system

Abstract

The system according to this embodiment aims to automate and efficiently process complex computer operations. [Solution] The system according to the embodiment comprises a screen recognition unit, a user command processing unit, a task execution unit, and a feedback unit. The screen recognition unit recognizes elements on the screen and grasps the current state. The user command processing unit understands user instructions entered via voice or text based on the information recognized by the screen recognition unit. The task execution unit controls mouse movements and keyboard inputs based on the instructions understood by the user command processing unit and automatically performs tasks. The feedback unit reconfirms the results of the tasks performed by the task execution unit and performs additional processing as necessary.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the system for automating computer operations is not sufficiently advanced and it is difficult to efficiently process complex tasks.

[0005] The system according to the embodiment aims to automate complex computer operations and process them efficiently.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a screen recognition unit, a user command processing unit, a task execution unit, and a feedback unit. The screen recognition unit recognizes elements on the screen and understands the current state. The user command processing unit understands user instructions entered via voice or text based on the information recognized by the screen recognition unit. The task execution unit controls mouse movements and keyboard inputs based on the instructions understood by the user command processing unit to automatically perform tasks. The feedback unit reconfirms the results of the tasks performed by the task execution unit and performs additional processing as necessary. [Effects of the Invention]

[0007] The system according to this embodiment can automate and efficiently process complex computer operations. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9]This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The AI ​​agent system according to an embodiment of the present invention is a system that utilizes generative AI to enable human-level computer operation. This AI agent system interacts with the user using all computer input devices (microphone, screen, mouse, keyboard, etc.) and operates the computer like a human. The specific configuration and functions are as follows: First, the AI ​​agent system uses computer vision technology for screen recognition and understanding to recognize elements on the screen and grasp the current state. It periodically captures the screen and extracts important information. Next, as processing user commands, the AI ​​agent system utilizes natural language processing to understand user instructions entered in voice or text. Based on the instructions, it creates an appropriate work plan. In the automated execution of tasks, the AI ​​agent system controls mouse movements and keyboard input to automatically perform the tasks instructed by the user. It utilizes generative AI models to generate and automate complex work procedures. Furthermore, as performance improvement through a feedback loop, the AI ​​agent system re-examines the work results and performs additional processing as needed. Through reinforcement learning, it learns from experience and continuously improves performance. This AI agent system automates and optimizes key tasks such as requirements definition, design, and schedule management, efficiently handling repetitive and complex tasks. Applicable to various industrial sectors, it aims to innovate overall business processes. For example, AI agent systems are expected to improve operational efficiency, reduce costs, decrease errors and improve quality, enable highly versatile automation, and strengthen market competitiveness. Specifically, it significantly reduces the time spent on repetitive tasks, increasing the productivity of the entire team. Automation of tasks allows teams to focus on important and creative tasks. Optimization of human resources reduces labor and operating costs, and streamlining business processes improves overall management efficiency. It minimizes human error, improves data accuracy and work quality, and delivers consistent deliverables through standardized processes. Because it can automate a wide range of business processes, not just specific tasks, it can be used in various departments and industries.By leveraging the latest generative AI technology, companies can accelerate their digital transformation and enhance their competitiveness in the market. This allows AI agent systems to improve operational efficiency, reduce costs, decrease errors and improve quality, enable highly versatile automation, and strengthen market competitiveness.

[0029] The AI ​​agent system according to this embodiment comprises a screen recognition unit, a user command processing unit, a task execution unit, and a feedback unit. The screen recognition unit recognizes elements on the screen and grasps the current state. The screen recognition unit recognizes elements such as buttons, text fields, and images on the screen using, for example, computer vision technology. The screen recognition unit can also analyze the active window and the user's operation history to grasp the current state. For example, the screen recognition unit identifies the active window and analyzes its contents. Furthermore, the screen recognition unit can also grasp the current state based on the user's operation history. The user command processing unit understands user instructions entered in voice or text based on the information recognized by the screen recognition unit. The user command processing unit performs speech recognition and text analysis using, for example, natural language processing technology. For example, the user command processing unit converts the user's voice instructions into text using speech recognition technology and analyzes its contents. The user command processing unit can also analyze the user's text instructions using text analysis technology. The task execution unit controls mouse movements and keyboard input based on the instructions understood by the user command processing unit and automatically performs tasks. The task execution unit controls mouse movements using, for example, robotics technology. The task execution unit can also control keyboard input using automation technology. For example, the task execution unit automatically performs specific application operations or data input. The feedback unit reconfirms the results of the tasks performed by the task execution unit and performs additional processing as needed. The feedback unit checks the accuracy of the work results using, for example, a reinforcement learning algorithm. The feedback unit can also perform error checking and correct errors or re-execute as needed. For example, the feedback unit evaluates the accuracy of the work results and re-executes if an error is detected. This enables the AI ​​agent system according to the embodiment to perform screen recognition, understand user commands, automatically execute tasks, and improve performance through feedback.

[0030] The screen recognition unit recognizes elements on the screen and understands the current state. For example, the screen recognition unit uses computer vision technology to recognize elements such as buttons, text fields, and images on the screen. Specifically, the screen recognition unit utilizes image recognition algorithms based on deep learning to identify each element on the screen with high accuracy. For example, it uses a convolutional neural network (CNN) to analyze the shape and color of buttons and icons and to determine their positions. It also uses optical character recognition (OCR) technology to read characters in text fields and obtain the content as digital data. Furthermore, the screen recognition unit can also analyze the active window and the user's operation history to understand the current state. For example, to identify the active window, it obtains the window handle and captures its contents as a screenshot. The captured image is analyzed by the aforementioned image recognition algorithm to identify elements within the window. Regarding the user's operation history, it analyzes log files and event tracking data to understand past operation patterns. This allows the screen recognition unit to accurately understand what operations the user is currently performing or intends to perform. This allows the screen recognition unit to monitor user actions in real time and provide information for the next process at the appropriate time.

[0031] The user command processing unit understands user instructions entered via voice or text based on information recognized by the screen recognition unit. For example, the user command processing unit performs speech recognition and text analysis using natural language processing techniques. Specifically, it converts the user's voice instructions into text using speech recognition technology and analyzes its content. Recurrent neural networks (RNNs) and transformer models are used for speech recognition to convert voice data into text with high accuracy. For example, if a user gives the voice instruction "Open the file," the speech recognition technology converts this instruction into text data, and then uses natural language processing technology to analyze its meaning. Text analysis technology performs morphological analysis and dependency structure analysis to analyze the user's text instructions and accurately understand the intent of the instruction. For example, if a user enters the text instruction "Open the report file in the documents folder," the text analysis technology analyzes this instruction and identifies the operation to open the report file in the documents folder. This allows the user command processing unit to accurately understand user instructions entered via voice or text and provide appropriate instructions to the next task execution unit.

[0032] The task execution unit controls mouse movements and keyboard inputs based on instructions understood by the user command processing unit, automatically performing tasks. For example, the task execution unit can control mouse movements using robotics technology. Specifically, it moves the mouse cursor to a specific position and performs clicks and drags according to user instructions. This involves using algorithms to calculate mouse coordinates and smoothly move the cursor. The task execution unit can also control keyboard input using automation technology. For example, it can program keyboard key sequences and simulate key inputs at specified timings to automatically perform specific application operations or data entry. This allows the task execution unit to automatically perform complex operations based on user instructions, significantly improving user work efficiency. Furthermore, the task execution unit can execute multiple tasks in parallel. For example, it can download files in the background while simultaneously performing data entry in another application. This allows the task execution unit to efficiently perform tasks based on user instructions, reducing overall work time.

[0033] The feedback unit re-verifies the results of the work performed by the work execution unit and performs additional processing as needed. For example, the feedback unit checks the accuracy of the work results using reinforcement learning algorithms. Specifically, the feedback unit evaluates the results of operations performed by the work execution unit and compares them to the expected results. For example, to verify whether a file copy operation was performed correctly, it scans the destination directory and checks whether the file exists correctly. The feedback unit can also perform error checking and correct or re-execute errors as needed. For example, if an error occurs in an operation performed by the work execution unit, the feedback unit detects the error, analyzes the error message, and identifies the cause. Once the cause is identified, the feedback unit performs additional processing to correct the error and executes the operation again. In this way, the feedback unit can guarantee the accuracy of the work results and improve the reliability of the entire system. Furthermore, the feedback unit can collect feedback from users and continuously improve the system's performance. For example, it can provide questionnaires or evaluation forms to collect user opinions in order to evaluate whether users are satisfied with the operation results. In this way, the feedback unit can improve the system according to user needs and enhance the user experience.

[0034] The screen recognition unit can periodically capture the screen and extract important information. The screen recognition unit can capture the screen at a frequency such as every second, every minute, or every hour. For example, the screen recognition unit can capture the screen every second and extract important information. It can also capture the screen every minute and extract important information. Furthermore, it can capture the screen every hour and extract important information. For example, the screen recognition unit can extract important information based on specific keywords or specific elements. This allows for the extraction of important information through periodic screen captures. Some or all of the above processing in the screen recognition unit may be performed using AI, for example, or without AI. For example, the screen recognition unit can input the captured screen data into a generating AI and have the generating AI perform the extraction of important information.

[0035] The user command processing unit can understand user instructions entered via voice or text by utilizing natural language processing. The user command processing unit employs natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis. For example, it uses morphological analysis to analyze words in voice and text. It can also analyze the grammatical structure of voice and text using grammatical analysis. Furthermore, it can analyze the meaning of voice and text using semantic analysis. For example, it uses speech recognition technology to convert user voice instructions into text and analyze its content. This allows for accurate understanding of user instructions through the use of natural language processing. Some or all of the above-described processes in the user command processing unit may be performed using AI, or without AI. For example, the user command processing unit can input voice and text data into a generating AI and have the generating AI understand the user's instructions.

[0036] The task execution unit can generate and automate complex work procedures by utilizing generative AI models. The task execution unit uses generative AI models such as large-scale language models. For example, the task execution unit generates complex work procedures using large-scale language models. Furthermore, the task execution unit can also generate complex work procedures using other generative AI models. For example, the task execution unit generates procedures that include multi-step operations and conditional branching. This allows for the automation of complex work procedures by utilizing generative AI models. Some or all of the above-described processes in the task execution unit may be performed using AI, for example, or without AI. For example, the task execution unit can input prompts to the generative AI model and perform automation based on the generated work procedures.

[0037] The feedback unit can learn from experience through reinforcement learning and continuously improve its performance. The feedback unit can use reinforcement learning algorithms such as Q-learning and SARSA. For example, the feedback unit can use Q-learning to evaluate the accuracy of the work results and improve performance. The feedback unit can also use SARSA to evaluate the accuracy of the work results and improve performance. Furthermore, the feedback unit can use other reinforcement learning algorithms to evaluate the accuracy of the work results and improve performance. For example, the feedback unit evaluates the accuracy of the work results and re-executes if an error is detected. In this way, the system's performance can be continuously improved through reinforcement learning. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can use an AI model that executes reinforcement learning algorithms to evaluate work results and improve performance.

[0038] The task execution unit can automate and optimize key tasks such as requirements definition, design, and schedule management. For example, the task execution unit automates key tasks such as project management and design work. For instance, the task execution unit automatically adjusts schedules using project management tools. It can also operate design software to automate design work. Furthermore, the task execution unit can optimize resource allocation. For example, it dynamically allocates resources according to the project's progress. This improves operational efficiency by automating and optimizing key tasks. Some or all of the above processes in the task execution unit may be performed using AI, or not. For example, the task execution unit can input data from project management tools into a generating AI and have the generating AI perform automatic schedule adjustments.

[0039] The screen recognition unit can prioritize extracting important information by focusing on specific applications or windows during screen recognition. For example, the screen recognition unit can prioritize capturing the window of the application the user is using and extract important information. For example, the screen recognition unit can identify the window of the application the user is using and analyze its contents. The screen recognition unit can also prioritize extracting information from a window if the user has a specific window open. For example, the screen recognition unit can analyze the contents of a window if the user has a specific window open. Furthermore, if the user is using multiple applications, the screen recognition unit can prioritize extracting information from the application that is used most frequently. For example, if the user is using multiple applications, the screen recognition unit can identify the window of the application that is used most frequently and analyze its contents. This allows for the priority extraction of important information by focusing on specific applications or windows. Some or all of the above processing in the screen recognition unit may be performed using AI, for example, or without AI. For example, the screen recognition unit can input the captured window data into a generating AI and have the generating AI perform the extraction of important information.

[0040] The screen recognition unit can improve the accuracy of extracting important information by referring to past screen capture history during screen recognition. For example, the screen recognition unit can analyze past screen capture history and learn patterns of important information. For example, the screen recognition unit can identify patterns of important information based on past screen capture history. The screen recognition unit can also extract important information from the current screen by referring to past screen capture history. For example, the screen recognition unit can identify important information from the current screen based on past screen capture history. Furthermore, the screen recognition unit can optimize the important information extraction algorithm based on past screen capture history. For example, the screen recognition unit adjusts the extraction algorithm based on past screen capture history. This improves the accuracy of extracting important information by referring to past screen capture history. Some or all of the above processing in the screen recognition unit may be performed using AI, for example, or without AI. For example, the screen recognition unit can input past screen capture history data into a generating AI and have the generating AI perform the task of improving the accuracy of extracting important information.

[0041] The screen recognition unit can prioritize extracting highly relevant information by considering the user's geographical location information during screen recognition. For example, if the user is in a specific region, the screen recognition unit will prioritize extracting information related to that region. For example, if the user is in a specific region, the screen recognition unit will identify and extract information related to that region. The screen recognition unit can also extract relevant information based on the user's current location if the user is on the move. For example, if the screen recognition unit is on the move, the screen recognition unit will identify and extract relevant information based on the user's current location. Furthermore, if the user is in a specific location, the screen recognition unit can prioritize extracting information related to that location. For example, if the screen recognition unit is in a specific location, the screen recognition unit will identify and extract information related to that location. In this way, by considering the user's geographical location information, highly relevant information can be prioritized. Some or all of the above processing in the screen recognition unit may be performed using AI, for example, or without AI. For example, the screen recognition unit can input the user's geographical location information data into a generating AI and have the generating AI perform the extraction of highly relevant information.

[0042] The screen recognition unit can analyze the user's social media activity and extract relevant information during screen recognition. For example, the screen recognition unit can analyze the content of the user's social media posts and extract relevant information. For example, the screen recognition unit analyzes the content of the user's social media posts and identifies relevant information. The screen recognition unit can also analyze the activities of the user's social media followers and friends and extract relevant information. For example, the screen recognition unit analyzes the activities of the user's social media followers and friends and identifies relevant information. Furthermore, the screen recognition unit can analyze the user's social media trends and extract relevant information. For example, the screen recognition unit analyzes the user's social media trends and identifies relevant information. In this way, relevant information can be extracted by analyzing the user's social media activity. Some or all of the above processing in the screen recognition unit may be performed using AI, for example, or without AI. For example, the screen recognition unit can input the user's social media activity data into a generating AI and have the generating AI perform the extraction of relevant information.

[0043] The user command processing unit can select the optimal interpretation method by referring to the user's past instruction history when processing a command. For example, the user command processing unit can analyze the user's past instruction history and select the optimal interpretation method. For example, the user command processing unit can identify the optimal interpretation method based on the user's past instruction history. The user command processing unit can also interpret the current command by referring to the user's past instruction history. For example, the user command processing unit can identify the current command based on the user's past instruction history. Furthermore, the user command processing unit can optimize the interpretation algorithm based on the user's past instruction history. For example, the user command processing unit can adjust the interpretation algorithm based on the user's past instruction history. This allows the optimal interpretation method to be selected by referring to the user's past instruction history. Some or all of the above processing in the user command processing unit may be performed using AI, for example, or without AI. For example, the user command processing unit can input the user's past instruction history data into a generating AI and have the generating AI select the optimal interpretation method.

[0044] The user command processing unit can apply different interpretation algorithms depending on the specific application or task during command processing. For example, the user command processing unit can apply the optimal interpretation algorithm for a specific application. For example, the user command processing unit can select and apply the optimal interpretation algorithm for a specific application. The user command processing unit can also apply different interpretation algorithms depending on the specific task. For example, the user command processing unit can select and apply the optimal interpretation algorithm for a specific task. Furthermore, the user command processing unit can select the optimal interpretation algorithm for multiple applications or tasks. For example, the user command processing unit can select and apply the optimal interpretation algorithm for multiple applications or tasks. This improves the accuracy of command interpretation by applying different interpretation algorithms depending on the specific application or task. Some or all of the above processing in the user command processing unit may be performed using AI, for example, or without AI. For example, the user command processing unit can input data for a specific application or task into a generating AI and have the generating AI perform the application of the optimal interpretation algorithm.

[0045] The user command processing unit can prioritize the processing of commands that are highly relevant, taking into account the user's geographical location information. For example, if the user is in a specific region, the user command processing unit can prioritize the processing of commands related to that region. For example, if the user is in a specific region, the user command processing unit can identify commands related to that region and prioritize their processing. Furthermore, if the user is on the move, the user command processing unit can process relevant commands based on the user's current location. For example, if the user is on the move, the user command processing unit can identify commands related to the user's current location and prioritize their processing. In addition, if the user is in a specific location, the user command processing unit can prioritize the processing of commands related to that location. For example, if the user is in a specific location, the user command processing unit can identify commands related to that location and prioritize their processing. This allows for the priority processing of highly relevant commands by considering the user's geographical location information. Some or all of the above processing in the user command processing unit may be performed using AI, for example, or without AI. For example, the user command processing unit can input the user's geographical location information data into a generating AI and have the generating AI execute the processing of highly relevant commands.

[0046] The user command processing unit can analyze the user's social media activity and process relevant commands during command processing. For example, the user command processing unit can analyze the content of the user's social media posts and process relevant commands. For example, the user command processing unit can analyze the content of the user's social media posts and identify relevant commands. The user command processing unit can also analyze the activity of the user's social media followers and friends and process relevant commands. For example, the user command processing unit can analyze the activity of the user's social media followers and friends and identify relevant commands. Furthermore, the user command processing unit can analyze the user's social media trends and process relevant commands. For example, the user command processing unit can analyze the user's social media trends and identify relevant commands. This allows for appropriate processing of relevant commands by analyzing the user's social media activity. Some or all of the above processing in the user command processing unit may be performed using AI, for example, or without AI. For example, the user command processing unit can input the user's social media activity data into a generating AI and have the generating AI execute the processing of relevant commands.

[0047] The task execution unit can generate the optimal work procedure by referring to the user's past work history when executing a task. For example, the task execution unit can analyze the user's past work history and generate the optimal work procedure. For example, the task execution unit can identify the optimal work procedure based on the user's past work history. The task execution unit can also generate the current work procedure by referring to the user's past work history. For example, the task execution unit can identify the current work procedure based on the user's past work history. Furthermore, the task execution unit can optimize the work procedure generation algorithm based on the user's past work history. For example, the task execution unit can adjust the generation algorithm based on the user's past work history. This allows the optimal work procedure to be generated by referring to the user's past work history. Some or all of the above processing in the task execution unit may be performed using AI, for example, or without using AI. For example, the task execution unit can input the user's past work history data into a generation AI and have the generation AI execute the generation of the optimal work procedure.

[0048] The task execution unit can apply different task procedure generation algorithms depending on the specific application or task during task execution. For example, the task execution unit can apply the optimal task procedure generation algorithm for a specific application. For example, the task execution unit can select and apply the optimal generation algorithm for a specific application. The task execution unit can also apply different task procedure generation algorithms depending on the specific task. For example, the task execution unit can select and apply the optimal generation algorithm for a specific task. Furthermore, the task execution unit can select the optimal task procedure generation algorithm for multiple applications or tasks. For example, the task execution unit can select and apply the optimal generation algorithm for multiple applications or tasks. This improves the accuracy of the task procedure by applying different task procedure generation algorithms depending on the specific application or task. Some or all of the above processing in the task execution unit may be performed using AI, for example, or without AI. For example, the task execution unit can input data for a specific application or task into a generation AI and have the generation AI execute the application of the optimal task procedure generation algorithm.

[0049] The task execution unit can prioritize generating highly relevant task procedures by considering the user's geographical location information during task execution. For example, if the user is in a specific region, the task execution unit will prioritize generating task procedures related to that region. For example, if the user is in a specific region, the task execution unit will identify and prioritize generating task procedures related to that region. Furthermore, if the user is on the move, the task execution unit can also generate relevant task procedures based on their current location. For example, if the user is on the move, the task execution unit will identify and prioritize generating relevant task procedures based on their current location. In addition, if the user is in a specific location, the task execution unit can also prioritize generating task procedures related to that location. For example, if the user is in a specific location, the task execution unit will identify and prioritize generating task procedures related to that location. This allows for the priority generation of highly relevant task procedures by considering the user's geographical location information. Some or all of the above processing in the task execution unit may be performed using AI, for example, or without AI. For example, the task execution unit can input the user's geographical location data into the generation AI and have the generation AI execute the generation of highly relevant work procedures.

[0050] The task execution unit can analyze the user's social media activity and generate relevant work procedures during task execution. For example, the task execution unit can analyze the content of the user's social media posts and generate relevant work procedures. For example, the task execution unit can analyze the content of the user's social media posts and identify relevant work procedures. The task execution unit can also analyze the activities of the user's social media followers and friends and generate relevant work procedures. For example, the task execution unit can analyze the activities of the user's social media followers and friends and identify relevant work procedures. Furthermore, the task execution unit can analyze the user's social media trends and generate relevant work procedures. For example, the task execution unit can analyze the user's social media trends and identify relevant work procedures. In this way, relevant work procedures can be generated by analyzing the user's social media activity. Some or all of the above processing in the task execution unit may be performed using AI, for example, or without AI. For example, the task execution unit can input the user's social media activity data into a generation AI and have the generation AI execute the generation of relevant work procedures.

[0051] The feedback unit can select the optimal feedback method by referring to the user's past feedback history when providing feedback. For example, the feedback unit can analyze the user's past feedback history and select the optimal feedback method. For example, the feedback unit can identify the optimal feedback method based on the user's past feedback history. The feedback unit can also provide current feedback by referring to the user's past feedback history. For example, the feedback unit can identify the current feedback based on the user's past feedback history. Furthermore, the feedback unit can optimize the feedback algorithm based on the user's past feedback history. For example, the feedback unit can adjust the feedback algorithm based on the user's past feedback history. This allows the optimal feedback method to be selected by referring to the user's past feedback history. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's past feedback history data into a generating AI and have the generating AI select the optimal feedback method.

[0052] The feedback unit can apply different feedback algorithms depending on the specific application or task during the feedback process. For example, the feedback unit can apply the optimal feedback algorithm for a particular application. For example, the feedback unit can select and apply the optimal feedback algorithm for a particular application. The feedback unit can also apply different feedback algorithms depending on the specific task. For example, the feedback unit can select and apply the optimal feedback algorithm for a particular task. Furthermore, the feedback unit can select the optimal feedback algorithm for multiple applications or tasks. For example, the feedback unit can select and apply the optimal feedback algorithm for multiple applications or tasks. This improves the accuracy of feedback by applying different feedback algorithms depending on the specific application or task. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input data for a specific application or task into a generating AI and have the generating AI execute the application of the optimal feedback algorithm.

[0053] The feedback unit can prioritize providing highly relevant feedback by considering the user's geographical location information. For example, if the user is in a specific region, the feedback unit can prioritize providing feedback related to that region. For example, if the user is in a specific region, the feedback unit can identify and prioritize feedback related to that region. Furthermore, if the user is on the move, the feedback unit can provide relevant feedback based on their current location. For example, if the user is on the move, the feedback unit can identify and prioritize feedback based on their current location. In addition, if the user is in a specific location, the feedback unit can prioritize providing feedback related to that location. For example, if the feedback unit is in a specific location, the feedback unit can identify and prioritize feedback related to that location. This allows the feedback unit to prioritize providing highly relevant feedback by considering the user's geographical location information. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's geographical location information data into a generating AI and have the generating AI perform the task of providing highly relevant feedback.

[0054] The feedback unit can analyze the user's social media activity and provide relevant feedback when providing feedback. For example, the feedback unit can analyze the content of the user's social media posts and provide relevant feedback. For example, the feedback unit can analyze the content of the user's social media posts and identify relevant feedback. The feedback unit can also analyze the activities of the user's social media followers and friends and provide relevant feedback. For example, the feedback unit can analyze the activities of the user's social media followers and friends and identify relevant feedback. Furthermore, the feedback unit can analyze the user's social media trends and provide relevant feedback. For example, the feedback unit can analyze the user's social media trends and identify relevant feedback. In this way, relevant feedback can be provided by analyzing the user's social media activity. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's social media activity data into a generating AI and have the generating AI perform the provision of relevant feedback.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] AI agent systems can analyze a user's past operation history and suggest optimal operating procedures. For example, they can suggest shortcuts to automate frequently performed operations. They can also learn patterns of past operations and predict and suggest the next steps to take. Furthermore, they can suggest the optimal procedures for a user to efficiently complete a specific task. In this way, by leveraging the user's operation history and suggesting efficient operating procedures, the system can improve the user's work efficiency.

[0057] The AI ​​agent system can prioritize displaying relevant information by considering the user's geographical location. For example, if the user is in a specific region, it can display news and event information related to that region. If the user is on the move, it can also display relevant traffic and weather information based on their current location. Furthermore, if the user is in a specific location, it can display tourist information and restaurant information related to that location. This leverages the user's geographical location to prioritize the display of relevant information, thereby improving user convenience.

[0058] The AI ​​agent system can analyze a user's social media activity and provide relevant information. For example, if a user posts about a specific topic, it can provide news and articles related to that topic. It can also analyze the activity of the user's followers and friends and suggest relevant events and activities. Furthermore, it can analyze the user's social media trends and provide relevant information. In this way, by leveraging the user's social media activity to provide relevant information, it can deliver information tailored to the user's interests and concerns.

[0059] The AI ​​agent system can select the optimal feedback method by referring to the user's past feedback history. For example, it can analyze the feedback format the user preferred in the past and provide feedback in a similar format. It can also analyze the content of feedback the user has received in the past and provide feedback that is appropriate for the current situation. Furthermore, it can optimize the feedback algorithm based on the user's past feedback history. By utilizing the user's past feedback history to select the optimal feedback method, it can provide feedback that is beneficial to the user.

[0060] The AI ​​agent system can display relevant advertisements by considering the user's geographical location. For example, if a user is in a specific area, it can display advertisements for stores and services related to that area. It can also display relevant advertisements based on the user's current location if the user is on the move. Furthermore, if a user is in a specific location, it can display advertisements related to that location. This allows the system to provide users with useful information by leveraging their geographical location to display relevant advertisements.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The screen recognition unit recognizes elements on the screen and understands the current state. For example, it uses computer vision technology to recognize elements such as buttons, text fields, and images on the screen. It can also understand the current state by analyzing the active window and the user's operation history. Step 2: The user command processing unit understands user instructions entered via voice or text based on the information recognized by the screen recognition unit. For example, it uses natural language processing technology to perform speech recognition and text analysis. It converts the user's voice instructions into text using speech recognition technology and analyzes the content. It can also analyze the user's text instructions using text analysis technology. Step 3: The task execution unit controls mouse movements and keyboard inputs based on instructions understood by the user command processing unit, automatically performing the task. For example, it can use robotics technology to control mouse movements and automation technology to control keyboard inputs. It can also automate specific application operations and data entry. Step 4: The feedback unit re-verifies the results of the work performed by the work execution unit and performs additional processing as needed. For example, it checks the accuracy of the work results using a reinforcement learning algorithm, performs error checking, and corrects errors or re-executes the process as necessary.

[0063] (Example of form 2) The AI ​​agent system according to an embodiment of the present invention is a system that utilizes generative AI to enable human-level computer operation. This AI agent system interacts with the user using all computer input devices (microphone, screen, mouse, keyboard, etc.) and operates the computer like a human. The specific configuration and functions are as follows: First, the AI ​​agent system uses computer vision technology for screen recognition and understanding to recognize elements on the screen and grasp the current state. It periodically captures the screen and extracts important information. Next, as processing user commands, the AI ​​agent system utilizes natural language processing to understand user instructions entered in voice or text. Based on the instructions, it creates an appropriate work plan. In the automated execution of tasks, the AI ​​agent system controls mouse movements and keyboard input to automatically perform the tasks instructed by the user. It utilizes generative AI models to generate and automate complex work procedures. Furthermore, as performance improvement through a feedback loop, the AI ​​agent system re-examines the work results and performs additional processing as needed. Through reinforcement learning, it learns from experience and continuously improves performance. This AI agent system automates and optimizes key tasks such as requirements definition, design, and schedule management, efficiently handling repetitive and complex tasks. Applicable to various industrial sectors, it aims to innovate overall business processes. For example, AI agent systems are expected to improve operational efficiency, reduce costs, decrease errors and improve quality, enable highly versatile automation, and strengthen market competitiveness. Specifically, it significantly reduces the time spent on repetitive tasks, increasing the productivity of the entire team. Automation of tasks allows teams to focus on important and creative tasks. Optimization of human resources reduces labor and operating costs, and streamlining business processes improves overall management efficiency. It minimizes human error, improves data accuracy and work quality, and delivers consistent deliverables through standardized processes. Because it can automate a wide range of business processes, not just specific tasks, it can be used in various departments and industries.By leveraging the latest generative AI technology, companies can accelerate their digital transformation and enhance their competitiveness in the market. This allows AI agent systems to improve operational efficiency, reduce costs, decrease errors and improve quality, enable highly versatile automation, and strengthen market competitiveness.

[0064] The AI ​​agent system according to this embodiment comprises a screen recognition unit, a user command processing unit, a task execution unit, and a feedback unit. The screen recognition unit recognizes elements on the screen and grasps the current state. The screen recognition unit recognizes elements such as buttons, text fields, and images on the screen using, for example, computer vision technology. The screen recognition unit can also analyze the active window and the user's operation history to grasp the current state. For example, the screen recognition unit identifies the active window and analyzes its contents. Furthermore, the screen recognition unit can also grasp the current state based on the user's operation history. The user command processing unit understands user instructions entered in voice or text based on the information recognized by the screen recognition unit. The user command processing unit performs speech recognition and text analysis using, for example, natural language processing technology. For example, the user command processing unit converts the user's voice instructions into text using speech recognition technology and analyzes its contents. The user command processing unit can also analyze the user's text instructions using text analysis technology. The task execution unit controls mouse movements and keyboard input based on the instructions understood by the user command processing unit and automatically performs tasks. The task execution unit controls mouse movements using, for example, robotics technology. The task execution unit can also control keyboard input using automation technology. For example, the task execution unit automatically performs specific application operations or data input. The feedback unit reconfirms the results of the tasks performed by the task execution unit and performs additional processing as needed. The feedback unit checks the accuracy of the work results using, for example, a reinforcement learning algorithm. The feedback unit can also perform error checking and correct errors or re-execute as needed. For example, the feedback unit evaluates the accuracy of the work results and re-executes if an error is detected. This enables the AI ​​agent system according to the embodiment to perform screen recognition, understand user commands, automatically execute tasks, and improve performance through feedback.

[0065] The screen recognition unit recognizes elements on the screen and understands the current state. For example, the screen recognition unit uses computer vision technology to recognize elements such as buttons, text fields, and images on the screen. Specifically, the screen recognition unit utilizes image recognition algorithms based on deep learning to identify each element on the screen with high accuracy. For example, it uses a convolutional neural network (CNN) to analyze the shape and color of buttons and icons and to determine their positions. It also uses optical character recognition (OCR) technology to read characters in text fields and obtain the content as digital data. Furthermore, the screen recognition unit can also analyze the active window and the user's operation history to understand the current state. For example, to identify the active window, it obtains the window handle and captures its contents as a screenshot. The captured image is analyzed by the aforementioned image recognition algorithm to identify elements within the window. Regarding the user's operation history, it analyzes log files and event tracking data to understand past operation patterns. This allows the screen recognition unit to accurately understand what operations the user is currently performing or intends to perform. This allows the screen recognition unit to monitor user actions in real time and provide information for the next process at the appropriate time.

[0066] The user command processing unit understands user instructions entered via voice or text based on information recognized by the screen recognition unit. For example, the user command processing unit performs speech recognition and text analysis using natural language processing techniques. Specifically, it converts the user's voice instructions into text using speech recognition technology and analyzes its content. Recurrent neural networks (RNNs) and transformer models are used for speech recognition to convert voice data into text with high accuracy. For example, if a user gives the voice instruction "Open the file," the speech recognition technology converts this instruction into text data, and then uses natural language processing technology to analyze its meaning. Text analysis technology performs morphological analysis and dependency structure analysis to analyze the user's text instructions and accurately understand the intent of the instruction. For example, if a user enters the text instruction "Open the report file in the documents folder," the text analysis technology analyzes this instruction and identifies the operation to open the report file in the documents folder. This allows the user command processing unit to accurately understand user instructions entered via voice or text and provide appropriate instructions to the next task execution unit.

[0067] The task execution unit controls mouse movements and keyboard inputs based on instructions understood by the user command processing unit, automatically performing tasks. For example, the task execution unit can control mouse movements using robotics technology. Specifically, it moves the mouse cursor to a specific position and performs clicks and drags according to user instructions. This involves using algorithms to calculate mouse coordinates and smoothly move the cursor. The task execution unit can also control keyboard input using automation technology. For example, it can program keyboard key sequences and simulate key inputs at specified timings to automatically perform specific application operations or data entry. This allows the task execution unit to automatically perform complex operations based on user instructions, significantly improving user work efficiency. Furthermore, the task execution unit can execute multiple tasks in parallel. For example, it can download files in the background while simultaneously performing data entry in another application. This allows the task execution unit to efficiently perform tasks based on user instructions, reducing overall work time.

[0068] The feedback unit re-verifies the results of the work performed by the work execution unit and performs additional processing as needed. For example, the feedback unit checks the accuracy of the work results using reinforcement learning algorithms. Specifically, the feedback unit evaluates the results of operations performed by the work execution unit and compares them to the expected results. For example, to verify whether a file copy operation was performed correctly, it scans the destination directory and checks whether the file exists correctly. The feedback unit can also perform error checking and correct or re-execute errors as needed. For example, if an error occurs in an operation performed by the work execution unit, the feedback unit detects the error, analyzes the error message, and identifies the cause. Once the cause is identified, the feedback unit performs additional processing to correct the error and executes the operation again. In this way, the feedback unit can guarantee the accuracy of the work results and improve the reliability of the entire system. Furthermore, the feedback unit can collect feedback from users and continuously improve the system's performance. For example, it can provide questionnaires or evaluation forms to collect user opinions in order to evaluate whether users are satisfied with the operation results. In this way, the feedback unit can improve the system according to user needs and enhance the user experience.

[0069] The screen recognition unit can periodically capture the screen and extract important information. The screen recognition unit can capture the screen at a frequency such as every second, every minute, or every hour. For example, the screen recognition unit can capture the screen every second and extract important information. It can also capture the screen every minute and extract important information. Furthermore, it can capture the screen every hour and extract important information. For example, the screen recognition unit can extract important information based on specific keywords or specific elements. This allows for the extraction of important information through periodic screen captures. Some or all of the above processing in the screen recognition unit may be performed using AI, for example, or without AI. For example, the screen recognition unit can input the captured screen data into a generating AI and have the generating AI perform the extraction of important information.

[0070] The user command processing unit can understand user instructions entered via voice or text by utilizing natural language processing. The user command processing unit employs natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis. For example, it uses morphological analysis to analyze words in voice and text. It can also analyze the grammatical structure of voice and text using grammatical analysis. Furthermore, it can analyze the meaning of voice and text using semantic analysis. For example, it uses speech recognition technology to convert user voice instructions into text and analyze its content. This allows for accurate understanding of user instructions through the use of natural language processing. Some or all of the above-described processes in the user command processing unit may be performed using AI, or without AI. For example, the user command processing unit can input voice and text data into a generating AI and have the generating AI understand the user's instructions.

[0071] The task execution unit can generate and automate complex work procedures by utilizing generative AI models. The task execution unit uses generative AI models such as large-scale language models. For example, the task execution unit generates complex work procedures using large-scale language models. Furthermore, the task execution unit can also generate complex work procedures using other generative AI models. For example, the task execution unit generates procedures that include multi-step operations and conditional branching. This allows for the automation of complex work procedures by utilizing generative AI models. Some or all of the above-described processes in the task execution unit may be performed using AI, for example, or without AI. For example, the task execution unit can input prompts to the generative AI model and perform automation based on the generated work procedures.

[0072] The feedback unit can learn from experience through reinforcement learning and continuously improve its performance. The feedback unit can use reinforcement learning algorithms such as Q-learning and SARSA. For example, the feedback unit can use Q-learning to evaluate the accuracy of the work results and improve performance. The feedback unit can also use SARSA to evaluate the accuracy of the work results and improve performance. Furthermore, the feedback unit can use other reinforcement learning algorithms to evaluate the accuracy of the work results and improve performance. For example, the feedback unit evaluates the accuracy of the work results and re-executes if an error is detected. In this way, the system's performance can be continuously improved through reinforcement learning. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can use an AI model that executes reinforcement learning algorithms to evaluate work results and improve performance.

[0073] The task execution unit can automate and optimize key tasks such as requirements definition, design, and schedule management. For example, the task execution unit automates key tasks such as project management and design work. For instance, the task execution unit automatically adjusts schedules using project management tools. It can also operate design software to automate design work. Furthermore, the task execution unit can optimize resource allocation. For example, it dynamically allocates resources according to the project's progress. This improves operational efficiency by automating and optimizing key tasks. Some or all of the above processes in the task execution unit may be performed using AI, or not. For example, the task execution unit can input data from project management tools into a generating AI and have the generating AI perform automatic schedule adjustments.

[0074] The screen recognition unit can estimate the user's emotions and adjust the frequency of screen captures based on the estimated emotions. For example, if the user is stressed, the screen recognition unit can reduce the frequency of screen captures to alleviate the burden. For example, if the user is stressed, the screen recognition unit can set the screen capture frequency to every minute. The screen recognition unit can also increase the frequency of screen captures to obtain more detailed information if the user is focused. For example, if the user is focused, the screen recognition unit can set the screen capture frequency to every second. Furthermore, if the user is relaxed, the screen recognition unit can maintain a normal screen capture frequency. For example, if the user is relaxed, the screen recognition unit can set the screen capture frequency to every hour. In this way, the user's burden can be reduced by adjusting the frequency of screen captures according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the screen recognition unit may be performed using AI, for example, or without AI. For example, the screen recognition unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0075] The screen recognition unit can prioritize extracting important information by focusing on specific applications or windows during screen recognition. For example, the screen recognition unit can prioritize capturing the window of the application the user is using and extract important information. For example, the screen recognition unit can identify the window of the application the user is using and analyze its contents. The screen recognition unit can also prioritize extracting information from a window if the user has a specific window open. For example, the screen recognition unit can analyze the contents of a window if the user has a specific window open. Furthermore, if the user is using multiple applications, the screen recognition unit can prioritize extracting information from the application that is used most frequently. For example, if the user is using multiple applications, the screen recognition unit can identify the window of the application that is used most frequently and analyze its contents. This allows for the priority extraction of important information by focusing on specific applications or windows. Some or all of the above processing in the screen recognition unit may be performed using AI, for example, or without AI. For example, the screen recognition unit can input the captured window data into a generating AI and have the generating AI perform the extraction of important information.

[0076] The screen recognition unit can improve the accuracy of extracting important information by referring to past screen capture history during screen recognition. For example, the screen recognition unit can analyze past screen capture history and learn patterns of important information. For example, the screen recognition unit can identify patterns of important information based on past screen capture history. The screen recognition unit can also extract important information from the current screen by referring to past screen capture history. For example, the screen recognition unit can identify important information from the current screen based on past screen capture history. Furthermore, the screen recognition unit can optimize the important information extraction algorithm based on past screen capture history. For example, the screen recognition unit adjusts the extraction algorithm based on past screen capture history. This improves the accuracy of extracting important information by referring to past screen capture history. Some or all of the above processing in the screen recognition unit may be performed using AI, for example, or without AI. For example, the screen recognition unit can input past screen capture history data into a generating AI and have the generating AI perform the task of improving the accuracy of extracting important information.

[0077] The screen recognition unit can estimate the user's emotions and determine the priority of important information on the screen based on the estimated user emotions. For example, if the user is stressed, the screen recognition unit will display important information concisely. For example, if the user is stressed, the screen recognition unit will set the information priority to display important information concisely. The screen recognition unit can also prioritize the display of detailed information if the user is focused. For example, if the user is focused, the screen recognition unit will set the information priority to display detailed information first. Furthermore, if the user is relaxed, the screen recognition unit will display information in the normal order of priority. For example, if the user is relaxed, the screen recognition unit will set the information priority to display information in the normal order of priority. In this way, the display of information is optimized by determining the priority of important information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the screen recognition unit may be performed using AI, for example, or without AI. For example, the screen recognition unit can input user emotion data into a generating AI, allowing the generating AI to perform emotion estimation.

[0078] The screen recognition unit can prioritize extracting highly relevant information by considering the user's geographical location information during screen recognition. For example, if the user is in a specific region, the screen recognition unit will prioritize extracting information related to that region. For example, if the user is in a specific region, the screen recognition unit will identify and extract information related to that region. The screen recognition unit can also extract relevant information based on the user's current location if the user is on the move. For example, if the screen recognition unit is on the move, the screen recognition unit will identify and extract relevant information based on the user's current location. Furthermore, if the user is in a specific location, the screen recognition unit can prioritize extracting information related to that location. For example, if the screen recognition unit is in a specific location, the screen recognition unit will identify and extract information related to that location. In this way, by considering the user's geographical location information, highly relevant information can be prioritized. Some or all of the above processing in the screen recognition unit may be performed using AI, for example, or without AI. For example, the screen recognition unit can input the user's geographical location information data into a generating AI and have the generating AI perform the extraction of highly relevant information.

[0079] The screen recognition unit can analyze the user's social media activity and extract relevant information during screen recognition. For example, the screen recognition unit can analyze the content of the user's social media posts and extract relevant information. For example, the screen recognition unit analyzes the content of the user's social media posts and identifies relevant information. The screen recognition unit can also analyze the activities of the user's social media followers and friends and extract relevant information. For example, the screen recognition unit analyzes the activities of the user's social media followers and friends and identifies relevant information. Furthermore, the screen recognition unit can analyze the user's social media trends and extract relevant information. For example, the screen recognition unit analyzes the user's social media trends and identifies relevant information. In this way, relevant information can be extracted by analyzing the user's social media activity. Some or all of the above processing in the screen recognition unit may be performed using AI, for example, or without AI. For example, the screen recognition unit can input the user's social media activity data into a generating AI and have the generating AI perform the extraction of relevant information.

[0080] The user command processing unit can estimate the user's emotions and adjust the command interpretation method based on the estimated emotions. For example, if the user is stressed, the user command processing unit can provide a concise command interpretation. For example, if the user is stressed, the user command processing unit can adjust the interpretation algorithm to provide a concise command interpretation. The user command processing unit can also provide a detailed command interpretation if the user is relaxed. For example, if the user is relaxed, the user command processing unit can adjust the interpretation algorithm to provide a detailed command interpretation. Furthermore, if the user is in a hurry, the user command processing unit can provide a rapid command interpretation. For example, if the user is in a hurry, the user command processing unit can adjust the interpretation algorithm to provide a rapid command interpretation. By adjusting the command interpretation method according to the user's emotions, more appropriate command interpretation becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the user command processing unit may be performed using AI, for example, or without AI. For example, the user command processing unit can input user emotion data into the generating AI and have the generating AI perform emotion estimation.

[0081] The user command processing unit can select the optimal interpretation method by referring to the user's past instruction history when processing a command. For example, the user command processing unit can analyze the user's past instruction history and select the optimal interpretation method. For example, the user command processing unit can identify the optimal interpretation method based on the user's past instruction history. The user command processing unit can also interpret the current command by referring to the user's past instruction history. For example, the user command processing unit can identify the current command based on the user's past instruction history. Furthermore, the user command processing unit can optimize the interpretation algorithm based on the user's past instruction history. For example, the user command processing unit can adjust the interpretation algorithm based on the user's past instruction history. This allows the optimal interpretation method to be selected by referring to the user's past instruction history. Some or all of the above processing in the user command processing unit may be performed using AI, for example, or without AI. For example, the user command processing unit can input the user's past instruction history data into a generating AI and have the generating AI select the optimal interpretation method.

[0082] The user command processing unit can apply different interpretation algorithms depending on the specific application or task during command processing. For example, the user command processing unit can apply the optimal interpretation algorithm for a specific application. For example, the user command processing unit can select and apply the optimal interpretation algorithm for a specific application. The user command processing unit can also apply different interpretation algorithms depending on the specific task. For example, the user command processing unit can select and apply the optimal interpretation algorithm for a specific task. Furthermore, the user command processing unit can select the optimal interpretation algorithm for multiple applications or tasks. For example, the user command processing unit can select and apply the optimal interpretation algorithm for multiple applications or tasks. This improves the accuracy of command interpretation by applying different interpretation algorithms depending on the specific application or task. Some or all of the above processing in the user command processing unit may be performed using AI, for example, or without AI. For example, the user command processing unit can input data for a specific application or task into a generating AI and have the generating AI perform the application of the optimal interpretation algorithm.

[0083] The user command processing unit can estimate the user's emotions and determine the priority of commands based on the estimated emotions. For example, if the user is stressed, the user command processing unit will prioritize important commands. For example, if the user is stressed, the user command processing unit will set the command priority to prioritize important commands. The user command processing unit can also process commands with normal priority if the user is relaxed. For example, if the user is relaxed, the user command processing unit will set the command priority to prioritize commands with normal priority. Furthermore, if the user is in a hurry, the user command processing unit can prioritize commands that need to be processed quickly. For example, if the user is in a hurry, the user command processing unit will set the command priority to prioritize commands that need to be processed quickly. In this way, important commands can be prioritized by determining the priority of commands according to the user's emotions. Emotion estimation is implemented using emotion estimation functions, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the user command processing unit may be performed using AI, for example, or without AI. For example, the user command processing unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0084] The user command processing unit can prioritize the processing of commands that are highly relevant, taking into account the user's geographical location information. For example, if the user is in a specific region, the user command processing unit can prioritize the processing of commands related to that region. For example, if the user is in a specific region, the user command processing unit can identify commands related to that region and prioritize their processing. Furthermore, if the user is on the move, the user command processing unit can process relevant commands based on the user's current location. For example, if the user is on the move, the user command processing unit can identify commands related to the user's current location and prioritize their processing. In addition, if the user is in a specific location, the user command processing unit can prioritize the processing of commands related to that location. For example, if the user is in a specific location, the user command processing unit can identify commands related to that location and prioritize their processing. This allows for the priority processing of highly relevant commands by considering the user's geographical location information. Some or all of the above processing in the user command processing unit may be performed using AI, for example, or without AI. For example, the user command processing unit can input the user's geographical location information data into a generating AI and have the generating AI execute the processing of highly relevant commands.

[0085] The user command processing unit can analyze the user's social media activity and process relevant commands during command processing. For example, the user command processing unit can analyze the content of the user's social media posts and process relevant commands. For example, the user command processing unit can analyze the content of the user's social media posts and identify relevant commands. The user command processing unit can also analyze the activity of the user's social media followers and friends and process relevant commands. For example, the user command processing unit can analyze the activity of the user's social media followers and friends and identify relevant commands. Furthermore, the user command processing unit can analyze the user's social media trends and process relevant commands. For example, the user command processing unit can analyze the user's social media trends and identify relevant commands. This allows for appropriate processing of relevant commands by analyzing the user's social media activity. Some or all of the above processing in the user command processing unit may be performed using AI, for example, or without AI. For example, the user command processing unit can input the user's social media activity data into a generating AI and have the generating AI execute the processing of relevant commands.

[0086] The task execution unit can estimate the user's emotions and adjust the method of generating work procedures based on the estimated user emotions. For example, if the user is stressed, the task execution unit can generate concise work procedures. For example, if the user is stressed, the task execution unit adjusts the generation algorithm to generate concise work procedures. The task execution unit can also generate detailed work procedures if the user is relaxed. For example, if the user is relaxed, the task execution unit adjusts the generation algorithm to generate detailed work procedures. Furthermore, if the user is in a hurry, the task execution unit can generate quick work procedures. For example, if the user is in a hurry, the task execution unit adjusts the generation algorithm to generate quick work procedures. In this way, by adjusting the method of generating work procedures according to the user's emotions, more appropriate work procedures can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the task execution unit may be performed using AI, for example, or without AI. For example, the task execution unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0087] The task execution unit can generate the optimal work procedure by referring to the user's past work history when executing a task. For example, the task execution unit can analyze the user's past work history and generate the optimal work procedure. For example, the task execution unit can identify the optimal work procedure based on the user's past work history. The task execution unit can also generate the current work procedure by referring to the user's past work history. For example, the task execution unit can identify the current work procedure based on the user's past work history. Furthermore, the task execution unit can optimize the work procedure generation algorithm based on the user's past work history. For example, the task execution unit can adjust the generation algorithm based on the user's past work history. This allows the optimal work procedure to be generated by referring to the user's past work history. Some or all of the above processing in the task execution unit may be performed using AI, for example, or without using AI. For example, the task execution unit can input the user's past work history data into a generation AI and have the generation AI execute the generation of the optimal work procedure.

[0088] The task execution unit can apply different task procedure generation algorithms depending on the specific application or task during task execution. For example, the task execution unit can apply the optimal task procedure generation algorithm for a specific application. For example, the task execution unit can select and apply the optimal generation algorithm for a specific application. The task execution unit can also apply different task procedure generation algorithms depending on the specific task. For example, the task execution unit can select and apply the optimal generation algorithm for a specific task. Furthermore, the task execution unit can select the optimal task procedure generation algorithm for multiple applications or tasks. For example, the task execution unit can select and apply the optimal generation algorithm for multiple applications or tasks. This improves the accuracy of the task procedure by applying different task procedure generation algorithms depending on the specific application or task. Some or all of the above processing in the task execution unit may be performed using AI, for example, or without AI. For example, the task execution unit can input data for a specific application or task into a generation AI and have the generation AI execute the application of the optimal task procedure generation algorithm.

[0089] The task execution unit can estimate the user's emotions and determine the priority of task procedures based on the estimated emotions. For example, if the user is stressed, the task execution unit will prioritize generating important task procedures. For example, if the user is stressed, the task execution unit will set the procedure priority to prioritize generating important task procedures. The task execution unit can also generate task procedures with normal priority if the user is relaxed. For example, if the user is relaxed, the task execution unit will set the procedure priority to generate task procedures with normal priority if the user is relaxed. Furthermore, if the user is in a hurry, the task execution unit can prioritize generating task procedures that need to be processed quickly. For example, if the user is in a hurry, the task execution unit will set the procedure priority to prioritize generating task procedures that need to be processed quickly. In this way, by determining the priority of task procedures according to the user's emotions, important task procedures can be generated preferentially. Emotion estimation is implemented using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the task execution unit may be performed using AI, for example, or without AI. For example, the task execution unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0090] The task execution unit can prioritize generating highly relevant task procedures by considering the user's geographical location information during task execution. For example, if the user is in a specific region, the task execution unit will prioritize generating task procedures related to that region. For example, if the user is in a specific region, the task execution unit will identify and prioritize generating task procedures related to that region. Furthermore, if the user is on the move, the task execution unit can also generate relevant task procedures based on their current location. For example, if the user is on the move, the task execution unit will identify and prioritize generating relevant task procedures based on their current location. In addition, if the user is in a specific location, the task execution unit can also prioritize generating task procedures related to that location. For example, if the user is in a specific location, the task execution unit will identify and prioritize generating task procedures related to that location. This allows for the priority generation of highly relevant task procedures by considering the user's geographical location information. Some or all of the above processing in the task execution unit may be performed using AI, for example, or without AI. For example, the task execution unit can input the user's geographical location data into the generation AI and have the generation AI execute the generation of highly relevant work procedures.

[0091] The task execution unit can analyze the user's social media activity and generate relevant work procedures during task execution. For example, the task execution unit can analyze the content of the user's social media posts and generate relevant work procedures. For example, the task execution unit can analyze the content of the user's social media posts and identify relevant work procedures. The task execution unit can also analyze the activities of the user's social media followers and friends and generate relevant work procedures. For example, the task execution unit can analyze the activities of the user's social media followers and friends and identify relevant work procedures. Furthermore, the task execution unit can analyze the user's social media trends and generate relevant work procedures. For example, the task execution unit can analyze the user's social media trends and identify relevant work procedures. In this way, relevant work procedures can be generated by analyzing the user's social media activity. Some or all of the above processing in the task execution unit may be performed using AI, for example, or without AI. For example, the task execution unit can input the user's social media activity data into a generation AI and have the generation AI execute the generation of relevant work procedures.

[0092] The feedback unit can estimate the user's emotions and adjust the content of the feedback based on the estimated emotions. For example, if the user is stressed, the feedback unit can provide concise feedback. For example, if the user is stressed, the feedback unit can adjust the content of the feedback to provide concise feedback. The feedback unit can also provide detailed feedback if the user is relaxed. For example, if the user is relaxed, the feedback unit can adjust the content of the feedback to provide detailed feedback. Furthermore, if the user is in a hurry, the feedback unit can provide quick feedback. For example, if the user is in a hurry, the feedback unit can adjust the content of the feedback to provide quick feedback. In this way, by adjusting the content of the feedback according to the user's emotions, more appropriate feedback can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0093] The feedback unit can select the optimal feedback method by referring to the user's past feedback history when providing feedback. For example, the feedback unit can analyze the user's past feedback history and select the optimal feedback method. For example, the feedback unit can identify the optimal feedback method based on the user's past feedback history. The feedback unit can also provide current feedback by referring to the user's past feedback history. For example, the feedback unit can identify the current feedback based on the user's past feedback history. Furthermore, the feedback unit can optimize the feedback algorithm based on the user's past feedback history. For example, the feedback unit can adjust the feedback algorithm based on the user's past feedback history. This allows the optimal feedback method to be selected by referring to the user's past feedback history. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's past feedback history data into a generating AI and have the generating AI select the optimal feedback method.

[0094] The feedback unit can apply different feedback algorithms depending on the specific application or task during the feedback process. For example, the feedback unit can apply the optimal feedback algorithm for a particular application. For example, the feedback unit can select and apply the optimal feedback algorithm for a particular application. The feedback unit can also apply different feedback algorithms depending on the specific task. For example, the feedback unit can select and apply the optimal feedback algorithm for a particular task. Furthermore, the feedback unit can select the optimal feedback algorithm for multiple applications or tasks. For example, the feedback unit can select and apply the optimal feedback algorithm for multiple applications or tasks. This improves the accuracy of feedback by applying different feedback algorithms depending on the specific application or task. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input data for a specific application or task into a generating AI and have the generating AI execute the application of the optimal feedback algorithm.

[0095] The feedback unit can estimate the user's emotions and determine the priority of feedback based on the estimated emotions. For example, if the user is stressed, the feedback unit will prioritize providing important feedback. For example, if the user is stressed, the feedback unit will set the priority of feedback to prioritize providing important feedback. The feedback unit can also provide feedback with normal priority if the user is relaxed. For example, if the user is relaxed, the feedback unit will set the priority of feedback to provide feedback with normal priority if the user is relaxed. Furthermore, if the user is in a hurry, the feedback unit will prioritize providing feedback that needs to be processed quickly. For example, if the user is in a hurry, the feedback unit will set the priority of feedback to prioritize providing feedback that needs to be processed quickly. In this way, important feedback can be prioritized by determining the priority of feedback according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0096] The feedback unit can prioritize providing highly relevant feedback by considering the user's geographical location information. For example, if the user is in a specific region, the feedback unit can prioritize providing feedback related to that region. For example, if the user is in a specific region, the feedback unit can identify and prioritize feedback related to that region. Furthermore, if the user is on the move, the feedback unit can provide relevant feedback based on their current location. For example, if the user is on the move, the feedback unit can identify and prioritize feedback based on their current location. In addition, if the user is in a specific location, the feedback unit can prioritize providing feedback related to that location. For example, if the feedback unit is in a specific location, the feedback unit can identify and prioritize feedback related to that location. This allows the feedback unit to prioritize providing highly relevant feedback by considering the user's geographical location information. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's geographical location information data into a generating AI and have the generating AI perform the task of providing highly relevant feedback.

[0097] The feedback unit can analyze the user's social media activity and provide relevant feedback when providing feedback. For example, the feedback unit can analyze the content of the user's social media posts and provide relevant feedback. For example, the feedback unit can analyze the content of the user's social media posts and identify relevant feedback. The feedback unit can also analyze the activities of the user's social media followers and friends and provide relevant feedback. For example, the feedback unit can analyze the activities of the user's social media followers and friends and identify relevant feedback. Furthermore, the feedback unit can analyze the user's social media trends and provide relevant feedback. For example, the feedback unit can analyze the user's social media trends and identify relevant feedback. In this way, relevant feedback can be provided by analyzing the user's social media activity. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's social media activity data into a generating AI and have the generating AI perform the provision of relevant feedback.

[0098] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0099] The AI ​​agent system can estimate a user's emotions and dynamically change the user interface layout based on those emotions. For example, if a user is stressed, the system can change to a simpler, more intuitive layout to reduce user burden. If the user is relaxed, it can change to a layout that displays more detailed information. Furthermore, if the user is focused, it can change to a layout that highlights important information. This allows for an improved user experience by dynamically changing the interface layout in response to the user's emotions.

[0100] AI agent systems can analyze a user's past operation history and suggest optimal operating procedures. For example, they can suggest shortcuts to automate frequently performed operations. They can also learn patterns of past operations and predict and suggest the next steps to take. Furthermore, they can suggest the optimal procedures for a user to efficiently complete a specific task. In this way, by leveraging the user's operation history and suggesting efficient operating procedures, the system can improve the user's work efficiency.

[0101] The AI ​​agent system can estimate the user's emotions and adjust the frequency and content of notifications based on those emotions. For example, if the user is stressed, the notification frequency will be reduced and only important notifications will be displayed. If the user is relaxed, notifications can be displayed at the normal frequency. Furthermore, if the user is concentrating, notifications can be temporarily suppressed and displayed all at once later. By adjusting the frequency and content of notifications according to the user's emotions, it is possible to maintain the user's concentration and reduce stress.

[0102] The AI ​​agent system can prioritize displaying relevant information by considering the user's geographical location. For example, if the user is in a specific region, it can display news and event information related to that region. If the user is on the move, it can also display relevant traffic and weather information based on their current location. Furthermore, if the user is in a specific location, it can display tourist information and restaurant information related to that location. This leverages the user's geographical location to prioritize the display of relevant information, thereby improving user convenience.

[0103] The AI ​​agent system can estimate the user's emotions and adjust the voice assistant's tone and speaking style based on those estimates. For example, if the user is stressed, the voice assistant will speak in a calm and soothing tone. If the user is relaxed, it can speak in a friendly and casual tone. Furthermore, if the user is focused, it can speak in a concise and clear tone. This allows for smoother communication with the user by adjusting the voice assistant's tone and speaking style according to the user's emotions.

[0104] The AI ​​agent system can analyze a user's social media activity and provide relevant information. For example, if a user posts about a specific topic, it can provide news and articles related to that topic. It can also analyze the activity of the user's followers and friends and suggest relevant events and activities. Furthermore, it can analyze the user's social media trends and provide relevant information. In this way, by leveraging the user's social media activity to provide relevant information, it can deliver information tailored to the user's interests and concerns.

[0105] The AI ​​agent system can estimate the user's emotions and adjust task priorities based on those emotions. For example, if the user is stressed, it can prioritize important tasks to reduce their burden. If the user is relaxed, it can process tasks with normal priorities. Furthermore, if the user is in a hurry, it can prioritize tasks that need to be handled quickly. This allows for more efficient work by adjusting task priorities according to the user's emotions.

[0106] The AI ​​agent system can select the optimal feedback method by referring to the user's past feedback history. For example, it can analyze the feedback format the user preferred in the past and provide feedback in a similar format. It can also analyze the content of feedback the user has received in the past and provide feedback that is appropriate for the current situation. Furthermore, it can optimize the feedback algorithm based on the user's past feedback history. By utilizing the user's past feedback history to select the optimal feedback method, it can provide feedback that is beneficial to the user.

[0107] The AI ​​agent system can estimate the user's emotions and adjust the difficulty level of learning content based on those emotions. For example, if the user is stressed, it can provide easy content to reduce the learning burden. If the user is relaxed, it can provide content of normal difficulty. Furthermore, if the user is focused, it can provide content of higher difficulty. In this way, by adjusting the difficulty level of learning content according to the user's emotions, it can support effective learning.

[0108] The AI ​​agent system can display relevant advertisements by considering the user's geographical location. For example, if a user is in a specific area, it can display advertisements for stores and services related to that area. It can also display relevant advertisements based on the user's current location if the user is on the move. Furthermore, if a user is in a specific location, it can display advertisements related to that location. This allows the system to provide users with useful information by leveraging their geographical location to display relevant advertisements.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The screen recognition unit recognizes elements on the screen and understands the current state. For example, it uses computer vision technology to recognize elements such as buttons, text fields, and images on the screen. It can also understand the current state by analyzing the active window and the user's operation history. Step 2: The user command processing unit understands user instructions entered via voice or text based on the information recognized by the screen recognition unit. For example, it uses natural language processing technology to perform speech recognition and text analysis. It converts the user's voice instructions into text using speech recognition technology and analyzes the content. It can also analyze the user's text instructions using text analysis technology. Step 3: The task execution unit controls mouse movements and keyboard inputs based on instructions understood by the user command processing unit, automatically performing the task. For example, it can use robotics technology to control mouse movements and automation technology to control keyboard inputs. It can also automate specific application operations and data entry. Step 4: The feedback unit re-verifies the results of the work performed by the work execution unit and performs additional processing as needed. For example, it checks the accuracy of the work results using a reinforcement learning algorithm, performs error checking, and corrects errors or re-executes the process as necessary.

[0111] 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.

[0112] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0113] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements described above, including the screen recognition unit, user command processing unit, task execution unit, and feedback unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the screen recognition unit recognizes elements on the screen using the camera 42 of the smart device 14 and computer vision technology to understand the current state. The user command processing unit is implemented in the specific processing unit 290 of the data processing unit 12 and understands user instructions entered in voice or text using natural language processing technology. The task execution unit is implemented in the specific processing unit 46A of the smart device 14 and automatically performs tasks by controlling mouse movements and keyboard input. The feedback unit is implemented in the specific processing unit 290 of the data processing unit 12 and reconfirms the work results and performs additional processing as necessary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] 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.

[0117] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0118] 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.

[0119] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0120] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] 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.

[0122] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0123] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0125] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0126] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0127] 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.

[0128] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the screen recognition unit, user command processing unit, task execution unit, and feedback unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the screen recognition unit recognizes elements on the screen using the camera 42 of the smart glasses 214 and computer vision technology to understand the current state. The user command processing unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and understands user instructions entered in voice or text using natural language processing technology. The task execution unit is implemented in the specific processing unit 46A of the smart glasses 214, for example, and controls mouse movements and keyboard input to automatically perform tasks. The feedback unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and reconfirms the work results and performs additional processing as necessary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0131] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0132] 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.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0134] 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.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0136] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] 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.

[0138] 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.

[0139] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] 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.

[0144] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the screen recognition unit, user command processing unit, task execution unit, and feedback unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the screen recognition unit recognizes elements on the screen using the camera 42 of the headset terminal 314 and computer vision technology to understand the current state. The user command processing unit is implemented in the specific processing unit 290 of the data processing unit 12 and understands user instructions entered in voice or text using natural language processing technology. The task execution unit is implemented in the specific processing unit 46A of the headset terminal 314 and automatically performs tasks by controlling mouse movements and keyboard input. The feedback unit is implemented in the specific processing unit 290 of the data processing unit 12 and reconfirms the work results and performs additional processing as necessary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0147] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] 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.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0150] 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.

[0151] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0152] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] 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.

[0154] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0155] 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.

[0156] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] 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.

[0161] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements described above, including the screen recognition unit, user command processing unit, task execution unit, and feedback unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the screen recognition unit recognizes elements on the screen using the camera 42 of the robot 414 or computer vision technology and grasps the current state. The user command processing unit is implemented in the specific processing unit 290 of the data processing unit 12 and understands user instructions entered in voice or text using natural language processing technology. The task execution unit is implemented in the control unit 46A of the robot 414 and automatically performs tasks by controlling mouse movements and keyboard input. The feedback unit is implemented in the specific processing unit 290 of the data processing unit 12 and reconfirms the work results and performs additional processing as necessary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0164] 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.

[0165] Figure 9 shows the 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.

[0166] 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.

[0167] 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.

[0168] 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, and motorcycles, 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 based, for example, 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.

[0169] 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."

[0170] 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.

[0171] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0180] 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 other things 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.

[0181] 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.

[0182] (Note 1) A screen recognition unit that recognizes elements on the screen and understands the current state, A user command processing unit that understands user instructions entered via voice or text based on the information recognized by the aforementioned screen recognition unit, A task execution unit controls mouse movements and keyboard inputs based on instructions understood by the user command processing unit, and automatically performs tasks. The unit includes a feedback unit that reconfirms the work results performed by the aforementioned work execution unit and performs additional processing as necessary. A system characterized by the following features. (Note 2) The aforementioned screen recognition unit, Regularly capture the screen and extract important information. The system described in Appendix 1, characterized by the features described herein. (Note 3) The user command processing unit said above, Utilizing natural language processing, it understands user instructions entered via voice or text. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned work execution unit is: We utilize generative AI models to generate and automate complex work procedures. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned feedback unit is Reinforcement learning allows for continuous improvement of performance through learning from experience. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned work execution unit is: Automate and optimize key tasks such as requirements definition, design, and schedule management. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned screen recognition unit, It estimates the user's emotions and adjusts the frequency of screen captures based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned screen recognition unit, During screen recognition, focus on specific applications or windows to prioritize the extraction of important information. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned screen recognition unit, During screen recognition, the system references past screen capture history to improve the accuracy of extracting important information. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned screen recognition unit, It estimates the user's emotions and prioritizes important information on the screen based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned screen recognition unit, During screen recognition, the system prioritizes extracting highly relevant information by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned screen recognition unit, During screen recognition, the system analyzes the user's social media activity and extracts relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The user command processing unit said above, It estimates the user's emotions and adjusts how commands are interpreted based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The user command processing unit said above, During command processing, the system references the user's past instruction history to select the most appropriate interpretation method. The system described in Appendix 1, characterized by the features described herein. (Note 15) The user command processing unit said above, When processing commands, different interpretation algorithms are applied depending on the specific application or task. The system described in Appendix 1, characterized by the features described herein. (Note 16) The user command processing unit said above, It estimates the user's emotions and determines the priority of commands based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The user command processing unit said above, When processing commands, the system prioritizes the processing of commands that are highly relevant to the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The user command processing unit said above, During command processing, the system analyzes the user's social media activity and processes relevant commands. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned work execution unit is: It estimates the user's emotions and adjusts the method of generating work procedures based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned work execution unit is: When executing a task, the system generates the optimal work procedure by referring to the user's past work history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned work execution unit is: When executing a task, different task procedure generation algorithms are applied depending on the specific application or task. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned work execution unit is: The system estimates the user's emotions and prioritizes work procedures based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned work execution unit is: When executing a task, the system prioritizes generating highly relevant work procedures by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned work execution unit is: During task execution, the system analyzes the user's social media activity and generates relevant work procedures. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned feedback unit is It estimates the user's emotions and adjusts the content of the feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned feedback unit is When providing feedback, the system selects the most suitable feedback method by referring to the user's past feedback history. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned feedback unit is When providing feedback, different feedback algorithms are applied depending on the specific application or task. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned feedback unit is It estimates the user's emotions and prioritizes feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned feedback unit is When providing feedback, we prioritize providing highly relevant feedback by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned feedback unit is When providing feedback, we analyze the user's social media activity and provide relevant feedback. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A screen recognition unit that recognizes elements on the screen and understands the current state, A user command processing unit that understands user instructions entered via voice or text based on the information recognized by the aforementioned screen recognition unit, A task execution unit controls mouse movements and keyboard inputs based on instructions understood by the user command processing unit, and automatically performs tasks. The unit includes a feedback unit that reconfirms the work results performed by the aforementioned work execution unit and performs additional processing as necessary. A system characterized by the following features.

2. The aforementioned screen recognition unit, Regularly capture the screen and extract important information. The system according to feature 1.

3. The user command processing unit said above, Utilizing natural language processing, it understands user instructions entered via voice or text. The system according to feature 1.

4. The aforementioned work execution unit is: By utilizing generative AI models, complex work procedures are generated and automated. The system according to feature 1.

5. The aforementioned feedback unit is Reinforcement learning allows for continuous improvement of performance through learning from experience. The system according to feature 1.

6. The aforementioned work execution unit is: Automate and optimize key tasks such as requirements definition, design, and schedule management. The system according to feature 1.

7. The aforementioned screen recognition unit, It estimates the user's emotions and adjusts the frequency of screen captures based on the estimated emotions. The system according to feature 1.

8. The aforementioned screen recognition unit, During screen recognition, focus on specific applications or windows to prioritize the extraction of important information. The system according to feature 1.

9. The aforementioned screen recognition unit, During screen recognition, the system references past screen capture history to improve the accuracy of extracting important information. The system according to feature 1.

10. The aforementioned screen recognition unit, It estimates the user's emotions and prioritizes important information on the screen based on those estimated emotions. The system according to feature 1.

Images