system

Abstract

We provide the system. [Solution] A means by which an information processing device automatically analyzes the content of an inquiry using an artificial intelligence model that is generated, A means of searching and retrieving past related cases from a data repository based on the analyzed content, A means of generating solutions based on acquired cases and inquiry content, A means by which the operating device performs actions to resolve the problem based on the generated solution, A means of providing feedback on the results of the actions taken and re-evaluating the solution as needed, A means of providing application software that allows users to report problem situations and receive immediate support from artificial intelligence, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] With the progress of information technology, there is a demand for improving the efficiency of inquiry response and incident response in system operation. However, these operations depend on referring to a vast amount of past knowledge and require personal judgment, making automation difficult. Also, in situations where 24 / 7 / 365 response is required, quick and accurate response is demanded, but it has been difficult to achieve this with conventional methods. By solving these problems, it is necessary to reduce the burden on system operators and realize efficient operation.

Means for Solving the Problems

[0005] This invention provides a mechanism that automatically analyzes inquiry content using a generated artificial intelligence model and searches and retrieves relevant past cases from a database. This mechanism generates solutions based on the analysis results and retrieved cases, and then a work device executes these solutions to resolve the problem. The execution results are fed back, and the solutions are re-evaluated as needed. Through this process, final confirmation and correction are performed using a user interface. This automated method enables system operation that allows for rapid and accurate responses without relying on human judgment.

[0006] "Generating artificial intelligence models" refers to algorithms and their implementations that analyze new inquiries based on past data and generate solutions.

[0007] An "information processing device" refers to a combination of hardware and software used to receive queries, perform analysis, and retrieve data from databases.

[0008] "Inquiry details" refers to information including questions and problem reports from users regarding the system.

[0009] A "database" refers to an information system that stores past related cases and knowledge in a searchable format.

[0010] "Solution" refers to the specific steps or actions for resolving the problem generated based on the analyzed inquiry content and related cases.

[0011] "Working equipment" refers to devices and software used to perform physical or logical operations based on the generated solution.

[0012] "User interface" refers to the means of interaction and screen display that users use to communicate with a system.

[0013] "Feedback" refers to information used to re-evaluate the results of implementing a solution by returning them to the system.

[0014] A "knowledge database" refers to a system for accumulating past cases and troubleshooting procedures that can be used as references to resolve inquiries. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Modes for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the language used in the following description will be explained.

[0018] In the following embodiments, a processor with a reference number (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.

[0019] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention automates inquiry handling in system operations using a generated artificial intelligence model. This system activates an artificial intelligence model, which functions as an agent, simultaneously with the information processing device receiving an inquiry.

[0037] Specifically, the system analyzes the content of the query received by the server and searches the knowledge database for past related cases based on that content. This allows for the rapid retrieval of past solutions to similar problems.

[0038] Next, the server generates the optimal solution based on the analyzed data and acquired cases. This solution includes detailed execution steps and recommended actions, and the generated solution is sent to the terminal.

[0039] The terminal initiates action based on the solution sent from the server. This may include system reconfiguration, process restart, or access to external resources. Once the action is complete, the terminal feeds the results back to the server.

[0040] Through this series of processes, users can propose solutions, verify the results, and, if necessary, modify the results and suggest improvements. Furthermore, information on resolved problems is registered in the database as new knowledge, contributing to the rapid resolution of future inquiries.

[0041] For example, if a user reports slow response times to a web service at night, the server analyzes system metrics and searches for relevant past cases. Based on this information, the server deduces that a memory leak is the cause and generates a solution recommending memory clearing and terminating unnecessary processes. The user can then quickly resolve the issue by executing this solution and feeding the results back to the server.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server receives the query and analyzes its contents. This analysis uses natural language processing techniques to identify the query's category and keywords, thereby pinpointing the general scope of the problem.

[0045] Step 2:

[0046] Based on the analysis results, the server searches the knowledge database for relevant past cases. Here, past cases are efficiently filtered based on identified keywords and categories.

[0047] Step 3:

[0048] The server generates a list of suitable solutions from the search results. This involves referring to solutions derived from past cases and listing the steps that are most appropriate for the current problem.

[0049] Step 4:

[0050] The terminal receives a proposed solution from the server and determines whether it is executable. This determination is made by checking the status of system resources and execution permissions.

[0051] Step 5:

[0052] The terminal will take action to resolve the problem based on the solutions it determines are feasible. Examples include adjusting system settings or restarting processes.

[0053] Step 6:

[0054] The terminal logs the execution results and feeds them back to the server. The feedback includes whether the execution was successful or not, whether any errors occurred, and the execution time.

[0055] Step 7:

[0056] The user reviews the feedback from the server and evaluates the validity of the final solution. If necessary, additional manual adjustments are made to complete the problem resolution.

[0057] Step 8:

[0058] Users register resolved cases in the knowledge database, adding new knowledge to prepare for future inquiries. The registration process is carried out after reviewing the content and standardizing the format.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] This invention relates to an automated system for improving the efficiency and accuracy of inquiry handling processes. In particular, it aims to quickly and accurately perform a series of processes from analyzing inquiry content to providing, executing, and providing feedback on the optimal solution. By solving this problem, users will be able to resolve issues quickly and improve operational efficiency.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for automatically analyzing the content of a query, means for searching and retrieving past related cases from a knowledge database, and means for rapidly retrieving related cases using a high-speed search algorithm. This makes it possible to construct and execute the optimal solution to the query.

[0064] A "generating artificial intelligence model" is a collection of artificially constructed knowledge and learning algorithms used to analyze inquiries and generate appropriate solutions.

[0065] An "information processing device" refers to any computer system used to receive and analyze queries, and includes data processing and storage functions.

[0066] A "database" is a collection of data in which past cases and solutions are systematically stored and made searchable.

[0067] A "working device" is a physical or logical device that executes solutions and takes action to resolve a problem based on instructions from a server.

[0068] "Feedback" refers to the information obtained by returning the results of an action to an information processing device, which is then used for further analysis and improvement.

[0069] A "user interface" refers to an interactive display screen or input method that allows a user to interact with a system and to input feedback and make corrections.

[0070] "Knowledge data" is a systematic collection of knowledge that stores information about problems that have been solved and the countermeasures taken to address them.

[0071] A "high-speed search algorithm" is a computational method for quickly searching for information within a database and efficiently obtaining highly relevant results.

[0072] This invention is a system designed to streamline the inquiry handling process. It utilizes a generative AI model to automatically analyze inquiries and generate optimal solutions. The system's hardware includes a standard server computer and terminals used for user access. The software combines natural language processing software with a high-speed search algorithm. When an inquiry comes in from a user, the server analyzes its content and searches for relevant knowledge data in the database. Based on the retrieved data, the server uses the generative AI model to construct a specific solution and sends it to the terminal. The terminal automatically takes actionable steps based on the received solution. For example, if the server's response speed slows down, the system can identify the cause from the inquiry and suggest recommended actions.

[0073] As a concrete example, suppose there is an inquiry about slow response times for a web service during the night. In this case, the server analyzes system metrics and infers that the cause is a memory leak. Based on this, the server generates a solution recommending memory clearing and stopping unnecessary processes. This solution is sent to the terminal, which takes action and feeds the results back to the server.

[0074] An example of a prompt message is, "Please provide recommended solutions for the slowdown in web service response speed at night." This invention significantly reduces the time from inquiry to the provision of a solution, thereby improving operational efficiency.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server receives a query from the user. In this step, the query content becomes the input data, and the server logs this data and stores it in a queue for analysis.

[0078] Step 2:

[0079] The server uses natural language processing software to analyze the query. This process takes the received text data as input, performs grammatical analysis and key phrase extraction, and outputs the query's subject and intent. This output data is then used for database searches in the next step.

[0080] Step 3:

[0081] The server uses a high-speed search algorithm based on the analysis results to search for relevant cases in the knowledge database. The input for this step is the analyzed query content, and it searches for past solutions and cases, outputting relevant information. This output is prepared for use in building solutions with a generative AI model.

[0082] Step 4:

[0083] The server uses a generated AI model to construct the optimal solution based on the acquired case examples. The input consists of past related cases and the current inquiry content, and by combining these, it outputs a solution that includes specific resolution steps and recommended actions.

[0084] Step 5:

[0085] The server sends the generated solution to the terminal. The input is a solution constructed on the server side, which is sent to the terminal and output in preparation for presentation to the user or automated execution.

[0086] Step 6:

[0087] The terminal performs executable actions based on the solution received from the server. The input is the solution instructions, and based on that, it executes specific commands, adjusts system settings, etc., and obtains the result as output.

[0088] Step 7:

[0089] The terminal feeds back the results of the actions it has performed to the server. In this step, the success / failure status of the action and detailed log information are used as input, and this information is sent back to the server as output.

[0090] Step 8:

[0091] Users can review the feedback received and, if necessary, propose corrections to the server. The feedback serves as input, and the user's judgment leads to the output of proposed corrections and improvements, which are then used in the next process.

[0092] (Application Example 1)

[0093] 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."

[0094] Many users face technical problems when using electronic payment services, but there is a lack of means to respond quickly and efficiently to these issues. Such problems can lead to a poor user experience and system operational stagnation. Traditional inquiry handling requires operator intervention and can be time-consuming; therefore, there is a need for a system that can automatically analyze problems and derive optimal solutions while maintaining convenience.

[0095] 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.

[0096] In this invention, the server includes means for automatically analyzing the content of an inquiry using an artificial intelligence model that is generated, means for searching for and retrieving relevant past cases from a data repository based on the analyzed content, and means for generating a solution based on the retrieved cases and the content of the inquiry. This makes it possible to quickly and accurately present a solution to an inquiry and improve user convenience.

[0097] A "generating artificial intelligence model" is a system equipped with a learning algorithm used to analyze inquiry content and automatically derive appropriate solutions.

[0098] An "information processing device" is an electronic device that can receive, analyze, and process data.

[0099] A "data repository" is an information storage system that stores past cases and related information, and allows for searching and retrieving them as needed.

[0100] An "operational device" is a system that executes specific tasks and actions to solve a problem based on the generated solution.

[0101] "Feedback" is the process of analyzing the results of an action taken and returning that information to the entire system.

[0102] A "user" is an individual or legal entity that uses an electronic payment service and requests technical support.

[0103] "Application software" refers to a program designed to allow users to report technical problems and receive rapid support from artificial intelligence.

[0104] The system for carrying out this invention is configured based on a server, a terminal, and user operations.

[0105] The server automatically analyzes user inquiries using an artificial intelligence model it generates. This analysis process utilizes Python's natural language processing (NLP) library. Once the inquiry is analyzed, the server accesses a data repository to search for and retrieve relevant past cases. This data repository is built as an SQL database. Next, the server uses TENSORFLOW® to generate the optimal solution based on the retrieved cases and the inquiry.

[0106] The terminal receives the solution sent from the server and executes the action to resolve the problem on the operating device. The result of the action is then fed back to the server. This entire process uses a RESTful API, enabling smooth data communication.

[0107] Users can report problems related to electronic payment services using devices such as smartphones and receive immediate solutions from AI models. In particular, the smartphone application software features an intuitive user interface, providing a system that allows users to easily make inquiries and implement solutions.

[0108] For example, if a user reports a problem where "payment was completed but not correctly displayed in the app," the generating AI model will suggest clearing the app's data cache based on similar past cases. The following prompt can be used as an example: "Please provide the best solution to resolve the issue that occurred with the electronic payment. Specifically, what should be done if the user has not received a payment completion notification?"

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] Users report problems with electronic payment services using their devices. The problem details entered by the user are sent to the server via the smartphone's application software. Here, the user inputs the problem as text information through the user interface.

[0112] Step 2:

[0113] The server analyzes the received query using natural language processing (NLP). It analyzes the input text data using NLP techniques to extract problem categories and keywords. This process identifies the specific problem, and the necessary information is set as search criteria for the data repository.

[0114] Step 3:

[0115] Based on the analyzed query, the server searches and retrieves relevant past cases from the data repository. Using SQL queries, it becomes possible to extract relevant cases from the database and obtain historical information useful for problem solving.

[0116] Step 4:

[0117] The server generates the optimal solution using a generative AI model based on acquired past cases and inquiry content. Using TensorFlow, it performs inference based on input data (acquired cases and analyzed content) and outputs a solution to the problem.

[0118] Step 5:

[0119] The server sends the generated solution to the terminal. The terminal receives the solution and displays it to the user. The user takes action to resolve the problem based on the displayed solution.

[0120] Step 6:

[0121] The terminal feeds back the results of actions performed by the user to the server. The execution results are sent to the server, which evaluates them and determines the effectiveness of the solution.

[0122] Step 7:

[0123] Based on the feedback received, the server re-evaluates the solution as needed and updates the problem resolution information in the data repository. This process analyzes the feedback data and updates the knowledge base with new solutions to help handle future inquiries.

[0124] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0125] This invention automates inquiry handling in system operations using a generated artificial intelligence model and an emotion engine that recognizes user emotions. In this system, when an information processing device receives an inquiry, the artificial intelligence model is automatically activated as an agent, and the emotion engine analyzes the user's emotions.

[0126] Specifically, when the server analyzes the content of an inquiry it receives, it simultaneously acquires the user's emotional information using an emotional engine. This emotional information is used to estimate the urgency of the inquiry and the user's stress level, and is considered an important factor in the analysis.

[0127] Next, the server generates the optimal solution by searching the knowledge database for relevant past cases based on the analysis results and sentiment information. The generated solution takes the user's emotional state into consideration, and adjustments are made to its content and expression. This solution is sent to the terminal, and the corresponding action is initiated.

[0128] Rapid troubleshooting is possible by having the device perform problem-solving actions based on solutions sent from the server. After the actions are completed, the device feeds the results back to the server, and the solutions are re-evaluated and adjusted as needed using the results and sentiment information.

[0129] For example, if a user expresses frustration with support, the server picks up on that emotion and prioritizes searching the database for past cases of rapid response. Based on this information, the server generates a rapid response plan and triggers an action on the terminal. This process ensures that the user receives a quick and appropriate response, resulting in emotionally caring support.

[0130] The system incorporating the emotion engine of the present invention can provide responses that contribute to the user's psychological stability, in addition to resolving issues through physical actions, thereby further improving the efficiency and quality of system operation.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The server receives inquiries from users and analyzes the content of those inquiries using natural language processing techniques. This analysis includes keyword extraction and contextual understanding.

[0134] Step 2:

[0135] The server activates the emotion engine along with the analyzed data to evaluate the user's emotional state. The emotion engine infers the user's current emotion (e.g., anger, confusion, frustration) from the tone of voice and the expression of the input text.

[0136] Step 3:

[0137] Based on the analysis results and emotional state, the server searches the knowledge database for relevant past cases. If the situation is deemed particularly urgent or emotionally burdensome, it prioritizes extracting cases that required immediate resolution.

[0138] Step 4:

[0139] The server generates solutions that take emotional information into account. If the user is feeling stressed, the solutions will be expressed in a gentler tone and with simpler instructions.

[0140] Step 5:

[0141] The terminal receives the solution sent from the server and makes final adjustments based on the situation before execution. Additional confirmations to the user are requested as needed.

[0142] Step 6:

[0143] The device will take specific actions based on the solution. This may include changing settings, restarting system processes, or sending instructional emails to the user.

[0144] Step 7:

[0145] The terminal records the results of the actions it performs and feeds the result log back to the server. This includes records of the problem resolution status and any anomalies that occurred during execution.

[0146] Step 8:

[0147] The server re-evaluates the effectiveness of solutions based on feedback information and sentiment data, and makes further adjustments or suggestions as needed. By utilizing the sentiment engine's input in this re-evaluation, user satisfaction and trust are maintained.

[0148] Step 9:

[0149] Users receive feedback from the system and confirm the final results. If necessary, they can register the case in the knowledge database to prepare for future use.

[0150] (Example 2)

[0151] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0152] Traditional customer support systems have a problem in that they do not take into account the user's emotions, resulting in an inability to provide prompt and accurate support and to sufficiently increase user satisfaction. In particular, by responding without understanding the user's emotional state, it becomes difficult to provide appropriate support to users who are feeling stressed.

[0153] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0154] In this invention, the server includes means for an information processing device to automatically analyze the content of an inquiry using a generated artificial intelligence model and sentiment analysis means, and to acquire the user's sentiment information; means for searching and acquiring past relevant cases from a database based on the analyzed content and acquired sentiment information; and means for generating a solution based on the acquired cases, inquiry content and sentiment information, and adjusting the content according to the user's emotional state. This enables prompt and accurate support that takes the user's emotions into consideration.

[0155] A "generated artificial intelligence model" is a program that operates using machine learning algorithms to automate tasks such as analyzing inquiries and suggesting solutions.

[0156] "Emotion analysis means" refers to technology that estimates and analyzes emotions in real time from a user's text or voice.

[0157] An "information processing device" is a computer that receives inquiries and analyzes their content and related data.

[0158] "User sentiment information" refers to data that captures the emotional responses and states obtained from user statements and inputs.

[0159] A "database" is a collection of data in which information such as past cases and solutions is systematically stored.

[0160] A "solution" is a specific plan or procedure that presents appropriate methods or actions in response to an inquiry.

[0161] A "working device" is something that performs physical or logical actions based on the generated solution.

[0162] "Feedback" refers to information used to evaluate the results of actions taken and to incorporate them into system improvements.

[0163] A "user interface" refers to the operating screen or means of interaction that enables the exchange of information between a system and a user.

[0164] One embodiment of this invention is a system that combines an artificial intelligence model and emotion analysis technology to enable a rapid and emotion-sensitive response to user inquiries. Specific embodiments are described below.

[0165] The server receives inquiries from users and performs analysis as needed. This analysis utilizes a generative AI model to understand the content of the inquiries. The system also employs software for sentiment analysis. This software analyzes user messages in real time and measures their emotional state. This technology uses natural language processing and machine learning algorithms, and specifically, it can utilize programming languages ​​and libraries such as Python and TensorFlow.

[0166] The server uses the emotional information and query content obtained to search the database for relevant past cases. Based on the results, it uses a generative AI model to generate the optimal solution. This solution is adjusted based on the emotional information; for example, if the user is angry, more careful wording and expressions will be chosen.

[0167] The generated solution is sent to the device, and actions to resolve the problem are taken according to the instructions. These actions include displaying specific troubleshooting steps to the user and automatically adjusting system settings.

[0168] After execution, the terminal feeds the results back to the server. This feedback includes the success rate of the executed action and changes in the user's emotions, and is used for re-evaluation and adjustment of solutions as needed.

[0169] For example, if a user makes an inquiry such as "My internet connection is slow," the system will analyze that the inquiry contains anxieties. In this case, the server will find a prompt message in the database such as "Please quickly find out specific ways to improve your internet connection speed" and then provide the optimal steps.

[0170] An example of a prompt message in such a system might be, "If the user expresses dissatisfaction with an order issue, please promptly provide a solution based on past handling cases." This invention can improve the efficiency of information processing and enhance user satisfaction.

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] The user enters a support inquiry into the system. This input includes a specific question or a description of the problem. The server receives the inquiry and prepares to analyze the data. The input data is text, which forms the basis for subsequent analysis.

[0174] Step 2:

[0175] The server activates a generative AI model to analyze the received query text. This model uses natural language processing techniques to understand the query and extract relevant information. In this process, text data is input, and analyzed data is output. This analyzed data includes important information such as the subject and urgency of the query.

[0176] Step 3:

[0177] The server utilizes sentiment analysis techniques to estimate the user's emotions from the inquiry text. This process takes text data as input and outputs emotional information. Sentiment analysis is crucial for determining the user's stress and anxiety levels, and emotion recognition algorithms are used for data processing.

[0178] Step 4:

[0179] The server uses the analyzed data and sentiment information to access the knowledge database and search for relevant past cases. The action taken at this stage is the execution of a database query. The input is the analyzed query data and sentiment information, and the output is a list of relevant past cases.

[0180] Step 5:

[0181] The server generates the optimal solution based on the obtained case studies and emotional information. In this process, the generative AI model is utilized again, and the solution is adjusted to take the user's emotional state into consideration. The input is past case studies and emotional information. The output is the adjusted solution.

[0182] Step 6:

[0183] The terminal receives a solution sent from the server and performs problem-solving actions based on the instructions. Specific actions include displaying instructions to the user and adjusting settings. The input is the solution, and the output is the result of the execution and notifications to the user.

[0184] Step 7:

[0185] The terminal feeds the execution results back to the server. This feedback includes the success rate of the action and whether any additional problems were encountered. The input is the action result, and the output is the server's re-evaluation of the data and suggestions for improvement.

[0186] (Application Example 2)

[0187] 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".

[0188] In recent years, as customer service automation has advanced, there has been a growing need for appropriate responses that take user emotions into consideration. However, conventional systems have struggled to adequately reflect users' emotional states, sometimes leading to user dissatisfaction and problems due to inappropriate responses. Furthermore, dynamic adjustments based on emotional states have not been sufficiently implemented in security. This invention aims to improve service quality by analyzing user emotions in real time and adjusting inquiry responses and security settings accordingly.

[0189] 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.

[0190] In this invention, the server includes means for analyzing information using a generated artificial intelligence model, means for acquiring cases based on the analysis results and emotional information, means for generating emotionally sensitive solutions, and means for monitoring the user's emotional state and adjusting security settings. This enables rapid and appropriate responses to inquiries and dynamic adjustment of security in accordance with the user's emotions.

[0191] An "artificial intelligence model" is a program or algorithm that uses a computer to mimic human intelligent behavior and automatically analyze the content of inquiries.

[0192] An "information processing device" is an electronic device that analyzes the content of an inquiry and generates a solution based on that analysis.

[0193] "Analysis" is the process by which an information processing device breaks down the content of an inquiry and the user's emotional information, and converts them into an understandable format.

[0194] "Emotional information" refers to data that indicates a user's emotional state and is used to understand the user's urgency and stress levels.

[0195] A "data bank" is an information aggregation system that stores and manages past cases and sentiment information related to inquiries.

[0196] A "solution" refers to specific methods or actions provided to resolve a user's problem based on the analyzed inquiry content and sentiment information.

[0197] A "working device" is a device or system used to carry out actual problem-solving actions based on the generated solution.

[0198] "Feedback" refers to information that is returned to an information processing device to evaluate or adjust the results of an action that has been performed.

[0199] "Monitoring" is the process of continuously monitoring the user's emotional state and adjusting responses in real time as needed.

[0200] "Security settings" refer to the defensive measures and strategies configured to maintain the security of a system, and they are dynamically adjustable.

[0201] One embodiment of this invention is a system that automates and optimizes user inquiry handling and security management by combining a generated artificial intelligence model with an emotion engine. When an inquiry is received, the server analyzes its content using the artificial intelligence model and simultaneously obtains the user's emotional information using the emotion engine. This makes it possible to evaluate the user's urgency and stress level.

[0202] The information processing device searches for relevant cases from a database based on the analyzed content and emotional information, and generates the optimal solution. This solution is adjusted to suit the user's emotional state and executed by the work device. The execution results are fed back, and the solution is re-evaluated as needed. Furthermore, security settings are dynamically adjusted based on the user's emotional state.

[0203] For example, if a user expresses frustration, the server senses that emotion and prioritizes searching for past examples of quick responses. Based on this, a solution is quickly proposed, and the work device implements the response quickly and effectively.

[0204] The hardware used includes network-enabled information processing devices and servers, while the software includes an emotion engine API and security modules. The present invention allows for specific configuration of operation using prompt statements such as, "Please tell me how to implement an application that uses the emotion engine API to acquire the current emotional state and enhances security features if stress or anxiety is detected."

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The server receives inquiries from users. The inquiry content, as input, is sent to a generating AI model for analysis. In this process, the server extracts the subject and keywords of the inquiry through text analysis. Structured data of the inquiry content is obtained as output.

[0208] Step 2:

[0209] The server uses an emotion engine in conjunction with the obtained structured data to acquire user emotion information. The input is communication data such as user text or voice, and analysis outputs an emotional state (e.g., stress, exhilaration, calmness). This data is used to determine the urgency and tone of the inquiry.

[0210] Step 3:

[0211] The server searches a database for relevant past cases based on the query content and sentiment information. The input consists of structured data and sentiment states, which are used to filter relevant cases within the database. The output is the optimal set of cases.

[0212] Step 4:

[0213] The server generates user-sensitive solutions based on relevant case studies. The input consists of relevant case studies and sentiment data, which an artificial intelligence model analyzes to create appropriate solutions. The output is a customized solution.

[0214] Step 5:

[0215] Based on the solution sent to the terminal, the work device performs problem-solving actions. The input is the solution sent from the server, which the terminal uses to create specific operational commands. The output is the execution of the problem-solving actions and their results.

[0216] Step 6:

[0217] The terminal provides feedback to the server regarding the results of the actions performed. The input is the result of the action, and the terminal provides this information to the server for evaluation of areas for improvement and the need for additional action. The output is a feedback report.

[0218] Step 7:

[0219] The server re-evaluates the solution as needed and modifies the settings based on new sentiment information. The input is a feedback report, which the server analyzes to generate an improved solution again. The output is the re-evaluated solution.

[0220] Step 8:

[0221] The server adjusts security settings as needed based on the user's emotional state. Inputs are emotional information and execution results, and the security strength is reset through data calculations. The output is the adjusted security settings.

[0222] 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.

[0223] Data generation model 58 is a type of 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.

[0224] 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.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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".

[0238] This invention automates inquiry handling in system operations using a generated artificial intelligence model. This system activates an artificial intelligence model, which functions as an agent, simultaneously with the information processing device receiving an inquiry.

[0239] Specifically, the system analyzes the content of the query received by the server and searches the knowledge database for past related cases based on that content. This allows for the rapid retrieval of past solutions to similar problems.

[0240] Next, the server generates the optimal solution based on the analyzed data and acquired cases. This solution includes detailed execution steps and recommended actions, and the generated solution is sent to the terminal.

[0241] The terminal initiates action based on the solution sent from the server. This may include system reconfiguration, process restart, or access to external resources. Once the action is complete, the terminal feeds the results back to the server.

[0242] Through this series of processes, users can propose solutions, verify the results, and, if necessary, modify the results and suggest improvements. Furthermore, information on resolved problems is registered in the database as new knowledge, contributing to the rapid resolution of future inquiries.

[0243] For example, if a user reports slow response times to a web service at night, the server analyzes system metrics and searches for relevant past cases. Based on this information, the server deduces that a memory leak is the cause and generates a solution recommending memory clearing and terminating unnecessary processes. The user can then quickly resolve the issue by executing this solution and feeding the results back to the server.

[0244] The following describes the processing flow.

[0245] Step 1:

[0246] The server receives the query and analyzes its contents. This analysis uses natural language processing techniques to identify the query's category and keywords, thereby pinpointing the general scope of the problem.

[0247] Step 2:

[0248] Based on the analysis results, the server searches the knowledge database for relevant past cases. Here, past cases are efficiently filtered based on identified keywords and categories.

[0249] Step 3:

[0250] The server generates a list of suitable solutions from the search results. This involves referring to solutions derived from past cases and listing the steps that are most appropriate for the current problem.

[0251] Step 4:

[0252] The terminal receives a proposed solution from the server and determines whether it is executable. This determination is made by checking the status of system resources and execution permissions.

[0253] Step 5:

[0254] The terminal will take action to resolve the problem based on the solutions it determines are feasible. Examples include adjusting system settings or restarting processes.

[0255] Step 6:

[0256] The terminal logs the execution results and feeds them back to the server. The feedback includes whether the execution was successful or not, whether any errors occurred, and the execution time.

[0257] Step 7:

[0258] The user reviews the feedback from the server and evaluates the validity of the final solution. If necessary, additional manual adjustments are made to complete the problem resolution.

[0259] Step 8:

[0260] Users register resolved cases in the knowledge database, adding new knowledge to prepare for future inquiries. The registration process is carried out after reviewing the content and standardizing the format.

[0261] (Example 1)

[0262] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0263] This invention relates to an automated system for improving the efficiency and accuracy of inquiry handling processes. In particular, it aims to quickly and accurately perform a series of processes from analyzing inquiry content to providing, executing, and providing feedback on the optimal solution. By solving this problem, users will be able to resolve issues quickly and improve operational efficiency.

[0264] 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.

[0265] In this invention, the server includes means for automatically analyzing the content of a query, means for searching and retrieving past related cases from a knowledge database, and means for rapidly retrieving related cases using a high-speed search algorithm. This makes it possible to construct and execute the optimal solution to the query.

[0266] A "generating artificial intelligence model" is a collection of artificially constructed knowledge and learning algorithms used to analyze inquiries and generate appropriate solutions.

[0267] An "information processing device" refers to any computer system used to receive and analyze queries, and includes data processing and storage functions.

[0268] A "database" is a collection of data in which past cases and solutions are systematically stored and made searchable.

[0269] A "working device" is a physical or logical device that executes solutions and takes action to resolve a problem based on instructions from a server.

[0270] "Feedback" refers to the information obtained by returning the results of an action to an information processing device, which is then used for further analysis and improvement.

[0271] A "user interface" refers to an interactive display screen or input method that allows a user to interact with a system and to input feedback and make corrections.

[0272] "Knowledge data" is a systematic collection of knowledge that stores information about problems that have been solved and the countermeasures taken to address them.

[0273] A "high-speed search algorithm" is a computational method for quickly searching for information within a database and efficiently obtaining highly relevant results.

[0274] This invention is a system designed to streamline the inquiry handling process. It utilizes a generative AI model to automatically analyze inquiries and generate optimal solutions. The system's hardware includes a standard server computer and terminals used for user access. The software combines natural language processing software with a high-speed search algorithm. When an inquiry comes in from a user, the server analyzes its content and searches for relevant knowledge data in the database. Based on the retrieved data, the server uses the generative AI model to construct a specific solution and sends it to the terminal. The terminal automatically takes actionable steps based on the received solution. For example, if the server's response speed slows down, the system can identify the cause from the inquiry and suggest recommended actions.

[0275] As a concrete example, suppose there is an inquiry about slow response times for a web service during the night. In this case, the server analyzes system metrics and infers that the cause is a memory leak. Based on this, the server generates a solution recommending memory clearing and stopping unnecessary processes. This solution is sent to the terminal, which takes action and feeds the results back to the server.

[0276] An example of a prompt message is, "Please provide recommended solutions for the slowdown in web service response speed at night." This invention significantly reduces the time from inquiry to the provision of a solution, thereby improving operational efficiency.

[0277] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0278] Step 1:

[0279] The server receives a query from the user. In this step, the query content becomes the input data, and the server logs this data and stores it in a queue for analysis.

[0280] Step 2:

[0281] The server uses natural language processing software to analyze the query. This process takes the received text data as input, performs grammatical analysis and key phrase extraction, and outputs the query's subject and intent. This output data is then used for database searches in the next step.

[0282] Step 3:

[0283] The server searches for relevant cases in the knowledge database using a fast search algorithm based on the analysis results. The input for this step is the analyzed query content, which searches for past solutions and cases and outputs relevant information. This output is prepared for use in constructing solutions by the generative AI model.

[0284] Step 4:

[0285] The server constructs an optimal solution using the generative AI model based on the obtained cases. The input is the past relevant cases and the current query content, and these are combined to output a solution including specific solution procedures and recommended actions.

[0286] Step 5:

[0287] The server sends the generated solution to the terminal. The input is the solution constructed on the server side, which is sent to the terminal and output for presentation to the user or preparation for automatic execution.

[0288] Step 6:

[0289] The terminal performs executable actions based on the solution received from the server. The input is the instruction of the solution, and based on it, specific commands are executed or system settings are adjusted, and the result is obtained as the output.

[0290] Step 7:

[0291] The terminal feeds back the result of the executed action to the server. In this step, the status of success or failure of the action and detailed log information are used as the input, and this is sent back to the server and output.

[0292] Step 8:

[0293] Users can review the feedback received and, if necessary, propose corrections to the server. The feedback serves as input, and the user's judgment leads to the output of proposed corrections and improvements, which are then used in the next process.

[0294] (Application Example 1)

[0295] 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."

[0296] Many users face technical problems when using electronic payment services, but there is a lack of means to respond quickly and efficiently to these issues. Such problems can lead to a poor user experience and system operational stagnation. Traditional inquiry handling requires operator intervention and can be time-consuming; therefore, there is a need for a system that can automatically analyze problems and derive optimal solutions while maintaining convenience.

[0297] 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.

[0298] In this invention, the server includes means for automatically analyzing the content of an inquiry using an artificial intelligence model that is generated, means for searching for and retrieving relevant past cases from a data repository based on the analyzed content, and means for generating a solution based on the retrieved cases and the content of the inquiry. This makes it possible to quickly and accurately present a solution to an inquiry and improve user convenience.

[0299] A "generating artificial intelligence model" is a system equipped with a learning algorithm used to analyze inquiry content and automatically derive appropriate solutions.

[0300] An "information processing device" is an electronic device that can receive, analyze, and process data.

[0301] A "data repository" is an information storage that saves past cases and related information and retrieves and acquires them as needed.

[0302] An "operation device" is a system that executes specific operations and actions for problem-solving based on the generated solutions.

[0303] "Feedback" is a process that analyzes the results of executed actions and returns that information to the entire system.

[0304] A "user" is an individual or corporation that uses an electronic payment service and requests technical support.

[0305] "Application software" is a program designed for users to report technical problems and receive prompt support from artificial intelligence.

[0306] The system for implementing this invention is configured based on the operations of a server, a terminal, and a user.

[0307] The server automatically analyzes the content of inquiries from users using the artificial intelligence model it generates. This analysis process is carried out by leveraging the natural language processing (NLP) library of Python. Once the content of the inquiry is analyzed, the server accesses the data repository to search for and acquire past related cases. This data repository is constructed as a SQL database. Next, the server generates an optimal solution using TensorFlow based on the acquired cases and the content of the inquiry.

[0308] The terminal receives the solution sent from the server and executes actions for problem-solving on the operation device. The results of the actions are fed back to the server again. This series of processes uses a RESTful API, enabling smooth data communication.

[0309] Users can report problems related to electronic payment services using devices such as smartphones and receive immediate solutions from AI models. In particular, the smartphone application software features an intuitive user interface, providing a system that allows users to easily make inquiries and implement solutions.

[0310] For example, if a user reports a problem where "payment was completed but not correctly displayed in the app," the generating AI model will suggest clearing the app's data cache based on similar past cases. The following prompt can be used as an example: "Please provide the best solution to resolve the issue that occurred with the electronic payment. Specifically, what should be done if the user has not received a payment completion notification?"

[0311] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0312] Step 1:

[0313] Users report problems with electronic payment services using their devices. The problem details entered by the user are sent to the server via the smartphone's application software. Here, the user inputs the problem as text information through the user interface.

[0314] Step 2:

[0315] The server analyzes the received query using natural language processing (NLP). It analyzes the input text data using NLP techniques to extract problem categories and keywords. This process identifies the specific problem, and the necessary information is set as search criteria for the data repository.

[0316] Step 3:

[0317] Based on the analyzed query, the server searches and retrieves relevant past cases from the data repository. Using SQL queries, it becomes possible to extract relevant cases from the database and obtain historical information useful for problem solving.

[0318] Step 4:

[0319] The server generates the optimal solution using a generative AI model based on acquired past cases and inquiry content. Using TensorFlow, it performs inference based on input data (acquired cases and analyzed content) and outputs a solution to the problem.

[0320] Step 5:

[0321] The server sends the generated solution to the terminal. The terminal receives the solution and displays it to the user. The user takes action to resolve the problem based on the displayed solution.

[0322] Step 6:

[0323] The terminal feeds back the results of actions performed by the user to the server. The execution results are sent to the server, which evaluates them and determines the effectiveness of the solution.

[0324] Step 7:

[0325] Based on the feedback received, the server re-evaluates the solution as needed and updates the problem resolution information in the data repository. This process analyzes the feedback data and updates the knowledge base with new solutions to help handle future inquiries.

[0326] 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.

[0327] This invention automates inquiry handling in system operations using a generated artificial intelligence model and an emotion engine that recognizes user emotions. In this system, when an information processing device receives an inquiry, the artificial intelligence model is automatically activated as an agent, and the emotion engine analyzes the user's emotions.

[0328] Specifically, when the server analyzes the content of an inquiry it receives, it simultaneously acquires the user's emotional information using an emotional engine. This emotional information is used to estimate the urgency of the inquiry and the user's stress level, and is considered an important factor in the analysis.

[0329] Next, the server generates the optimal solution by searching the knowledge database for relevant past cases based on the analysis results and sentiment information. The generated solution takes the user's emotional state into consideration, and adjustments are made to its content and expression. This solution is sent to the terminal, and the corresponding action is initiated.

[0330] Rapid troubleshooting is possible by having the device perform problem-solving actions based on solutions sent from the server. After the actions are completed, the device feeds the results back to the server, and the solutions are re-evaluated and adjusted as needed using the results and sentiment information.

[0331] For example, if a user expresses frustration with support, the server picks up on that emotion and prioritizes searching the database for past cases of rapid response. Based on this information, the server generates a rapid response plan and triggers an action on the terminal. This process ensures that the user receives a quick and appropriate response, resulting in emotionally caring support.

[0332] The system incorporating the emotion engine of the present invention can provide responses that contribute to the user's psychological stability, in addition to resolving issues through physical actions, thereby further improving the efficiency and quality of system operation.

[0333] The following describes the processing flow.

[0334] Step 1:

[0335] The server receives inquiries from users and analyzes the content of those inquiries using natural language processing techniques. This analysis includes keyword extraction and contextual understanding.

[0336] Step 2:

[0337] The server activates the emotion engine along with the analyzed data to evaluate the user's emotional state. The emotion engine infers the user's current emotion (e.g., anger, confusion, frustration) from the tone of voice and the expression of the input text.

[0338] Step 3:

[0339] Based on the analysis results and emotional state, the server searches the knowledge database for relevant past cases. If the situation is deemed particularly urgent or emotionally burdensome, it prioritizes extracting cases that required immediate resolution.

[0340] Step 4:

[0341] The server generates solutions that take emotional information into account. If the user is feeling stressed, the solutions will be expressed in a gentler tone and with simpler instructions.

[0342] Step 5:

[0343] The terminal receives the solution sent from the server and makes final adjustments based on the situation before execution. Additional confirmations to the user are requested as needed.

[0344] Step 6:

[0345] The device will take specific actions based on the solution. This may include changing settings, restarting system processes, or sending instructional emails to the user.

[0346] Step 7:

[0347] The terminal records the results of the actions it performs and feeds the result log back to the server. This includes records of the problem resolution status and any anomalies that occurred during execution.

[0348] Step 8:

[0349] The server re-evaluates the effectiveness of solutions based on feedback information and sentiment data, and makes further adjustments or suggestions as needed. By utilizing the sentiment engine's input in this re-evaluation, user satisfaction and trust are maintained.

[0350] Step 9:

[0351] Users receive feedback from the system and confirm the final results. If necessary, they can register the case in the knowledge database to prepare for future use.

[0352] (Example 2)

[0353] 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".

[0354] Traditional customer support systems have a problem in that they do not take into account the user's emotions, resulting in an inability to provide prompt and accurate support and to sufficiently increase user satisfaction. In particular, by responding without understanding the user's emotional state, it becomes difficult to provide appropriate support to users who are feeling stressed.

[0355] 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.

[0356] In this invention, the server includes means for an information processing device to automatically analyze the content of an inquiry using a generated artificial intelligence model and sentiment analysis means, and to acquire the user's sentiment information; means for searching and acquiring past relevant cases from a database based on the analyzed content and acquired sentiment information; and means for generating a solution based on the acquired cases, inquiry content and sentiment information, and adjusting the content according to the user's emotional state. This enables prompt and accurate support that takes the user's emotions into consideration.

[0357] A "generated artificial intelligence model" is a program that operates using machine learning algorithms to automate tasks such as analyzing inquiries and suggesting solutions.

[0358] "Emotion analysis means" refers to technology that estimates and analyzes emotions in real time from a user's text or voice.

[0359] An "information processing device" is a computer that receives inquiries and analyzes their content and related data.

[0360] "User sentiment information" refers to data that captures the emotional responses and states obtained from user statements and inputs.

[0361] A "database" is a collection of data in which information such as past cases and solutions is systematically stored.

[0362] A "solution" is a specific plan or procedure that presents appropriate methods or actions in response to an inquiry.

[0363] A "working device" is something that performs physical or logical actions based on the generated solution.

[0364] "Feedback" refers to information used to evaluate the results of actions taken and to incorporate them into system improvements.

[0365] A "user interface" refers to the operating screen or means of interaction that enables the exchange of information between a system and a user.

[0366] One embodiment of this invention is a system that combines an artificial intelligence model and emotion analysis technology to enable a rapid and emotion-sensitive response to user inquiries. Specific embodiments are described below.

[0367] The server receives inquiries from users and performs analysis as needed. This analysis utilizes a generative AI model to understand the content of the inquiries. The system also employs software for sentiment analysis. This software analyzes user messages in real time and measures their emotional state. This technology uses natural language processing and machine learning algorithms, and specifically, it can utilize programming languages ​​and libraries such as Python and TensorFlow.

[0368] The server uses the emotional information and query content obtained to search the database for relevant past cases. Based on the results, it uses a generative AI model to generate the optimal solution. This solution is adjusted based on the emotional information; for example, if the user is angry, more careful wording and expressions will be chosen.

[0369] The generated solution is sent to the device, and actions to resolve the problem are taken according to the instructions. These actions include displaying specific troubleshooting steps to the user and automatically adjusting system settings.

[0370] After execution, the terminal feeds the results back to the server. This feedback includes the success rate of the executed action and changes in the user's emotions, and is used for re-evaluation and adjustment of solutions as needed.

[0371] For example, if a user makes an inquiry such as "My internet connection is slow," the system will analyze that the inquiry contains anxieties. In this case, the server will find a prompt message in the database such as "Please quickly find out specific ways to improve your internet connection speed" and then provide the optimal steps.

[0372] An example of a prompt message in such a system might be, "If the user expresses dissatisfaction with an order issue, please promptly provide a solution based on past handling cases." This invention can improve the efficiency of information processing and enhance user satisfaction.

[0373] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0374] Step 1:

[0375] The user enters a support inquiry into the system. This input includes a specific question or a description of the problem. The server receives the inquiry and prepares to analyze the data. The input data is text, which forms the basis for subsequent analysis.

[0376] Step 2:

[0377] The server activates a generative AI model to analyze the received query text. This model uses natural language processing techniques to understand the query and extract relevant information. In this process, text data is input, and analyzed data is output. This analyzed data includes important information such as the subject and urgency of the query.

[0378] Step 3:

[0379] The server utilizes sentiment analysis techniques to estimate the user's emotions from the inquiry text. This process takes text data as input and outputs emotional information. Sentiment analysis is crucial for determining the user's stress and anxiety levels, and emotion recognition algorithms are used for data processing.

[0380] Step 4:

[0381] The server uses the analyzed data and sentiment information to access the knowledge database and search for relevant past cases. The action taken at this stage is the execution of a database query. The input is the analyzed query data and sentiment information, and the output is a list of relevant past cases.

[0382] Step 5:

[0383] The server generates the optimal solution based on the obtained case studies and emotional information. In this process, the generative AI model is utilized again, and the solution is adjusted to take the user's emotional state into consideration. The input is past case studies and emotional information. The output is the adjusted solution.

[0384] Step 6:

[0385] The terminal receives a solution sent from the server and performs problem-solving actions based on the instructions. Specific actions include displaying instructions to the user and adjusting settings. The input is the solution, and the output is the result of the execution and notifications to the user.

[0386] Step 7:

[0387] The terminal feeds the execution results back to the server. This feedback includes the success rate of the action and whether any additional problems were encountered. The input is the action result, and the output is the server's re-evaluation of the data and suggestions for improvement.

[0388] (Application Example 2)

[0389] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0390] In recent years, as customer service automation has advanced, there has been a growing need for appropriate responses that take user emotions into consideration. However, conventional systems have struggled to adequately reflect users' emotional states, sometimes leading to user dissatisfaction and problems due to inappropriate responses. Furthermore, dynamic adjustments based on emotional states have not been sufficiently implemented in security. This invention aims to improve service quality by analyzing user emotions in real time and adjusting inquiry responses and security settings accordingly.

[0391] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0392] In this invention, the server includes means for analyzing information using a generated artificial intelligence model, means for acquiring cases based on the analysis results and emotional information, means for generating emotionally sensitive solutions, and means for monitoring the user's emotional state and adjusting security settings. This enables rapid and appropriate responses to inquiries and dynamic adjustment of security in accordance with the user's emotions.

[0393] An "artificial intelligence model" is a program or algorithm that uses a computer to mimic human intelligent behavior and automatically analyze the content of inquiries.

[0394] An "information processing device" is an electronic device that analyzes the content of an inquiry and generates a solution based on that analysis.

[0395] "Analysis" is the process by which an information processing device breaks down the content of an inquiry and the user's emotional information, and converts them into an understandable format.

[0396] "Emotional information" refers to data that indicates a user's emotional state and is used to understand the user's urgency and stress levels.

[0397] A "data bank" is an information aggregation system that stores and manages past cases and sentiment information related to inquiries.

[0398] A "solution" refers to specific methods or actions provided to resolve a user's problem based on the analyzed inquiry content and sentiment information.

[0399] A "working device" is a device or system used to carry out actual problem-solving actions based on the generated solution.

[0400] "Feedback" refers to information that is returned to an information processing device to evaluate or adjust the results of an action that has been performed.

[0401] "Monitoring" is the process of continuously monitoring the user's emotional state and adjusting responses in real time as needed.

[0402] "Security settings" refer to the defensive measures and strategies configured to maintain the security of a system, and they are dynamically adjustable.

[0403] One embodiment of this invention is a system that automates and optimizes user inquiry handling and security management by combining a generated artificial intelligence model with an emotion engine. When an inquiry is received, the server analyzes its content using the artificial intelligence model and simultaneously obtains the user's emotional information using the emotion engine. This makes it possible to evaluate the user's urgency and stress level.

[0404] The information processing device searches for relevant cases from a database based on the analyzed content and emotional information, and generates the optimal solution. This solution is adjusted to suit the user's emotional state and executed by the work device. The execution results are fed back, and the solution is re-evaluated as needed. Furthermore, security settings are dynamically adjusted based on the user's emotional state.

[0405] For example, if a user expresses frustration, the server senses that emotion and prioritizes searching for past examples of quick responses. Based on this, a solution is quickly proposed, and the work device implements the response quickly and effectively.

[0406] The hardware used includes network-enabled information processing devices and servers, while the software includes an emotion engine API and security modules. The present invention allows for specific configuration of operation using prompt statements such as, "Please tell me how to implement an application that uses the emotion engine API to acquire the current emotional state and enhances security features if stress or anxiety is detected."

[0407] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0408] Step 1:

[0409] The server receives inquiries from users. The inquiry content, as input, is sent to a generating AI model for analysis. In this process, the server extracts the subject and keywords of the inquiry through text analysis. Structured data of the inquiry content is obtained as output.

[0410] Step 2:

[0411] The server uses an emotion engine in conjunction with the obtained structured data to acquire user emotion information. The input is communication data such as user text or voice, and analysis outputs an emotional state (e.g., stress, exhilaration, calmness). This data is used to determine the urgency and tone of the inquiry.

[0412] Step 3:

[0413] The server searches a database for relevant past cases based on the query content and sentiment information. The input consists of structured data and sentiment states, which are used to filter relevant cases within the database. The output is the optimal set of cases.

[0414] Step 4:

[0415] The server generates user-sensitive solutions based on relevant case studies. The input consists of relevant case studies and sentiment data, which an artificial intelligence model analyzes to create appropriate solutions. The output is a customized solution.

[0416] Step 5:

[0417] Based on the solution sent to the terminal, the work device performs problem-solving actions. The input is the solution sent from the server, which the terminal uses to create specific operational commands. The output is the execution of the problem-solving actions and their results.

[0418] Step 6:

[0419] The terminal provides feedback to the server regarding the results of the actions performed. The input is the result of the action, and the terminal provides this information to the server for evaluation of areas for improvement and the need for additional action. The output is a feedback report.

[0420] Step 7:

[0421] The server re-evaluates the solution as needed and modifies the settings based on new sentiment information. The input is a feedback report, which the server analyzes to generate an improved solution again. The output is the re-evaluated solution.

[0422] Step 8:

[0423] The server adjusts security settings as needed based on the user's emotional state. Inputs are emotional information and execution results, and the security strength is reset through data calculations. The output is the adjusted security settings.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] [Third Embodiment]

[0428] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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".

[0440] This invention automates inquiry handling in system operations using a generated artificial intelligence model. This system activates an artificial intelligence model, which functions as an agent, simultaneously with the information processing device receiving an inquiry.

[0441] Specifically, the system analyzes the content of the query received by the server and searches the knowledge database for past related cases based on that content. This allows for the rapid retrieval of past solutions to similar problems.

[0442] Next, the server generates the optimal solution based on the analyzed data and acquired cases. This solution includes detailed execution steps and recommended actions, and the generated solution is sent to the terminal.

[0443] The terminal initiates action based on the solution sent from the server. This may include system reconfiguration, process restart, or access to external resources. Once the action is complete, the terminal feeds the results back to the server.

[0444] Through this series of processes, users can propose solutions, verify the results, and, if necessary, modify the results and suggest improvements. Furthermore, information on resolved problems is registered in the database as new knowledge, contributing to the rapid resolution of future inquiries.

[0445] For example, if a user reports slow response times to a web service at night, the server analyzes system metrics and searches for relevant past cases. Based on this information, the server deduces that a memory leak is the cause and generates a solution recommending memory clearing and terminating unnecessary processes. The user can then quickly resolve the issue by executing this solution and feeding the results back to the server.

[0446] The following describes the processing flow.

[0447] Step 1:

[0448] The server receives the query and analyzes its contents. This analysis uses natural language processing techniques to identify the query's category and keywords, thereby pinpointing the general scope of the problem.

[0449] Step 2:

[0450] Based on the analysis results, the server searches the knowledge database for relevant past cases. Here, past cases are efficiently filtered based on identified keywords and categories.

[0451] Step 3:

[0452] The server generates a list of suitable solutions from the search results. This involves referring to solutions derived from past cases and listing the steps that are most appropriate for the current problem.

[0453] Step 4:

[0454] The terminal receives a proposed solution from the server and determines whether it is executable. This determination is made by checking the status of system resources and execution permissions.

[0455] Step 5:

[0456] The terminal will take action to resolve the problem based on the solutions it determines are feasible. Examples include adjusting system settings or restarting processes.

[0457] Step 6:

[0458] The terminal logs the execution results and feeds them back to the server. The feedback includes whether the execution was successful or not, whether any errors occurred, and the execution time.

[0459] Step 7:

[0460] The user reviews the feedback from the server and evaluates the validity of the final solution. If necessary, additional manual adjustments are made to complete the problem resolution.

[0461] Step 8:

[0462] Users register resolved cases in the knowledge database, adding new knowledge to prepare for future inquiries. The registration process is carried out after reviewing the content and standardizing the format.

[0463] (Example 1)

[0464] 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."

[0465] This invention relates to an automated system for improving the efficiency and accuracy of inquiry handling processes. In particular, it aims to quickly and accurately perform a series of processes from analyzing inquiry content to providing, executing, and providing feedback on the optimal solution. By solving this problem, users will be able to resolve issues quickly and improve operational efficiency.

[0466] 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.

[0467] In this invention, the server includes means for automatically analyzing the content of a query, means for searching and retrieving past related cases from a knowledge database, and means for rapidly retrieving related cases using a high-speed search algorithm. This makes it possible to construct and execute the optimal solution to the query.

[0468] A "generating artificial intelligence model" is a collection of artificially constructed knowledge and learning algorithms used to analyze inquiries and generate appropriate solutions.

[0469] An "information processing device" refers to any computer system used to receive and analyze queries, and includes data processing and storage functions.

[0470] A "database" is a collection of data in which past cases and solutions are systematically stored and made searchable.

[0471] A "working device" is a physical or logical device that executes solutions and takes action to resolve a problem based on instructions from a server.

[0472] "Feedback" refers to the information obtained by returning the results of an action to an information processing device, which is then used for further analysis and improvement.

[0473] A "user interface" refers to an interactive display screen or input method that allows a user to interact with a system and to input feedback and make corrections.

[0474] "Knowledge data" is a systematic collection of knowledge that stores information about problems that have been solved and the countermeasures taken to address them.

[0475] A "high-speed search algorithm" is a computational method for quickly searching for information within a database and efficiently obtaining highly relevant results.

[0476] This invention is a system designed to streamline the inquiry handling process. It utilizes a generative AI model to automatically analyze inquiries and generate optimal solutions. The system's hardware includes a standard server computer and terminals used for user access. The software combines natural language processing software with a high-speed search algorithm. When an inquiry comes in from a user, the server analyzes its content and searches for relevant knowledge data in the database. Based on the retrieved data, the server uses the generative AI model to construct a specific solution and sends it to the terminal. The terminal automatically takes actionable steps based on the received solution. For example, if the server's response speed slows down, the system can identify the cause from the inquiry and suggest recommended actions.

[0477] As a concrete example, suppose there is an inquiry about slow response times for a web service during the night. In this case, the server analyzes system metrics and infers that the cause is a memory leak. Based on this, the server generates a solution recommending memory clearing and stopping unnecessary processes. This solution is sent to the terminal, which takes action and feeds the results back to the server.

[0478] An example of a prompt message is, "Please provide recommended solutions for the slowdown in web service response speed at night." This invention significantly reduces the time from inquiry to the provision of a solution, thereby improving operational efficiency.

[0479] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0480] Step 1:

[0481] The server receives a query from the user. In this step, the query content becomes the input data, and the server logs this data and stores it in a queue for analysis.

[0482] Step 2:

[0483] The server uses natural language processing software to analyze the query. This process takes the received text data as input, performs grammatical analysis and key phrase extraction, and outputs the query's subject and intent. This output data is then used for database searches in the next step.

[0484] Step 3:

[0485] The server uses a high-speed search algorithm based on the analysis results to search for relevant cases in the knowledge database. The input for this step is the analyzed query content, and it searches for past solutions and cases, outputting relevant information. This output is prepared for use in building solutions with a generative AI model.

[0486] Step 4:

[0487] The server uses a generated AI model to construct the optimal solution based on the acquired case examples. The input consists of past related cases and the current inquiry content, and by combining these, it outputs a solution that includes specific resolution steps and recommended actions.

[0488] Step 5:

[0489] The server sends the generated solution to the terminal. The input is a solution constructed on the server side, which is sent to the terminal and output in preparation for presentation to the user or automated execution.

[0490] Step 6:

[0491] The terminal performs executable actions based on the solution received from the server. The input is the solution instructions, and based on that, it executes specific commands, adjusts system settings, etc., and obtains the result as output.

[0492] Step 7:

[0493] The terminal feeds back the results of the actions it has performed to the server. In this step, the success / failure status of the action and detailed log information are used as input, and this information is sent back to the server as output.

[0494] Step 8:

[0495] Users can review the feedback received and, if necessary, propose corrections to the server. The feedback serves as input, and the user's judgment leads to the output of proposed corrections and improvements, which are then used in the next process.

[0496] (Application Example 1)

[0497] 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."

[0498] Many users face technical problems when using electronic payment services, but there is a lack of means to respond quickly and efficiently to these issues. Such problems can lead to a poor user experience and system operational stagnation. Traditional inquiry handling requires operator intervention and can be time-consuming; therefore, there is a need for a system that can automatically analyze problems and derive optimal solutions while maintaining convenience.

[0499] 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.

[0500] In this invention, the server includes means for automatically analyzing the content of an inquiry using an artificial intelligence model that is generated, means for searching for and retrieving relevant past cases from a data repository based on the analyzed content, and means for generating a solution based on the retrieved cases and the content of the inquiry. This makes it possible to quickly and accurately present a solution to an inquiry and improve user convenience.

[0501] A "generating artificial intelligence model" is a system equipped with a learning algorithm used to analyze inquiry content and automatically derive appropriate solutions.

[0502] An "information processing device" is an electronic device that can receive, analyze, and process data.

[0503] A "data repository" is an information storage system that stores past cases and related information, and allows for searching and retrieving them as needed.

[0504] An "operational device" is a system that executes specific tasks and actions to solve a problem based on the generated solution.

[0505] "Feedback" is the process of analyzing the results of an action taken and returning that information to the entire system.

[0506] A "user" is an individual or legal entity that uses an electronic payment service and requests technical support.

[0507] "Application software" refers to a program designed to allow users to report technical problems and receive rapid support from artificial intelligence.

[0508] The system for carrying out this invention is configured based on a server, a terminal, and user operations.

[0509] The server automatically analyzes user inquiries using an artificial intelligence model it generates. This analysis process utilizes Python's natural language processing (NLP) library. Once the inquiry is analyzed, the server accesses a data repository to search for and retrieve relevant past cases. This data repository is built as an SQL database. Next, the server uses TensorFlow to generate the optimal solution based on the retrieved cases and the inquiry.

[0510] The terminal receives the solution sent from the server and executes the action to resolve the problem on the operating device. The result of the action is then fed back to the server. This entire process uses a RESTful API, enabling smooth data communication.

[0511] Users can report problems related to electronic payment services using devices such as smartphones and receive immediate solutions from AI models. In particular, the smartphone application software features an intuitive user interface, providing a system that allows users to easily make inquiries and implement solutions.

[0512] For example, if a user reports a problem where "payment was completed but not correctly displayed in the app," the generating AI model will suggest clearing the app's data cache based on similar past cases. The following prompt can be used as an example: "Please provide the best solution to resolve the issue that occurred with the electronic payment. Specifically, what should be done if the user has not received a payment completion notification?"

[0513] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0514] Step 1:

[0515] Users report problems with electronic payment services using their devices. The problem details entered by the user are sent to the server via the smartphone's application software. Here, the user inputs the problem as text information through the user interface.

[0516] Step 2:

[0517] The server analyzes the received query using natural language processing (NLP). It analyzes the input text data using NLP techniques to extract problem categories and keywords. This process identifies the specific problem, and the necessary information is set as search criteria for the data repository.

[0518] Step 3:

[0519] Based on the analyzed query, the server searches and retrieves relevant past cases from the data repository. Using SQL queries, it becomes possible to extract relevant cases from the database and obtain historical information useful for problem solving.

[0520] Step 4:

[0521] The server generates the optimal solution using a generative AI model based on acquired past cases and inquiry content. Using TensorFlow, it performs inference based on input data (acquired cases and analyzed content) and outputs a solution to the problem.

[0522] Step 5:

[0523] The server sends the generated solution to the terminal. The terminal receives the solution and displays it to the user. The user takes action to resolve the problem based on the displayed solution.

[0524] Step 6:

[0525] The terminal feeds back the results of actions performed by the user to the server. The execution results are sent to the server, which evaluates them and determines the effectiveness of the solution.

[0526] Step 7:

[0527] Based on the feedback received, the server re-evaluates the solution as needed and updates the problem resolution information in the data repository. This process analyzes the feedback data and updates the knowledge base with new solutions to help handle future inquiries.

[0528] 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.

[0529] This invention automates inquiry handling in system operations using a generated artificial intelligence model and an emotion engine that recognizes user emotions. In this system, when an information processing device receives an inquiry, the artificial intelligence model is automatically activated as an agent, and the emotion engine analyzes the user's emotions.

[0530] Specifically, when the server analyzes the content of an inquiry it receives, it simultaneously acquires the user's emotional information using an emotional engine. This emotional information is used to estimate the urgency of the inquiry and the user's stress level, and is considered an important factor in the analysis.

[0531] Next, the server generates the optimal solution by searching the knowledge database for relevant past cases based on the analysis results and sentiment information. The generated solution takes the user's emotional state into consideration, and adjustments are made to its content and expression. This solution is sent to the terminal, and the corresponding action is initiated.

[0532] Rapid troubleshooting is possible by having the device perform problem-solving actions based on solutions sent from the server. After the actions are completed, the device feeds the results back to the server, and the solutions are re-evaluated and adjusted as needed using the results and sentiment information.

[0533] For example, if a user expresses frustration with support, the server picks up on that emotion and prioritizes searching the database for past cases of rapid response. Based on this information, the server generates a rapid response plan and triggers an action on the terminal. This process ensures that the user receives a quick and appropriate response, resulting in emotionally caring support.

[0534] The system incorporating the emotion engine of the present invention can provide responses that contribute to the user's psychological stability, in addition to resolving issues through physical actions, thereby further improving the efficiency and quality of system operation.

[0535] The following describes the processing flow.

[0536] Step 1:

[0537] The server receives inquiries from users and analyzes the content of those inquiries using natural language processing techniques. This analysis includes keyword extraction and contextual understanding.

[0538] Step 2:

[0539] The server activates the emotion engine along with the analyzed data to evaluate the user's emotional state. The emotion engine infers the user's current emotion (e.g., anger, confusion, frustration) from the tone of voice and the expression of the input text.

[0540] Step 3:

[0541] Based on the analysis results and emotional state, the server searches the knowledge database for relevant past cases. If the situation is deemed particularly urgent or emotionally burdensome, it prioritizes extracting cases that required immediate resolution.

[0542] Step 4:

[0543] The server generates solutions that take emotional information into account. If the user is feeling stressed, the solutions will be expressed in a gentler tone and with simpler instructions.

[0544] Step 5:

[0545] The terminal receives the solution sent from the server and makes final adjustments based on the situation before execution. Additional confirmations to the user are requested as needed.

[0546] Step 6:

[0547] The device will take specific actions based on the solution. This may include changing settings, restarting system processes, or sending instructional emails to the user.

[0548] Step 7:

[0549] The terminal records the results of the actions it performs and feeds the result log back to the server. This includes records of the problem resolution status and any anomalies that occurred during execution.

[0550] Step 8:

[0551] The server re-evaluates the effectiveness of solutions based on feedback information and sentiment data, and makes further adjustments or suggestions as needed. By utilizing the sentiment engine's input in this re-evaluation, user satisfaction and trust are maintained.

[0552] Step 9:

[0553] Users receive feedback from the system and confirm the final results. If necessary, they can register the case in the knowledge database to prepare for future use.

[0554] (Example 2)

[0555] 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."

[0556] Traditional customer support systems have a problem in that they do not take into account the user's emotions, resulting in an inability to provide prompt and accurate support and to sufficiently increase user satisfaction. In particular, by responding without understanding the user's emotional state, it becomes difficult to provide appropriate support to users who are feeling stressed.

[0557] 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.

[0558] In this invention, the server includes means for an information processing device to automatically analyze the content of an inquiry using a generated artificial intelligence model and sentiment analysis means, and to acquire the user's sentiment information; means for searching and acquiring past relevant cases from a database based on the analyzed content and acquired sentiment information; and means for generating a solution based on the acquired cases, inquiry content and sentiment information, and adjusting the content according to the user's emotional state. This enables prompt and accurate support that takes the user's emotions into consideration.

[0559] A "generated artificial intelligence model" is a program that operates using machine learning algorithms to automate tasks such as analyzing inquiries and suggesting solutions.

[0560] "Emotion analysis means" refers to technology that estimates and analyzes emotions in real time from a user's text or voice.

[0561] An "information processing device" is a computer that receives inquiries and analyzes their content and related data.

[0562] "User sentiment information" refers to data that captures the emotional responses and states obtained from user statements and inputs.

[0563] A "database" is a collection of data in which information such as past cases and solutions is systematically stored.

[0564] A "solution" is a specific plan or procedure that presents appropriate methods or actions in response to an inquiry.

[0565] A "working device" is something that performs physical or logical actions based on the generated solution.

[0566] "Feedback" refers to information used to evaluate the results of actions taken and to incorporate them into system improvements.

[0567] A "user interface" refers to the operating screen or means of interaction that enables the exchange of information between a system and a user.

[0568] One embodiment of this invention is a system that combines an artificial intelligence model and emotion analysis technology to enable a rapid and emotion-sensitive response to user inquiries. Specific embodiments are described below.

[0569] The server receives inquiries from users and performs analysis as needed. This analysis utilizes a generative AI model to understand the content of the inquiries. The system also employs software for sentiment analysis. This software analyzes user messages in real time and measures their emotional state. This technology uses natural language processing and machine learning algorithms, and specifically, it can utilize programming languages ​​and libraries such as Python and TensorFlow.

[0570] The server uses the emotional information and query content obtained to search the database for relevant past cases. Based on the results, it uses a generative AI model to generate the optimal solution. This solution is adjusted based on the emotional information; for example, if the user is angry, more careful wording and expressions will be chosen.

[0571] The generated solution is sent to the device, and actions to resolve the problem are taken according to the instructions. These actions include displaying specific troubleshooting steps to the user and automatically adjusting system settings.

[0572] After execution, the terminal feeds the results back to the server. This feedback includes the success rate of the executed action and changes in the user's emotions, and is used for re-evaluation and adjustment of solutions as needed.

[0573] For example, if a user makes an inquiry such as "My internet connection is slow," the system will analyze that the inquiry contains anxieties. In this case, the server will find a prompt message in the database such as "Please quickly find out specific ways to improve your internet connection speed" and then provide the optimal steps.

[0574] An example of a prompt message in such a system might be, "If the user expresses dissatisfaction with an order issue, please promptly provide a solution based on past handling cases." This invention can improve the efficiency of information processing and enhance user satisfaction.

[0575] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0576] Step 1:

[0577] The user enters a support inquiry into the system. This input includes a specific question or a description of the problem. The server receives the inquiry and prepares to analyze the data. The input data is text, which forms the basis for subsequent analysis.

[0578] Step 2:

[0579] The server activates a generative AI model to analyze the received query text. This model uses natural language processing techniques to understand the query and extract relevant information. In this process, text data is input, and analyzed data is output. This analyzed data includes important information such as the subject and urgency of the query.

[0580] Step 3:

[0581] The server utilizes sentiment analysis techniques to estimate the user's emotions from the inquiry text. This process takes text data as input and outputs emotional information. Sentiment analysis is crucial for determining the user's stress and anxiety levels, and emotion recognition algorithms are used for data processing.

[0582] Step 4:

[0583] The server uses the analyzed data and sentiment information to access the knowledge database and search for relevant past cases. The action taken at this stage is the execution of a database query. The input is the analyzed query data and sentiment information, and the output is a list of relevant past cases.

[0584] Step 5:

[0585] The server generates the optimal solution based on the obtained case studies and emotional information. In this process, the generative AI model is utilized again, and the solution is adjusted to take the user's emotional state into consideration. The input is past case studies and emotional information. The output is the adjusted solution.

[0586] Step 6:

[0587] The terminal receives a solution sent from the server and performs problem-solving actions based on the instructions. Specific actions include displaying instructions to the user and adjusting settings. The input is the solution, and the output is the result of the execution and notifications to the user.

[0588] Step 7:

[0589] The terminal feeds the execution results back to the server. This feedback includes the success rate of the action and whether any additional problems were encountered. The input is the action result, and the output is the server's re-evaluation of the data and suggestions for improvement.

[0590] (Application Example 2)

[0591] 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."

[0592] In recent years, as customer service automation has advanced, there has been a growing need for appropriate responses that take user emotions into consideration. However, conventional systems have struggled to adequately reflect users' emotional states, sometimes leading to user dissatisfaction and problems due to inappropriate responses. Furthermore, dynamic adjustments based on emotional states have not been sufficiently implemented in security. This invention aims to improve service quality by analyzing user emotions in real time and adjusting inquiry responses and security settings accordingly.

[0593] 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.

[0594] In this invention, the server includes means for analyzing information using a generated artificial intelligence model, means for acquiring cases based on the analysis results and emotional information, means for generating emotionally sensitive solutions, and means for monitoring the user's emotional state and adjusting security settings. This enables rapid and appropriate responses to inquiries and dynamic adjustment of security in accordance with the user's emotions.

[0595] An "artificial intelligence model" is a program or algorithm that uses a computer to mimic human intelligent behavior and automatically analyze the content of inquiries.

[0596] An "information processing device" is an electronic device that analyzes the content of an inquiry and generates a solution based on that analysis.

[0597] "Analysis" is the process by which an information processing device breaks down the content of an inquiry and the user's emotional information, and converts them into an understandable format.

[0598] "Emotional information" refers to data that indicates a user's emotional state and is used to understand the user's urgency and stress levels.

[0599] A "data bank" is an information aggregation system that stores and manages past cases and sentiment information related to inquiries.

[0600] A "solution" refers to specific methods or actions provided to resolve a user's problem based on the analyzed inquiry content and sentiment information.

[0601] A "working device" is a device or system used to carry out actual problem-solving actions based on the generated solution.

[0602] "Feedback" refers to information that is returned to an information processing device to evaluate or adjust the results of an action that has been performed.

[0603] "Monitoring" is the process of continuously monitoring the user's emotional state and adjusting responses in real time as needed.

[0604] "Security settings" refer to the defensive measures and strategies configured to maintain the security of a system, and they are dynamically adjustable.

[0605] One embodiment of this invention is a system that automates and optimizes user inquiry handling and security management by combining a generated artificial intelligence model with an emotion engine. When an inquiry is received, the server analyzes its content using the artificial intelligence model and simultaneously obtains the user's emotional information using the emotion engine. This makes it possible to evaluate the user's urgency and stress level.

[0606] The information processing device searches for relevant cases from a database based on the analyzed content and emotional information, and generates the optimal solution. This solution is adjusted to suit the user's emotional state and executed by the work device. The execution results are fed back, and the solution is re-evaluated as needed. Furthermore, security settings are dynamically adjusted based on the user's emotional state.

[0607] For example, if a user expresses frustration, the server senses that emotion and prioritizes searching for past examples of quick responses. Based on this, a solution is quickly proposed, and the work device implements the response quickly and effectively.

[0608] The hardware used includes network-enabled information processing devices and servers, while the software includes an emotion engine API and security modules. The present invention allows for specific configuration of operation using prompt statements such as, "Please tell me how to implement an application that uses the emotion engine API to acquire the current emotional state and enhances security features if stress or anxiety is detected."

[0609] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0610] Step 1:

[0611] The server receives inquiries from users. The inquiry content, as input, is sent to a generating AI model for analysis. In this process, the server extracts the subject and keywords of the inquiry through text analysis. Structured data of the inquiry content is obtained as output.

[0612] Step 2:

[0613] The server uses an emotion engine in conjunction with the obtained structured data to acquire user emotion information. The input is communication data such as user text or voice, and analysis outputs an emotional state (e.g., stress, exhilaration, calmness). This data is used to determine the urgency and tone of the inquiry.

[0614] Step 3:

[0615] The server searches a database for relevant past cases based on the query content and sentiment information. The input consists of structured data and sentiment states, which are used to filter relevant cases within the database. The output is the optimal set of cases.

[0616] Step 4:

[0617] The server generates user-sensitive solutions based on relevant case studies. The input consists of relevant case studies and sentiment data, which an artificial intelligence model analyzes to create appropriate solutions. The output is a customized solution.

[0618] Step 5:

[0619] Based on the solution sent to the terminal, the work device performs problem-solving actions. The input is the solution sent from the server, which the terminal uses to create specific operational commands. The output is the execution of the problem-solving actions and their results.

[0620] Step 6:

[0621] The terminal provides feedback to the server regarding the results of the actions performed. The input is the result of the action, and the terminal provides this information to the server for evaluation of areas for improvement and the need for additional action. The output is a feedback report.

[0622] Step 7:

[0623] The server re-evaluates the solution as needed and modifies the settings based on new sentiment information. The input is a feedback report, which the server analyzes to generate an improved solution again. The output is the re-evaluated solution.

[0624] Step 8:

[0625] The server adjusts security settings as needed based on the user's emotional state. Inputs are emotional information and execution results, and the security strength is reset through data calculations. The output is the adjusted security settings.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] [Fourth Embodiment]

[0630] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0631] 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.

[0632] 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).

[0633] 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.

[0634] 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.

[0635] 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).

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] 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".

[0643] This invention automates inquiry handling in system operations using a generated artificial intelligence model. This system activates an artificial intelligence model, which functions as an agent, simultaneously with the information processing device receiving an inquiry.

[0644] Specifically, the system analyzes the content of the query received by the server and searches the knowledge database for past related cases based on that content. This allows for the rapid retrieval of past solutions to similar problems.

[0645] Next, the server generates the optimal solution based on the analyzed data and acquired cases. This solution includes detailed execution steps and recommended actions, and the generated solution is sent to the terminal.

[0646] The terminal initiates action based on the solution sent from the server. This may include system reconfiguration, process restart, or access to external resources. Once the action is complete, the terminal feeds the results back to the server.

[0647] Through this series of processes, users can propose solutions, verify the results, and, if necessary, modify the results and suggest improvements. Furthermore, information on resolved problems is registered in the database as new knowledge, contributing to the rapid resolution of future inquiries.

[0648] For example, if a user reports slow response times to a web service at night, the server analyzes system metrics and searches for relevant past cases. Based on this information, the server deduces that a memory leak is the cause and generates a solution recommending memory clearing and terminating unnecessary processes. The user can then quickly resolve the issue by executing this solution and feeding the results back to the server.

[0649] The following describes the processing flow.

[0650] Step 1:

[0651] The server receives the query and analyzes its contents. This analysis uses natural language processing techniques to identify the query's category and keywords, thereby pinpointing the general scope of the problem.

[0652] Step 2:

[0653] Based on the analysis results, the server searches the knowledge database for relevant past cases. Here, past cases are efficiently filtered based on identified keywords and categories.

[0654] Step 3:

[0655] The server generates a list of suitable solutions from the search results. This involves referring to solutions derived from past cases and listing the steps that are most appropriate for the current problem.

[0656] Step 4:

[0657] The terminal receives a proposed solution from the server and determines whether it is executable. This determination is made by checking the status of system resources and execution permissions.

[0658] Step 5:

[0659] The terminal will take action to resolve the problem based on the solutions it determines are feasible. Examples include adjusting system settings or restarting processes.

[0660] Step 6:

[0661] The terminal logs the execution results and feeds them back to the server. The feedback includes whether the execution was successful or not, whether any errors occurred, and the execution time.

[0662] Step 7:

[0663] The user reviews the feedback from the server and evaluates the validity of the final solution. If necessary, additional manual adjustments are made to complete the problem resolution.

[0664] Step 8:

[0665] Users register resolved cases in the knowledge database, adding new knowledge to prepare for future inquiries. The registration process is carried out after reviewing the content and standardizing the format.

[0666] (Example 1)

[0667] 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".

[0668] This invention relates to an automated system for improving the efficiency and accuracy of inquiry handling processes. In particular, it aims to quickly and accurately perform a series of processes from analyzing inquiry content to providing, executing, and providing feedback on the optimal solution. By solving this problem, users will be able to resolve issues quickly and improve operational efficiency.

[0669] 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.

[0670] In this invention, the server includes means for automatically analyzing the content of a query, means for searching and retrieving past related cases from a knowledge database, and means for rapidly retrieving related cases using a high-speed search algorithm. This makes it possible to construct and execute the optimal solution to the query.

[0671] A "generating artificial intelligence model" is a collection of artificially constructed knowledge and learning algorithms used to analyze inquiries and generate appropriate solutions.

[0672] An "information processing device" refers to any computer system used to receive and analyze queries, and includes data processing and storage functions.

[0673] A "database" is a collection of data in which past cases and solutions are systematically stored and made searchable.

[0674] A "working device" is a physical or logical device that executes solutions and takes action to resolve a problem based on instructions from a server.

[0675] "Feedback" refers to the information obtained by returning the results of an action to an information processing device, which is then used for further analysis and improvement.

[0676] A "user interface" refers to an interactive display screen or input method that allows a user to interact with a system and to input feedback and make corrections.

[0677] "Knowledge data" is a systematic collection of knowledge that stores information about problems that have been solved and the countermeasures taken to address them.

[0678] A "high-speed search algorithm" is a computational method for quickly searching for information within a database and efficiently obtaining highly relevant results.

[0679] This invention is a system designed to streamline the inquiry handling process. It utilizes a generative AI model to automatically analyze inquiries and generate optimal solutions. The system's hardware includes a standard server computer and terminals used for user access. The software combines natural language processing software with a high-speed search algorithm. When an inquiry comes in from a user, the server analyzes its content and searches for relevant knowledge data in the database. Based on the retrieved data, the server uses the generative AI model to construct a specific solution and sends it to the terminal. The terminal automatically takes actionable steps based on the received solution. For example, if the server's response speed slows down, the system can identify the cause from the inquiry and suggest recommended actions.

[0680] As a concrete example, suppose there is an inquiry about slow response times for a web service during the night. In this case, the server analyzes system metrics and infers that the cause is a memory leak. Based on this, the server generates a solution recommending memory clearing and stopping unnecessary processes. This solution is sent to the terminal, which takes action and feeds the results back to the server.

[0681] An example of a prompt message is, "Please provide recommended solutions for the slowdown in web service response speed at night." This invention significantly reduces the time from inquiry to the provision of a solution, thereby improving operational efficiency.

[0682] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0683] Step 1:

[0684] The server receives a query from the user. In this step, the query content becomes the input data, and the server logs this data and stores it in a queue for analysis.

[0685] Step 2:

[0686] The server uses natural language processing software to analyze the query. This process takes the received text data as input, performs grammatical analysis and key phrase extraction, and outputs the query's subject and intent. This output data is then used for database searches in the next step.

[0687] Step 3:

[0688] The server uses a high-speed search algorithm based on the analysis results to search for relevant cases in the knowledge database. The input for this step is the analyzed query content, and it searches for past solutions and cases, outputting relevant information. This output is prepared for use in building solutions with a generative AI model.

[0689] Step 4:

[0690] The server uses a generated AI model to construct the optimal solution based on the acquired case examples. The input consists of past related cases and the current inquiry content, and by combining these, it outputs a solution that includes specific resolution steps and recommended actions.

[0691] Step 5:

[0692] The server sends the generated solution to the terminal. The input is a solution constructed on the server side, which is sent to the terminal and output in preparation for presentation to the user or automated execution.

[0693] Step 6:

[0694] The terminal performs executable actions based on the solution received from the server. The input is the solution instructions, and based on that, it executes specific commands, adjusts system settings, etc., and obtains the result as output.

[0695] Step 7:

[0696] The terminal feeds back the results of the actions it has performed to the server. In this step, the success / failure status of the action and detailed log information are used as input, and this information is sent back to the server as output.

[0697] Step 8:

[0698] Users can review the feedback received and, if necessary, propose corrections to the server. The feedback serves as input, and the user's judgment leads to the output of proposed corrections and improvements, which are then used in the next process.

[0699] (Application Example 1)

[0700] 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".

[0701] Many users face technical problems when using electronic payment services, but there is a lack of means to respond quickly and efficiently to these issues. Such problems can lead to a poor user experience and system operational stagnation. Traditional inquiry handling requires operator intervention and can be time-consuming; therefore, there is a need for a system that can automatically analyze problems and derive optimal solutions while maintaining convenience.

[0702] 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.

[0703] In this invention, the server includes means for automatically analyzing the content of an inquiry using an artificial intelligence model that is generated, means for searching for and retrieving relevant past cases from a data repository based on the analyzed content, and means for generating a solution based on the retrieved cases and the content of the inquiry. This makes it possible to quickly and accurately present a solution to an inquiry and improve user convenience.

[0704] A "generating artificial intelligence model" is a system equipped with a learning algorithm used to analyze inquiry content and automatically derive appropriate solutions.

[0705] An "information processing device" is an electronic device that can receive, analyze, and process data.

[0706] A "data repository" is an information storage system that stores past cases and related information, and allows for searching and retrieving them as needed.

[0707] An "operational device" is a system that executes specific tasks and actions to solve a problem based on the generated solution.

[0708] "Feedback" is the process of analyzing the results of an action taken and returning that information to the entire system.

[0709] A "user" is an individual or legal entity that uses an electronic payment service and requests technical support.

[0710] "Application software" refers to a program designed to allow users to report technical problems and receive rapid support from artificial intelligence.

[0711] The system for carrying out this invention is configured based on a server, a terminal, and user operations.

[0712] The server automatically analyzes user inquiries using an artificial intelligence model it generates. This analysis process utilizes Python's natural language processing (NLP) library. Once the inquiry is analyzed, the server accesses a data repository to search for and retrieve relevant past cases. This data repository is built as an SQL database. Next, the server uses TensorFlow to generate the optimal solution based on the retrieved cases and the inquiry.

[0713] The terminal receives the solution sent from the server and executes the action to resolve the problem on the operating device. The result of the action is then fed back to the server. This entire process uses a RESTful API, enabling smooth data communication.

[0714] Users can report problems related to electronic payment services using devices such as smartphones and receive immediate solutions from AI models. In particular, the smartphone application software features an intuitive user interface, providing a system that allows users to easily make inquiries and implement solutions.

[0715] For example, if a user reports a problem where "payment was completed but not correctly displayed in the app," the generating AI model will suggest clearing the app's data cache based on similar past cases. The following prompt can be used as an example: "Please provide the best solution to resolve the issue that occurred with the electronic payment. Specifically, what should be done if the user has not received a payment completion notification?"

[0716] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0717] Step 1:

[0718] Users report problems with electronic payment services using their devices. The problem details entered by the user are sent to the server via the smartphone's application software. Here, the user inputs the problem as text information through the user interface.

[0719] Step 2:

[0720] The server analyzes the received query using natural language processing (NLP). It analyzes the input text data using NLP techniques to extract problem categories and keywords. This process identifies the specific problem, and the necessary information is set as search criteria for the data repository.

[0721] Step 3:

[0722] Based on the analyzed query, the server searches and retrieves relevant past cases from the data repository. Using SQL queries, it becomes possible to extract relevant cases from the database and obtain historical information useful for problem solving.

[0723] Step 4:

[0724] The server generates the optimal solution using a generative AI model based on acquired past cases and inquiry content. Using TensorFlow, it performs inference based on input data (acquired cases and analyzed content) and outputs a solution to the problem.

[0725] Step 5:

[0726] The server sends the generated solution to the terminal. The terminal receives the solution and displays it to the user. The user takes action to resolve the problem based on the displayed solution.

[0727] Step 6:

[0728] The terminal feeds back the results of actions performed by the user to the server. The execution results are sent to the server, which evaluates them and determines the effectiveness of the solution.

[0729] Step 7:

[0730] Based on the feedback received, the server re-evaluates the solution as needed and updates the problem resolution information in the data repository. This process analyzes the feedback data and updates the knowledge base with new solutions to help handle future inquiries.

[0731] 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.

[0732] This invention automates inquiry handling in system operations using a generated artificial intelligence model and an emotion engine that recognizes user emotions. In this system, when an information processing device receives an inquiry, the artificial intelligence model is automatically activated as an agent, and the emotion engine analyzes the user's emotions.

[0733] Specifically, when the server analyzes the content of an inquiry it receives, it simultaneously acquires the user's emotional information using an emotional engine. This emotional information is used to estimate the urgency of the inquiry and the user's stress level, and is considered an important factor in the analysis.

[0734] Next, the server generates the optimal solution by searching the knowledge database for relevant past cases based on the analysis results and sentiment information. The generated solution takes the user's emotional state into consideration, and adjustments are made to its content and expression. This solution is sent to the terminal, and the corresponding action is initiated.

[0735] Rapid troubleshooting is possible by having the device perform problem-solving actions based on solutions sent from the server. After the actions are completed, the device feeds the results back to the server, and the solutions are re-evaluated and adjusted as needed using the results and sentiment information.

[0736] For example, if a user expresses frustration with support, the server picks up on that emotion and prioritizes searching the database for past cases of rapid response. Based on this information, the server generates a rapid response plan and triggers an action on the terminal. This process ensures that the user receives a quick and appropriate response, resulting in emotionally caring support.

[0737] The system incorporating the emotion engine of the present invention can provide responses that contribute to the user's psychological stability, in addition to resolving issues through physical actions, thereby further improving the efficiency and quality of system operation.

[0738] The following describes the processing flow.

[0739] Step 1:

[0740] The server receives inquiries from users and analyzes the content of those inquiries using natural language processing techniques. This analysis includes keyword extraction and contextual understanding.

[0741] Step 2:

[0742] The server activates the emotion engine along with the analyzed data to evaluate the user's emotional state. The emotion engine infers the user's current emotion (e.g., anger, confusion, frustration) from the tone of voice and the expression of the input text.

[0743] Step 3:

[0744] Based on the analysis results and emotional state, the server searches the knowledge database for relevant past cases. If the situation is deemed particularly urgent or emotionally burdensome, it prioritizes extracting cases that required immediate resolution.

[0745] Step 4:

[0746] The server generates solutions that take emotional information into account. If the user is feeling stressed, the solutions will be expressed in a gentler tone and with simpler instructions.

[0747] Step 5:

[0748] The terminal receives the solution sent from the server and makes final adjustments based on the situation before execution. Additional confirmations to the user are requested as needed.

[0749] Step 6:

[0750] The device will take specific actions based on the solution. This may include changing settings, restarting system processes, or sending instructional emails to the user.

[0751] Step 7:

[0752] The terminal records the results of the actions it performs and feeds the result log back to the server. This includes records of the problem resolution status and any anomalies that occurred during execution.

[0753] Step 8:

[0754] The server re-evaluates the effectiveness of solutions based on feedback information and sentiment data, and makes further adjustments or suggestions as needed. By utilizing the sentiment engine's input in this re-evaluation, user satisfaction and trust are maintained.

[0755] Step 9:

[0756] Users receive feedback from the system and confirm the final results. If necessary, they can register the case in the knowledge database to prepare for future use.

[0757] (Example 2)

[0758] 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".

[0759] Traditional customer support systems have a problem in that they do not take into account the user's emotions, resulting in an inability to provide prompt and accurate support and to sufficiently increase user satisfaction. In particular, by responding without understanding the user's emotional state, it becomes difficult to provide appropriate support to users who are feeling stressed.

[0760] 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.

[0761] In this invention, the server includes means for an information processing device to automatically analyze the content of an inquiry using a generated artificial intelligence model and sentiment analysis means, and to acquire the user's sentiment information; means for searching and acquiring past relevant cases from a database based on the analyzed content and acquired sentiment information; and means for generating a solution based on the acquired cases, inquiry content and sentiment information, and adjusting the content according to the user's emotional state. This enables prompt and accurate support that takes the user's emotions into consideration.

[0762] A "generated artificial intelligence model" is a program that operates using machine learning algorithms to automate tasks such as analyzing inquiries and suggesting solutions.

[0763] "Emotion analysis means" refers to technology that estimates and analyzes emotions in real time from a user's text or voice.

[0764] An "information processing device" is a computer that receives inquiries and analyzes their content and related data.

[0765] "User sentiment information" refers to data that captures the emotional responses and states obtained from user statements and inputs.

[0766] A "database" is a collection of data in which information such as past cases and solutions is systematically stored.

[0767] A "solution" is a specific plan or procedure that presents appropriate methods or actions in response to an inquiry.

[0768] A "working device" is something that performs physical or logical actions based on the generated solution.

[0769] "Feedback" refers to information used to evaluate the results of actions taken and to incorporate them into system improvements.

[0770] A "user interface" refers to the operating screen or means of interaction that enables the exchange of information between a system and a user.

[0771] One embodiment of this invention is a system that combines an artificial intelligence model and emotion analysis technology to enable a rapid and emotion-sensitive response to user inquiries. Specific embodiments are described below.

[0772] The server receives inquiries from users and performs analysis as needed. This analysis utilizes a generative AI model to understand the content of the inquiries. The system also employs software for sentiment analysis. This software analyzes user messages in real time and measures their emotional state. This technology uses natural language processing and machine learning algorithms, and specifically, it can utilize programming languages ​​and libraries such as Python and TensorFlow.

[0773] The server uses the emotional information and query content obtained to search the database for relevant past cases. Based on the results, it uses a generative AI model to generate the optimal solution. This solution is adjusted based on the emotional information; for example, if the user is angry, more careful wording and expressions will be chosen.

[0774] The generated solution is sent to the device, and actions to resolve the problem are taken according to the instructions. These actions include displaying specific troubleshooting steps to the user and automatically adjusting system settings.

[0775] After execution, the terminal feeds the results back to the server. This feedback includes the success rate of the executed action and changes in the user's emotions, and is used for re-evaluation and adjustment of solutions as needed.

[0776] For example, if a user makes an inquiry such as "My internet connection is slow," the system will analyze that the inquiry contains anxieties. In this case, the server will find a prompt message in the database such as "Please quickly find out specific ways to improve your internet connection speed" and then provide the optimal steps.

[0777] An example of a prompt message in such a system might be, "If the user expresses dissatisfaction with an order issue, please promptly provide a solution based on past handling cases." This invention can improve the efficiency of information processing and enhance user satisfaction.

[0778] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0779] Step 1:

[0780] The user enters a support inquiry into the system. This input includes a specific question or a description of the problem. The server receives the inquiry and prepares to analyze the data. The input data is text, which forms the basis for subsequent analysis.

[0781] Step 2:

[0782] The server activates a generative AI model to analyze the received query text. This model uses natural language processing techniques to understand the query and extract relevant information. In this process, text data is input, and analyzed data is output. This analyzed data includes important information such as the subject and urgency of the query.

[0783] Step 3:

[0784] The server utilizes sentiment analysis techniques to estimate the user's emotions from the inquiry text. This process takes text data as input and outputs emotional information. Sentiment analysis is crucial for determining the user's stress and anxiety levels, and emotion recognition algorithms are used for data processing.

[0785] Step 4:

[0786] The server uses the analyzed data and sentiment information to access the knowledge database and search for relevant past cases. The action taken at this stage is the execution of a database query. The input is the analyzed query data and sentiment information, and the output is a list of relevant past cases.

[0787] Step 5:

[0788] The server generates the optimal solution based on the obtained case studies and emotional information. In this process, the generative AI model is utilized again, and the solution is adjusted to take the user's emotional state into consideration. The input is past case studies and emotional information. The output is the adjusted solution.

[0789] Step 6:

[0790] The terminal receives a solution sent from the server and performs problem-solving actions based on the instructions. Specific actions include displaying instructions to the user and adjusting settings. The input is the solution, and the output is the result of the execution and notifications to the user.

[0791] Step 7:

[0792] The terminal feeds the execution results back to the server. This feedback includes the success rate of the action and whether any additional problems were encountered. The input is the action result, and the output is the server's re-evaluation of the data and suggestions for improvement.

[0793] (Application Example 2)

[0794] 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".

[0795] In recent years, as customer service automation has advanced, there has been a growing need for appropriate responses that take user emotions into consideration. However, conventional systems have struggled to adequately reflect users' emotional states, sometimes leading to user dissatisfaction and problems due to inappropriate responses. Furthermore, dynamic adjustments based on emotional states have not been sufficiently implemented in security. This invention aims to improve service quality by analyzing user emotions in real time and adjusting inquiry responses and security settings accordingly.

[0796] 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.

[0797] In this invention, the server includes means for analyzing information using a generated artificial intelligence model, means for acquiring cases based on the analysis results and emotional information, means for generating emotionally sensitive solutions, and means for monitoring the user's emotional state and adjusting security settings. This enables rapid and appropriate responses to inquiries and dynamic adjustment of security in accordance with the user's emotions.

[0798] An "artificial intelligence model" is a program or algorithm that uses a computer to mimic human intelligent behavior and automatically analyze the content of inquiries.

[0799] An "information processing device" is an electronic device that analyzes the content of an inquiry and generates a solution based on that analysis.

[0800] "Analysis" is the process by which an information processing device breaks down the content of an inquiry and the user's emotional information, and converts them into an understandable format.

[0801] "Emotional information" refers to data that indicates a user's emotional state and is used to understand the user's urgency and stress levels.

[0802] A "data bank" is an information aggregation system that stores and manages past cases and sentiment information related to inquiries.

[0803] A "solution" refers to specific methods or actions provided to resolve a user's problem based on the analyzed inquiry content and sentiment information.

[0804] A "working device" is a device or system used to carry out actual problem-solving actions based on the generated solution.

[0805] "Feedback" refers to information that is returned to an information processing device to evaluate or adjust the results of an action that has been performed.

[0806] "Monitoring" is the process of continuously monitoring the user's emotional state and adjusting responses in real time as needed.

[0807] "Security settings" refer to the defensive measures and strategies configured to maintain the security of a system, and they are dynamically adjustable.

[0808] One embodiment of this invention is a system that automates and optimizes user inquiry handling and security management by combining a generated artificial intelligence model with an emotion engine. When an inquiry is received, the server analyzes its content using the artificial intelligence model and simultaneously obtains the user's emotional information using the emotion engine. This makes it possible to evaluate the user's urgency and stress level.

[0809] The information processing device searches for relevant cases from a database based on the analyzed content and emotional information, and generates the optimal solution. This solution is adjusted to suit the user's emotional state and executed by the work device. The execution results are fed back, and the solution is re-evaluated as needed. Furthermore, security settings are dynamically adjusted based on the user's emotional state.

[0810] For example, if a user expresses frustration, the server senses that emotion and prioritizes searching for past examples of quick responses. Based on this, a solution is quickly proposed, and the work device implements the response quickly and effectively.

[0811] The hardware used includes network-enabled information processing devices and servers, while the software includes an emotion engine API and security modules. The present invention allows for specific configuration of operation using prompt statements such as, "Please tell me how to implement an application that uses the emotion engine API to acquire the current emotional state and enhances security features if stress or anxiety is detected."

[0812] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0813] Step 1:

[0814] The server receives inquiries from users. The inquiry content, as input, is sent to a generating AI model for analysis. In this process, the server extracts the subject and keywords of the inquiry through text analysis. Structured data of the inquiry content is obtained as output.

[0815] Step 2:

[0816] The server uses an emotion engine in conjunction with the obtained structured data to acquire user emotion information. The input is communication data such as user text or voice, and analysis outputs an emotional state (e.g., stress, exhilaration, calmness). This data is used to determine the urgency and tone of the inquiry.

[0817] Step 3:

[0818] The server searches a database for relevant past cases based on the query content and sentiment information. The input consists of structured data and sentiment states, which are used to filter relevant cases within the database. The output is the optimal set of cases.

[0819] Step 4:

[0820] The server generates user-sensitive solutions based on relevant case studies. The input consists of relevant case studies and sentiment data, which an artificial intelligence model analyzes to create appropriate solutions. The output is a customized solution.

[0821] Step 5:

[0822] Based on the solution sent to the terminal, the work device performs problem-solving actions. The input is the solution sent from the server, which the terminal uses to create specific operational commands. The output is the execution of the problem-solving actions and their results.

[0823] Step 6:

[0824] The terminal provides feedback to the server regarding the results of the actions performed. The input is the result of the action, and the terminal provides this information to the server for evaluation of areas for improvement and the need for additional action. The output is a feedback report.

[0825] Step 7:

[0826] The server re-evaluates the solution as needed and modifies the settings based on new sentiment information. The input is a feedback report, which the server analyzes to generate an improved solution again. The output is the re-evaluated solution.

[0827] Step 8:

[0828] The server adjusts security settings as needed based on the user's emotional state. Inputs are emotional information and execution results, and the security strength is reset through data calculations. The output is the adjusted security settings.

[0829] 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.

[0830] 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.

[0831] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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."

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] The following is further disclosed regarding the embodiments described above.

[0851] (Claim 1)

[0852] A means by which an information processing device automatically analyzes the content of an inquiry using an artificial intelligence model that is generated,

[0853] A means of searching and retrieving past related cases from a database based on the analyzed content,

[0854] A means of generating solutions based on acquired cases and inquiry content,

[0855] A means by which the work apparatus performs actions for problem solving based on the generated solution,

[0856] A means of providing feedback on the results of the actions taken and re-evaluating the solution as needed,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, characterized by having a user interface for performing final confirmation and correction based on feedback results.

[0860] (Claim 3)

[0861] The system according to claim 1, further comprising means for updating and registering information on resolved problems in a database.

[0862] "Example 1"

[0863] (Claim 1)

[0864] A means by which an information processing device automatically analyzes the content of an inquiry using an artificial intelligence model that is generated,

[0865] A means of searching and retrieving past related cases from a database based on the analyzed content,

[0866] A means of quickly obtaining relevant cases using a high-speed search algorithm,

[0867] A means by which a generated AI model constructs a solution based on acquired case studies and inquiry content,

[0868] A means for sending the generated solution to a work device and executing actions to resolve the problem,

[0869] A means for feeding back the results of the executed action to the information processing device,

[0870] A means of re-evaluating the solution based on the feedback received and making corrections as necessary,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, characterized in that the final confirmation and correction of feedback results are performed via a user interface.

[0874] (Claim 3)

[0875] The system according to claim 1, further comprising means for updating and registering information about resolved problems as knowledge data in a database.

[0876] "Application Example 1"

[0877] (Claim 1)

[0878] A means by which an information processing device automatically analyzes the content of an inquiry using an artificial intelligence model that is generated,

[0879] A means of searching and retrieving past related cases from a data repository based on the analyzed content,

[0880] A means of generating solutions based on acquired cases and inquiry content,

[0881] A means by which the operating device performs actions to resolve the problem based on the generated solution,

[0882] A means of providing feedback on the results of the actions taken and re-evaluating the solution as needed,

[0883] A means of providing application software that allows users to report problem situations and receive immediate support from artificial intelligence,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, characterized by having an operating interface for performing final confirmation and correction based on feedback results.

[0887] (Claim 3)

[0888] The system according to claim 1, further comprising means for updating and registering information about resolved problems in a data storage medium.

[0889] "Example 2 of combining an emotion engine"

[0890] (Claim 1)

[0891] Using a generated artificial intelligence model and emotion analysis means, the information processing device automatically analyzes the content of the inquiry and obtains the user's emotion information.

[0892] A means of searching and retrieving past related cases from a database based on the analyzed content and acquired sentiment information,

[0893] A means for generating solutions based on acquired cases, inquiries, and sentiment information, and adjusting the content according to the user's emotional state,

[0894] A means by which the work apparatus performs actions for problem solving based on the generated solution,

[0895] A means of providing feedback on the results of the actions taken, re-evaluating the solution along with emotional information, and adjusting it as necessary,

[0896] A system that includes this.

[0897] (Claim 2)

[0898] The system according to claim 1, characterized by having a user interface for final confirmation and correction based on feedback results and sentiment information.

[0899] (Claim 3)

[0900] The system according to claim 1, further comprising means for updating a database of resolved issues and related sentiment information.

[0901] "Application example 2 when combining with an emotional engine"

[0902] (Claim 1)

[0903] A means by which an information processing device automatically analyzes the content of an inquiry using an artificial intelligence model that is generated,

[0904] A means of searching and retrieving past relevant cases from a database based on the analyzed content and user sentiment information,

[0905] A means for generating solutions that take into account the user's emotional state based on acquired case studies, inquiry content, and sentiment information,

[0906] A means by which the work apparatus performs actions for problem solving based on the generated solution,

[0907] A means of providing feedback on the results of the actions taken and re-evaluating the solution as needed,

[0908] A means of monitoring the user's emotional state and adjusting security settings according to emotional information,

[0909] A system that includes this.

[0910] (Claim 2)

[0911] The system according to claim 1, characterized by having a human-machine interface that performs final confirmation and correction based on feedback results and emotional information.

[0912] (Claim 3)

[0913] The system according to claim 1, further comprising means for updating and registering records of resolved problems and related emotional information in a database. [Explanation of Symbols]

[0914] 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 by which an information processing device automatically analyzes the content of an inquiry using an artificial intelligence model that is generated, A means of searching and retrieving past related cases from a data repository based on the analyzed content, A means of generating solutions based on acquired cases and inquiry content, A means by which the operating device performs actions to resolve the problem based on the generated solution, A means of providing feedback on the results of the actions taken and re-evaluating the solution as needed, A means of providing application software that allows users to report problem situations and receive immediate support from artificial intelligence, A system that includes this.

2. The system according to claim 1, characterized by having an operating interface for performing final confirmation and correction based on feedback results.

3. The system according to claim 1, further comprising means for updating and registering information about resolved problems in a data storage medium.

Images