system

Abstract

We provide the system. [Solution] A means of recording actions performed by a user on a computer, A means for analyzing characteristic patterns from recorded motion data, Means for generating an automated model based on the analyzed patterns, A means of running the generated automation model on a computer, A system that includes this.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 Conventional business automation systems have the problems of requiring knowledge of specific tools or programming languages and depending on users with specialized skills. There are also problems such as the secularization of operations, the decrease in usage frequency, and the variation in business quality. The purpose of this invention is to easily automate daily business without users learning specific technologies and solve these problems. 【Means for Solving the Problems】 【0005】 This invention provides a system comprising means for recording the user's computer operations, means for analyzing patterns from the recorded data, means for generating an automation model based on the patterns, and means for executing the model. Furthermore, by including means for improving the automation model based on user feedback and for centrally managing the operation data by sending it to a server, anyone can easily automate their work. This system aims to standardize work quality and improve work efficiency. 【0006】 "Means for recording user actions on a computer" refers to a system that records user operations on a computer in real time and stores that data. 【0007】 "Means for analyzing characteristic patterns from recorded action data" refers to a mechanism that analyzes collected user operation data to identify frequently performed procedures and repetitive tasks. 【0008】 "Means for generating automation models based on analyzed patterns" refers to the process of constructing a model for automation by imitating identified operational patterns. 【0009】 "Means for executing the generated automation model on a computer" refers to a mechanism for actually automatically completing tasks on a computer using the constructed automation model. 【0010】 "Means of receiving user feedback and improving generated automation models" refers to methods of incorporating user evaluations and comments to improve the accuracy and functionality of existing automation models. 【0011】 "Means for sending recorded operation data to a server and managing it centrally" refers to the process of sending and storing user operation data on a server in order to centrally manage this data. [Brief explanation of the drawing] 【0012】 [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 the data processing device and 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] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention] 【0013】 An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings. 【0014】 First, the terms used in the following description will be explained. 【0015】 In the following embodiments, a tagged processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0016】 In the following embodiments, a tagged RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0017】 In the following embodiments, a tagged storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc. 【0018】 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). 【0019】 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." 【0020】 [First Embodiment] 【0021】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0022】 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. 【0023】 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). 【0024】 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. 【0025】 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. 【0026】 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. 【0027】 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. 【0028】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0029】 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. 【0030】 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. 【0031】 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. 【0032】 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". 【0033】 The embodiment of the system in this invention utilizes an AI agent running on a computer to automate the user's daily tasks. The program processing of this system is described below in natural language. 【0034】 User behavior collection and data transmission 【0035】 The device records all user actions in real time. Specifically, it records information such as when the user launched an application, what actions they performed, and what data they entered. This information is sent to the server at predetermined intervals. 【0036】 Data analysis on the server 【0037】 The server analyzes the received data and identifies frequently performed operation patterns. This allows it to recognize recurring tasks performed by users and determine which parts should be automated. 【0038】 Generation and execution of automation models 【0039】 The server generates an automated model based on the analysis results and sends it back to the terminal. The terminal uses this model to automatically perform actions that mimic user operations when specific trigger conditions are met. 【0040】 Processing user feedback 【0041】 Users review the results of the automated tasks performed and provide feedback on the system's performance. This feedback is sent to the server and used to improve future models. 【0042】 Specific example 【0043】 For example, if a user opens the same spreadsheet every morning and updates specific data, the device records this action, and the server detects it as a pattern. Based on this pattern, the server generates an automation model, and the device automatically performs this action from the next day onward. The user reviews the results and provides feedback to the server to fine-tune the spreadsheet updates as needed. This process allows the user to efficiently reduce the burden of repetitive tasks. 【0044】 The following describes the processing flow. 【0045】 Step 1: 【0046】 The device records the user's computer operations in real time. It monitors actions such as keyboard input, mouse clicks, and application launches and shutdowns, and stores this information as a log. 【0047】 Step 2: 【0048】 The device transmits accumulated operation data to the server at predetermined intervals. During this transmission, the data is appropriately encrypted to protect the user's privacy. 【0049】 Step 3: 【0050】 The server analyzes the received operation data and uses a pattern recognition algorithm to identify recurring operations. This analysis allows for the extraction of specific tasks or flows. 【0051】 Step 4: 【0052】 The server generates a model suitable for automation from the analyzed patterns. This model mimics repetitive user operations and includes a set of rules for executing automated tasks. 【0053】 Step 5: 【0054】 The server sends the generated automation model to the terminal for installation. The terminal then uses that model to prepare to execute automated tasks when the trigger conditions for user interaction are met. 【0055】 Step 6: 【0056】 The device automates tasks based on an automation model, performing tasks on behalf of the user. This automates everyday tasks such as drafting emails and entering data. 【0057】 Step 7: 【0058】 Users review the results of automated tasks and provide feedback on their accuracy and satisfaction. This feedback is sent from the terminal to the server. 【0059】 Step 8: 【0060】 The server receives user feedback and uses it to improve the automation model. This allows for adjustments to ensure that subsequent automation tasks are executed more efficiently and accurately. 【0061】 (Example 1) 【0062】 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." 【0063】 Conventional automation support systems suffer from insufficient processes for recording and analyzing user actions, resulting in reduced accuracy and efficiency of automation. Furthermore, the lack of model improvement based on user feedback makes continuous optimization difficult. 【0064】 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. 【0065】 In this invention, the server includes means for recording actions performed by the user on an information processing device, means for analyzing characteristic patterns from the recorded action information, means for generating an artificial intelligence model based on the analyzed patterns, means for transmitting the recorded action information to an aggregation device for centralized management, means for receiving evaluations from the user and improving the generated artificial intelligence model, and means for identifying automation candidates based on the user's actions and imitating them. This enables accurate recording and analysis of the user's actions, optimal automation, and continuous model improvement. 【0066】 "Information processing equipment" refers to all computer devices used by users to perform actions, and includes desktop computers, laptop computers, and tablet devices. 【0067】 "Operation information" refers to detailed data about a series of operations performed by the user, including application startup time, operation details, and entered data. 【0068】 A "data aggregation device" is a server device used to centrally manage and analyze operational information transmitted from multiple information processing devices. 【0069】 A "characteristic pattern" is a combination of frequently performed operations or a specific sequence of operations that can be extracted from recorded operational information. 【0070】 An "artificial intelligence model" is a program or algorithm generated based on characteristic patterns to automate user actions. 【0071】 "Evaluation" refers to the act of users providing feedback on automated tasks performed, indicating their impressions and suggestions for improvement regarding the system's performance and accuracy. 【0072】 "Candidates for automation" are specific tasks or work procedures that can be automated, identified based on user actions. 【0073】 This invention is a system that automates operations performed by users on a daily basis by making full use of information processing devices and aggregation devices. Specifically, it is a mechanism in which a terminal collects all of the user's actions in real time and transmits that information to a server. 【0074】 A terminal refers to hardware used by a user, such as a desktop computer, laptop computer, or tablet device. These terminals are connected to the internet and run software that records user activity logs. The activity log includes detailed information about the user's actions, such as application usage, entered data, and clicked buttons. 【0075】 The server is responsible for analyzing the received operation logs. The analysis uses Python-based data analysis libraries such as Pandas and NumPy to identify frequently occurring operation patterns and tasks that can be automated. Furthermore, machine learning libraries such as TENSORFLOW and PyTorch are used to generate artificial intelligence models based on the analysis results. 【0076】 The generated artificial intelligence model is sent to the terminal and used for automation. This allows the system to automatically mimic operations when user-defined conditions are met. Furthermore, users can check the execution results and send feedback to the server, enabling continuous system improvement. 【0077】 For example, if a user wants to automate updating a spreadsheet every morning, the device records a series of actions, including opening and updating the spreadsheet. The server analyzes this information and recognizes it as a pattern. An AI model is generated, and the device automatically performs this operation from the next day onward. 【0078】 An example of a prompt to input into a generating AI model is, "Automate the spreadsheet update operation that the user performs every morning." Using this prompt allows for the efficient automation of specific tasks, reducing the user's workload. 【0079】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0080】 Step 1: 【0081】 The terminal records user actions in real time. Inputs include the applications used by the user, clicks and keystrokes, and login times. Based on this input, the operation information is stored in a database format. The output is operation log data organized by time. 【0082】 Step 2: 【0083】 The terminal sends recorded operation log data to the server at regular intervals. The data is encrypted during transmission. The input is the operation log data acquired in step 1, and the output is secure data used by the server's analysis system. 【0084】 Step 3: 【0085】 The server analyzes the received operation log data. The input is raw data sent from the terminal. The server uses Python-based data analysis libraries (e.g., Pandas or NumPy) to perform statistical processing on the data and identify user operation patterns. The output is the identified characteristic pattern data. 【0086】 Step 4: 【0087】 The server generates an artificial intelligence model based on the analyzed patterns. The input is the characteristic pattern data obtained in step 3. Machine learning libraries such as TensorFlow and PyTorch are used for generation, and a model that has learned the optimal automation procedure is generated. The output is the artificial intelligence model that is sent to the terminal. 【0088】 Step 5: 【0089】 The terminal automates its actions using an artificial intelligence model received from the server. This model is designed to mimic user actions when the conditions are met. The input is the artificial intelligence model generated in step 4, and the output is the automated sequence of actions from the user's perspective. 【0090】 Step 6: 【0091】 The user reviews the work performed by the automation and provides feedback. The input is the result of the automated operation in step 5 and the user's evaluation comments. The output is the feedback data received by the server, which is used to improve the model in the future. 【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】 Repetitive and monotonous daily tasks within the home are a source of wasted time and effort for users. In particular, these tasks often become routine, hindering the focus on more productive activities. In this context, there is a need for methods to efficiently automate these household tasks and reduce the burden on users. 【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 recording operations performed by the user on a computer, means for analyzing characteristic patterns from the recorded operation information, and means for constructing an automation model based on the analyzed patterns. This makes it possible to control a household robot and automatically perform repetitive tasks. 【0097】 A "computer" is a device used for information processing, specifically for recording and analyzing user operations. 【0098】 "Operation information" refers to a series of actions and input data performed by a user on a computer, and serves as foundational data for extracting characteristic patterns from these records. 【0099】 A "characteristic pattern" refers to a series of frequently occurring actions or routines that are analyzed from operational information and are targets for automation. 【0100】 An "automation model" is built on analyzed characteristic patterns and contains guidelines and structures that allow a computer to automatically mimic behavior under specific trigger conditions. 【0101】 A "household robot" is a device designed to automatically perform specific, repetitive tasks within the home, and functions to alleviate the user's daily workload. 【0102】 An "information processing device" is a hardware or software system for transmitting and centrally managing recorded operation information. 【0103】 "User evaluations" are feedback given regarding the performance and results of automated models, and are used to improve the models. 【0104】 To implement this invention, hardware such as a computer, information processing device, and home robot, as well as dedicated software that runs on each piece of hardware, are required. First, the user performs daily operations on the computer, and these operations are recorded by a dedicated program. The recorded operation information is analyzed to extract characteristic patterns. This analysis is performed using analysis software that runs on the computer. 【0105】 Next, an automation model is built based on the analyzed characteristic patterns. The built model is sent to a household robot, which then performs actions that mimic those patterns when specific trigger conditions occur. The household robot automatically starts moving according to the model sent from the computer and performs repetitive tasks. These actions include routine tasks such as cleaning every morning. 【0106】 Furthermore, users evaluate the results of the tasks performed and send the feedback to the information processing device. This feedback is used to improve the model. For example, by providing feedback on the desired cleaning time, the automated model can be improved to adapt to that time. 【0107】 To configure this system, it is necessary to use an edge AI computing device such as the NVIDIA Jetson Nano as the computer and install software for building analysis and automation models. An example of a prompt message might be, "Tell us what you do every morning. Based on this information, we will suggest how a home robot can automate those tasks." This would enable the efficient automation of repetitive tasks in the home. 【0108】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0109】 Step 1: 【0110】 The terminal records a series of operations performed by the user on the computer. It receives user actions and input data as input, and stores this as operation information. As output, it generates log data of operation information organized chronologically. Specifically, it monitors the applications used and data entered by the user, and writes them to a file. 【0111】 Step 2: 【0112】 The server receives operation information sent from the terminal and analyzes characteristic patterns. Log data of operation information is used as input. Data processing involves analyzing frequently occurring operation sequences and similarities to extract patterns suitable for automation. The output is a list of characteristic patterns obtained from the analysis. Specifically, machine learning algorithms are used to detect repetitive operations and organize them in an efficient format. 【0113】 Step 3: 【0114】 The server constructs an automation model based on the analysis results. It uses a list of characteristic patterns as input. For data computation, it designs rules and processes to automate each pattern and describes them as a generative AI model. The output is the constructed automation model. In terms of concrete operation, it generates program code or scripts and constructs them as a model. 【0115】 Step 4: 【0116】 The server sends the constructed automation model to the terminal. The automation model is used as input. The output is a model ready to run on the user's terminal. Specifically, the model data is transferred to the terminal via the communication network and deployed to the execution environment on the terminal. 【0117】 Step 5: 【0118】 The terminal executes automation models and controls household robots. It uses automation trigger conditions and transmitted models as inputs. The output is the automated execution of repetitive daily tasks performed by the user. Specifically, it sends commands to the robot to perform actions such as cleaning or opening curtains at specific times. 【0119】 Step 6: 【0120】 The user reviews the results of the tasks performed and provides feedback. The input is the results of tasks performed by the home robot. The output is feedback data containing evaluations and requests. Specifically, the user records aspects they dislike or want improved and sends this information to the server. 【0121】 Step 7: 【0122】 The server receives feedback from users and improves the automation model. Feedback data is used as input. Data processing involves adjusting the model based on user evaluations to create a more adaptive generative AI model. The output is a newly improved automation model. Specifically, the algorithm is retrained and optimized to improve user satisfaction. 【0123】 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. 【0124】 This invention is a system that incorporates an AI agent that records, analyzes, and automates user computer operations, as well as an emotion engine that recognizes user emotions in real time. This system comprehensively analyzes user actions and emotions to more adaptively automate business processes. 【0125】 The system first collects user operation data from the terminal. Furthermore, the emotion engine identifies the user's emotional state using facial recognition and voice tone analysis (and in some cases, biosignal analysis using sensors). This data is transmitted from the terminal to a server for centralized management. 【0126】 The server analyzes the relationship between actions and emotions based on the received data. It learns the user's preferred processes and patterns of operations that cause stress, and incorporates this into the automation model. Emotional data is also used as feedback and incorporated into the model training. 【0127】 Once an automation model is generated, the device executes this model. The automated operations are adaptively performed according to the user's emotional state. For example, if the user is feeling stressed, it may be possible to prioritize the automation of certain time-consuming tasks. 【0128】 For example, if the system detects that a user is experiencing fatigue while processing emails, it will automate more efficient email classification and reply creation. Furthermore, if the user exhibits positive emotions, it will execute standard automated processes, but if negative emotions are detected, it will adaptively adjust the process, prioritizing time-consuming tasks for automation. 【0129】 Thus, the present invention is a system that can dynamically respond to the diverse emotional states of users, thereby simultaneously achieving improved work efficiency and reduced user stress. 【0130】 The following describes the processing flow. 【0131】 Step 1: 【0132】 The device records user actions in real time. These actions include keyboard input, mouse movements, and application launches and shutdowns. Additionally, an emotion engine analyzes the user's facial expressions and voice to recognize their current emotional state. This information is stored on the device. 【0133】 Step 2: 【0134】 The device sends collected operational and emotional data to the server at regular intervals. The data is encrypted and uses appropriate security protocols to protect privacy. 【0135】 Step 3: 【0136】 The server analyzes the received data to identify user behavior and emotional patterns. By associating the timing of significant changes in user emotions with corresponding actions, a more precise automation model is formed. 【0137】 Step 4: 【0138】 The server generates an automated model based on behavioral and emotional patterns. This model includes a flexible set of rules that change priorities or modify specific actions based on the user's emotions. 【0139】 Step 5: 【0140】 The server sends the generated automation model to the terminal for installation. The terminal then prepares to automate operations based on this model according to the given conditions. 【0141】 Step 6: 【0142】 The device automates tasks according to an automation model, performing tasks on behalf of the user. An emotion engine continuously monitors the user's state, and if, for example, the user is stressed, it prioritizes automating tasks that help reduce stress. 【0143】 Step 7: 【0144】 Users review the results of automated tasks and provide feedback on their accuracy and satisfaction. This feedback is sent from the terminal to the server and collected. 【0145】 Step 8: 【0146】 The server adjusts and improves the automation model based on user feedback. Through this feedback loop, subsequent automations are adjusted to become more adaptive and efficient. 【0147】 (Example 2) 【0148】 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". 【0149】 When users utilize information processing devices, the stress and inefficiencies associated with their operation are significant, potentially reducing productivity and accuracy. In particular, conventional systems that do not consider the user's emotional state fail to adapt to user needs, resulting in increased stress. To address these challenges, a system is needed that analyzes and adaptively automates user actions and emotions in a coordinated manner. 【0150】 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. 【0151】 In this invention, the server includes means for recording operations performed by the user on the information processing device, means for integrating operation data and sentiment data and analyzing their relationships, and means for generating an automation model based on the analyzed patterns and sentiment data. This enables a reduction in user stress during operations and efficient and adaptive automation of tasks. 【0152】 An "information processing device" is a device used by users to perform operations and process data, and includes computers, smartphones, and other similar devices. 【0153】 "Operation data" refers to information such as keyboard and mouse input performed by the user on the information processing device, and application usage status. 【0154】 An "emotion analysis engine" refers to a software or hardware component that analyzes a user's face, voice, biometric information, etc., to recognize their emotions in real time. 【0155】 An "automation model" refers to a program or algorithm that automatically performs specific actions based on analyzed patterns and sentiment data. 【0156】 "Centralized management" refers to the process of collecting multiple pieces of information and managing them centrally, thereby enabling efficient access and use. 【0157】 This system consists of a user terminal and a server that analyzes and manages the data. First, the terminal records the user's actions. This action data includes keyboard and mouse input, application usage history, and more. The terminal also uses an emotion analysis engine to recognize the user's emotional state in real time. This engine collects the user's emotional data through facial recognition and voice tone analysis. 【0158】 This data is transmitted to a server via the network. The server integrates the received operation data and emotion data and analyzes the patterns. This analysis uses machine learning algorithms to find the relationship between user operation patterns and emotions. Analysis software such as Spark or TensorFlow may be used. Based on the results of this analysis, the server generates an automated model to optimize user operations. 【0159】 The automation model flexibly adjusts to the user's emotional state and adaptively automates operations. For example, if a user shows signs of fatigue while creating a document, the model reduces the user's workload by automatically searching for and suggesting relevant documents. It also generates an automated reply template if the user receives a message and indicates stress. 【0160】 A concrete example of a prompt message would be, "If fatigue is detected during email processing, which processes should be prioritized for automation?" This could be a suggestion or question about how to utilize the generative AI model. This would enable the design of more accurate automation processes. 【0161】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0162】 Step 1: 【0163】 The terminal records user actions in real time. Input includes operational data such as keyboard and mouse actions and application usage history. The terminal collects this data and records it in a database format. For example, it collects the time a user spends editing a document and the specific commands they use. 【0164】 Step 2: 【0165】 The device collects emotional data using an emotion analysis engine. Inputs include the user's facial expressions, voice tone, and biosensor signals. The device uses a machine learning model to estimate the user's emotional state from this input data and outputs the identified emotion as data. Specifically, it measures eyebrow movements, voice intonation, and other parameters to analyze emotions such as stress and joy. 【0166】 Step 3: 【0167】 The terminal sends the collected operational and emotional data to the server. The input is the previously collected data, which the terminal bundles into data packets and securely transmits to the server over the network. Specifically, a large amount of data is sent in a single batch using an endpoint-to-server data transfer protocol. 【0168】 Step 4: 【0169】 The server integrates and analyzes received operation data and emotion data. The input is data sent from the terminal. Using machine learning algorithms and data analysis software, the server analyzes the correlation between the user's operation patterns and emotional states from this data, and outputs the analysis results as patterns. Specifically, it compares the operation history with an emotion timeline to reveal which operations trigger specific emotions in the user. 【0170】 Step 5: 【0171】 The server generates an automated model based on the analysis results. The input is pattern information obtained through integrated analysis. Using generative AI modeling technology, the server creates a model that includes the optimal operating procedure according to the user's emotions and outputs it. As a specific example, it generates a model that prioritizes tasks based on emotions. 【0172】 Step 6: 【0173】 The terminal receives and executes an automation model from the server. The input is the automation model sent from the server. The terminal applies this model and performs specific actions that flexibly automate work processes according to the user's emotional state, thereby increasing the user's efficiency. For example, if the user is showing signs of fatigue, the terminal will prioritize automating email processing. 【0174】 (Application Example 2) 【0175】 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". 【0176】 In modern brick-and-mortar stores, staff emotions and stress levels significantly impact the efficiency of customer service and customer satisfaction. However, a lack of means to properly manage these factors in real time and optimize operations makes it difficult to dynamically adjust work processes while considering staff emotional states in store operations. 【0177】 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. 【0178】 In this invention, the server includes facial recognition and voice analysis means for identifying the user's emotional state in real time, means for analyzing the relationship between the emotional state and behavioral data and reflecting it in an automated model, and means for transmitting recorded behavioral data to a central processing unit for centralized management. This enables dynamic optimization of operations and adaptive task assignment while taking into account the emotional state of store staff in physical stores. 【0179】 A "user" is an individual or group that operates an information processing device. 【0180】 An "information processing device" is an electronic device, such as a computer, used for recording, analyzing, and executing data. 【0181】 "Behavioral data" refers to information that describes a series of operations and procedures performed by a user on an information processing device. 【0182】 A "characteristic pattern" refers to the repetition of important operations or common characteristics identified from recorded behavioral data. 【0183】 An "automation model" is a program or system that is generated based on analyzed patterns to automatically handle specific tasks. 【0184】 "Facial recognition" is a technology that uses sensor devices such as cameras to analyze the features of a user's face and identify their emotional state. 【0185】 "Voice analysis means" refers to a technology that uses sensor devices such as microphones to analyze the characteristics of a user's voice and determine their emotional state and intentions. 【0186】 "Emotional state" refers to the user's psychological and emotional state, and includes, for example, stress, joy, and fatigue. 【0187】 A "central processing unit" is a server or data center used to process and manage multiple pieces of information in an integrated manner. 【0188】 The system for realizing this invention mainly consists of a user-operated terminal and a server. The terminal, as an information processing device, is equipped with a camera for facial recognition and a microphone for voice analysis, and records the user's behavioral data and emotional state in real time. When the user performs their daily tasks, the terminal records the behavioral data and further analyzes the user's emotional state using the camera and microphone. The analyzed data is transmitted to the server in stages. 【0189】 Based on the received data, the server uses Python-based natural language processing techniques and the machine learning framework TensorFlow to analyze the relationship between characteristic patterns in behavioral data and emotional states. The automation model generated from this analysis is designed to optimize business processes in accordance with the user's emotional state. In particular, when a user is experiencing stress, the server uses the automation model to prioritize automating time-consuming tasks and delivers them to the user. 【0190】 A concrete example of this system is inventory management in a store. When staff stress levels rise during work, the system prioritizes automating monotonous tasks such as rearranging merchandise and instructs other staff members to handle customer service. In this way, staff can work more efficiently and with less burden. 【0191】 An example of a prompt would be, "Please tell me how to implement a system that analyzes the emotions of store staff and teaches the AI ​​how to optimally allocate tasks." This would enhance the adaptive capabilities of the AI ​​model that monitors the psychological state of staff and dynamically adjusts task allocation. 【0192】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0193】 Step 1: 【0194】 The terminal records user actions on the information processing device. This includes actions such as operation logs, mouse clicks, and keyboard input. It receives various operation data performed by the user as input and records it as an operation log organized chronologically. The output is an action dataset for use in subsequent processing steps. 【0195】 Step 2: 【0196】 The device uses a camera and microphone to analyze the user's facial expressions and voice, identifying their emotional state in real time. It collects the user's facial image and voice tone as input. Using facial recognition and voice analysis algorithms, it generates emotional labels such as positive, negative, and stress. The output of this process is emotional state data recorded over time. 【0197】 Step 3: 【0198】 The terminal sends collected behavioral and emotional state data to the server. It receives the data generated in steps 1 and 2 as input. This data is packetized and sent to the server via the network. The output is an integrated dataset stored on the server. 【0199】 Step 4: 【0200】 The server analyzes the received integrated dataset to find relationships between behavioral data and emotional state data. It uses the collected integrated dataset as input. Machine learning techniques are used to extract features and analyze data correlations. The output is an automated model optimized based on this data. 【0201】 Step 5: 【0202】 The server optimizes business processes using the generated automation model. It uses the automation model, built based on analysis, as input. If users are experiencing stress, it adjusts work allocation, such as prioritizing specific tasks. The output is the optimized business procedure based on this. 【0203】 Step 6: 【0204】 The user performs tasks according to optimized workflow procedures. The workflow procedures are received from the server as input. The terminal continuously monitors the user's work and repeats the process from step 1 as needed. The output is efficient work execution and reduced user stress. 【0205】 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. 【0206】 Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0207】 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. 【0208】 [Second Embodiment] 【0209】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0210】 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. 【0211】 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). 【0212】 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. 【0213】 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. 【0214】 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). 【0215】 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. 【0216】 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. 【0217】 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. 【0218】 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. 【0219】 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. 【0220】 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". 【0221】 The embodiment of the system in this invention utilizes an AI agent running on a computer to automate the user's daily tasks. The program processing of this system is described below in natural language. 【0222】 User behavior collection and data transmission 【0223】 The device records all user actions in real time. Specifically, it records information such as when the user launched an application, what actions they performed, and what data they entered. This information is sent to the server at predetermined intervals. 【0224】 Data analysis on the server 【0225】 The server analyzes the received data and identifies frequently performed operation patterns. This allows it to recognize recurring tasks performed by users and determine which parts should be automated. 【0226】 Generation and execution of automation models 【0227】 The server generates an automated model based on the analysis results and sends it back to the terminal. The terminal uses this model to automatically perform actions that mimic user operations when specific trigger conditions are met. 【0228】 Processing user feedback 【0229】 Users review the results of the automated tasks performed and provide feedback on the system's performance. This feedback is sent to the server and used to improve future models. 【0230】 Specific example 【0231】 For example, if a user opens the same spreadsheet every morning and updates specific data, the device records this action, and the server detects it as a pattern. Based on this pattern, the server generates an automation model, and the device automatically performs this action from the next day onward. The user reviews the results and provides feedback to the server to fine-tune the spreadsheet updates as needed. This process allows the user to efficiently reduce the burden of repetitive tasks. 【0232】 The following describes the processing flow. 【0233】 Step 1: 【0234】 The device records the user's computer operations in real time. It monitors actions such as keyboard input, mouse clicks, and application launches and shutdowns, and stores this information as a log. 【0235】 Step 2: 【0236】 The device transmits accumulated operation data to the server at predetermined intervals. During this transmission, the data is appropriately encrypted to protect the user's privacy. 【0237】 Step 3: 【0238】 The server analyzes the received operation data and uses a pattern recognition algorithm to identify recurring operations. This analysis allows for the extraction of specific tasks or flows. 【0239】 Step 4: 【0240】 The server generates a model suitable for automation from the analyzed patterns. This model mimics repetitive user operations and includes a set of rules for executing automated tasks. 【0241】 Step 5: 【0242】 The server sends the generated automation model to the terminal for installation. The terminal then uses that model to prepare to execute automated tasks when the trigger conditions for user interaction are met. 【0243】 Step 6: 【0244】 The device automates tasks based on an automation model, performing tasks on behalf of the user. This automates everyday tasks such as drafting emails and entering data. 【0245】 Step 7: 【0246】 Users review the results of automated tasks and provide feedback on their accuracy and satisfaction. This feedback is sent from the terminal to the server. 【0247】 Step 8: 【0248】 The server receives user feedback and uses it to improve the automation model. This allows for adjustments to ensure that subsequent automation tasks are executed more efficiently and accurately. 【0249】 (Example 1) 【0250】 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". 【0251】 Conventional automation support systems suffer from insufficient processes for recording and analyzing user actions, resulting in reduced accuracy and efficiency of automation. Furthermore, the lack of model improvement based on user feedback makes continuous optimization difficult. 【0252】 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. 【0253】 In this invention, the server includes means for recording actions performed by the user on an information processing device, means for analyzing characteristic patterns from the recorded action information, means for generating an artificial intelligence model based on the analyzed patterns, means for transmitting the recorded action information to an aggregation device for centralized management, means for receiving evaluations from the user and improving the generated artificial intelligence model, and means for identifying automation candidates based on the user's actions and imitating them. This enables accurate recording and analysis of the user's actions, optimal automation, and continuous model improvement. 【0254】 "Information processing equipment" refers to all computer devices used by users to perform actions, and includes desktop computers, laptop computers, and tablet devices. 【0255】 "Operation information" refers to detailed data about a series of operations performed by the user, including application startup time, operation details, and entered data. 【0256】 A "data aggregation device" is a server device used to centrally manage and analyze operational information transmitted from multiple information processing devices. 【0257】 A "characteristic pattern" is a combination of frequently performed operations or a specific sequence of operations that can be extracted from recorded operational information. 【0258】 An "artificial intelligence model" is a program or algorithm generated based on characteristic patterns to automate user actions. 【0259】 "Evaluation" refers to the act of users providing feedback on automated tasks performed, indicating their impressions and suggestions for improvement regarding the system's performance and accuracy. 【0260】 "Candidates for automation" are specific tasks or work procedures that can be automated, identified based on user actions. 【0261】 This invention is a system that automates operations performed by users on a daily basis by making full use of information processing devices and aggregation devices. Specifically, it is a mechanism in which a terminal collects all of the user's actions in real time and transmits that information to a server. 【0262】 A terminal refers to hardware used by a user, such as a desktop computer, laptop computer, or tablet device. These terminals are connected to the internet and run software that records user activity logs. The activity log includes detailed information about the user's actions, such as application usage, entered data, and clicked buttons. 【0263】 The server is responsible for analyzing the received operation logs. Python-based data analysis libraries such as Pandas and NumPy are used for the analysis to identify frequently occurring operation patterns and tasks that can be automated. Furthermore, machine learning libraries such as TensorFlow and PyTorch are used to generate artificial intelligence models based on the analysis results. 【0264】 The generated artificial intelligence model is sent to the terminal and used for automation. This allows the system to automatically mimic operations when user-defined conditions are met. Furthermore, users can check the execution results and send feedback to the server, enabling continuous system improvement. 【0265】 For example, if a user wants to automate updating a spreadsheet every morning, the device records a series of actions, including opening and updating the spreadsheet. The server analyzes this information and recognizes it as a pattern. An AI model is generated, and the device automatically performs this operation from the next day onward. 【0266】 An example of a prompt to input into a generating AI model is, "Automate the spreadsheet update operation that the user performs every morning." Using this prompt allows for the efficient automation of specific tasks, reducing the user's workload. 【0267】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0268】 Step 1: 【0269】 The terminal records user actions in real time. Inputs include the applications used by the user, clicks and keystrokes, and login times. Based on this input, the operation information is stored in a database format. The output is operation log data organized by time. 【0270】 Step 2: 【0271】 The terminal sends recorded operation log data to the server at regular intervals. The data is encrypted during transmission. The input is the operation log data acquired in step 1, and the output is secure data used by the server's analysis system. 【0272】 Step 3: 【0273】 The server analyzes the received operation log data. The input is raw data sent from the terminal. The server uses Python-based data analysis libraries (e.g., Pandas or NumPy) to perform statistical processing on the data and identify user operation patterns. The output is the identified characteristic pattern data. 【0274】 Step 4: 【0275】 The server generates an artificial intelligence model based on the analyzed patterns. The input is the characteristic pattern data obtained in step 3. Machine learning libraries such as TensorFlow and PyTorch are used for generation, and a model that has learned the optimal automation procedure is generated. The output is the artificial intelligence model that is sent to the terminal. 【0276】 Step 5: 【0277】 The terminal automates its actions using an artificial intelligence model received from the server. This model is designed to mimic user actions when the conditions are met. The input is the artificial intelligence model generated in step 4, and the output is the automated sequence of actions from the user's perspective. 【0278】 Step 6: 【0279】 The user checks the operations executed by automation and provides feedback. The input is the result of the automation operation in Step 5 and the user's evaluation comments. The output is the feedback data received by the server, based on which future model improvements are made. 【0280】 (Application Example 1) 【0281】 Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal". 【0282】 Repeated tasks and monotonous daily operations within the home are factors that waste time and effort for the user. In particular, these tasks often become routine tasks and prevent concentration on more productive activities. In such a situation, there is a need for a method to efficiently automate home tasks and reduce the burden on the user. 【0283】 The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0284】 In this invention, the server includes means for recording the operations performed by the user on a computer, means for analyzing characteristic patterns from the recorded operation information, and means for constructing an automation model based on the analyzed patterns. Thereby, it becomes possible to control a home robot and automatically perform repeated tasks. 【0285】 A "computer" is a device for performing information processing and is used to record and analyze the operations of the user. 【0286】 "Operation information" refers to a series of actions and input data performed by the user on the computer and is the basic data for extracting characteristic patterns from their records. 【0287】 The "characteristic pattern" refers to a series of frequently seen operations or routines analyzed from operation information and is the target of automation. 【0288】 The "automation model" is constructed based on the analyzed characteristic pattern and has guidelines or structures for the computer to automatically imitate operations under specific trigger conditions. 【0289】 The "household robot" is a device aimed at automatically performing specific repetitive tasks within the household and functions to reduce the user's daily operations. 【0290】 The "information processing device" is a hardware or software system for transmitting recorded operation information and performing centralized management. 【0291】 The "user evaluation" is the feedback given to the performance and results of the automation model and is useful for improving the model. 【0292】 To implement this invention, hardware such as a computer, an information processing device, and a household robot, as well as dedicated software operating on each hardware, are required. First, the user performs daily operations on the computer, and these operations are recorded by a dedicated program. The recorded operation information is analyzed to extract characteristic patterns. This analysis is performed using analysis software operating on the computer. 【0293】 Next, an automation model is constructed based on the analyzed characteristic pattern. The constructed model is transmitted to the household robot, and when a specific trigger condition occurs, it executes an operation to imitate that pattern. The household robot automatically starts moving according to the model transmitted from the computer and performs repetitive tasks. This operation includes, for example, routine tasks such as cleaning every morning. 【0294】 Furthermore, users evaluate the results of the tasks performed and send the feedback to the information processing device. This feedback is used to improve the model. For example, by providing feedback on the desired cleaning time, the automated model can be improved to adapt to that time. 【0295】 To configure this system, it is necessary to use an edge AI computing device such as the NVIDIA Jetson Nano as the computer and install software for building analysis and automation models. An example of a prompt message might be, "Tell us what you do every morning. Based on this information, we will suggest how a home robot can automate those tasks." This would enable the efficient automation of repetitive tasks in the home. 【0296】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0297】 Step 1: 【0298】 The terminal records a series of operations performed by the user on the computer. It receives user actions and input data as input, and stores this as operation information. As output, it generates log data of operation information organized chronologically. Specifically, it monitors the applications used and data entered by the user, and writes them to a file. 【0299】 Step 2: 【0300】 The server receives the operation information sent from the terminal and analyzes the characteristic patterns. As input, it uses the log data of the operation information. As data processing, it analyzes the frequently occurring operation sequences and similarities, and extracts patterns suitable for automation. As output, it generates a list of characteristic patterns obtained as the analysis result. As a specific operation, it uses a machine learning algorithm to detect iterative operations and organize them in an efficient format. 【0301】 Step 3: 【0302】 Based on the analysis result, the server constructs an automation model. As input, it uses the list of characteristic patterns. As data calculation, it designs rules and processes for automating each pattern and describes them as a generated AI model. As output, the constructed automation model is obtained. As a specific operation, it generates program code and scripts and constructs them as a model. 【0303】 Step 4: 【0304】 The server sends the constructed automation model to the terminal. As input, it uses the automation model. As output, a model in a state executable on the user's terminal is obtained. As a specific operation, it transfers the model data to the terminal via a communication network and deploys it in the execution environment on the terminal. 【0305】 Step 5: 【0306】 The terminal executes the automation model and controls the household robot. As input, it uses the automation trigger condition and the transmitted model. As output, the automatic execution of the daily tasks repeatedly performed by the user is obtained. As a specific operation, it sends commands to the robot and performs operations such as cleaning and opening the curtains at a specific time. 【0307】 Step 6: 【0308】 The user reviews the results of the tasks performed and provides feedback. The input is the results of tasks performed by the home robot. The output is feedback data containing evaluations and requests. Specifically, the user records aspects they dislike or want improved and sends this information to the server. 【0309】 Step 7: 【0310】 The server receives feedback from users and improves the automation model. Feedback data is used as input. Data processing involves adjusting the model based on user evaluations to create a more adaptive generative AI model. The output is a newly improved automation model. Specifically, the algorithm is retrained and optimized to improve user satisfaction. 【0311】 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. 【0312】 This invention is a system that incorporates an AI agent that records, analyzes, and automates user computer operations, as well as an emotion engine that recognizes user emotions in real time. This system comprehensively analyzes user actions and emotions to more adaptively automate business processes. 【0313】 The system first collects user operation data from the terminal. Furthermore, the emotion engine identifies the user's emotional state using facial recognition and voice tone analysis (and in some cases, biosignal analysis using sensors). This data is transmitted from the terminal to a server for centralized management. 【0314】 The server analyzes the relationship between actions and emotions based on the received data. It learns the user's preferred processes and patterns of operations that cause stress, and incorporates this into the automation model. Emotional data is also used as feedback and incorporated into the model training. 【0315】 Once an automation model is generated, the device executes this model. The automated operations are adaptively performed according to the user's emotional state. For example, if the user is feeling stressed, it may be possible to prioritize the automation of certain time-consuming tasks. 【0316】 For example, if the system detects that a user is experiencing fatigue while processing emails, it will automate more efficient email classification and reply creation. Furthermore, if the user exhibits positive emotions, it will execute standard automated processes, but if negative emotions are detected, it will adaptively adjust the process, prioritizing time-consuming tasks for automation. 【0317】 Thus, the present invention is a system that can dynamically respond to the diverse emotional states of users, thereby simultaneously achieving improved work efficiency and reduced user stress. 【0318】 The following describes the processing flow. 【0319】 Step 1: 【0320】 The device records user actions in real time. These actions include keyboard input, mouse movements, and application launches and shutdowns. Additionally, an emotion engine analyzes the user's facial expressions and voice to recognize their current emotional state. This information is stored on the device. 【0321】 Step 2: 【0322】 The device sends collected operational and emotional data to the server at regular intervals. The data is encrypted and uses appropriate security protocols to protect privacy. 【0323】 Step 3: 【0324】 The server analyzes the received data to identify user behavior and emotional patterns. By associating the timing of significant changes in user emotions with corresponding actions, a more precise automation model is formed. 【0325】 Step 4: 【0326】 The server generates an automated model based on behavioral and emotional patterns. This model includes a flexible set of rules that change priorities or modify specific actions based on the user's emotions. 【0327】 Step 5: 【0328】 The server sends the generated automation model to the terminal for installation. The terminal then prepares to automate operations based on this model according to the given conditions. 【0329】 Step 6: 【0330】 The device automates tasks according to an automation model, performing tasks on behalf of the user. An emotion engine continuously monitors the user's state, and if, for example, the user is stressed, it prioritizes automating tasks that help reduce stress. 【0331】 Step 7: 【0332】 Users review the results of automated tasks and provide feedback on their accuracy and satisfaction. This feedback is sent from the terminal to the server and collected. 【0333】 Step 8: 【0334】 The server adjusts and improves the automation model based on user feedback. Through this feedback loop, subsequent automations are adjusted to become more adaptive and efficient. 【0335】 (Example 2) 【0336】 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". 【0337】 When users utilize information processing devices, the stress and inefficiencies associated with their operation are significant, potentially reducing productivity and accuracy. In particular, conventional systems that do not consider the user's emotional state fail to adapt to user needs, resulting in increased stress. To address these challenges, a system is needed that analyzes and adaptively automates user actions and emotions in a coordinated manner. 【0338】 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. 【0339】 In this invention, the server includes means for recording operations performed by the user on the information processing device, means for integrating operation data and sentiment data and analyzing their relationships, and means for generating an automation model based on the analyzed patterns and sentiment data. This enables a reduction in user stress during operations and efficient and adaptive automation of tasks. 【0340】 An "information processing device" is a device used by users to perform operations and process data, and includes computers, smartphones, and other similar devices. 【0341】 "Operation data" refers to information such as keyboard and mouse input performed by the user on the information processing device, and application usage status. 【0342】 An "emotion analysis engine" refers to a software or hardware component that analyzes a user's face, voice, biometric information, etc., to recognize their emotions in real time. 【0343】 An "automation model" refers to a program or algorithm that automatically performs specific actions based on analyzed patterns and sentiment data. 【0344】 "Centralized management" refers to the process of collecting multiple pieces of information and managing them centrally, thereby enabling efficient access and use. 【0345】 This system consists of a user terminal and a server that analyzes and manages the data. First, the terminal records the user's actions. This action data includes keyboard and mouse input, application usage history, and more. The terminal also uses an emotion analysis engine to recognize the user's emotional state in real time. This engine collects the user's emotional data through facial recognition and voice tone analysis. 【0346】 This data is transmitted to a server via the network. The server integrates the received operation data and emotion data and analyzes the patterns. This analysis uses machine learning algorithms to find the relationship between user operation patterns and emotions. Analysis software such as Spark or TensorFlow may be used. Based on the results of this analysis, the server generates an automated model to optimize user operations. 【0347】 The automation model flexibly adjusts to the user's emotional state and adaptively automates operations. For example, if a user shows signs of fatigue while creating a document, the model reduces the user's workload by automatically searching for and suggesting relevant documents. It also generates an automated reply template if the user receives a message and indicates stress. 【0348】 A concrete example of a prompt message would be, "If fatigue is detected during email processing, which processes should be prioritized for automation?" This could be a suggestion or question about how to utilize the generative AI model. This would enable the design of more accurate automation processes. 【0349】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0350】 Step 1: 【0351】 The terminal records user actions in real time. Input includes operational data such as keyboard and mouse actions and application usage history. The terminal collects this data and records it in a database format. For example, it collects the time a user spends editing a document and the specific commands they use. 【0352】 Step 2: 【0353】 The device collects emotional data using an emotion analysis engine. Inputs include the user's facial expressions, voice tone, and biosensor signals. The device uses a machine learning model to estimate the user's emotional state from this input data and outputs the identified emotion as data. Specifically, it measures eyebrow movements, voice intonation, and other parameters to analyze emotions such as stress and joy. 【0354】 Step 3: 【0355】 The terminal sends the collected operational and emotional data to the server. The input is the previously collected data, which the terminal bundles into data packets and securely transmits to the server over the network. Specifically, a large amount of data is sent in a single batch using an endpoint-to-server data transfer protocol. 【0356】 Step 4: 【0357】 The server integrates and analyzes received operation data and emotion data. The input is data sent from the terminal. Using machine learning algorithms and data analysis software, the server analyzes the correlation between the user's operation patterns and emotional states from this data, and outputs the analysis results as patterns. Specifically, it compares the operation history with an emotion timeline to reveal which operations trigger specific emotions in the user. 【0358】 Step 5: 【0359】 The server generates an automated model based on the analysis results. The input is pattern information obtained through integrated analysis. Using generative AI modeling technology, the server creates a model that includes the optimal operating procedure according to the user's emotions and outputs it. As a specific example, it generates a model that prioritizes tasks based on emotions. 【0360】 Step 6: 【0361】 The terminal receives and executes an automation model from the server. The input is the automation model sent from the server. The terminal applies this model and performs specific actions that flexibly automate work processes according to the user's emotional state, thereby increasing the user's efficiency. For example, if the user is showing signs of fatigue, the terminal will prioritize automating email processing. 【0362】 (Application Example 2) 【0363】 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 as the "terminal". 【0364】 In modern brick-and-mortar stores, staff emotions and stress levels significantly impact the efficiency of customer service and customer satisfaction. However, a lack of means to properly manage these factors in real time and optimize operations makes it difficult to dynamically adjust work processes while considering staff emotional states in store operations. 【0365】 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. 【0366】 In this invention, the server includes facial recognition and voice analysis means for identifying the user's emotional state in real time, means for analyzing the relationship between the emotional state and behavioral data and reflecting it in an automated model, and means for transmitting recorded behavioral data to a central processing unit for centralized management. This enables dynamic optimization of operations and adaptive task assignment while taking into account the emotional state of store staff in physical stores. 【0367】 A "user" is an individual or group that operates an information processing device. 【0368】 An "information processing device" is an electronic device, such as a computer, used for recording, analyzing, and executing data. 【0369】 "Behavioral data" refers to information that describes a series of operations and procedures performed by a user on an information processing device. 【0370】 A "characteristic pattern" refers to the repetition of important operations or common characteristics identified from recorded behavioral data. 【0371】 An "automation model" is a program or system that is generated based on analyzed patterns to automatically handle specific tasks. 【0372】 "Facial recognition" is a technology that uses sensor devices such as cameras to analyze the features of a user's face and identify their emotional state. 【0373】 "Voice analysis means" refers to a technology that uses sensor devices such as microphones to analyze the characteristics of a user's voice and determine their emotional state and intentions. 【0374】 "Emotional state" refers to the user's psychological and emotional state, and includes, for example, stress, joy, and fatigue. 【0375】 A "central processing unit" is a server or data center used to process and manage multiple pieces of information in an integrated manner. 【0376】 The system for realizing this invention mainly consists of a user-operated terminal and a server. The terminal, as an information processing device, is equipped with a camera for facial recognition and a microphone for voice analysis, and records the user's behavioral data and emotional state in real time. When the user performs their daily tasks, the terminal records the behavioral data and further analyzes the user's emotional state using the camera and microphone. The analyzed data is transmitted to the server in stages. 【0377】 Based on the received data, the server uses Python-based natural language processing techniques and the machine learning framework TensorFlow to analyze the relationship between characteristic patterns in behavioral data and emotional states. The automation model generated from this analysis is designed to optimize business processes in accordance with the user's emotional state. In particular, when a user is experiencing stress, the server uses the automation model to prioritize automating time-consuming tasks and delivers them to the user. 【0378】 A concrete example of this system is inventory management in a store. When staff stress levels rise during work, the system prioritizes automating monotonous tasks such as rearranging merchandise and instructs other staff members to handle customer service. In this way, staff can work more efficiently and with less burden. 【0379】 An example of a prompt would be, "Please tell me how to implement a system that analyzes the emotions of store staff and teaches the AI ​​how to optimally allocate tasks." This would enhance the adaptive capabilities of the AI ​​model that monitors the psychological state of staff and dynamically adjusts task allocation. 【0380】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0381】 Step 1: 【0382】 The terminal records user actions on the information processing device. This includes actions such as operation logs, mouse clicks, and keyboard input. It receives various operation data performed by the user as input and records it as an operation log organized chronologically. The output is an action dataset for use in subsequent processing steps. 【0383】 Step 2: 【0384】 The device uses a camera and microphone to analyze the user's facial expressions and voice, identifying their emotional state in real time. It collects the user's facial image and voice tone as input. Using facial recognition and voice analysis algorithms, it generates emotional labels such as positive, negative, and stress. The output of this process is emotional state data recorded over time. 【0385】 Step 3: 【0386】 The terminal sends collected behavioral and emotional state data to the server. It receives the data generated in steps 1 and 2 as input. This data is packetized and sent to the server via the network. The output is an integrated dataset stored on the server. 【0387】 Step 4: 【0388】 The server analyzes the received integrated dataset to find relationships between behavioral data and emotional state data. It uses the collected integrated dataset as input. Machine learning techniques are used to extract features and analyze data correlations. The output is an automated model optimized based on this data. 【0389】 Step 5: 【0390】 The server optimizes business processes using the generated automation model. It uses the automation model, built based on analysis, as input. If users are experiencing stress, it adjusts work allocation, such as prioritizing specific tasks. The output is the optimized business procedure based on this. 【0391】 Step 6: 【0392】 The user performs tasks according to optimized workflow procedures. The workflow procedures are received from the server as input. The terminal continuously monitors the user's work and repeats the process from step 1 as needed. The output is efficient work execution and reduced user stress. 【0393】 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. 【0394】 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. 【0395】 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. 【0396】 [Third Embodiment] 【0397】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0398】 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. 【0399】 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). 【0400】 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. 【0401】 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. 【0402】 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). 【0403】 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. 【0404】 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. 【0405】 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. 【0406】 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. 【0407】 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. 【0408】 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". 【0409】 The embodiment of the system in this invention utilizes an AI agent running on a computer to automate the user's daily tasks. The program processing of this system is described below in natural language. 【0410】 User behavior collection and data transmission 【0411】 The device records all user actions in real time. Specifically, it records information such as when the user launched an application, what actions they performed, and what data they entered. This information is sent to the server at predetermined intervals. 【0412】 Data analysis on the server 【0413】 The server analyzes the received data and identifies frequently performed operation patterns. This allows it to recognize recurring tasks performed by users and determine which parts should be automated. 【0414】 Generation and execution of automation models 【0415】 The server generates an automated model based on the analysis results and sends it back to the terminal. The terminal uses this model to automatically perform actions that mimic user operations when specific trigger conditions are met. 【0416】 Processing user feedback 【0417】 Users review the results of the automated tasks performed and provide feedback on the system's performance. This feedback is sent to the server and used to improve future models. 【0418】 Specific example 【0419】 For example, if a user opens the same spreadsheet every morning and updates specific data, the device records this action, and the server detects it as a pattern. Based on this pattern, the server generates an automation model, and the device automatically performs this action from the next day onward. The user reviews the results and provides feedback to the server to fine-tune the spreadsheet updates as needed. This process allows the user to efficiently reduce the burden of repetitive tasks. 【0420】 The following describes the processing flow. 【0421】 Step 1: 【0422】 The device records the user's computer operations in real time. It monitors actions such as keyboard input, mouse clicks, and application launches and shutdowns, and stores this information as a log. 【0423】 Step 2: 【0424】 The device transmits accumulated operation data to the server at predetermined intervals. During this transmission, the data is appropriately encrypted to protect the user's privacy. 【0425】 Step 3: 【0426】 The server analyzes the received operation data and uses a pattern recognition algorithm to identify recurring operations. This analysis allows for the extraction of specific tasks or flows. 【0427】 Step 4: 【0428】 The server generates a model suitable for automation from the analyzed patterns. This model mimics repetitive user operations and includes a set of rules for executing automated tasks. 【0429】 Step 5: 【0430】 The server sends the generated automation model to the terminal for installation. The terminal then uses that model to prepare to execute automated tasks when the trigger conditions for user interaction are met. 【0431】 Step 6: 【0432】 The device automates tasks based on an automation model, performing tasks on behalf of the user. This automates everyday tasks such as drafting emails and entering data. 【0433】 Step 7: 【0434】 Users review the results of automated tasks and provide feedback on their accuracy and satisfaction. This feedback is sent from the terminal to the server. 【0435】 Step 8: 【0436】 The server receives user feedback and uses it to improve the automation model. This allows for adjustments to ensure that subsequent automation tasks are executed more efficiently and accurately. 【0437】 (Example 1) 【0438】 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." 【0439】 Conventional automation support systems suffer from insufficient processes for recording and analyzing user actions, resulting in reduced accuracy and efficiency of automation. Furthermore, the lack of model improvement based on user feedback makes continuous optimization difficult. 【0440】 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. 【0441】 In this invention, the server includes means for recording actions performed by the user on an information processing device, means for analyzing characteristic patterns from the recorded action information, means for generating an artificial intelligence model based on the analyzed patterns, means for transmitting the recorded action information to an aggregation device for centralized management, means for receiving evaluations from the user and improving the generated artificial intelligence model, and means for identifying automation candidates based on the user's actions and imitating them. This enables accurate recording and analysis of the user's actions, optimal automation, and continuous model improvement. 【0442】 "Information processing equipment" refers to all computer devices used by users to perform actions, and includes desktop computers, laptop computers, and tablet devices. 【0443】 "Operation information" refers to detailed data about a series of operations performed by the user, including application startup time, operation details, and entered data. 【0444】 A "data aggregation device" is a server device used to centrally manage and analyze operational information transmitted from multiple information processing devices. 【0445】 A "characteristic pattern" is a combination of frequently performed operations or a specific sequence of operations that can be extracted from recorded operational information. 【0446】 An "artificial intelligence model" is a program or algorithm generated based on characteristic patterns to automate user actions. 【0447】 "Evaluation" refers to the act of users providing feedback on automated tasks performed, indicating their impressions and suggestions for improvement regarding the system's performance and accuracy. 【0448】 "Candidates for automation" are specific tasks or work procedures that can be automated, identified based on user actions. 【0449】 This invention is a system that automates operations performed by users on a daily basis by making full use of information processing devices and aggregation devices. Specifically, it is a mechanism in which a terminal collects all of the user's actions in real time and transmits that information to a server. 【0450】 A terminal refers to hardware used by a user, such as a desktop computer, laptop computer, or tablet device. These terminals are connected to the internet and run software that records user activity logs. The activity log includes detailed information about the user's actions, such as application usage, entered data, and clicked buttons. 【0451】 The server is responsible for analyzing the received operation logs. Python-based data analysis libraries such as Pandas and NumPy are used for the analysis to identify frequently occurring operation patterns and tasks that can be automated. Furthermore, machine learning libraries such as TensorFlow and PyTorch are used to generate artificial intelligence models based on the analysis results. 【0452】 The generated artificial intelligence model is sent to the terminal and used for automation. This allows the system to automatically mimic operations when user-defined conditions are met. Furthermore, users can check the execution results and send feedback to the server, enabling continuous system improvement. 【0453】 For example, if a user wants to automate updating a spreadsheet every morning, the device records a series of actions, including opening and updating the spreadsheet. The server analyzes this information and recognizes it as a pattern. An AI model is generated, and the device automatically performs this operation from the next day onward. 【0454】 An example of a prompt to input into a generating AI model is, "Automate the spreadsheet update operation that the user performs every morning." Using this prompt allows for the efficient automation of specific tasks, reducing the user's workload. 【0455】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0456】 Step 1: 【0457】 The terminal records user actions in real time. Inputs include the applications used by the user, clicks and keystrokes, and login times. Based on this input, the operation information is stored in a database format. The output is operation log data organized by time. 【0458】 Step 2: 【0459】 The terminal sends recorded operation log data to the server at regular intervals. The data is encrypted during transmission. The input is the operation log data acquired in step 1, and the output is secure data used by the server's analysis system. 【0460】 Step 3: 【0461】 The server analyzes the received operation log data. The input is raw data sent from the terminal. The server uses Python-based data analysis libraries (e.g., Pandas or NumPy) to perform statistical processing on the data and identify user operation patterns. The output is the identified characteristic pattern data. 【0462】 Step 4: 【0463】 The server generates an artificial intelligence model based on the analyzed patterns. The input is the characteristic pattern data obtained in step 3. Machine learning libraries such as TensorFlow and PyTorch are used for generation, and a model that has learned the optimal automation procedure is generated. The output is the artificial intelligence model that is sent to the terminal. 【0464】 Step 5: 【0465】 The terminal automates its actions using an artificial intelligence model received from the server. This model is designed to mimic user actions when the conditions are met. The input is the artificial intelligence model generated in step 4, and the output is the automated sequence of actions from the user's perspective. 【0466】 Step 6: 【0467】 The user reviews the work performed by the automation and provides feedback. The input is the result of the automated operation in step 5 and the user's evaluation comments. The output is the feedback data received by the server, which is used to improve the model in the future. 【0468】 (Application Example 1) 【0469】 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." 【0470】 Repetitive and monotonous daily tasks within the home are a source of wasted time and effort for users. In particular, these tasks often become routine, hindering the focus on more productive activities. In this context, there is a need for methods to efficiently automate these household tasks and reduce the burden on users. 【0471】 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. 【0472】 In this invention, the server includes means for recording operations performed by the user on a computer, means for analyzing characteristic patterns from the recorded operation information, and means for constructing an automation model based on the analyzed patterns. This makes it possible to control a household robot and automatically perform repetitive tasks. 【0473】 A "computer" is a device used for information processing, specifically for recording and analyzing user operations. 【0474】 "Operation information" refers to a series of actions and input data performed by a user on a computer, and serves as foundational data for extracting characteristic patterns from these records. 【0475】 A "characteristic pattern" refers to a series of frequently occurring actions or routines that are analyzed from operational information and are targets for automation. 【0476】 An "automation model" is built on analyzed characteristic patterns and contains guidelines and structures that allow a computer to automatically mimic behavior under specific trigger conditions. 【0477】 A "household robot" is a device designed to automatically perform specific, repetitive tasks within the home, and functions to alleviate the user's daily workload. 【0478】 An "information processing device" is a hardware or software system for transmitting and centrally managing recorded operation information. 【0479】 "User evaluations" are feedback given regarding the performance and results of automated models, and are used to improve the models. 【0480】 To implement this invention, hardware such as a computer, information processing device, and home robot, as well as dedicated software that runs on each piece of hardware, are required. First, the user performs daily operations on the computer, and these operations are recorded by a dedicated program. The recorded operation information is analyzed to extract characteristic patterns. This analysis is performed using analysis software that runs on the computer. 【0481】 Next, an automation model is built based on the analyzed characteristic patterns. The built model is sent to a household robot, which then performs actions that mimic those patterns when specific trigger conditions occur. The household robot automatically starts moving according to the model sent from the computer and performs repetitive tasks. These actions include routine tasks such as cleaning every morning. 【0482】 Furthermore, users evaluate the results of the tasks performed and send the feedback to the information processing device. This feedback is used to improve the model. For example, by providing feedback on the desired cleaning time, the automated model can be improved to adapt to that time. 【0483】 To configure this system, it is necessary to use an edge AI computing device such as the NVIDIA Jetson Nano as the computer and install software for building analysis and automation models. An example of a prompt message might be, "Tell us what you do every morning. Based on this information, we will suggest how a home robot can automate those tasks." This would enable the efficient automation of repetitive tasks in the home. 【0484】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0485】 Step 1: 【0486】 The terminal records a series of operations performed by the user on the computer. It receives user actions and input data as input, and stores this as operation information. As output, it generates log data of operation information organized chronologically. Specifically, it monitors the applications used and data entered by the user, and writes them to a file. 【0487】 Step 2: 【0488】 The server receives operation information sent from the terminal and analyzes characteristic patterns. Log data of operation information is used as input. Data processing involves analyzing frequently occurring operation sequences and similarities to extract patterns suitable for automation. The output is a list of characteristic patterns obtained from the analysis. Specifically, machine learning algorithms are used to detect repetitive operations and organize them in an efficient format. 【0489】 Step 3: 【0490】 The server constructs an automation model based on the analysis results. It uses a list of characteristic patterns as input. For data computation, it designs rules and processes to automate each pattern and describes them as a generative AI model. The output is the constructed automation model. In terms of concrete operation, it generates program code or scripts and constructs them as a model. 【0491】 Step 4: 【0492】 The server sends the constructed automation model to the terminal. The automation model is used as input. The output is a model ready to run on the user's terminal. Specifically, the model data is transferred to the terminal via the communication network and deployed to the execution environment on the terminal. 【0493】 Step 5: 【0494】 The terminal executes automation models and controls household robots. It uses automation trigger conditions and transmitted models as inputs. The output is the automated execution of repetitive daily tasks performed by the user. Specifically, it sends commands to the robot to perform actions such as cleaning or opening curtains at specific times. 【0495】 Step 6: 【0496】 The user reviews the results of the tasks performed and provides feedback. The input is the results of tasks performed by the home robot. The output is feedback data containing evaluations and requests. Specifically, the user records aspects they dislike or want improved and sends this information to the server. 【0497】 Step 7: 【0498】 The server receives feedback from users and improves the automation model. Feedback data is used as input. Data processing involves adjusting the model based on user evaluations to create a more adaptive generative AI model. The output is a newly improved automation model. Specifically, the algorithm is retrained and optimized to improve user satisfaction. 【0499】 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. 【0500】 This invention is a system that incorporates an AI agent that records, analyzes, and automates user computer operations, as well as an emotion engine that recognizes user emotions in real time. This system comprehensively analyzes user actions and emotions to more adaptively automate business processes. 【0501】 The system first collects user operation data from the terminal. Furthermore, the emotion engine identifies the user's emotional state using facial recognition and voice tone analysis (and in some cases, biosignal analysis using sensors). This data is transmitted from the terminal to a server for centralized management. 【0502】 The server analyzes the relationship between actions and emotions based on the received data. It learns the user's preferred processes and patterns of operations that cause stress, and incorporates this into the automation model. Emotional data is also used as feedback and incorporated into the model training. 【0503】 Once an automation model is generated, the device executes this model. The automated operations are adaptively performed according to the user's emotional state. For example, if the user is feeling stressed, it may be possible to prioritize the automation of certain time-consuming tasks. 【0504】 For example, if the system detects that a user is experiencing fatigue while processing emails, it will automate more efficient email classification and reply creation. Furthermore, if the user exhibits positive emotions, it will execute standard automated processes, but if negative emotions are detected, it will adaptively adjust the process, prioritizing time-consuming tasks for automation. 【0505】 Thus, the present invention is a system that can dynamically respond to the diverse emotional states of users, thereby simultaneously achieving improved work efficiency and reduced user stress. 【0506】 The following describes the processing flow. 【0507】 Step 1: 【0508】 The device records user actions in real time. These actions include keyboard input, mouse movements, and application launches and shutdowns. Additionally, an emotion engine analyzes the user's facial expressions and voice to recognize their current emotional state. This information is stored on the device. 【0509】 Step 2: 【0510】 The device sends collected operational and emotional data to the server at regular intervals. The data is encrypted and uses appropriate security protocols to protect privacy. 【0511】 Step 3: 【0512】 The server analyzes the received data to identify user behavior and emotional patterns. By associating the timing of significant changes in user emotions with corresponding actions, a more precise automation model is formed. 【0513】 Step 4: 【0514】 The server generates an automated model based on behavioral and emotional patterns. This model includes a flexible set of rules that change priorities or modify specific actions based on the user's emotions. 【0515】 Step 5: 【0516】 The server sends the generated automation model to the terminal for installation. The terminal then prepares to automate operations based on this model according to the given conditions. 【0517】 Step 6: 【0518】 The device automates tasks according to an automation model, performing tasks on behalf of the user. An emotion engine continuously monitors the user's state, and if, for example, the user is stressed, it prioritizes automating tasks that help reduce stress. 【0519】 Step 7: 【0520】 Users review the results of automated tasks and provide feedback on their accuracy and satisfaction. This feedback is sent from the terminal to the server and collected. 【0521】 Step 8: 【0522】 The server adjusts and improves the automation model based on user feedback. Through this feedback loop, subsequent automations are adjusted to become more adaptive and efficient. 【0523】 (Example 2) 【0524】 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." 【0525】 When users utilize information processing devices, the stress and inefficiencies associated with their operation are significant, potentially reducing productivity and accuracy. In particular, conventional systems that do not consider the user's emotional state fail to adapt to user needs, resulting in increased stress. To address these challenges, a system is needed that analyzes and adaptively automates user actions and emotions in a coordinated manner. 【0526】 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. 【0527】 In this invention, the server includes means for recording operations performed by the user on the information processing device, means for integrating operation data and sentiment data and analyzing their relationships, and means for generating an automation model based on the analyzed patterns and sentiment data. This enables a reduction in user stress during operations and efficient and adaptive automation of tasks. 【0528】 An "information processing device" is a device used by users to perform operations and process data, and includes computers, smartphones, and other similar devices. 【0529】 "Operation data" refers to information such as keyboard and mouse input performed by the user on the information processing device, and application usage status. 【0530】 An "emotion analysis engine" refers to a software or hardware component that analyzes a user's face, voice, biometric information, etc., to recognize their emotions in real time. 【0531】 An "automation model" refers to a program or algorithm that automatically performs specific actions based on analyzed patterns and sentiment data. 【0532】 "Centralized management" refers to the process of collecting multiple pieces of information and managing them centrally, thereby enabling efficient access and use. 【0533】 This system consists of a user terminal and a server that analyzes and manages the data. First, the terminal records the user's actions. This action data includes keyboard and mouse input, application usage history, and more. The terminal also uses an emotion analysis engine to recognize the user's emotional state in real time. This engine collects the user's emotional data through facial recognition and voice tone analysis. 【0534】 This data is transmitted to a server via the network. The server integrates the received operation data and emotion data and analyzes the patterns. This analysis uses machine learning algorithms to find the relationship between user operation patterns and emotions. Analysis software such as Spark or TensorFlow may be used. Based on the results of this analysis, the server generates an automated model to optimize user operations. 【0535】 The automation model flexibly adjusts to the user's emotional state and adaptively automates operations. For example, if a user shows signs of fatigue while creating a document, the model reduces the user's workload by automatically searching for and suggesting relevant documents. It also generates an automated reply template if the user receives a message and indicates stress. 【0536】 A concrete example of a prompt message would be, "If fatigue is detected during email processing, which processes should be prioritized for automation?" This could be a suggestion or question about how to utilize the generative AI model. This would enable the design of more accurate automation processes. 【0537】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0538】 Step 1: 【0539】 The terminal records user actions in real time. Input includes operational data such as keyboard and mouse actions and application usage history. The terminal collects this data and records it in a database format. For example, it collects the time a user spends editing a document and the specific commands they use. 【0540】 Step 2: 【0541】 The device collects emotional data using an emotion analysis engine. Inputs include the user's facial expressions, voice tone, and biosensor signals. The device uses a machine learning model to estimate the user's emotional state from this input data and outputs the identified emotion as data. Specifically, it measures eyebrow movements, voice intonation, and other parameters to analyze emotions such as stress and joy. 【0542】 Step 3: 【0543】 The terminal sends the collected operational and emotional data to the server. The input is the previously collected data, which the terminal bundles into data packets and securely transmits to the server over the network. Specifically, a large amount of data is sent in a single batch using an endpoint-to-server data transfer protocol. 【0544】 Step 4: 【0545】 The server integrates and analyzes received operation data and emotion data. The input is data sent from the terminal. Using machine learning algorithms and data analysis software, the server analyzes the correlation between the user's operation patterns and emotional states from this data, and outputs the analysis results as patterns. Specifically, it compares the operation history with an emotion timeline to reveal which operations trigger specific emotions in the user. 【0546】 Step 5: 【0547】 The server generates an automated model based on the analysis results. The input is pattern information obtained through integrated analysis. Using generative AI modeling technology, the server creates a model that includes the optimal operating procedure according to the user's emotions and outputs it. As a specific example, it generates a model that prioritizes tasks based on emotions. 【0548】 Step 6: 【0549】 The terminal receives and executes an automation model from the server. The input is the automation model sent from the server. The terminal applies this model and performs specific actions that flexibly automate work processes according to the user's emotional state, thereby increasing the user's efficiency. For example, if the user is showing signs of fatigue, the terminal will prioritize automating email processing. 【0550】 (Application Example 2) 【0551】 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." 【0552】 In modern brick-and-mortar stores, staff emotions and stress levels significantly impact the efficiency of customer service and customer satisfaction. However, a lack of means to properly manage these factors in real time and optimize operations makes it difficult to dynamically adjust work processes while considering staff emotional states in store operations. 【0553】 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. 【0554】 In this invention, the server includes facial recognition and voice analysis means for identifying the user's emotional state in real time, means for analyzing the relationship between the emotional state and behavioral data and reflecting it in an automated model, and means for transmitting recorded behavioral data to a central processing unit for centralized management. This enables dynamic optimization of operations and adaptive task assignment while taking into account the emotional state of store staff in physical stores. 【0555】 A "user" is an individual or group that operates an information processing device. 【0556】 An "information processing device" is an electronic device, such as a computer, used for recording, analyzing, and executing data. 【0557】 "Behavioral data" refers to information that describes a series of operations and procedures performed by a user on an information processing device. 【0558】 A "characteristic pattern" refers to the repetition of important operations or common characteristics identified from recorded behavioral data. 【0559】 An "automation model" is a program or system that is generated based on analyzed patterns to automatically handle specific tasks. 【0560】 "Facial recognition" is a technology that uses sensor devices such as cameras to analyze the features of a user's face and identify their emotional state. 【0561】 "Voice analysis means" refers to a technology that uses sensor devices such as microphones to analyze the characteristics of a user's voice and determine their emotional state and intentions. 【0562】 "Emotional state" refers to the user's psychological and emotional state, and includes, for example, stress, joy, and fatigue. 【0563】 A "central processing unit" is a server or data center used to process and manage multiple pieces of information in an integrated manner. 【0564】 The system for realizing this invention mainly consists of a user-operated terminal and a server. The terminal, as an information processing device, is equipped with a camera for facial recognition and a microphone for voice analysis, and records the user's behavioral data and emotional state in real time. When the user performs their daily tasks, the terminal records the behavioral data and further analyzes the user's emotional state using the camera and microphone. The analyzed data is transmitted to the server in stages. 【0565】 Based on the received data, the server uses Python-based natural language processing techniques and the machine learning framework TensorFlow to analyze the relationship between characteristic patterns in behavioral data and emotional states. The automation model generated from this analysis is designed to optimize business processes in accordance with the user's emotional state. In particular, when a user is experiencing stress, the server uses the automation model to prioritize automating time-consuming tasks and delivers them to the user. 【0566】 A concrete example of this system is inventory management in a store. When staff stress levels rise during work, the system prioritizes automating monotonous tasks such as rearranging merchandise and instructs other staff members to handle customer service. In this way, staff can work more efficiently and with less burden. 【0567】 An example of a prompt would be, "Please tell me how to implement a system that analyzes the emotions of store staff and teaches the AI ​​how to optimally allocate tasks." This would enhance the adaptive capabilities of the AI ​​model that monitors the psychological state of staff and dynamically adjusts task allocation. 【0568】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0569】 Step 1: 【0570】 The terminal records user actions on the information processing device. This includes actions such as operation logs, mouse clicks, and keyboard input. It receives various operation data performed by the user as input and records it as an operation log organized chronologically. The output is an action dataset for use in subsequent processing steps. 【0571】 Step 2: 【0572】 The device uses a camera and microphone to analyze the user's facial expressions and voice, identifying their emotional state in real time. It collects the user's facial image and voice tone as input. Using facial recognition and voice analysis algorithms, it generates emotional labels such as positive, negative, and stress. The output of this process is emotional state data recorded over time. 【0573】 Step 3: 【0574】 The terminal sends collected behavioral and emotional state data to the server. It receives the data generated in steps 1 and 2 as input. This data is packetized and sent to the server via the network. The output is an integrated dataset stored on the server. 【0575】 Step 4: 【0576】 The server analyzes the received integrated dataset to find relationships between behavioral data and emotional state data. It uses the collected integrated dataset as input. Machine learning techniques are used to extract features and analyze data correlations. The output is an automated model optimized based on this data. 【0577】 Step 5: 【0578】 The server optimizes business processes using the generated automation model. It uses the automation model, built based on analysis, as input. If users are experiencing stress, it adjusts work allocation, such as prioritizing specific tasks. The output is the optimized business procedure based on this. 【0579】 Step 6: 【0580】 The user performs tasks according to optimized workflow procedures. The workflow procedures are received from the server as input. The terminal continuously monitors the user's work and repeats the process from step 1 as needed. The output is efficient work execution and reduced user stress. 【0581】 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. 【0582】 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. 【0583】 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. 【0584】 [Fourth Embodiment] 【0585】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0586】 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. 【0587】 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). 【0588】 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. 【0589】 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. 【0590】 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). 【0591】 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. 【0592】 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. 【0593】 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. 【0594】 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. 【0595】 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. 【0596】 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. 【0597】 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". 【0598】 The embodiment of the system in this invention utilizes an AI agent running on a computer to automate the user's daily tasks. The program processing of this system is described below in natural language. 【0599】 User behavior collection and data transmission 【0600】 The device records all user actions in real time. Specifically, it records information such as when the user launched an application, what actions they performed, and what data they entered. This information is sent to the server at predetermined intervals. 【0601】 Data analysis on the server 【0602】 The server analyzes the received data and identifies frequently performed operation patterns. This allows it to recognize recurring tasks performed by users and determine which parts should be automated. 【0603】 Generation and execution of automation models 【0604】 The server generates an automated model based on the analysis results and sends it back to the terminal. The terminal uses this model to automatically perform actions that mimic user operations when specific trigger conditions are met. 【0605】 Processing user feedback 【0606】 Users review the results of the automated tasks performed and provide feedback on the system's performance. This feedback is sent to the server and used to improve future models. 【0607】 Specific example 【0608】 For example, if a user opens the same spreadsheet every morning and updates specific data, the device records this action, and the server detects it as a pattern. Based on this pattern, the server generates an automation model, and the device automatically performs this action from the next day onward. The user reviews the results and provides feedback to the server to fine-tune the spreadsheet updates as needed. This process allows the user to efficiently reduce the burden of repetitive tasks. 【0609】 The following describes the processing flow. 【0610】 Step 1: 【0611】 The device records the user's computer operations in real time. It monitors actions such as keyboard input, mouse clicks, and application launches and shutdowns, and stores this information as a log. 【0612】 Step 2: 【0613】 The device transmits accumulated operation data to the server at predetermined intervals. During this transmission, the data is appropriately encrypted to protect the user's privacy. 【0614】 Step 3: 【0615】 The server analyzes the received operation data and uses a pattern recognition algorithm to identify recurring operations. This analysis allows for the extraction of specific tasks or flows. 【0616】 Step 4: 【0617】 The server generates a model suitable for automation from the analyzed patterns. This model mimics repetitive user operations and includes a set of rules for executing automated tasks. 【0618】 Step 5: 【0619】 The server sends the generated automation model to the terminal for installation. The terminal then uses that model to prepare to execute automated tasks when the trigger conditions for user interaction are met. 【0620】 Step 6: 【0621】 The device automates tasks based on an automation model, performing tasks on behalf of the user. This automates everyday tasks such as drafting emails and entering data. 【0622】 Step 7: 【0623】 Users review the results of automated tasks and provide feedback on their accuracy and satisfaction. This feedback is sent from the terminal to the server. 【0624】 Step 8: 【0625】 The server receives user feedback and uses it to improve the automation model. This allows for adjustments to ensure that subsequent automation tasks are executed more efficiently and accurately. 【0626】 (Example 1) 【0627】 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". 【0628】 Conventional automation support systems suffer from insufficient processes for recording and analyzing user actions, resulting in reduced accuracy and efficiency of automation. Furthermore, the lack of model improvement based on user feedback makes continuous optimization difficult. 【0629】 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. 【0630】 In this invention, the server includes means for recording actions performed by the user on an information processing device, means for analyzing characteristic patterns from the recorded action information, means for generating an artificial intelligence model based on the analyzed patterns, means for transmitting the recorded action information to an aggregation device for centralized management, means for receiving evaluations from the user and improving the generated artificial intelligence model, and means for identifying automation candidates based on the user's actions and imitating them. This enables accurate recording and analysis of the user's actions, optimal automation, and continuous model improvement. 【0631】 "Information processing equipment" refers to all computer devices used by users to perform actions, and includes desktop computers, laptop computers, and tablet devices. 【0632】 "Operation information" refers to detailed data about a series of operations performed by the user, including application startup time, operation details, and entered data. 【0633】 A "data aggregation device" is a server device used to centrally manage and analyze operational information transmitted from multiple information processing devices. 【0634】 A "characteristic pattern" is a combination of frequently performed operations or a specific sequence of operations that can be extracted from recorded operational information. 【0635】 An "artificial intelligence model" is a program or algorithm generated based on characteristic patterns to automate user actions. 【0636】 "Evaluation" refers to the act of users providing feedback on automated tasks performed, indicating their impressions and suggestions for improvement regarding the system's performance and accuracy. 【0637】 "Candidates for automation" are specific tasks or work procedures that can be automated, identified based on user actions. 【0638】 This invention is a system that automates operations performed by users on a daily basis by making full use of information processing devices and aggregation devices. Specifically, it is a mechanism in which a terminal collects all of the user's actions in real time and transmits that information to a server. 【0639】 A terminal refers to hardware used by a user, such as a desktop computer, laptop computer, or tablet device. These terminals are connected to the internet and run software that records user activity logs. The activity log includes detailed information about the user's actions, such as application usage, entered data, and clicked buttons. 【0640】 The server is responsible for analyzing the received operation logs. Python-based data analysis libraries such as Pandas and NumPy are used for the analysis to identify frequently occurring operation patterns and tasks that can be automated. Furthermore, machine learning libraries such as TensorFlow and PyTorch are used to generate artificial intelligence models based on the analysis results. 【0641】 The generated artificial intelligence model is sent to the terminal and used for automation. This allows the system to automatically mimic operations when user-defined conditions are met. Furthermore, users can check the execution results and send feedback to the server, enabling continuous system improvement. 【0642】 For example, if a user wants to automate updating a spreadsheet every morning, the device records a series of actions, including opening and updating the spreadsheet. The server analyzes this information and recognizes it as a pattern. An AI model is generated, and the device automatically performs this operation from the next day onward. 【0643】 An example of a prompt to input into a generating AI model is, "Automate the spreadsheet update operation that the user performs every morning." Using this prompt allows for the efficient automation of specific tasks, reducing the user's workload. 【0644】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0645】 Step 1: 【0646】 The terminal records user actions in real time. Inputs include the applications used by the user, clicks and keystrokes, and login times. Based on this input, the operation information is stored in a database format. The output is operation log data organized by time. 【0647】 Step 2: 【0648】 The terminal sends recorded operation log data to the server at regular intervals. The data is encrypted during transmission. The input is the operation log data acquired in step 1, and the output is secure data used by the server's analysis system. 【0649】 Step 3: 【0650】 The server analyzes the received operation log data. The input is raw data sent from the terminal. The server uses Python-based data analysis libraries (e.g., Pandas or NumPy) to perform statistical processing on the data and identify user operation patterns. The output is the identified characteristic pattern data. 【0651】 Step 4: 【0652】 The server generates an artificial intelligence model based on the analyzed patterns. The input is the characteristic pattern data obtained in step 3. Machine learning libraries such as TensorFlow and PyTorch are used for generation, and a model that has learned the optimal automation procedure is generated. The output is the artificial intelligence model that is sent to the terminal. 【0653】 Step 5: 【0654】 The terminal automates its actions using an artificial intelligence model received from the server. This model is designed to mimic user actions when the conditions are met. The input is the artificial intelligence model generated in step 4, and the output is the automated sequence of actions from the user's perspective. 【0655】 Step 6: 【0656】 The user reviews the work performed by the automation and provides feedback. The input is the result of the automated operation in step 5 and the user's evaluation comments. The output is the feedback data received by the server, which is used to improve the model in the future. 【0657】 (Application Example 1) 【0658】 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". 【0659】 Repetitive and monotonous daily tasks within the home are a source of wasted time and effort for users. In particular, these tasks often become routine, hindering the focus on more productive activities. In this context, there is a need for methods to efficiently automate these household tasks and reduce the burden on users. 【0660】 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. 【0661】 In this invention, the server includes means for recording operations performed by the user on a computer, means for analyzing characteristic patterns from the recorded operation information, and means for constructing an automation model based on the analyzed patterns. This makes it possible to control a household robot and automatically perform repetitive tasks. 【0662】 A "computer" is a device used for information processing, specifically for recording and analyzing user operations. 【0663】 "Operation information" refers to a series of actions and input data performed by a user on a computer, and serves as foundational data for extracting characteristic patterns from these records. 【0664】 A "characteristic pattern" refers to a series of frequently occurring actions or routines that are analyzed from operational information and are targets for automation. 【0665】 An "automation model" is built on analyzed characteristic patterns and contains guidelines and structures that allow a computer to automatically mimic behavior under specific trigger conditions. 【0666】 A "household robot" is a device designed to automatically perform specific, repetitive tasks within the home, and functions to alleviate the user's daily workload. 【0667】 An "information processing device" is a hardware or software system for transmitting and centrally managing recorded operation information. 【0668】 "User evaluations" are feedback given regarding the performance and results of automated models, and are used to improve the models. 【0669】 To implement this invention, hardware such as a computer, information processing device, and home robot, as well as dedicated software that runs on each piece of hardware, are required. First, the user performs daily operations on the computer, and these operations are recorded by a dedicated program. The recorded operation information is analyzed to extract characteristic patterns. This analysis is performed using analysis software that runs on the computer. 【0670】 Next, an automation model is built based on the analyzed characteristic patterns. The built model is sent to a household robot, which then performs actions that mimic those patterns when specific trigger conditions occur. The household robot automatically starts moving according to the model sent from the computer and performs repetitive tasks. These actions include routine tasks such as cleaning every morning. 【0671】 Furthermore, users evaluate the results of the tasks performed and send the feedback to the information processing device. This feedback is used to improve the model. For example, by providing feedback on the desired cleaning time, the automated model can be improved to adapt to that time. 【0672】 To configure this system, it is necessary to use an edge AI computing device such as the NVIDIA Jetson Nano as the computer and install software for building analysis and automation models. An example of a prompt message might be, "Tell us what you do every morning. Based on this information, we will suggest how a home robot can automate those tasks." This would enable the efficient automation of repetitive tasks in the home. 【0673】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0674】 Step 1: 【0675】 The terminal records a series of operations performed by the user on the computer. It receives user actions and input data as input, and stores this as operation information. As output, it generates log data of operation information organized chronologically. Specifically, it monitors the applications used and data entered by the user, and writes them to a file. 【0676】 Step 2: 【0677】 The server receives operation information sent from the terminal and analyzes characteristic patterns. Log data of operation information is used as input. Data processing involves analyzing frequently occurring operation sequences and similarities to extract patterns suitable for automation. The output is a list of characteristic patterns obtained from the analysis. Specifically, machine learning algorithms are used to detect repetitive operations and organize them in an efficient format. 【0678】 Step 3: 【0679】 The server constructs an automation model based on the analysis results. It uses a list of characteristic patterns as input. For data computation, it designs rules and processes to automate each pattern and describes them as a generative AI model. The output is the constructed automation model. In terms of concrete operation, it generates program code or scripts and constructs them as a model. 【0680】 Step 4: 【0681】 The server sends the constructed automation model to the terminal. The automation model is used as input. The output is a model ready to run on the user's terminal. Specifically, the model data is transferred to the terminal via the communication network and deployed to the execution environment on the terminal. 【0682】 Step 5: 【0683】 The terminal executes automation models and controls household robots. It uses automation trigger conditions and transmitted models as inputs. The output is the automated execution of repetitive daily tasks performed by the user. Specifically, it sends commands to the robot to perform actions such as cleaning or opening curtains at specific times. 【0684】 Step 6: 【0685】 The user reviews the results of the tasks performed and provides feedback. The input is the results of tasks performed by the home robot. The output is feedback data containing evaluations and requests. Specifically, the user records aspects they dislike or want improved and sends this information to the server. 【0686】 Step 7: 【0687】 The server receives feedback from users and improves the automation model. Feedback data is used as input. Data processing involves adjusting the model based on user evaluations to create a more adaptive generative AI model. The output is a newly improved automation model. Specifically, the algorithm is retrained and optimized to improve user satisfaction. 【0688】 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. 【0689】 This invention is a system that incorporates an AI agent that records, analyzes, and automates user computer operations, as well as an emotion engine that recognizes user emotions in real time. This system comprehensively analyzes user actions and emotions to more adaptively automate business processes. 【0690】 The system first collects user operation data from the terminal. Furthermore, the emotion engine identifies the user's emotional state using facial recognition and voice tone analysis (and in some cases, biosignal analysis using sensors). This data is transmitted from the terminal to a server for centralized management. 【0691】 The server analyzes the relationship between actions and emotions based on the received data. It learns the user's preferred processes and patterns of operations that cause stress, and incorporates this into the automation model. Emotional data is also used as feedback and incorporated into the model training. 【0692】 Once an automation model is generated, the device executes this model. The automated operations are adaptively performed according to the user's emotional state. For example, if the user is feeling stressed, it may be possible to prioritize the automation of certain time-consuming tasks. 【0693】 For example, if the system detects that a user is experiencing fatigue while processing emails, it will automate more efficient email classification and reply creation. Furthermore, if the user exhibits positive emotions, it will execute standard automated processes, but if negative emotions are detected, it will adaptively adjust the process, prioritizing time-consuming tasks for automation. 【0694】 Thus, the present invention is a system that can dynamically respond to the diverse emotional states of users, thereby simultaneously achieving improved work efficiency and reduced user stress. 【0695】 The following describes the processing flow. 【0696】 Step 1: 【0697】 The device records user actions in real time. These actions include keyboard input, mouse movements, and application launches and shutdowns. Additionally, an emotion engine analyzes the user's facial expressions and voice to recognize their current emotional state. This information is stored on the device. 【0698】 Step 2: 【0699】 The device sends collected operational and emotional data to the server at regular intervals. The data is encrypted and uses appropriate security protocols to protect privacy. 【0700】 Step 3: 【0701】 The server analyzes the received data to identify user behavior and emotional patterns. By associating the timing of significant changes in user emotions with corresponding actions, a more precise automation model is formed. 【0702】 Step 4: 【0703】 The server generates an automated model based on behavioral and emotional patterns. This model includes a flexible set of rules that change priorities or modify specific actions based on the user's emotions. 【0704】 Step 5: 【0705】 The server sends the generated automation model to the terminal for installation. The terminal then prepares to automate operations based on this model according to the given conditions. 【0706】 Step 6: 【0707】 The device automates tasks according to an automation model, performing tasks on behalf of the user. An emotion engine continuously monitors the user's state, and if, for example, the user is stressed, it prioritizes automating tasks that help reduce stress. 【0708】 Step 7: 【0709】 Users review the results of automated tasks and provide feedback on their accuracy and satisfaction. This feedback is sent from the terminal to the server and collected. 【0710】 Step 8: 【0711】 The server adjusts and improves the automation model based on user feedback. Through this feedback loop, subsequent automations are adjusted to become more adaptive and efficient. 【0712】 (Example 2) 【0713】 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". 【0714】 When users utilize information processing devices, the stress and inefficiencies associated with their operation are significant, potentially reducing productivity and accuracy. In particular, conventional systems that do not consider the user's emotional state fail to adapt to user needs, resulting in increased stress. To address these challenges, a system is needed that analyzes and adaptively automates user actions and emotions in a coordinated manner. 【0715】 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. 【0716】 In this invention, the server includes means for recording operations performed by the user on the information processing device, means for integrating operation data and sentiment data and analyzing their relationships, and means for generating an automation model based on the analyzed patterns and sentiment data. This enables a reduction in user stress during operations and efficient and adaptive automation of tasks. 【0717】 An "information processing device" is a device used by users to perform operations and process data, and includes computers, smartphones, and other similar devices. 【0718】 "Operation data" refers to information such as keyboard and mouse input performed by the user on the information processing device, and application usage status. 【0719】 An "emotion analysis engine" refers to a software or hardware component that analyzes a user's face, voice, biometric information, etc., to recognize their emotions in real time. 【0720】 An "automation model" refers to a program or algorithm that automatically performs specific actions based on analyzed patterns and sentiment data. 【0721】 "Centralized management" refers to the process of collecting multiple pieces of information and managing them centrally, thereby enabling efficient access and use. 【0722】 This system consists of a user terminal and a server that analyzes and manages the data. First, the terminal records the user's actions. This action data includes keyboard and mouse input, application usage history, and more. The terminal also uses an emotion analysis engine to recognize the user's emotional state in real time. This engine collects the user's emotional data through facial recognition and voice tone analysis. 【0723】 This data is transmitted to a server via the network. The server integrates the received operation data and emotion data and analyzes the patterns. This analysis uses machine learning algorithms to find the relationship between user operation patterns and emotions. Analysis software such as Spark or TensorFlow may be used. Based on the results of this analysis, the server generates an automated model to optimize user operations. 【0724】 The automation model flexibly adjusts to the user's emotional state and adaptively automates operations. For example, if a user shows signs of fatigue while creating a document, the model reduces the user's workload by automatically searching for and suggesting relevant documents. It also generates an automated reply template if the user receives a message and indicates stress. 【0725】 A concrete example of a prompt message would be, "If fatigue is detected during email processing, which processes should be prioritized for automation?" This could be a suggestion or question about how to utilize the generative AI model. This would enable the design of more accurate automation processes. 【0726】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0727】 Step 1: 【0728】 The terminal records user actions in real time. Input includes operational data such as keyboard and mouse actions and application usage history. The terminal collects this data and records it in a database format. For example, it collects the time a user spends editing a document and the specific commands they use. 【0729】 Step 2: 【0730】 The device collects emotional data using an emotion analysis engine. Inputs include the user's facial expressions, voice tone, and biosensor signals. The device uses a machine learning model to estimate the user's emotional state from this input data and outputs the identified emotion as data. Specifically, it measures eyebrow movements, voice intonation, and other parameters to analyze emotions such as stress and joy. 【0731】 Step 3: 【0732】 The terminal sends the collected operational and emotional data to the server. The input is the previously collected data, which the terminal bundles into data packets and securely transmits to the server over the network. Specifically, a large amount of data is sent in a single batch using an endpoint-to-server data transfer protocol. 【0733】 Step 4: 【0734】 The server integrates and analyzes received operation data and emotion data. The input is data sent from the terminal. Using machine learning algorithms and data analysis software, the server analyzes the correlation between the user's operation patterns and emotional states from this data, and outputs the analysis results as patterns. Specifically, it compares the operation history with an emotion timeline to reveal which operations trigger specific emotions in the user. 【0735】 Step 5: 【0736】 The server generates an automated model based on the analysis results. The input is pattern information obtained through integrated analysis. Using generative AI modeling technology, the server creates a model that includes the optimal operating procedure according to the user's emotions and outputs it. As a specific example, it generates a model that prioritizes tasks based on emotions. 【0737】 Step 6: 【0738】 The terminal receives and executes an automation model from the server. The input is the automation model sent from the server. The terminal applies this model and performs specific actions that flexibly automate work processes according to the user's emotional state, thereby increasing the user's efficiency. For example, if the user is showing signs of fatigue, the terminal will prioritize automating email processing. 【0739】 (Application Example 2) 【0740】 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". 【0741】 In modern brick-and-mortar stores, staff emotions and stress levels significantly impact the efficiency of customer service and customer satisfaction. However, a lack of means to properly manage these factors in real time and optimize operations makes it difficult to dynamically adjust work processes while considering staff emotional states in store operations. 【0742】 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. 【0743】 In this invention, the server includes facial recognition and voice analysis means for identifying the user's emotional state in real time, means for analyzing the relationship between the emotional state and behavioral data and reflecting it in an automated model, and means for transmitting recorded behavioral data to a central processing unit for centralized management. This enables dynamic optimization of operations and adaptive task assignment while taking into account the emotional state of store staff in physical stores. 【0744】 A "user" is an individual or group that operates an information processing device. 【0745】 An "information processing device" is an electronic device, such as a computer, used for recording, analyzing, and executing data. 【0746】 "Behavioral data" refers to information that describes a series of operations and procedures performed by a user on an information processing device. 【0747】 A "characteristic pattern" refers to the repetition of important operations or common characteristics identified from recorded behavioral data. 【0748】 An "automation model" is a program or system that is generated based on analyzed patterns to automatically handle specific tasks. 【0749】 "Facial recognition" is a technology that uses sensor devices such as cameras to analyze the features of a user's face and identify their emotional state. 【0750】 "Voice analysis means" refers to a technology that uses sensor devices such as microphones to analyze the characteristics of a user's voice and determine their emotional state and intentions. 【0751】 "Emotional state" refers to the user's psychological and emotional state, and includes, for example, stress, joy, and fatigue. 【0752】 A "central processing unit" is a server or data center used to process and manage multiple pieces of information in an integrated manner. 【0753】 The system for realizing this invention mainly consists of a user-operated terminal and a server. The terminal, as an information processing device, is equipped with a camera for facial recognition and a microphone for voice analysis, and records the user's behavioral data and emotional state in real time. When the user performs their daily tasks, the terminal records the behavioral data and further analyzes the user's emotional state using the camera and microphone. The analyzed data is transmitted to the server in stages. 【0754】 Based on the received data, the server uses Python-based natural language processing techniques and the machine learning framework TensorFlow to analyze the relationship between characteristic patterns in behavioral data and emotional states. The automation model generated from this analysis is designed to optimize business processes in accordance with the user's emotional state. In particular, when a user is experiencing stress, the server uses the automation model to prioritize automating time-consuming tasks and delivers them to the user. 【0755】 A concrete example of this system is inventory management in a store. When staff stress levels rise during work, the system prioritizes automating monotonous tasks such as rearranging merchandise and instructs other staff members to handle customer service. In this way, staff can work more efficiently and with less burden. 【0756】 An example of a prompt would be, "Please tell me how to implement a system that analyzes the emotions of store staff and teaches the AI ​​how to optimally allocate tasks." This would enhance the adaptive capabilities of the AI ​​model that monitors the psychological state of staff and dynamically adjusts task allocation. 【0757】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0758】 Step 1: 【0759】 The terminal records user actions on the information processing device. This includes actions such as operation logs, mouse clicks, and keyboard input. It receives various operation data performed by the user as input and records it as an operation log organized chronologically. The output is an action dataset for use in subsequent processing steps. 【0760】 Step 2: 【0761】 The device uses a camera and microphone to analyze the user's facial expressions and voice, identifying their emotional state in real time. It collects the user's facial image and voice tone as input. Using facial recognition and voice analysis algorithms, it generates emotional labels such as positive, negative, and stress. The output of this process is emotional state data recorded over time. 【0762】 Step 3: 【0763】 The terminal sends collected behavioral and emotional state data to the server. It receives the data generated in steps 1 and 2 as input. This data is packetized and sent to the server via the network. The output is an integrated dataset stored on the server. 【0764】 Step 4: 【0765】 The server analyzes the received integrated dataset to find relationships between behavioral data and emotional state data. It uses the collected integrated dataset as input. Machine learning techniques are used to extract features and analyze data correlations. The output is an automated model optimized based on this data. 【0766】 Step 5: 【0767】 The server optimizes business processes using the generated automation model. It uses the automation model, built based on analysis, as input. If users are experiencing stress, it adjusts work allocation, such as prioritizing specific tasks. The output is the optimized business procedure based on this. 【0768】 Step 6: 【0769】 The user performs tasks according to optimized workflow procedures. The workflow procedures are received from the server as input. The terminal continuously monitors the user's work and repeats the process from step 1 as needed. The output is efficient work execution and reduced user stress. 【0770】 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. 【0771】 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. 【0772】 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. 【0773】 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. 【0774】 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. 【0775】 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. 【0776】 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. 【0777】 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. 【0778】 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." 【0779】 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. 【0780】 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. 【0781】 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. 【0782】 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. 【0783】 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. 【0784】 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. 【0785】 The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using this memory. 【0786】 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. 【0787】 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. 【0788】 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. 【0789】 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. 【0790】 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. 【0791】 The following is further disclosed regarding the embodiments described above. 【0792】 (Claim 1) 【0793】 A means of recording actions performed by a user on a computer, 【0794】 A means for analyzing characteristic patterns from recorded motion data, 【0795】 Means for generating an automated model based on the analyzed patterns, 【0796】 A means of running the generated automation model on a computer, 【0797】 A system that includes this. 【0798】 (Claim 2) 【0799】 The system according to claim 1, further comprising means for receiving user feedback and improving the generated automation model. 【0800】 (Claim 3) 【0801】 The system according to claim 1, further comprising means for transmitting recorded operational data to a server for centralized management. 【0802】 "Example 1" 【0803】 (Claim 1) 【0804】 A means for recording the actions performed by the user on the information processing device, 【0805】 A means for analyzing characteristic patterns from recorded motion information, 【0806】 A means for generating an artificial intelligence model based on analyzed patterns, 【0807】 A means for executing the generated artificial intelligence model on an information processing device, 【0808】 A means for transmitting recorded operational information to a centralized device for centralized management, 【0809】 A system that includes this. 【0810】 (Claim 2) 【0811】 The system according to claim 1, further comprising means for receiving user feedback and improving the generated artificial intelligence model. 【0812】 (Claim 3) 【0813】 The system according to claim 1, further comprising means for identifying and mimicking candidates for automation based on user actions. 【0814】 "Application Example 1" 【0815】 (Claim 1) 【0816】 A means of recording the operations performed by the user on the computer, 【0817】 A means for analyzing characteristic patterns from recorded operation information, 【0818】 Means for constructing an automated model based on the analyzed patterns, 【0819】 Means for executing the constructed automation model on a computer, 【0820】 A means of controlling a household robot to automatically perform repetitive household tasks based on the results of recording and analyzing those tasks, 【0821】 A system that includes this. 【0822】 (Claim 2) 【0823】 The system according to claim 1, further comprising means for receiving user feedback and improving the built automation model. 【0824】 (Claim 3) 【0825】 The system according to claim 1, further comprising means for transmitting recorded operation information to an information processing device and centrally managing it. 【0826】 "Example 2 of combining an emotion engine" 【0827】 (Claim 1) 【0828】 A means for recording operations performed by a user on an information processing device, 【0829】 A means for analyzing characteristic patterns from recorded operation data, 【0830】 A method using an emotion analysis engine to recognize the user's emotional state in real time, 【0831】 A means of integrating operational data and emotional data and analyzing their relationships, 【0832】 A means for generating an automated model based on analyzed patterns and sentiment data, 【0833】 A means for executing the generated automation model on an information processing device and adaptively automating operations according to the user's emotional state, 【0834】 A system that includes this. 【0835】 (Claim 2) 【0836】 The system according to claim 1, further comprising means for receiving user responses and improving the generated automation model. 【0837】 (Claim 3) 【0838】 The system according to claim 1, further comprising means for transmitting recorded operation data and emotion data to an information processing device and centrally managing them. 【0839】 "Application example 2 when combining with an emotional engine" 【0840】 (Claim 1) 【0841】 A means for recording the actions performed by a user on an information processing device, 【0842】 A means of analyzing characteristic patterns from recorded behavioral data, 【0843】 Means for generating an automated model based on the analyzed patterns, 【0844】 A means for executing the generated automation model on an information processing device, 【0845】 A means for facial recognition and voice analysis to identify the user's emotional state in real time, 【0846】 A means to analyze the relationship between emotional states and behavioral data and reflect it in automated models, 【0847】 A system that includes this. 【0848】 (Claim 2) 【0849】 The system according to claim 1, further comprising means for receiving user feedback and improving the generated automation model. 【0850】 (Claim 3) 【0851】 The system according to claim 1, further comprising means for transmitting recorded behavioral data to a central processing unit and centrally managing it. [Explanation of symbols] 【0852】 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] A means of recording actions performed by a user on a computer, A means for analyzing characteristic patterns from recorded motion data, Means for generating an automated model based on the analyzed patterns, A means of running the generated automation model on a computer, A system that includes this. [Claim 2] The system according to claim 1, further comprising means for receiving user feedback and improving the generated automation model. [Claim 3] The system according to claim 1, further comprising means for transmitting recorded operation data to a server and centrally managing it.

Images