input specific instructions or questions to a generative AI model.

[0730] This invention is an inquiry response system that utilizes an AI agent. Its purpose is to provide quick and accurate responses when users make technical inquiries.

[0731] In the operation of the system, users use a terminal to input technical questions and send the inquiry details to the server. In this process, the terminal used by the user includes personal computers and smartphones.

[0732] The server uses natural language processing techniques to analyze incoming queries. This technique utilizes Python and libraries such as NLTK and spaCy. This allows the server to effectively extract the key points of the query content.

[0733] Based on the analyzed information, the server utilizes an AI agent to collect relevant information. This process involves accessing search engines and internal knowledge bases to gather necessary technical information. Web scraping tools and APIs are used for information gathering, ensuring efficient data collection.

[0734] If a user's inquiry meets certain conditions, the server will create a virtual environment using virtualization technologies such as Docker. This makes it possible to test related technical operations within the virtual environment and verify their operation.

[0735] Based on the collected information and the results of operational checks, the server generates suggested answers using a generative AI model. For example, a general generative AI can be used as a natural language model to form answers in natural language. An example of a prompt used during generation is, "Please tell me the procedure for configuring network equipment."

[0736] The generated draft answers are reviewed by the person in charge and revised as needed. This process ensures that users receive accurate and reliable technical information quickly. For example, if a user asks, "I want to change my Wi-Fi router password," the server checks the relevant procedures and provides the best possible steps.

[0737] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0738] Step 1:

[0739] The user initiates the inquiry by entering a technical question into the terminal. The input concerns problems or settings the user wants to resolve. The terminal sends this input data to the server, which initiates the inquiry processing.

[0740] Step 2:

[0741] The server receives query data from the terminal as input. Next, it analyzes the data using natural language processing techniques. Specifically, it uses the Python NLTK library to extract important keywords and phrases from the text. This process outputs the main points of the query, which are then used for subsequent processing.

[0742] Step 3:

[0743] Based on the analysis results, the server begins collecting relevant information. Using the extracted key points as input, it accesses external information sources and internal knowledge bases. Web scraping tools and APIs are used for information gathering. As output, a set of technical information related to the user's question is generated.

[0744] Step 4:

[0745] The server builds a virtual environment based on the conditions. The input here is a determination of whether the user's inquiry requires operational verification. A virtual environment is created using virtualization technology (e.g., Docker), and operational verification is performed within it. The output is the operational verification result data.

[0746] Step 5:

[0747] The server generates suggested answers using a generative AI model based on the collected information and the results of operational checks. The input includes relevant information and operational check results. The generative AI model (e.g., a natural language model) is used to generate answers in natural language. The output is a suggested answer corresponding to the user's inquiry.

[0748] Step 6:

[0749] The generated draft answers are sent from the server to the person in charge. In this step, the person in charge reviews the generated draft answers as input. The person in charge checks the content of the answers and makes corrections if necessary. Finally, the final answer is prepared based on the review results.

[0750] Step 7:

[0751] The server sends the final response, approved by the person in charge, to the user's terminal. The input here is the revised final response, and the output is the information the user receives on their terminal. This allows the user to review the necessary technical information and use it to solve the problem.

[0752] (Application Example 1)

[0753] 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".

[0754] Electronic payment services require the rapid and accurate resolution of technical problems faced by users. Current systems often require manual responses to user inquiries, which is not only time-consuming but also places a heavy burden on staff. Furthermore, depending on the user's technical skills, understanding their inquiries and providing appropriate solutions can be difficult.

[0755] 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.

[0756] In this invention, the server includes means for receiving information input from a user and analyzing the key points of the information using natural language processing; means for automatically collecting relevant technical documents from external data sources and internal record bases based on the analyzed key points; and means for constructing a virtual simulation under specific environmental conditions and performing relevant work verification. This makes it possible to provide quick and accurate solutions to technical problems faced by users and reduce the burden on personnel.

[0757] A "user" is someone who uses the system to seek technical support or assistance in resolving issues related to electronic payment services.

[0758] "Information input" refers to the act or data that a user provides to a system regarding technical problems or inquiries.

[0759] "Natural language processing" is a technology that enables computers to understand and appropriately analyze human language.

[0760] "Technical documentation" refers to documents and records that include relevant technical information and data and are referenced for problem-solving.

[0761] An "external data source" is a source of information that exists outside the system and is referenced to obtain technical information related to a query.

[0762] An "internal record base" is a database of technical information managed within an organization and used as reference material.

[0763] "Virtual simulation" is a technique that uses computer models that mimic real-world environments to verify and test functionality.

[0764] "Operation verification" is the process of confirming that operations and processes are performed correctly in a virtual environment or a real environment.

[0765] An "expert" is someone who checks the generated solutions and proposed answers and verifies their accuracy.

[0766] A "smart device" is a portable communication device that has the functionality to run applications related to electronic payment services.

[0767] "Real-time" refers to a temporal characteristic where a response to a user's request or action is provided immediately.

[0768] This invention relates to a technical support system for an AI-powered electronic payment service. When a user makes an inquiry via a smart device, the device sends the information to a server. The server analyzes the content of the received inquiry using natural language processing and extracts the key points. Software used for analysis includes NLP libraries (e.g., spaCy and NLTK).

[0769] Based on the analyzed key points, the server automatically collects relevant technical documentation from external data sources and internal record bases. Web scraping techniques and API access are used for information gathering. Existing web server technologies such as Apache or Nginx can be used.

[0770] Subsequently, the server will build a virtual simulation environment using Docker as needed and perform related work verification. This environment is used to verify operation using a virtual model corresponding to the user's inquiry.

[0771] Based on the results of the work verification, the AI ​​model generates the optimal answer. The generating AI model utilizes advanced models such as the GPT series. At this stage, the generated answer is not presented as is; it is checked by experts and modified as necessary. The final answer is provided to the user in real time via a smart device.

[0772] For example, when a user asks, "Please tell me how to resolve error code 1234," the system quickly gathers and verifies relevant information and presents a solution. An example of a prompt sentence input to the generating AI model in this case would be, "Please tell me how to resolve error code 1234 that occurs in the electronic payment function."

[0773] In this way, the system provides a solution that can quickly and accurately resolve users' technical problems and improve the convenience of electronic payment services.

[0774] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0775] Step 1:

[0776] The user enters inquiry information using a smart device. This input information is sent to the device as text data in natural language format. The device then prepares to send this data to the server.

[0777] Step 2:

[0778] The server receives query information sent from the terminal. The received data is analyzed using natural language processing software (e.g., spaCy or NLTK) to extract key points. The input is the user's query text, and the output is structured data containing the key points. Keyword extraction and contextual analysis are performed during this analysis process.

[0779] Step 3:

[0780] The server automatically collects relevant technical documents from external data sources and internal record bases based on the analyzed key points. Using web scraping and API access techniques, the input is a list of extracted key points, and the output is a dataset of related technical documents. This process allows for the organized retrieval of relevant information.

[0781] Step 4:

[0782] The server uses Docker to build a virtual simulation environment based on specific environmental conditions requested by the user. The input consists of a technical data dataset and environment configuration information, while the output is the simulation results. System operation is then verified within the constructed virtual environment.

[0783] Step 5:

[0784] The server generates suggested answers using a generative AI model (e.g., the GPT series) based on the work verification results and collected information. The input is the simulation results and a technical document dataset, and the output is the suggested answer for the user. Here, appropriate answers are derived by using prompt statements for the generative AI model.

[0785] Step 6:

[0786] The server generates a draft answer and sends it to an expert. The expert reviews this answer and makes revisions if necessary. The input is the generated draft answer, and the output is the revised final answer. The accuracy of the answer is improved based on the expert's knowledge.

[0787] Step 7:

[0788] The corrected final answer is sent to the user's smart device in real time. The server manages the response notification to the user's device. The input is the final answer, and the output is the notification to the user. This process allows for the rapid and accurate delivery of solutions to the user.

[0789] 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.

[0790] This invention aims to recognize user emotions and personalize responses by combining an emotion engine with an AI agent-based inquiry response system. This system is implemented as follows.

[0791] When a user submits an inquiry from their device, the server receives the inquiry. The server then uses natural language processing techniques to analyze the key points of the inquiry. In addition, it uses an emotion engine to recognize the user's emotional state. This emotion recognition detects emotions such as joy, anxiety, and anger from the user's word choice and the tone of their input.

[0792] Based on the analyzed key points and emotions, the server launches an AI agent optimized for the individual user experience and automatically collects relevant technical information from web sources and internal knowledge bases. Under specific conditions, a virtual environment is created and necessary operational checks are performed. As a result, accurate information is obtained.

[0793] Next, the AI ​​agent generates suggested answers based on the collected information and the results of the operational checks. The tone of the suggested answers is adjusted based on the user's emotional state, as determined by the emotion engine. For example, for a user who is feeling angry, a more calm and empathetic response will be generated.

[0794] The generated draft answers are reviewed by a designated person. The person reviews the answers for technical accuracy and makes revisions as needed. Finally, the server sends the reviewed answers to the user. At this stage, the system automatically determines whether to prioritize the user's request, taking into account their emotional state.

[0795] For example, when receiving an urgent inquiry regarding a network failure, the server can not only provide technical solutions but also use an emotion engine to select kind and helpful language to reduce stress. In this way, the present invention improves the accuracy and quality of inquiry responses and contributes to increased customer satisfaction.

[0796] The following describes the processing flow.

[0797] Step 1:

[0798] The user operates their device to enter a question into the inquiry form and submit it. The inquiry contains specific problems or questions.

[0799] Step 2:

[0800] The server receives the query sent from the terminal. The server saves this query to the database and prepares it for analysis.

[0801] Step 3:

[0802] The server uses natural language processing technology to analyze the query content and extract key keywords and essential points. This analysis identifies the information necessary to resolve the query.

[0803] Step 4:

[0804] The server uses an emotion engine to analyze the user's emotions from the wording of the inquiry. This analysis determines whether the user is experiencing emotions such as anger, joy, or anxiety.

[0805] Step 5:

[0806] The server activates an AI agent that automatically collects relevant technical information from the web and internal knowledge bases based on extracted keywords and sentiments.

[0807] Step 6:

[0808] When certain conditions are met, the server creates a virtual environment and performs operational checks related to the query. This allows the technical problem to be reproduced and the solution to be verified.

[0809] Step 7:

[0810] The server integrates the collected information and the results of operational checks, and the AI ​​agent generates suggested answers. The tone of these suggested answers is adjusted according to the user's emotional state.

[0811] Step 8:

[0812] The generated draft response is sent from the server to the person in charge. The person in charge checks for technical accuracy and emotional considerations and makes revisions as needed.

[0813] Step 9:

[0814] The final answer is provided to the user from the server. Through the device, the user receives the adjusted answer and can proceed with taking steps toward resolving the problem. The customer experience is improved by taking emotions into consideration.

[0815] (Example 2)

[0816] 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".

[0817] While understanding and appropriately responding to user inquiries is crucial, traditional systems struggled to analyze the key points of inquiries and consider user emotions. Furthermore, processes such as automated information gathering and testing, tone adjustment of responses, and priority determination were not integrated, resulting in challenges regarding response quality and speed. There is a need to solve these problems and provide more personalized and effective responses.

[0818] 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.

[0819] In this invention, the server includes means for receiving inquiry information from a user and analyzing key points using natural language processing, means for automatically collecting digital information from a group of information sources based on the analyzed key points and the user's emotional state, and means for constructing a virtual execution environment and performing operational verification. This makes it possible to quickly collect necessary information and provide highly accurate answers while taking the user's emotions into consideration.

[0820] A "user" refers to an individual or organization that uses the system to make inquiries.

[0821] "Inquiry information" refers to data about questions and requests that users enter or submit through the system.

[0822] "Natural language processing" refers to the technology that enables computers to understand and analyze human language.

[0823] "Key points" refer to the essential information or the core of the problem extracted from the inquiry information.

[0824] "Emotional state" refers to the emotional response and mental state of a user when they make an inquiry.

[0825] "Digital information" refers to any form of electronic data obtained from the set of information sources that a system collects.

[0826] A "collection of information sources" refers to a set of internal or external databases and websites that are referenced to obtain relevant technical information.

[0827] A "virtual execution environment" refers to a virtual space where simulations and tests can be performed on a system that replicates an actual system.

[0828] "Operational verification" is the process of conducting tests in a virtual execution environment under specific scenarios to verify whether the system operates as expected.

[0829] A "draft response" refers to an initial solution or suggestion generated as an answer to a user's inquiry.

[0830] "Tone adjustment" refers to the process of optimizing the expression and wording of generated response suggestions to match the user's emotional state.

[0831] The present invention is a system aimed at providing a rapid and appropriate response to user inquiries. Specific embodiments thereof are described below.

[0832] When a user submits an inquiry via their device, the server receives the inquiry information. Inquiries may include questions about product defects, usage instructions, or technical specifications. The server first extracts the key points of the inquiry using natural language processing techniques. At this stage, a text analysis engine is used to extract keywords and identify intent. Specifically, general text analysis software is used for natural language processing.

[0833] Next, the server uses an emotion engine to analyze the emotional state of the user making the inquiry. The user's linguistic characteristics and text tone are crucial factors in this emotion recognition. The emotion engine detects whether the user is feeling anger or anxiety, and the server utilizes the results.

[0834] Once the analysis is complete, the server collects relevant information from digital sources. These sources include internal knowledge bases and external web databases, and web scraping techniques are used for information gathering. At this stage, if a specific virtual execution environment is required, the server builds it and performs operational verification. By conducting operational tests in this virtual environment, the server verifies whether the proposed solution is effective.

[0835] Based on the collected information, the server uses a generative AI model to create suggested answers. These answers are generated with a tone adjusted by an emotion engine, taking into account the user's emotional state. For example, a user expressing anger will receive a calm and empathetic response.

[0836] The final response is reviewed by a staff member, and any necessary revisions are made. Once the staff member has reviewed the response, it is sent from the server to the user. At this point, the system prioritizes the response based on the user's emotional state, and if a faster response is required, the sending process is optimized according to that metric.

[0837] As a concrete example, the prompt "The user has reported a network problem and is experiencing significant stress. Please create a response that suggests a technical solution while maintaining a reassuring tone" is input to the AI ​​model. In this way, an appropriate response to the user is automatically generated.

[0838] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0839] Step 1:

[0840] The user inputs and submits inquiry information via a terminal. The input data consists of text-based questions and problem descriptions. The terminal uses a communication protocol to transfer this data to the server.

[0841] Step 2:

[0842] The server receives the query information. The received data is recorded as a log and passed to the natural language processing engine. The input here is the text data of the query information, and the output is the extraction of key points. Specifically, the process extracts keywords and important phrases from the text.

[0843] Step 3:

[0844] The server uses an emotion engine to analyze the user's emotional state. The input is the user's inquiry text, and the output is the type of emotion (joy, anxiety, anger, etc.) and its intensity. At this stage, data calculations are performed to calculate an emotion score from the text content.

[0845] Step 4:

[0846] The server automatically collects relevant digital information from databases and external web sources based on the analyzed key points and sentiment data. The input is key points and sentiment data, and the output is the collected technical information. Specifically, it uses APIs and crawling technologies to collect the necessary data.

[0847] Step 5:

[0848] The server will build a virtual execution environment as needed and perform operational verification. The input consists of collected technical data and virtual environment settings, while the output is the test results. Tools and emulators are used in specific scenarios to verify that the system functions correctly.

[0849] Step 6:

[0850] The server uses a generative AI model to create suggested answers based on collected information and emotional states. The input is collected technical information and emotional scores, and the output is the adjusted suggested answer. Here, the generative AI model uses prompts such as "output an answer optimized according to the user's emotions."

[0851] Step 7:

[0852] The generated draft answers are reviewed by the assigned person. The input is the generated draft answer, and the output is the assigned person's proposed revisions or comments. The assigned person performs a specific review to check the technical accuracy and tone of the answer.

[0853] Step 8:

[0854] The server sends the revised, final response to the user. The input consists of the reviewed draft response and the user's inquiry information, while the output is the final response message to the user. This process adjusts the timing and method of sending the response based on the user's sentiment and priorities.

[0855] (Application Example 2)

[0856] 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".

[0857] Conventional customer service systems were unable to respond appropriately to users' emotions, and therefore could not adequately improve customer satisfaction. Furthermore, security systems struggled to analyze people's emotions and detect potential threats early on.

[0858] 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.

[0859] In this invention, the server includes means for receiving user inquiries and analyzing the key points of the inquiries using natural language processing; means for automatically collecting relevant technical information from information sources and internal knowledge bases based on the analyzed key points; means for constructing a virtual space under specific conditions and performing relevant behavioral verification; and means for analyzing a person's emotions using a video device and automatically sending a warning to the administrator in specific situations based on the analysis results. This enables inquiry responses that take user emotions into consideration and real-time security improvements.

[0860] "Inquiry details" refer to text information of questions or problem reports that users submit to the system or service.

[0861] "Natural language processing" is the technology that enables computers to understand the language that humans normally use.

[0862] The "key points" refer to the core information that is particularly important within the content of the inquiry.

[0863] "Technical information" refers to specialized knowledge and data related to the content of the inquiry.

[0864] "Information sources" refer to internet resources such as websites and digital repositories from which relevant information can be obtained.

[0865] An "internal knowledge base" refers to the know-how and databases accumulated within an organization.

[0866] A "virtual space" is a simulation environment built on a computer.

[0867] "Behavior verification" is a process to verify that a system or device is functioning correctly.

[0868] "Video equipment" refers to hardware such as cameras used to acquire visual information.

[0869] "Emotional analysis" is the process of identifying a person's emotions from video or text.

[0870] A "warning" is an alert that notifies you of a potential danger or anomaly.

[0871] An "administrator" is a person responsible for the operation and management of a system or service.

[0872] This system is designed for handling inquiries and security analysis. First, the server receives user inquiries and analyzes their key points using natural language processing techniques. Natural language processing libraries such as "NLTK" are suitable software for this purpose.

[0873] Next, the server automatically collects relevant technical information from external sources and internal knowledge bases based on the analyzed key points. Based on the definition of information sources, this includes resources on the internet and internal databases.

[0874] Furthermore, under certain conditions, the server uses software such as "Unity" or "Unreal Engine" to construct a virtual space and verify related behaviors. This allows for a simulation of how the proposed solutions will function in a real-world environment.

[0875] Furthermore, the server performs emotion analysis using video footage acquired by video equipment connected to the terminal. This process utilizes tools such as "OpenCV" and "Emotion-RNN" to identify a person's emotions in real time. For example, if a camera installed as a security measure in a shopping mall detects a person's anxiety, it will warn of potential danger.

[0876] The server distributes appropriately generated response proposals and warnings to the responsible personnel, who can then review the information and make corrections as needed. This entire process, when integrated, makes it possible to provide users with a richer and safer experience.

[0877] An example of a prompt sentence to be input to the generating AI model would be, "Analyze the emotions of people in security camera footage and notify me in real time if a specific emotion is detected."

[0878] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0879] Step 1:

[0880] The server receives the query from the user. It takes text data sent by the user from their terminal as input. Based on this data, the server uses the natural language processing library "NLTK" to analyze the key points of the query. The analysis results in a keyword list that identifies the subject and important points of the query.

[0881] Step 2:

[0882] Based on the analyzed key points, the server accesses information sources and internal knowledge bases to collect relevant technical information. The keywords obtained from the analysis results in Step 1 are used as input. The server queries web resources and databases via APIs, filtering relevant information and organizing the collected data. This ensures that useful information is obtained in response to user inquiries.

[0883] Step 3:

[0884] When certain conditions are met, the server uses Unity or Unreal Engine to construct a virtual space. At this stage, collected technical information and pre-configured simulation scenarios are used as input. The server uses this data to model the virtual environment and perform related behavioral checks. The simulation results are used to verify whether the operating conditions are met.

[0885] Step 4:

[0886] The server performs emotion analysis on a person using video data acquired from a video device. The input is a real-time video stream. The server uses "OpenCV" and "Emotion-RNN" to analyze facial expressions in the video and identify emotions. As a result of this analysis, the type of emotion (e.g., joy, anxiety, anger) and its intensity are output.

[0887] Step 5:

[0888] Based on the analysis results, the server automatically sends a warning to the administrator if a specific emotion is detected. The input includes the user inquiry analysis results and the emotion analysis results. The server compares the warning criteria and, if the threshold requiring notification is met, delivers a warning message to the administrator through the notification system. This output allows the administrator to receive appropriate information for immediate action.

[0889] 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.

[0890] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0891] 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.

[0892] 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.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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."

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] The following is further disclosed regarding the embodiments described above.

[0911] (Claim 1)

[0912] A means of receiving user inquiries and analyzing the key points of those inquiries using natural language processing,

[0913] A means to automatically collect relevant technical information from web sources and internal knowledge bases based on the analyzed key points,

[0914] A means of building a virtual environment under specific conditions and performing related operational checks,

[0915] A means of generating suggested answers using artificial intelligence based on collected information and the results of operational checks,

[0916] In order to provide the generated response draft, a means is provided for the person in charge to review the content and make final revisions,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, further comprising means for automatically querying an external organization for the specifications of equipment related to the inquiry.

[0920] (Claim 3)

[0921] The system according to claim 1, further comprising means for sending generated draft answers to a person in charge and for automatically sending a final answer to a user based on the person in charge's review results.

[0922] "Example 1"

[0923] (Claim 1)

[0924] A means of receiving user inquiries and analyzing the key points of those inquiries using natural language processing,

[0925] A means for automatically collecting relevant information from external sources and internal knowledge bases based on the analyzed key points,

[0926] A means of creating a virtual environment according to the conditions and performing related operational checks,

[0927] A means of generating response suggestions using a generative AI model based on collected information and operational verification results,

[0928] In order to provide the generated draft response, a means is provided for the person in charge to review the content and make final revisions.

[0929] A means of sending the final answer via the user terminal,

[0930] A system that includes this.

[0931] (Claim 2)

[0932] The system according to claim 1, further comprising means for automatically querying an external organization for technical characteristics related to a user inquiry.

[0933] (Claim 3)

[0934] The system according to claim 1, further comprising means for sending the generated draft response to a person in charge and for automatically sending the final response to the user based on the person in charge's confirmation.

[0935] "Application Example 1"

[0936] (Claim 1)

[0937] A means of receiving information input from a user and analyzing the key points of the information using natural language processing,

[0938] A means for automatically collecting relevant technical documents from external data sources and internal record bases based on the analyzed key points,

[0939] A means of constructing a virtual simulation under specific environmental conditions and performing related work verification,

[0940] A method for generating proposed answers using artificial intelligence based on collected materials and the results of work verification,

[0941] In order to provide the generated draft answers, there is a means by which experts can check the content and make final changes,

[0942] A means of quickly providing users with the optimal solution in real time through an application installed on a smart device,

[0943] A system that includes this.

[0944] (Claim 2)

[0945] The system according to claim 1, further comprising means for extracting specific error information related to information from the user and generating a prompt statement to provide a solution.

[0946] (Claim 3)

[0947] The system according to claim 1, further comprising means for sending generated draft answers to experts and automatically sending a final answer to a user device based on the experts' review results.

[0948] "Example 2 of combining an emotion engine"

[0949] (Claim 1)

[0950] A means for receiving inquiry information from users and analyzing the key points of the inquiry using natural language processing,

[0951] A means for automatically collecting relevant digital information from a group of information sources based on the analyzed key points and the user's emotional state,

[0952] A means of building a virtual execution environment under specific conditions and performing related operational checks,

[0953] A means of generating suggested answers using artificial intelligence based on collected information and the results of operational checks,

[0954] A means of adjusting the tone of the generated response suggestions, taking into account the user's emotional state,

[0955] In order to provide the generated response draft, a means is provided for the person in charge to review the content and make final revisions,

[0956] A method for sending the revised final response to the user and automatically determining the priority,

[0957] A system that includes this.

[0958] (Claim 2)

[0959] The system according to claim 1, further comprising means for automatically querying an external organization for the characteristics of equipment related to the inquiry.

[0960] (Claim 3)

[0961] The system according to claim 1, further comprising means for sending generated draft answers to a person in charge and for automatically sending a final answer to a user based on the person in charge's review results.

[0962] "Application example 2 when combining with an emotional engine"

[0963] (Claim 1)

[0964] A means of receiving user inquiries and analyzing the key points of those inquiries using natural language processing,

[0965] A means for automatically collecting relevant technical information from information sources and internal knowledge centers based on the analyzed key points,

[0966] A means for constructing a virtual space under specific conditions and verifying related behaviors,

[0967] A means of generating response proposals using artificial intelligence based on collected information and behavioral confirmation results,

[0968] In order to provide the generated response draft, a means is provided for the person in charge to evaluate the content and make final revisions,

[0969] A means of analyzing a person's emotions using video equipment and automatically sending a warning to the administrator in specific situations based on the analysis results,

[0970] A system that includes this.

[0971] (Claim 2)

[0972] The system according to claim 1, further comprising means for automatically inquiring with an external organization about the specifications of a device related to the inquiry.

[0973] (Claim 3)

[0974] The system according to claim 1, further comprising means for sending the generated response draft to the person in charge and for automatically sending the final response to the user based on the person in charge's evaluation. [Explanation of Symbols]

[0975] 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 means of receiving information input from a user and analyzing the key points of the information using natural language processing, A means for automatically collecting relevant technical documents from external data sources and internal record bases based on the analyzed key points, A means of constructing a virtual simulation under specific environmental conditions and performing related work verification, A method for generating proposed answers using artificial intelligence based on collected materials and the results of work verification, In order to provide the generated draft answers, there is a means by which experts can check the content and make final changes, A means of quickly providing users with the optimal solution in real time through an application installed on a smart device, A system that includes this.

2. The system according to claim 1, further comprising means for extracting specific error information related to information from the user and generating a prompt message to provide a solution.

3. The system according to claim 1, further comprising means for sending generated draft answers to experts and automatically sending a final answer to a user device based on the experts' review results.

Images