System

Abstract

A system is provided.SOLUTION: A system comprising: means for using generative artificial intelligence to understand a user's computer operations and generate a program for automating the operations; means for using a machine learning model to learn a user's work patterns and design an optimal automation process; and voice recognition means for understanding a user's voice commands and performing automated operations based on the voice commands.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Currently, many computer operations are performed manually, reducing user work efficiency. In particular, there are high hurdles to automating operations that require specialized skills and knowledge, or operations that involve detailed work processes. Furthermore, in environments where multiple tools are used simultaneously, it is difficult to integrate and automate these computer operations, resulting in limited use of AI in actual work. A new method is needed to solve this problem and improve user work efficiency. [Means for solving the problem]

[0005] This invention provides a system that understands and automates a user's computer operations by using generative artificial intelligence, a machine learning model, and a speech recognition means. Specifically, the system includes: means for understanding a user's computer operations using generative artificial intelligence and generating a program for automating the operations; means for using a machine learning model to learn the user's work patterns and design an optimal automation process; and speech recognition means for understanding the user's voice commands and executing automated operations based on the voice commands. The system also includes means for recording the user's computer operations and presenting the user with program code generated based on the recorded operations, and means for providing an interface for the user to modify the generated program code and instructions, thereby realizing a system that allows the user to easily set up automation and use it effectively.

[0006] "Generative AI" is AI that has the ability to analyze a user's computer operations and data, and generate new content and program code based on this.

[0007] "Computer operation" refers to mouse clicks, keyboard input, and related screen operations performed by a user on a computer.

[0008] An "automation program" is a program that includes procedures and code for automatically executing user operations.

[0009] "Program code" is text that contains instructions for a computer to understand and execute.

[0010] A "procedure" is a document that describes the steps to perform a specific operation.

[0011] A "machine learning model" is an algorithm or system that learns patterns and trends based on data and makes predictions and optimizations.

[0012] "Speech recognition" is a technology that analyzes a user's voice and converts it into commands or text that a computer can understand.

[0013] "Interface" refers to the means or method by which a user interacts with a system, including graphical user interfaces (GUIs) and voice interfaces. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a 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.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] This invention is a system that automates a user's computer operations using generative artificial intelligence, machine learning models, and speech recognition means. The system records the user's operations, generates an automation program based on the records, and learns the user's work patterns to propose and execute an optimal process. Specific embodiments for implementing this system are described below.

[0036] Overall system configuration

[0037] The system mainly consists of a terminal, a server, and a user. The terminal is a device operated by the user, and performs functions such as recording computer operations, performing voice recognition, and running automation programs. The server mainly hosts generative artificial intelligence and machine learning models, analyzes the user's computer operations, and generates automation programs. The user is the entity that performs the computer operations and interacts with the system through an interface.

[0038] Program processing

[0039] 1. Recording user actions

[0040] The terminal records the user's computer operations in real time, including mouse clicks, keyboard input, screen scrolling, etc. The terminal records these operations in detail and sends them to the server.

[0041] 2. Data submission and analysis

[0042] The device sends the recorded operation data to a server, which uses generative artificial intelligence to analyze the operation and create an automation program based on the received data. The generated program code is then formatted and presented to the user as a procedure manual.

[0043] 3. User confirmation and correction

[0044] The user checks the instructions provided through the terminal. If necessary, the user can modify the operating procedures and program code. The modified instructions are then sent back to the server, where further analysis and program modification are performed.

[0045] 4. Optimization using machine learning models

[0046] The device continuously records the user's operation patterns and sends them to the server. The transmitted data is analyzed by a machine learning model to learn the user's operation patterns. Based on the learning results, an optimal automated process is designed and proposed to the user. The user can then approve or modify the proposal.

[0047] 5. Voice recognition and operation execution

[0048] The user inputs voice commands into the terminal. The server analyzes the voice commands using a voice recognition means and integrates the corresponding operations into an automated program. The terminal executes the integrated program and automates the user's computer operations. The execution results are fed back to the user in real time.

[0049] Specific examples

[0050] For example, consider the operation of a system that automates the daily tasks of updating Excel files and sending them by email.

[0051] Recording operations

[0052] First, the user commands the device to "start recording operations" by voice. The device enters recording mode and records all operations performed by the user. The series of operations performed by the user, such as opening an Excel file, entering data, saving the file, and sending it by email, are recorded.

[0053] Data analysis and program generation

[0054] The device sends the recorded data to a server, which uses generative artificial intelligence to analyze the operations and generate an automation program based on the Excel operating procedures. The generated program is presented to the user as a textual instruction manual.

[0055] User confirmation and correction

[0056] The user checks the procedure manual and issues correction instructions as necessary. The correction instructions are sent via the terminal to the server, where the data is reanalyzed and corrected.

[0057] Machine learning optimization

[0058] The device continuously records the operation patterns of Excel files and the server learns from them. Based on the learning results, the server proposes the optimal operation procedure and presents it to the user.

[0059] Speech recognition and automatic execution

[0060] The user issues a voice command such as "Update and send the Excel file." The device analyzes the voice command using a voice recognition system and executes the instructed operation. The entire process, from updating the Excel file to sending the email, is carried out automatically, and the results are fed back to the user.

[0061] In this way, by using this system, users can efficiently automate computer operations, resulting in a significant improvement in work efficiency.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The user commands the device to "start recording operations" by voice. The device switches to recording mode and gets ready.

[0065] Step 2:

[0066] The device captures all of the user's computer operations (mouse clicks, keyboard input, window movement and scrolling, etc.) in real time and temporarily stores them in storage.

[0067] Step 3:

[0068] When the user completes the operation, the terminal stops recording and sends the captured data to the server.

[0069] Step 4:

[0070] The server inputs the received operation data into the multimodal AI, which analyzes the operation data and generates the corresponding program code.

[0071] Step 5:

[0072] The server then formats the generated code and presents it to the user as a procedure manual, who can then review the manual and provide corrections if necessary.

[0073] Step 6:

[0074] If there are any correction instructions, the terminal sends them to the server, which then reanalyzes the program based on the instructions and generates new program code.

[0075] Step 7:

[0076] The device continuously records the user's operation patterns and periodically sends them to the server, which then updates the machine learning model based on the data sent and learns the user's operation patterns.

[0077] Step 8:

[0078] The machine learning model then proposes the optimal automation process based on the results of its learning, which the server then presents to the user, who can then approve or modify it.

[0079] Step 9:

[0080] The user issues a voice command to the device to perform a specific operation, and the device uses voice recognition AI to analyze the voice command and determine the corresponding operation.

[0081] Step 10:

[0082] The server then integrates the voice command into an automated program based on the analysis results, and the terminal executes the automated program to perform the specified operation.

[0083] Step 11:

[0084] The device provides real-time feedback to the user on the results of the operation, and if necessary, instructions for correction are issued, and further improvements are made based on those instructions.

[0085] Example 1

[0086] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0087] Many of the computer operations that users perform on a daily basis are repetitive and therefore time-consuming and labor-intensive. Furthermore, while these operations should be automated efficiently, conventional automation technologies have been unable to fully understand users' operation patterns, making it difficult to generate appropriate automation programs. Furthermore, when users use voice commands to perform operations, the coordination between voice recognition and automation is often insufficient, preventing smooth operation.

[0088] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0089] In this invention, the server includes means for understanding a user's computer operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn the user's work patterns and design an optimal automation process, and voice recognition means for understanding the user's voice commands and executing automated operations based on the voice commands, thereby enabling the server to accurately capture the user's operation patterns and generate and execute automation programs in real time.

[0090] "Generative AI" refers to AI that has the ability to generate new information and answers based on data.

[0091] "Computer operation" includes user actions for operating a computer or related device, such as mouse clicks, keyboard input, and screen scrolling.

[0092] "Means for generating a program" refers to the device or software that analyzes the user's operations and controls the process of generating program code for automation.

[0093] A "work pattern" refers to a set of computer operations that a user performs to accomplish a specific task.

[0094] An "optimal automated process" refers to an automated procedure that is designed to analyze a user's work patterns and enable the user to perform the work efficiently.

[0095] A "machine learning model" refers to an algorithm or statistical model that learns from data and makes predictions and judgments.

[0096] "Voice command" refers to a command given by a user to give instructions to a computer or related device using voice.

[0097] "Voice recognition means" refers to technology or devices for analyzing a user's voice commands and executing appropriate instructions or operations.

[0098] "Means for recording and transmitting in real time" refers to a process in which every time a user performs a computer operation, that operation is immediately recorded and transmitted to a server.

[0099] A "procedure" is a document that details each step in accomplishing a specific task.

[0100] "Interface" refers to the means or methods by which a user interacts with a system and inputs or displays data.

[0101] This invention is a system for automating user computer operations and improving business efficiency. The system is mainly composed of terminals, a server, and users. Each component and its operation will be specifically described below.

[0102] 1. Recording user actions

[0103] The device is responsible for recording the user's computer operations in real time. This includes mouse clicks, keyboard input, and screen scrolling. When a user operates an Excel file, all specific operations such as opening and closing it, entering data, and saving are recorded. For voice commands, the device uses the Google Speech-to-Text API to convert the voice into text data.

[0104] 2. Data submission and analysis

[0105] The device sends the recorded operation data to the server, using a secure communication protocol (e.g., HTTPS) to ensure the data is transmitted safely.

[0106] The server analyzes the received data using generative artificial intelligence such as OpenAI's GPT-3 model, which allows it to understand the user's operational procedures and generate an automated program.

[0107] The generated program code is formatted as a procedure and the details are presented to the user.

[0108] 3. User confirmation and correction

[0109] The user checks the presented procedure manual through the terminal and makes corrections as necessary. Using the interface, the user inputs the specific corrections. Based on this, the server analyzes the data again and corrects the program.

[0110] 4. Optimization using machine learning models

[0111] The device continuously records the user's operation patterns and periodically sends the data to a server. The server then analyzes the data using machine learning models such as TensorFlow and Scikit-learn to learn the user's operation patterns. Based on the results of this learning, optimal automation procedures are designed and proposed to the user.

[0112] 5. Voice recognition and operation execution

[0113] The user inputs a voice command to the terminal, such as "Update and send the Excel file." The terminal uses a voice recognition means to analyze the voice command and transmits it to the server.

[0114] The server integrates the automation program based on the analysis results and sends the determined commands to the terminal, which then executes the operations according to the received commands and provides the results to the user in real time.

[0115] As a concrete example, consider a situation where you want to automate the task of entering sales data into specific cells in an Excel file every day, saving the file, and sending it by email.

[0116] For example, by inputting a prompt such as, "Generate a program that will automate the task of entering sales data into specific cells in an Excel file every day, saving the file, and sending it by email," into the generation AI, the entire series of operations above will be automated.

[0117] In this way, by using this system, users can efficiently automate computer operations and greatly improve business efficiency.

[0118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0119] Step 1:

[0120] The user inputs a voice command to the terminal saying, "Start recording operations."

[0121] Input: Voice commands given by the user

[0122] Processing: The device uses a voice recognition method (e.g., Google Speech-to-Text API) to parse the voice command and convert it into text data. If the voice command is recognized as an instruction to start recording mode, the device enters recording mode.

[0123] Output: Recording mode is started

[0124] Step 2:

[0125] A user opens an Excel file, enters sales data into specific cells, saves the file, and performs other operations.

[0126] Input: User-operated computer operations (mouse clicks, keyboard input, screen scrolling, etc.)

[0127] Processing: The device records these operations in real time and stores detailed operations in a log.

[0128] Output: Recorded operation log

[0129] Step 3:

[0130] The terminal transmits the recorded operation data to the server.

[0131] Input: Recorded operation log

[0132] Processing: The terminal sends the operation log to the server using a secure communication protocol (e.g., HTTPS).

[0133] Output: Operation log sent to the server

[0134] Step 4:

[0135] The server analyzes the received operation data and generates an automation program using generative artificial intelligence (e.g., OpenAI's GPT-3).

[0136] Input: Operation log sent to the server

[0137] Processing: The server uses generative artificial intelligence to generate an automated program by analyzing the operation log. This program is created by imitating the user's computer operations.

[0138] Output: Generated automation program

[0139] Step 5:

[0140] The server formats the generated program code as a procedure manual and sends it to the terminal.

[0141] Input: Generated automation program

[0142] Processing: The server formats the program code into a user-friendly instruction manual that the user can later review and modify.

[0143] Output: Automation program in the form of a procedure manual

[0144] Step 6:

[0145] The terminal displays the procedure manual to the user.

[0146] Input: Automation program in the form of a procedure manual

[0147] Processing: The terminal displays the procedure manual on the screen and asks the user for confirmation. The user checks the contents and, if necessary, inputs correction instructions through the interface.

[0148] Output: User checks the procedure manual and gives instructions for correction

[0149] Step 7:

[0150] The terminal transmits the user's correction instructions to the server.

[0151] Input: User correction instructions

[0152] Processing: The terminal sends correction instructions to the server, and the server re-analyzes the data.

[0153] Output: Correction instructions sent to the server

[0154] Step 8:

[0155] The server reanalyzes the program code based on the modification instructions and generates a modified automation program.

[0156] Input: Correction instructions sent to the server

[0157] Processing: The server re-analyzes the program code based on the correction instructions and generates an optimized automation program.

[0158] Output: Modified automation program

[0159] Step 9:

[0160] The terminal receives the modified automation program from the server and prepares it for execution.

[0161] Input: Modified automation program

[0162] Processing: The device checks whether the operation is executed correctly based on the received program. Once preparation is complete, the user can start the operation by entering a voice command.

[0163] Output: An automated program ready to run

[0164] Step 10:

[0165] The user inputs a voice command into the terminal saying, "Update and send the Excel file."

[0166] Input: Voice commands given by the user

[0167] Processing: The terminal uses voice recognition means to analyze the voice command, convert it into text data, and send it to the server.

[0168] Output: Voice command sent to the server

[0169] Step 11:

[0170] The server sends instructions to the terminal to execute an automated program based on the voice command.

[0171] Input: Voice command sent to the server

[0172] Processing: The server selects the appropriate automated program based on the voice command and sends the instructions to the terminal.

[0173] Output: Instructions to run the automation program

[0174] Step 12:

[0175] Based on the instructions received, the device automatically performs a series of operations, from updating the Excel file to sending an email.

[0176] Input: Instruction to run the automation program

[0177] Processing: The device opens an Excel file, enters sales data into designated cells, saves the file, and sends it by email.

[0178] Output: automated operations and feedback of the operation results

[0179] Step 13:

[0180] The terminal provides the execution results to the user in real time.

[0181] Input: Automated operation results

[0182] Processing: The device displays detailed results to the user, including whether the operation was successful or an error occurred.

[0183] Output: Real-time feedback of the operation results

[0184] (Application example 1)

[0185] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0186] Operating robots in factories requires a high level of specialized knowledge, and it takes time and training to operate them efficiently. Furthermore, workers tend to tire and make mistakes when performing the same operations every time. Consistent operation is also required even when different workers operate the robots, but this is difficult to achieve. There is a need to solve these issues, improve work efficiency, and reduce errors.

[0187] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0188] In this invention, the server includes means for understanding user operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn user work patterns and design an optimal automation process, means for understanding user voice commands and executing automated operations based on the voice commands, means for recording operations on a terminal and sending the recording to the server, means for presenting the generated program code and instructions to the user, means for continuously learning the operation history and proposing optimal operations, and means for executing operations based on voice recognition and providing feedback on the results. This enables more efficient and consistent robot operation in factories and reduces human error.

[0189] "Generative artificial intelligence" is a technology that generates models based on data and analyzes and automates user operations.

[0190] "User operation" refers to a series of actions or commands performed to operate a machine such as an industrial robot.

[0191] An "automation program" is software code that is generated to automatically perform a user operation.

[0192] A "machine learning model" is a statistical model that learns from data and proposes optimal operating processes.

[0193] A "voice command" is a command that a user issues to a system or machine using voice.

[0194] "Voice recognition means" refers to technology for analyzing a user's voice command and performing the corresponding operation.

[0195] An "operation record" is data that stores a series of actions performed by a user and is used for later analysis and learning.

[0196] A "procedure manual" is a document that describes in detail the operating procedure and is presented to the user.

[0197] "Continuous learning" means that the machine learning model constantly learns the optimal operation process based on recorded operation data.

[0198] "Feedback" refers to communicating to the user the results of an operation that has been performed.

[0199] This invention embodies a system that improves the efficiency and automation of industrial robot operations. This system uses generative artificial intelligence, machine learning models, and voice recognition functions to automate user operations, reducing operational errors and improving efficiency.

[0200] The terminal is a device for recording the user's robot operation in real time, recording detailed actions such as mouse clicks, keyboard input, and touch operations. The recorded data is then sent to a server, which hosts a generative artificial intelligence (AI) that analyzes the user's input and generates an optimal automation program.

[0201] The generated program is presented to the user as a text-formatted instruction manual. The user checks this manual, and if any corrections are necessary, they send the correction instructions to the server again via their terminal. The server reanalyzes the program based on these correction instructions and generates an optimized program.

[0202] Furthermore, the server continuously learns user operation data and proposes optimal operation processes, thereby enabling optimized operations that always reflect the latest operation patterns.Users can also easily operate the system through voice commands, and the server uses voice recognition means to analyze these voice commands and immediately execute the corresponding operations.

[0203] For example, consider a factory worker using a robot to record the operation of placing parts on an assembly line. The user gives a voice command to the terminal to record the operation, then starts operating the robot. Once the operation recording is complete, the terminal sends the data to a server, which then uses generative artificial intelligence to generate an automation program.

[0204] As an example of a prompt sentence, consider the voice command "Place new parts on the assembly line." The server analyzes this voice command and automatically controls the robot to execute the specified operation. As a result, the series of tasks from placing parts to moving on to the next step is automated.

[0205] The hardware required is a device (e.g., a tablet or PC) for user operation, a server for saving and transmitting operation records, and a microphone for inputting voice commands.The software required is a voice recognition library (e.g., speech_recognition), a machine learning model (e.g., a homemade AI model), and a server communication library.

[0206] This will enable more efficient and consistent robot operation in factories, and reduce human error.

[0207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0208] Step 1:

[0209] The user inputs a voice command into the terminal to start operation recording. Specifically, the voice command "Start operation recording" is issued through the microphone. The input data is voice, and the terminal converts this voice command into text using voice recognition software. The output is the start of operation recording mode.

[0210] Step 2:

[0211] The device records a series of user operations in detail. Operation data (mouse clicks, keyboard input, touch operations, etc.) is saved in a log in real time. The input data is the user's operation, and the device compiles this as an operation record. The output is the operation record data.

[0212] Step 3:

[0213] The terminal sends the recorded operation data to the server. The server receives this data. The input data is the operation record data, which the server stores in the database. The output is the operation record stored in the database.

[0214] Step 4:

[0215] The server analyzes the received operation data and generates an optimal automation program using generative artificial intelligence. The input data is the operation record data, which the server analyzes and executes an algorithm to generate the automation program. The output is the generated automation program code.

[0216] Step 5:

[0217] The server sends the generated program code to the terminal as a procedure manual and presents it to the user. The input data is the automation program code, which the server formats in procedure manual format. The output is a procedure manual that the user can check.

[0218] Step 6:

[0219] The user checks the procedure manual and, if any corrections are necessary, sends the correction instructions to the server via the terminal. The input data is the correction instructions, which the terminal sends to the server. The output is the transmission of the correction instructions.

[0220] Step 7:

[0221] The server receives the modification instructions and reanalyzes and modifies the automation program. The input data are the modification instructions, which the server uses for further analysis. The output is the modified automation program code.

[0222] Step 8:

[0223] The server continuously learns from the user's operation data and proposes the optimal operation process. The input data is the newly recorded operation data, and the server updates the machine learning model. The output is the proposed optimized operation process.

[0224] Step 9:

[0225] The user then executes the generated program by again inputting voice commands into the terminal. Specifically, the user inputs a specific prompt through the microphone, such as "Place the new part on the assembly line." The input data is voice, which the terminal converts into text using voice recognition software and sends to the server. The output is the automated operation to be executed.

[0226] Step 10:

[0227] The server analyzes the voice commands and executes the corresponding automated program. The input data is the text of the voice commands, which the server matches with the automated program and executes. The output is the result of the automated operation.

[0228] Step 11:

[0229] The execution results are fed back to the user through the terminal. The input data is the execution results, which the server sends to the terminal. The output is feedback information that the user can check.

[0230] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0231] This invention is a system that automates a user's computer operations using generative artificial intelligence, a machine learning model, a speech recognition means, and an emotion engine. This system not only records and analyzes the user's operations and generates an automation program, but also recognizes the user's emotional state and adjusts operating procedures and processes based on that. Specific embodiments for implementing this system are described below.

[0232] Overall system configuration

[0233] The system mainly consists of a terminal, a server, and a user. The terminal is a device operated by the user, and performs tasks such as recording computer operations, performing voice recognition, recognizing emotions using an emotion engine, and running automation programs. The server mainly hosts generative artificial intelligence and machine learning models, analyzes the user's computer operations, and generates automation programs. The user is the entity that interacts with the system via an interface and performs computer operations.

[0234] Program processing

[0235] The specific processing flow of the program and the operation at each step will be explained below.

[0236] 1. Recording user actions

[0237] The terminal records the user's computer operations in real time, including mouse clicks, keyboard input, and screen scrolling.

[0238] 2. Data submission and analysis

[0239] The device sends the recorded operation data to a server, which then inputs the received data into a generative artificial intelligence (AI) system, analyzes it, and generates an automation program. The generated program code is then formatted and presented to the user as a procedure manual.

[0240] 3. User confirmation and correction

[0241] The user checks the procedure manual provided through the terminal. If necessary, the user can modify the operation procedure or program code and send the modification instructions to the server. The server then reanalyzes the program based on the modification instructions and generates new program code.

[0242] 4. Optimization using machine learning models

[0243] The device continuously records the user's operation patterns and sends them to the server. The server uses the data to update the machine learning model and learns the user's operation patterns. Based on the learning results, an optimal automated process is designed and proposed to the user. The user can then approve or modify the proposal.

[0244] 5. Emotion Recognition by Emotion Engine

[0245] The device uses an emotion engine to recognize the user's emotional state in real time, which is analyzed based on data collected through sensors such as cameras and microphones.

[0246] 6. Emotion-based process adjustment

[0247] The server receives the emotional data analyzed by the emotion engine and adjusts the automation process based on the user's emotional state. For example, if the system detects that the user is fatigued, it will simplify the operation procedure or suggest that the user take a break.

[0248] 7. Voice recognition and operation execution

[0249] The user inputs voice commands to the terminal to perform specific operations. The server analyzes the voice commands using a voice recognition means and integrates the corresponding operations into an automation program. The terminal executes the integrated program and automates the user's computer operations.

[0250] 8. Operation Feedback

[0251] The device provides real-time feedback to the user on the results of the operations performed, and if necessary, instructions are given for correction, which are then used to make further improvements.

[0252] Specific examples

[0253] For example, consider the operation of a system that automates the daily tasks of updating Excel files and sending them by email.

[0254] Recording operations

[0255] The user first commands the device to "start recording operations." The device then enters recording mode and records all operations performed by the user. The series of operations performed by the user, including opening an Excel file, entering data, saving the file, and sending it by email, are recorded.

[0256] Data analysis and program generation

[0257] The device sends the recorded data to a server, which uses generative artificial intelligence to analyze the operations and generate an automation program based on the Excel operating procedures. The generated program is presented to the user as a textual instruction manual.

[0258] User confirmation and correction

[0259] The user checks the procedure manual and issues correction instructions as necessary. The terminal sends the correction instructions to the server, which reanalyzes the program and generates new program code.

[0260] Emotion recognition and operational adjustment

[0261] The device uses an emotion engine to recognize the user's emotions from their facial expressions and voice. For example, if the user is feeling stressed, the server will adjust the device to simplify the operation procedure.

[0262] Speech recognition and automatic execution

[0263] The user issues a voice command such as "Update and send the Excel file." The device analyzes the command using voice recognition and executes the specified operation. The results of the operation are fed back to the user in real time.

[0264] In this way, this system allows users to automate computer operations efficiently and respond flexibly to their emotional state, resulting in a significant improvement in the user's work efficiency and a more comfortable working environment.

[0265] The processing flow will be explained below.

[0266] Step 1:

[0267] The user commands the terminal by voice, "Start recording my operations." The terminal switches to recording mode and prepares for computer operations.

[0268] Step 2:

[0269] The terminal captures the user's computer operations in real time and temporarily stores data such as mouse clicks, keyboard input, and window operations.

[0270] Step 3:

[0271] When the user completes the operation, the terminal stops recording and sends the captured data to the server.

[0272] Step 4:

[0273] The server inputs the received operation data into the generative AI, analyzes it, and generates an automation program. The server then formats the generated program code and presents it to the user as a procedure manual.

[0274] Step 5:

[0275] The user checks the procedure manual through the terminal and issues instructions to correct the operation procedures or program code as necessary. The correction instructions are sent from the terminal to the server.

[0276] Step 6:

[0277] The server re-analyzes the program based on the correction instructions, generates new program code, and presents the corrected procedure manual or program code to the user again.

[0278] Step 7:

[0279] The device continuously records the user's operation patterns and sends them to the server, which then updates the machine learning model and learns the user's operation patterns.

[0280] Step 8:

[0281] The machine learning model designs the optimal automated process, which the server presents to the user, who can then approve or modify the proposal via their device.

[0282] Step 9:

[0283] The device uses an emotion engine to recognize the user's emotional state in real time and collect emotion data.

[0284] Step 10:

[0285] The server receives the emotional data analyzed by the emotion engine and adjusts the automated process based on the user's emotional state, for example, simplifying the operation procedure if the user is tired.

[0286] Step 11:

[0287] The user issues a voice command to the terminal to perform a specific operation, and the terminal uses a voice recognition means to analyze the voice command and determine the corresponding operation.

[0288] Step 12:

[0289] The server integrates operations corresponding to the voice commands into an automated program, and the terminal executes the automated program to automate the user's computer operations.

[0290] Step 13:

[0291] The device provides real-time feedback to the user on the results of the operation, and if necessary, instructions for correction are issued again, and further improvements are made based on those instructions.

[0292] Example 2

[0293] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0294] In conventional systems, it is difficult to automate user computer operations, and each individual operation procedure must be set manually, resulting in reduced work efficiency. Furthermore, because dynamic adjustments based on the user's work patterns and emotional state are not made, users are prone to accumulate stress and fatigue, leading to frequent operational errors. The present invention aims to solve these problems.

[0295] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0296] In this invention, the server includes means for understanding a user's computer operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn the user's work patterns and design an optimal automation process, voice recognition means for understanding the user's voice commands and executing automated operations based on the voice commands, means for recognizing the user's emotional state in real time and adjusting the automation process based on the emotional state, and means for recording the user's computer operations and presenting the user with program code and instructions generated based on the recorded operation data. This makes it possible to automate the user's operations efficiently and flexibly and adjust the process optimally according to the user's emotional state.

[0297] "Generative AI" is AI that understands a user's computer operations and generates a program to automate those operations.

[0298] A "machine learning model" is a learning algorithm that learns user work patterns and designs optimal automation processes.

[0299] "Voice recognition means" refers to technology for understanding a user's voice commands and performing automated operations based on the voice commands.

[0300] An "emotion engine" is a system that recognizes a user's emotional state in real time and adjusts automated processes based on this.

[0301] "Camera and Microphone" are video and audio sensors used to collect the user's emotional state.

[0302] "Computer operation" refers to all operations that a user performs using a computer.

[0303] "Operation data" is data that records the user's computer operations.

[0304] "Program code" means source code generated for automation by generative artificial intelligence.

[0305] A "procedure manual" is a document of operating procedures that is presented to the user based on the generated program code.

[0306] The "modification interface" is a user interface that allows a user to make modifications to the generated program code and procedure manual.

[0307] MODE FOR CARRYING OUT THE INVENTION

[0308] This invention is a system that automates user computer operations using generative artificial intelligence, machine learning models, speech recognition means, and an emotion engine. This system not only records and analyzes user operations and generates automation programs, but also recognizes the user's emotional state and adjusts operating procedures and processes based on that.

[0309] The system mainly consists of a server, a terminal, and a user. The terminal is a device operated by the user, and performs tasks such as recording computer operations, performing voice recognition, recognizing emotions using an emotion engine, and running automation programs. The server mainly hosts generative artificial intelligence and machine learning models, analyzes the user's computer operations, and generates automation programs. The user is the entity that interacts with the system via an interface and performs computer operations.

[0310] Specifically, the device records the user's actions and sends the data to a server. The server then analyzes the actions using a generative AI model (such as ChatGPT) and generates the necessary programs. The device can also monitor the user's emotional state in real time and send that information to the server. The server then analyzes the emotional state using an emotion engine (such as the Affectiva SDK) and adjusts the automation process as needed.

[0311] Specific examples

[0312] For example, consider the case where the user wants to automate the daily task of updating an Excel file and sending it by email. First, the user commands the device to "start recording operations." At this time, the device enters recording mode and records all operations performed by the user. Operations such as the user opening the Excel file, entering data, saving the file, and sending it by email are recorded.

[0313] The recorded data is sent from the device to a server, which then uses a generative AI model to analyze the operation and generate an automation program. The generated program is presented to the user as a procedure manual, which the user can review and provide correction instructions as needed.

[0314] The device then uses an emotion engine to monitor the user's emotional state. For example, if the device detects that the user is feeling stressed, the server can make adjustments, such as simplifying the operation procedure.

[0315] Finally, the user can issue a voice command such as "Update and send the Excel file." The device will interpret the command using a voice recognition method (e.g., Google Cloud Speech-to-Text API) and execute the automated operation, providing real-time feedback to the user.

[0316] Prompt Sentence Examples

[0317] Here are some examples of prompts to input to a generative AI model:

[0318] "Create a program to automatically update Excel data and send emails daily. Follow these steps:

[0319] 1. Open the Excel file

[0320] 2. Enter your data

[0321] 3. Save the file

[0322] 4. Send the saved file by email.

[0323] By using this system, users can efficiently automate computer operations and optimally adjust processes according to their emotional state, significantly improving their work efficiency and providing a more comfortable working environment.

[0324] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0325] Step 1:

[0326] Recording user actions

[0327] When the user starts operating the computer, the terminal enters the recording mode by issuing a command to "start recording the operation."

[0328] Input: User actions such as mouse clicks, keyboard input, and screen scrolling.

[0329] Data processing: Record the entered operations in a log file.

[0330] Output: Recorded operation data.

[0331] Specific actions: Everything a user does, from opening Excel, entering data, saving, and emailing, is recorded.

[0332] Step 2:

[0333] Data transmission and analysis

[0334] The terminal transmits the recorded operation data to the server periodically or after the operation is completed.

[0335] Input: Recorded operation data.

[0336] Data processing: Input the operational data into a generative AI model (e.g., ChatGPT) and perform analysis.

[0337] Output: Program code for the automation process.

[0338] Specific operation: After the data is sent to the server, the generative AI model analyzes the operation procedures and creates an automation program based on the Excel operation procedures.

[0339] Step 3:

[0340] User confirmation and correction

[0341] The user checks the procedure manual presented via the terminal.

[0342] Input: Presented instructions and generated program code.

[0343] Data processing: The user makes corrections and sends the correction instructions to the server via their device. The server reuses the generative AI model and regenerates the program code.

[0344] Output: Updated program code and instructions.

[0345] Specific operation: When the user instructs "This step is unnecessary, so please delete it," the server generates a new procedure manual and program based on the instruction.

[0346] Step 4:

[0347] Optimization with machine learning models

[0348] The terminal continuously records the user's operation patterns and transmits them to the server.

[0349] Input: Continuously recorded operational data.

[0350] Data processing: Using machine learning models (e.g., TensorFlow) to learn operational patterns.

[0351] Output: A recommendation of the best automation process for the user.

[0352] What it does: It collects data over a long period of time and then the server suggests to the user, "We've optimized it so that you can perform all operations with just one click."

[0353] Step 5:

[0354] Emotion recognition by emotion engine

[0355] The device uses an emotion engine (e.g., Affectiva SDK) to recognize the user's emotional state in real time.

[0356] Input: User facial and voice data collected through camera and microphone.

[0357] Data processing: The emotion engine analyzes facial expressions and voice to determine the emotional state.

[0358] Output: The user's real-time emotional state.

[0359] Specific operation: If the user shows signs of fatigue during operation, the emotion engine will recognize the state as "fatigue."

[0360] Step 6:

[0361] Emotion-based process adjustment

[0362] The server adjusts the automation process based on the emotion data received from the emotion engine.

[0363] Input: Emotional state data from the emotion engine.

[0364] Data processing: Adjusting automated processes, simplifying steps or suggesting breaks where necessary.

[0365] Output: A coordinated automated process.

[0366] Specific operation: The server suggests, "Would you like to take a break?" and presents instructions to simplify the operation procedure.

[0367] Step 7:

[0368] Voice recognition and operation execution

[0369] The user issues a voice command, which the terminal recognizes.

[0370] Input: Voice command.

[0371] Data processing: The voice is analyzed using a speech recognition tool (e.g., Google Cloud Speech-to-Text API) and sent to a server, which then integrates the instructions into an automated program and returns instructions for execution.

[0372] Output: Execution of automated operations based on voice commands.

[0373] Specific operation: When a user commands, "Update and send the Excel file," the device analyzes the voice and generates an execution command on the server, after which the Excel file is automatically updated and an email is sent.

[0374] Step 8:

[0375] Operation feedback

[0376] The terminal provides the user with real-time feedback on the results of the operation.

[0377] Input: The result of running an automated program.

[0378] Data processing: Analyze the execution results and provide feedback to the user.

[0379] Output: Feedback information.

[0380] Specific operation: When the user commands, "Check if the operation was successful," the device displays the execution results and gives feedback that "All operations were successful."

[0381] (Application example 2)

[0382] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0383] In modern self-driving vehicles, automation of driver operations and voice commands, and environmental adjustments based on real-time emotion recognition have not yet been fully realized. Therefore, reducing the burden on the driver and improving safety are issues. In addition, the generation of automated programs based on the analysis of operation data and the interface for modifying them are not yet fully developed, so an efficient automated system is required.

[0384] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0385] In this invention, the server includes means for understanding user operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn the user's work patterns and design an optimal automation process, voice recognition means for understanding the user's voice commands and executing automated operations based on the voice commands, means for recording, analyzing, and automating the driver's operations and voice commands, and means for recognizing the driver's emotional state in real time and adjusting the in-vehicle environment and navigation based on that state. This makes it possible to efficiently automate the driver's operations and further adjust the in-vehicle environment and navigation based on the driver's emotional state.

[0386] "Generative AI" is an AI technology that understands user operations and generates programs to automate those operations.

[0387] A "machine learning model" is an algorithm or method for learning user work patterns and designing optimal automation processes.

[0388] "Voice recognition means" refers to technology for understanding a user's voice commands and performing automated operations based on the voice commands.

[0389] The "operation recording means" is a function for recording user operations and voice commands, analyzing them, and automating them.

[0390] "Emotion recognition means" is a technology that recognizes the driver's emotional state in real time and adjusts the in-car environment and navigation based on that state.

[0391] An "autonomous vehicle" is a vehicle that drives autonomously without the need for manual operation by a driver.

[0392] The "user interface" refers to a screen or input means that allows the user to modify the generated program code and procedure manual.

[0393] This invention relates to a system that records, analyzes, and automates driver operations and voice commands of an autonomous vehicle. This system has a function of supporting comfortable driving by the driver using generative artificial intelligence, machine learning models, voice recognition means, and emotion recognition means. Detailed embodiments of the system are described below.

[0394] Overall system configuration

[0395] The system mainly consists of an in-vehicle device, a server, and a driver. The in-vehicle device records the driver's operations and voice commands and collects data for emotion recognition. The server hosts generative artificial intelligence and machine learning models, analyzes operation data, and generates automated programs. The driver interacts with the system via an interface and is the entity that performs driving operations.

[0396] System Program

[0397] Operation recording means

[0398] The in-vehicle device records the driver's actions and voice commands in real time, including steering, pedal operation, touchscreen operation, etc. It also uses cameras and sensors to collect the driver's facial expressions and voice.

[0399] Data transmission and analysis

[0400] The vehicle-mounted device sends the recorded operation data to a server, which then inputs the received data into a generative artificial intelligence system, analyzes it, and generates an automation program. This uses machine learning libraries such as TensorFlow and PyTorch.

[0401] Automated Program Generation and Emotion Recognition

[0402] The server generates the optimal automation program based on the operation data. It also uses technologies such as OpenCV to analyze data acquired from cameras and microphones and recognize the driver's emotional state. Based on this emotional state, the automation program and navigation are adjusted.

[0403] Voice recognition and operation execution

[0404] The driver can input voice commands into the vehicle's in-vehicle device, and the server will interpret the voice commands through speech recognition means and perform the corresponding operations, using the Google Speech-to-Text API.

[0405] feedback

[0406] The in-vehicle device provides real-time feedback to the driver on the results of the maneuver, allowing the driver to issue additional voice commands or corrective actions if necessary.

[0407] Specific examples

[0408] For example, if a driver issues the voice command "Go home," the system will:

[0409] 1. Voice command recognition:

[0410] Driver: "Going home."

[0411] In-vehicle device: Google Speech-to-Text converts voice commands into text

[0412] 2. Navigation adjustment:

[0413] Server: Analyzes the text data and generates a route to home

[0414] Emotional state analysis: if the driver is tired, add optimal rest stops to the route

[0415] 3. Feedback:

[0416] In-vehicle device: Provides voice feedback to the driver on route guidance

[0417] Example prompt sentence:

[0418] User: I want to go home

[0419] System: Searching for a route to your home. Please wait.

[0420] System (feedback): Your route is planned. It looks like you might need a break along the way, so we've added appropriate stops. Please resume driving.

[0421] In this way, the system effectively automates driver operations and also adjusts the in-car environment and navigation according to the driver's emotional state, providing a more comfortable and safer driving experience.

[0422] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0423] Step 1:

[0424] Recording of operation and emotional data

[0425] Subject: Terminal

[0426] The terminal (vehicle-mounted device) records the driver's operations and voice commands in real time. The terminal also uses cameras and sensors to collect the driver's facial expressions and voice. Input data includes steering wheel operations, pedal operations, touchscreen operations, facial expressions, and voice. This data is temporarily stored locally and prepared for real-time analysis as needed.

[0427] Step 2:

[0428] Data transmission and analysis

[0429] Subject: Terminal

[0430] The device sends the recorded operation data and emotion data to the server. The input data includes the operation log and emotion data collected in step 1. The server analyzes the received data and generates an automation program using generative artificial intelligence (e.g., TensorFlow, PyTorch). Data analysis includes splitting time-series data and feature extraction. The output after analysis is the initial script for the automation program.

[0431] Step 3:

[0432] Generating automation programs

[0433] Subject: Server

[0434] The server uses generative artificial intelligence to generate an automation program based on the analytical data. The analytical data obtained in step 2 is used as input. The generative AI model generates program code, creating operating procedures and scripts during the generation process. The output is program code containing automated operating procedures.

[0435] Step 4:

[0436] Emotion recognition and process regulation

[0437] Subject: Server

[0438] The server uses emotion recognition means (e.g., OpenCV) to recognize the driver's emotional state from the collected facial and voice data. The emotional data collected in steps 1 and 2 is used as input. Based on the results of the emotional state analysis, the automation program and navigation plan are adjusted. The output is an automated program adjusted according to the emotional state.

[0439] Step 5:

[0440] Entering and recognizing voice commands

[0441] Subject: User

[0442] The user (driver) inputs voice commands to the vehicle's onboard device. The input data is the voice command. The server uses a voice recognition method (e.g., Google Speech-to-Text) to convert the voice command into text data. The text data is then analyzed and integrated into the automation program. The output is an operation instruction based on the analyzed voice command.

[0443] Step 6:

[0444] Running an automation program

[0445] Subject: Terminal

[0446] The device executes the automation program received from the server. The input data includes the adjusted automation program and the analysis results of the voice commands. The device automatically executes the operation procedures, performing navigation, adjusting the in-car environment, etc. The output is the execution result of the automated operation.

[0447] Step 7:

[0448] Providing Feedback

[0449] Subject: Terminal

[0450] The terminal provides real-time feedback on the results of the operation to the user. The input data are the execution results and, if necessary, additional instructions from the user. The terminal analyzes this data and determines the next operation steps or necessary adjustments. The output is a report of the operation results to the user and a suggestion for the next operation step.

[0451] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0452] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0453] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0454] [Second embodiment]

[0455] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0456] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0457] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[0458] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0459] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0460] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0461] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0462] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0463] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0464] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0465] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0466] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0467] This invention is a system that automates a user's computer operations using generative artificial intelligence, machine learning models, and speech recognition means. The system records the user's operations, generates an automation program based on the records, and learns the user's work patterns to propose and execute an optimal process. Specific embodiments for implementing this system are described below.

[0468] Overall system configuration

[0469] The system mainly consists of a terminal, a server, and a user. The terminal is a device operated by the user, and performs functions such as recording computer operations, performing voice recognition, and running automation programs. The server mainly hosts generative artificial intelligence and machine learning models, analyzes the user's computer operations, and generates automation programs. The user is the entity that performs the computer operations and interacts with the system through an interface.

[0470] Program processing

[0471] 1. Recording user actions

[0472] The terminal records the user's computer operations in real time, including mouse clicks, keyboard input, screen scrolling, etc. The terminal records these operations in detail and sends them to the server.

[0473] 2. Data submission and analysis

[0474] The device sends the recorded operation data to a server, which uses generative artificial intelligence to analyze the operation and create an automation program based on the received data. The generated program code is then formatted and presented to the user as a procedure manual.

[0475] 3. User confirmation and correction

[0476] The user checks the instructions provided through the terminal. If necessary, the user can modify the operating procedures and program code. The modified instructions are then sent back to the server, where further analysis and program modification are performed.

[0477] 4. Optimization using machine learning models

[0478] The device continuously records the user's operation patterns and sends them to the server. The transmitted data is analyzed by a machine learning model to learn the user's operation patterns. Based on the learning results, an optimal automated process is designed and proposed to the user. The user can then approve or modify the proposal.

[0479] 5. Voice recognition and operation execution

[0480] The user inputs voice commands into the terminal. The server analyzes the voice commands using a voice recognition means and integrates the corresponding operations into an automated program. The terminal executes the integrated program and automates the user's computer operations. The execution results are fed back to the user in real time.

[0481] Specific examples

[0482] For example, consider the operation of a system that automates the daily tasks of updating Excel files and sending them by email.

[0483] Recording operations

[0484] First, the user commands the device to "start recording operations" by voice. The device enters recording mode and records all operations performed by the user. The series of operations performed by the user, such as opening an Excel file, entering data, saving the file, and sending it by email, are recorded.

[0485] Data analysis and program generation

[0486] The device sends the recorded data to a server, which uses generative artificial intelligence to analyze the operations and generate an automation program based on the Excel operating procedures. The generated program is presented to the user as a textual instruction manual.

[0487] User confirmation and correction

[0488] The user checks the procedure manual and issues correction instructions as necessary. The correction instructions are sent via the terminal to the server, where the data is reanalyzed and corrected.

[0489] Machine learning optimization

[0490] The device continuously records the operation patterns of Excel files and the server learns from them. Based on the learning results, the server proposes the optimal operation procedure and presents it to the user.

[0491] Speech recognition and automatic execution

[0492] The user issues a voice command such as "Update and send the Excel file." The device analyzes the voice command using a voice recognition system and executes the instructed operation. The entire process, from updating the Excel file to sending the email, is carried out automatically, and the results are fed back to the user.

[0493] In this way, by using this system, users can efficiently automate computer operations, resulting in a significant improvement in work efficiency.

[0494] The processing flow will be explained below.

[0495] Step 1:

[0496] The user commands the device to "start recording operations" by voice. The device switches to recording mode and gets ready.

[0497] Step 2:

[0498] The device captures all of the user's computer operations (mouse clicks, keyboard input, window movement and scrolling, etc.) in real time and temporarily stores them in storage.

[0499] Step 3:

[0500] When the user completes the operation, the terminal stops recording and sends the captured data to the server.

[0501] Step 4:

[0502] The server inputs the received operation data into the multimodal AI, which analyzes the operation data and generates the corresponding program code.

[0503] Step 5:

[0504] The server then formats the generated code and presents it to the user as a procedure manual, who can then review the manual and provide corrections if necessary.

[0505] Step 6:

[0506] If there are any correction instructions, the terminal sends them to the server, which then reanalyzes the program based on the instructions and generates new program code.

[0507] Step 7:

[0508] The device continuously records the user's operation patterns and periodically sends them to the server, which then updates the machine learning model based on the data sent and learns the user's operation patterns.

[0509] Step 8:

[0510] The machine learning model then proposes the optimal automation process based on the results of its learning, which the server then presents to the user, who can then approve or modify it.

[0511] Step 9:

[0512] The user issues a voice command to the device to perform a specific operation, and the device uses voice recognition AI to analyze the voice command and determine the corresponding operation.

[0513] Step 10:

[0514] The server then integrates the voice command into an automated program based on the analysis results, and the terminal executes the automated program to perform the specified operation.

[0515] Step 11:

[0516] The device provides real-time feedback to the user on the results of the operation, and if necessary, instructions for correction are issued, and further improvements are made based on those instructions.

[0517] Example 1

[0518] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0519] Many of the computer operations that users perform on a daily basis are repetitive and therefore time-consuming and labor-intensive. Furthermore, while these operations should be automated efficiently, conventional automation technologies have been unable to fully understand users' operation patterns, making it difficult to generate appropriate automation programs. Furthermore, when users use voice commands to perform operations, the coordination between voice recognition and automation is often insufficient, preventing smooth operation.

[0520] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0521] In this invention, the server includes means for understanding a user's computer operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn the user's work patterns and design an optimal automation process, and voice recognition means for understanding the user's voice commands and executing automated operations based on the voice commands, thereby enabling the server to accurately capture the user's operation patterns and generate and execute automation programs in real time.

[0522] "Generative AI" refers to AI that has the ability to generate new information and answers based on data.

[0523] "Computer operation" includes user actions for operating a computer or related device, such as mouse clicks, keyboard input, and screen scrolling.

[0524] "Means for generating a program" refers to the device or software that analyzes the user's operations and controls the process of generating program code for automation.

[0525] A "work pattern" refers to a set of computer operations that a user performs to accomplish a specific task.

[0526] An "optimal automated process" refers to an automated procedure that is designed to analyze a user's work patterns and enable the user to perform the work efficiently.

[0527] A "machine learning model" refers to an algorithm or statistical model that learns from data and makes predictions and judgments.

[0528] "Voice command" refers to a command given by a user to give instructions to a computer or related device using voice.

[0529] "Voice recognition means" refers to technology or devices for analyzing a user's voice commands and executing appropriate instructions or operations.

[0530] "Means for recording and transmitting in real time" refers to a process in which every time a user performs a computer operation, that operation is immediately recorded and transmitted to a server.

[0531] A "procedure" is a document that details each step in accomplishing a specific task.

[0532] "Interface" refers to the means or methods by which a user interacts with a system and inputs or displays data.

[0533] This invention is a system for automating user computer operations and improving business efficiency. The system is mainly composed of terminals, a server, and users. Each component and its operation will be specifically described below.

[0534] 1. Recording user actions

[0535] The device is responsible for recording the user's computer operations in real time. This includes mouse clicks, keyboard input, and screen scrolling. When a user operates an Excel file, all specific operations such as opening and closing it, entering data, and saving are recorded. For voice commands, the device uses the Google Speech-to-Text API to convert the voice into text data.

[0536] 2. Data submission and analysis

[0537] The device sends the recorded operation data to the server, using a secure communication protocol (e.g., HTTPS) to ensure the data is transmitted safely.

[0538] The server analyzes the received data using generative artificial intelligence such as OpenAI's GPT-3 model, which allows it to understand the user's operational procedures and generate an automated program.

[0539] The generated program code is formatted as a procedure and the details are presented to the user.

[0540] 3. User confirmation and correction

[0541] The user checks the presented procedure manual through the terminal and makes corrections as necessary. Using the interface, the user inputs the specific corrections. Based on this, the server analyzes the data again and corrects the program.

[0542] 4. Optimization using machine learning models

[0543] The device continuously records the user's operation patterns and periodically sends the data to a server. The server then analyzes the data using machine learning models such as TensorFlow and Scikit-learn to learn the user's operation patterns. Based on the results of this learning, optimal automation procedures are designed and proposed to the user.

[0544] 5. Voice recognition and operation execution

[0545] The user inputs a voice command to the terminal, such as "Update and send the Excel file." The terminal uses a voice recognition means to analyze the voice command and transmits it to the server.

[0546] The server integrates the automation program based on the analysis results and sends the determined commands to the terminal, which then executes the operations according to the received commands and provides the results to the user in real time.

[0547] As a concrete example, consider a situation where you want to automate the task of entering sales data into specific cells in an Excel file every day, saving the file, and sending it by email.

[0548] For example, by inputting a prompt such as, "Generate a program that will automate the task of entering sales data into specific cells in an Excel file every day, saving the file, and sending it by email," into the generation AI, the entire series of operations above will be automated.

[0549] In this way, by using this system, users can efficiently automate computer operations and greatly improve business efficiency.

[0550] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0551] Step 1:

[0552] The user inputs a voice command to the terminal saying, "Start recording operations."

[0553] Input: Voice commands given by the user

[0554] Processing: The device uses a voice recognition method (e.g., Google Speech-to-Text API) to parse the voice command and convert it into text data. If the voice command is recognized as an instruction to start recording mode, the device enters recording mode.

[0555] Output: Recording mode is started

[0556] Step 2:

[0557] A user opens an Excel file, enters sales data into specific cells, saves the file, and performs other operations.

[0558] Input: User-operated computer operations (mouse clicks, keyboard input, screen scrolling, etc.)

[0559] Processing: The device records these operations in real time and stores detailed operations in a log.

[0560] Output: Recorded operation log

[0561] Step 3:

[0562] The terminal transmits the recorded operation data to the server.

[0563] Input: Recorded operation log

[0564] Processing: The terminal sends the operation log to the server using a secure communication protocol (e.g., HTTPS).

[0565] Output: Operation log sent to the server

[0566] Step 4:

[0567] The server analyzes the received operation data and generates an automation program using generative artificial intelligence (e.g., OpenAI's GPT-3).

[0568] Input: Operation log sent to the server

[0569] Processing: The server uses generative artificial intelligence to generate an automated program by analyzing the operation log. This program is created by imitating the user's computer operations.

[0570] Output: Generated automation program

[0571] Step 5:

[0572] The server formats the generated program code as a procedure manual and sends it to the terminal.

[0573] Input: Generated automation program

[0574] Processing: The server formats the program code into a user-friendly instruction manual that the user can later review and modify.

[0575] Output: Automation program in the form of a procedure manual

[0576] Step 6:

[0577] The terminal displays the procedure manual to the user.

[0578] Input: Automation program in the form of a procedure manual

[0579] Processing: The terminal displays the procedure manual on the screen and asks the user for confirmation. The user checks the contents and, if necessary, inputs correction instructions through the interface.

[0580] Output: User checks the procedure manual and gives instructions for correction

[0581] Step 7:

[0582] The terminal transmits the user's correction instructions to the server.

[0583] Input: User correction instructions

[0584] Processing: The terminal sends correction instructions to the server, and the server re-analyzes the data.

[0585] Output: Correction instructions sent to the server

[0586] Step 8:

[0587] The server reanalyzes the program code based on the modification instructions and generates a modified automation program.

[0588] Input: Correction instructions sent to the server

[0589] Processing: The server re-analyzes the program code based on the correction instructions and generates an optimized automation program.

[0590] Output: Modified automation program

[0591] Step 9:

[0592] The terminal receives the modified automation program from the server and prepares it for execution.

[0593] Input: Modified automation program

[0594] Processing: The device checks whether the operation is executed correctly based on the received program. Once preparation is complete, the user can start the operation by entering a voice command.

[0595] Output: An automated program ready to run

[0596] Step 10:

[0597] The user inputs a voice command into the terminal saying, "Update and send the Excel file."

[0598] Input: Voice commands given by the user

[0599] Processing: The terminal uses voice recognition means to analyze the voice command, convert it into text data, and send it to the server.

[0600] Output: Voice command sent to the server

[0601] Step 11:

[0602] The server sends instructions to the terminal to execute an automated program based on the voice command.

[0603] Input: Voice command sent to the server

[0604] Processing: The server selects the appropriate automated program based on the voice command and sends the instructions to the terminal.

[0605] Output: Instructions to run the automation program

[0606] Step 12:

[0607] Based on the instructions received, the device automatically performs a series of operations, from updating the Excel file to sending an email.

[0608] Input: Instruction to run the automation program

[0609] Processing: The device opens an Excel file, enters sales data into designated cells, saves the file, and sends it by email.

[0610] Output: automated operations and feedback of the operation results

[0611] Step 13:

[0612] The terminal provides the execution results to the user in real time.

[0613] Input: Automated operation results

[0614] Processing: The device displays detailed results to the user, including whether the operation was successful or an error occurred.

[0615] Output: Real-time feedback of the operation results

[0616] (Application example 1)

[0617] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0618] Operating robots in factories requires a high level of specialized knowledge, and it takes time and training to operate them efficiently. Furthermore, workers tend to tire and make mistakes when performing the same operations every time. Consistent operation is also required even when different workers operate the robots, but this is difficult to achieve. There is a need to solve these issues, improve work efficiency, and reduce errors.

[0619] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0620] In this invention, the server includes means for understanding user operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn user work patterns and design an optimal automation process, means for understanding user voice commands and executing automated operations based on the voice commands, means for recording operations on a terminal and sending the recording to the server, means for presenting the generated program code and instructions to the user, means for continuously learning the operation history and proposing optimal operations, and means for executing operations based on voice recognition and providing feedback on the results. This enables more efficient and consistent robot operation in factories and reduces human error.

[0621] "Generative artificial intelligence" is a technology that generates models based on data and analyzes and automates user operations.

[0622] "User operation" refers to a series of actions or commands performed to operate a machine such as an industrial robot.

[0623] An "automation program" is software code that is generated to automatically perform a user operation.

[0624] A "machine learning model" is a statistical model that learns from data and proposes optimal operating processes.

[0625] A "voice command" is a command that a user issues to a system or machine using voice.

[0626] "Voice recognition means" refers to technology for analyzing a user's voice command and performing the corresponding operation.

[0627] An "operation record" is data that stores a series of actions performed by a user and is used for later analysis and learning.

[0628] A "procedure manual" is a document that describes in detail the operating procedure and is presented to the user.

[0629] "Continuous learning" means that the machine learning model constantly learns the optimal operation process based on recorded operation data.

[0630] "Feedback" refers to communicating to the user the results of an operation that has been performed.

[0631] This invention embodies a system that improves the efficiency and automation of industrial robot operations. This system uses generative artificial intelligence, machine learning models, and voice recognition functions to automate user operations, reducing operational errors and improving efficiency.

[0632] The terminal is a device for recording the user's robot operation in real time, recording detailed actions such as mouse clicks, keyboard input, and touch operations. The recorded data is then sent to a server, which hosts a generative artificial intelligence (AI) that analyzes the user's input and generates an optimal automation program.

[0633] The generated program is presented to the user as a text-formatted instruction manual. The user checks this manual, and if any corrections are necessary, they send the correction instructions to the server again via their terminal. The server reanalyzes the program based on these correction instructions and generates an optimized program.

[0634] Furthermore, the server continuously learns user operation data and proposes optimal operation processes, thereby enabling optimized operations that always reflect the latest operation patterns.Users can also easily operate the system through voice commands, and the server uses voice recognition means to analyze these voice commands and immediately execute the corresponding operations.

[0635] For example, consider a factory worker using a robot to record the operation of placing parts on an assembly line. The user gives a voice command to the terminal to record the operation, then starts operating the robot. Once the operation recording is complete, the terminal sends the data to a server, which then uses generative artificial intelligence to generate an automation program.

[0636] As an example of a prompt sentence, consider the voice command "Place new parts on the assembly line." The server analyzes this voice command and automatically controls the robot to execute the specified operation. As a result, the series of tasks from placing parts to moving on to the next step is automated.

[0637] The hardware required is a device (e.g., a tablet or PC) for user operation, a server for saving and transmitting operation records, and a microphone for inputting voice commands.The software required is a voice recognition library (e.g., speech_recognition), a machine learning model (e.g., a homemade AI model), and a server communication library.

[0638] This will enable more efficient and consistent robot operation in factories, and reduce human error.

[0639] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0640] Step 1:

[0641] The user inputs a voice command into the terminal to start operation recording. Specifically, the voice command "Start operation recording" is issued through the microphone. The input data is voice, and the terminal converts this voice command into text using voice recognition software. The output is the start of operation recording mode.

[0642] Step 2:

[0643] The device records a series of user operations in detail. Operation data (mouse clicks, keyboard input, touch operations, etc.) is saved in a log in real time. The input data is the user's operation, and the device compiles this as an operation record. The output is the operation record data.

[0644] Step 3:

[0645] The terminal sends the recorded operation data to the server. The server receives this data. The input data is the operation record data, which the server stores in the database. The output is the operation record stored in the database.

[0646] Step 4:

[0647] The server analyzes the received operation data and generates an optimal automation program using generative artificial intelligence. The input data is the operation record data, which the server analyzes and executes an algorithm to generate the automation program. The output is the generated automation program code.

[0648] Step 5:

[0649] The server sends the generated program code to the terminal as a procedure manual and presents it to the user. The input data is the automation program code, which the server formats in procedure manual format. The output is a procedure manual that the user can check.

[0650] Step 6:

[0651] The user checks the procedure manual and, if any corrections are necessary, sends the correction instructions to the server via the terminal. The input data is the correction instructions, which the terminal sends to the server. The output is the transmission of the correction instructions.

[0652] Step 7:

[0653] The server receives the modification instructions and reanalyzes and modifies the automation program. The input data are the modification instructions, which the server uses for further analysis. The output is the modified automation program code.

[0654] Step 8:

[0655] The server continuously learns from the user's operation data and proposes the optimal operation process. The input data is the newly recorded operation data, and the server updates the machine learning model. The output is the proposed optimized operation process.

[0656] Step 9:

[0657] The user then executes the generated program by again inputting voice commands into the terminal. Specifically, the user inputs a specific prompt through the microphone, such as "Place the new part on the assembly line." The input data is voice, which the terminal converts into text using voice recognition software and sends to the server. The output is the automated operation to be executed.

[0658] Step 10:

[0659] The server analyzes the voice commands and executes the corresponding automated program. The input data is the text of the voice commands, which the server matches with the automated program and executes. The output is the result of the automated operation.

[0660] Step 11:

[0661] The execution results are fed back to the user through the terminal. The input data is the execution results, which the server sends to the terminal. The output is feedback information that the user can check.

[0662] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0663] This invention is a system that automates a user's computer operations using generative artificial intelligence, a machine learning model, a speech recognition means, and an emotion engine. This system not only records and analyzes the user's operations and generates an automation program, but also recognizes the user's emotional state and adjusts operating procedures and processes based on that. Specific embodiments for implementing this system are described below.

[0664] Overall system configuration

[0665] The system mainly consists of a terminal, a server, and a user. The terminal is a device operated by the user, and performs tasks such as recording computer operations, performing voice recognition, recognizing emotions using an emotion engine, and running automation programs. The server mainly hosts generative artificial intelligence and machine learning models, analyzes the user's computer operations, and generates automation programs. The user is the entity that interacts with the system via an interface and performs computer operations.

[0666] Program processing

[0667] The specific processing flow of the program and the operation at each step will be explained below.

[0668] 1. Recording user actions

[0669] The terminal records the user's computer operations in real time, including mouse clicks, keyboard input, and screen scrolling.

[0670] 2. Data submission and analysis

[0671] The device sends the recorded operation data to a server, which then inputs the received data into a generative artificial intelligence (AI) system, analyzes it, and generates an automation program. The generated program code is then formatted and presented to the user as a procedure manual.

[0672] 3. User confirmation and correction

[0673] The user checks the procedure manual provided through the terminal. If necessary, the user can modify the operation procedure or program code and send the modification instructions to the server. The server then reanalyzes the program based on the modification instructions and generates new program code.

[0674] 4. Optimization using machine learning models

[0675] The device continuously records the user's operation patterns and sends them to the server. The server uses the data to update the machine learning model and learns the user's operation patterns. Based on the learning results, an optimal automated process is designed and proposed to the user. The user can then approve or modify the proposal.

[0676] 5. Emotion Recognition by Emotion Engine

[0677] The device uses an emotion engine to recognize the user's emotional state in real time, which is analyzed based on data collected through sensors such as cameras and microphones.

[0678] 6. Emotion-based process adjustment

[0679] The server receives the emotional data analyzed by the emotion engine and adjusts the automation process based on the user's emotional state. For example, if the system detects that the user is fatigued, it will simplify the operation procedure or suggest that the user take a break.

[0680] 7. Voice recognition and operation execution

[0681] The user inputs voice commands to the terminal to perform specific operations. The server analyzes the voice commands using a voice recognition means and integrates the corresponding operations into an automation program. The terminal executes the integrated program and automates the user's computer operations.

[0682] 8. Operation Feedback

[0683] The device provides real-time feedback to the user on the results of the operations performed, and if necessary, instructions are given for correction, which are then used to make further improvements.

[0684] Specific examples

[0685] For example, consider the operation of a system that automates the daily tasks of updating Excel files and sending them by email.

[0686] Recording operations

[0687] The user first commands the device to "start recording operations." The device then enters recording mode and records all operations performed by the user. The series of operations performed by the user, including opening an Excel file, entering data, saving the file, and sending it by email, are recorded.

[0688] Data analysis and program generation

[0689] The device sends the recorded data to a server, which uses generative artificial intelligence to analyze the operations and generate an automation program based on the Excel operating procedures. The generated program is presented to the user as a textual instruction manual.

[0690] User confirmation and correction

[0691] The user checks the procedure manual and issues correction instructions as necessary. The terminal sends the correction instructions to the server, which reanalyzes the program and generates new program code.

[0692] Emotion recognition and operational adjustment

[0693] The device uses an emotion engine to recognize the user's emotions from their facial expressions and voice. For example, if the user is feeling stressed, the server will adjust the device to simplify the operation procedure.

[0694] Speech recognition and automatic execution

[0695] The user issues a voice command such as "Update and send the Excel file." The device analyzes the command using voice recognition and executes the specified operation. The results of the operation are fed back to the user in real time.

[0696] In this way, this system allows users to automate computer operations efficiently and respond flexibly to their emotional state, resulting in a significant improvement in the user's work efficiency and a more comfortable working environment.

[0697] The processing flow will be explained below.

[0698] Step 1:

[0699] The user commands the terminal by voice, "Start recording my operations." The terminal switches to recording mode and prepares for computer operations.

[0700] Step 2:

[0701] The terminal captures the user's computer operations in real time and temporarily stores data such as mouse clicks, keyboard input, and window operations.

[0702] Step 3:

[0703] When the user completes the operation, the terminal stops recording and sends the captured data to the server.

[0704] Step 4:

[0705] The server inputs the received operation data into the generative AI, analyzes it, and generates an automation program. The server then formats the generated program code and presents it to the user as a procedure manual.

[0706] Step 5:

[0707] The user checks the procedure manual through the terminal and issues instructions to correct the operation procedures or program code as necessary. The correction instructions are sent from the terminal to the server.

[0708] Step 6:

[0709] The server re-analyzes the program based on the correction instructions, generates new program code, and presents the corrected procedure manual or program code to the user again.

[0710] Step 7:

[0711] The device continuously records the user's operation patterns and sends them to the server, which then updates the machine learning model and learns the user's operation patterns.

[0712] Step 8:

[0713] The machine learning model designs the optimal automated process, which the server presents to the user, who can then approve or modify the proposal via their device.

[0714] Step 9:

[0715] The device uses an emotion engine to recognize the user's emotional state in real time and collect emotion data.

[0716] Step 10:

[0717] The server receives the emotional data analyzed by the emotion engine and adjusts the automated process based on the user's emotional state, for example, simplifying the operation procedure if the user is tired.

[0718] Step 11:

[0719] The user issues a voice command to the terminal to perform a specific operation, and the terminal uses a voice recognition means to analyze the voice command and determine the corresponding operation.

[0720] Step 12:

[0721] The server integrates operations corresponding to the voice commands into an automated program, and the terminal executes the automated program to automate the user's computer operations.

[0722] Step 13:

[0723] The device provides real-time feedback to the user on the results of the operation, and if necessary, instructions for correction are issued again, and further improvements are made based on those instructions.

[0724] Example 2

[0725] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0726] In conventional systems, it is difficult to automate user computer operations, and each individual operation procedure must be set manually, resulting in reduced work efficiency. Furthermore, because dynamic adjustments based on the user's work patterns and emotional state are not made, users are prone to accumulate stress and fatigue, leading to frequent operational errors. The present invention aims to solve these problems.

[0727] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0728] In this invention, the server includes means for understanding a user's computer operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn the user's work patterns and design an optimal automation process, voice recognition means for understanding the user's voice commands and executing automated operations based on the voice commands, means for recognizing the user's emotional state in real time and adjusting the automation process based on the emotional state, and means for recording the user's computer operations and presenting the user with program code and instructions generated based on the recorded operation data. This makes it possible to automate the user's operations efficiently and flexibly and adjust the process optimally according to the user's emotional state.

[0729] "Generative AI" is AI that understands a user's computer operations and generates a program to automate those operations.

[0730] A "machine learning model" is a learning algorithm that learns user work patterns and designs optimal automation processes.

[0731] "Voice recognition means" refers to technology for understanding a user's voice commands and performing automated operations based on the voice commands.

[0732] An "emotion engine" is a system that recognizes a user's emotional state in real time and adjusts automated processes based on this.

[0733] "Camera and Microphone" are video and audio sensors used to collect the user's emotional state.

[0734] "Computer operation" refers to all operations that a user performs using a computer.

[0735] "Operation data" is data that records the user's computer operations.

[0736] "Program code" means source code generated for automation by generative artificial intelligence.

[0737] A "procedure manual" is a document of operating procedures that is presented to the user based on the generated program code.

[0738] The "modification interface" is a user interface that allows a user to make modifications to the generated program code and procedure manual.

[0739] MODE FOR CARRYING OUT THE INVENTION

[0740] This invention is a system that automates user computer operations using generative artificial intelligence, machine learning models, speech recognition means, and an emotion engine. This system not only records and analyzes user operations and generates automation programs, but also recognizes the user's emotional state and adjusts operating procedures and processes based on that.

[0741] The system mainly consists of a server, a terminal, and a user. The terminal is a device operated by the user, and performs tasks such as recording computer operations, performing voice recognition, recognizing emotions using an emotion engine, and running automation programs. The server mainly hosts generative artificial intelligence and machine learning models, analyzes the user's computer operations, and generates automation programs. The user is the entity that interacts with the system via an interface and performs computer operations.

[0742] Specifically, the device records the user's actions and sends the data to a server. The server then analyzes the actions using a generative AI model (such as ChatGPT) and generates the necessary programs. The device can also monitor the user's emotional state in real time and send that information to the server. The server then analyzes the emotional state using an emotion engine (such as the Affectiva SDK) and adjusts the automation process as needed.

[0743] Specific examples

[0744] For example, consider the case where the user wants to automate the daily task of updating an Excel file and sending it by email. First, the user commands the device to "start recording operations." At this time, the device enters recording mode and records all operations performed by the user. Operations such as the user opening the Excel file, entering data, saving the file, and sending it by email are recorded.

[0745] The recorded data is sent from the device to a server, which then uses a generative AI model to analyze the operation and generate an automation program. The generated program is presented to the user as a procedure manual, which the user can review and provide correction instructions as needed.

[0746] The device then uses an emotion engine to monitor the user's emotional state. For example, if the device detects that the user is feeling stressed, the server can make adjustments, such as simplifying the operation procedure.

[0747] Finally, the user can issue a voice command such as "Update and send the Excel file." The device will interpret the command using a voice recognition method (e.g., Google Cloud Speech-to-Text API) and execute the automated operation, providing real-time feedback to the user.

[0748] Prompt Sentence Examples

[0749] Here are some examples of prompts to input to a generative AI model:

[0750] "Create a program to automatically update Excel data and send emails daily. Follow these steps:

[0751] 1. Open the Excel file

[0752] 2. Enter your data

[0753] 3. Save the file

[0754] 4. Send the saved file by email.

[0755] By using this system, users can efficiently automate computer operations and optimally adjust processes according to their emotional state, significantly improving their work efficiency and providing a more comfortable working environment.

[0756] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0757] Step 1:

[0758] Recording user actions

[0759] When the user starts operating the computer, the terminal enters the recording mode by issuing a command to "start recording the operation."

[0760] Input: User actions such as mouse clicks, keyboard input, and screen scrolling.

[0761] Data processing: Record the entered operations in a log file.

[0762] Output: Recorded operation data.

[0763] Specific actions: Everything a user does, from opening Excel, entering data, saving, and emailing, is recorded.

[0764] Step 2:

[0765] Data transmission and analysis

[0766] The terminal transmits the recorded operation data to the server periodically or after the operation is completed.

[0767] Input: Recorded operation data.

[0768] Data processing: Input the operational data into a generative AI model (e.g., ChatGPT) and perform analysis.

[0769] Output: Program code for the automation process.

[0770] Specific operation: After the data is sent to the server, the generative AI model analyzes the operation procedures and creates an automation program based on the Excel operation procedures.

[0771] Step 3:

[0772] User confirmation and correction

[0773] The user checks the procedure manual presented via the terminal.

[0774] Input: Presented instructions and generated program code.

[0775] Data processing: The user makes corrections and sends the correction instructions to the server via their device. The server reuses the generative AI model and regenerates the program code.

[0776] Output: Updated program code and instructions.

[0777] Specific operation: When the user instructs "This step is unnecessary, so please delete it," the server generates a new procedure manual and program based on the instruction.

[0778] Step 4:

[0779] Optimization with machine learning models

[0780] The terminal continuously records the user's operation patterns and transmits them to the server.

[0781] Input: Continuously recorded operational data.

[0782] Data processing: Using machine learning models (e.g., TensorFlow) to learn operational patterns.

[0783] Output: A recommendation of the best automation process for the user.

[0784] What it does: It collects data over a long period of time and then the server suggests to the user, "We've optimized it so that you can perform all operations with just one click."

[0785] Step 5:

[0786] Emotion recognition by emotion engine

[0787] The device uses an emotion engine (e.g., Affectiva SDK) to recognize the user's emotional state in real time.

[0788] Input: User facial and voice data collected through camera and microphone.

[0789] Data processing: The emotion engine analyzes facial expressions and voice to determine the emotional state.

[0790] Output: The user's real-time emotional state.

[0791] Specific operation: If the user shows signs of fatigue during operation, the emotion engine will recognize the state as "fatigue."

[0792] Step 6:

[0793] Emotion-based process adjustment

[0794] The server adjusts the automation process based on the emotion data received from the emotion engine.

[0795] Input: Emotional state data from the emotion engine.

[0796] Data processing: Adjusting automated processes, simplifying steps or suggesting breaks where necessary.

[0797] Output: A coordinated automated process.

[0798] Specific operation: The server suggests, "Would you like to take a break?" and presents instructions to simplify the operation procedure.

[0799] Step 7:

[0800] Voice recognition and operation execution

[0801] The user issues a voice command, which the terminal recognizes.

[0802] Input: Voice command.

[0803] Data processing: The voice is analyzed using a speech recognition tool (e.g., Google Cloud Speech-to-Text API) and sent to a server, which then integrates the instructions into an automated program and returns instructions for execution.

[0804] Output: Execution of automated operations based on voice commands.

[0805] Specific operation: When a user commands, "Update and send the Excel file," the device analyzes the voice and generates an execution command on the server, after which the Excel file is automatically updated and an email is sent.

[0806] Step 8:

[0807] Operation feedback

[0808] The terminal provides the user with real-time feedback on the results of the operation.

[0809] Input: The result of running an automated program.

[0810] Data processing: Analyze the execution results and provide feedback to the user.

[0811] Output: Feedback information.

[0812] Specific operation: When the user commands, "Check if the operation was successful," the device displays the execution results and gives feedback that "All operations were successful."

[0813] (Application example 2)

[0814] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0815] In modern self-driving vehicles, automation of driver operations and voice commands, and environmental adjustments based on real-time emotion recognition have not yet been fully realized. Therefore, reducing the burden on the driver and improving safety are issues. In addition, the generation of automated programs based on the analysis of operation data and the interface for modifying them are not yet fully developed, so an efficient automated system is required.

[0816] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0817] In this invention, the server includes means for understanding user operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn the user's work patterns and design an optimal automation process, voice recognition means for understanding the user's voice commands and executing automated operations based on the voice commands, means for recording, analyzing, and automating the driver's operations and voice commands, and means for recognizing the driver's emotional state in real time and adjusting the in-vehicle environment and navigation based on that state. This makes it possible to efficiently automate the driver's operations and further adjust the in-vehicle environment and navigation based on the driver's emotional state.

[0818] "Generative AI" is an AI technology that understands user operations and generates programs to automate those operations.

[0819] A "machine learning model" is an algorithm or method for learning user work patterns and designing optimal automation processes.

[0820] "Voice recognition means" refers to technology for understanding a user's voice commands and performing automated operations based on the voice commands.

[0821] The "operation recording means" is a function for recording user operations and voice commands, analyzing them, and automating them.

[0822] "Emotion recognition means" is a technology that recognizes the driver's emotional state in real time and adjusts the in-car environment and navigation based on that state.

[0823] An "autonomous vehicle" is a vehicle that drives autonomously without the need for manual operation by a driver.

[0824] The "user interface" refers to a screen or input means that allows the user to modify the generated program code and procedure manual.

[0825] This invention relates to a system that records, analyzes, and automates driver operations and voice commands of an autonomous vehicle. This system has a function of supporting comfortable driving by the driver using generative artificial intelligence, machine learning models, voice recognition means, and emotion recognition means. Detailed embodiments of the system are described below.

[0826] Overall system configuration

[0827] The system mainly consists of an in-vehicle device, a server, and a driver. The in-vehicle device records the driver's operations and voice commands and collects data for emotion recognition. The server hosts generative artificial intelligence and machine learning models, analyzes operation data, and generates automated programs. The driver interacts with the system via an interface and is the entity that performs driving operations.

[0828] System Program

[0829] Operation recording means

[0830] The in-vehicle device records the driver's actions and voice commands in real time, including steering, pedal operation, touchscreen operation, etc. It also uses cameras and sensors to collect the driver's facial expressions and voice.

[0831] Data transmission and analysis

[0832] The vehicle-mounted device sends the recorded operation data to a server, which then inputs the received data into a generative artificial intelligence system, analyzes it, and generates an automation program. This uses machine learning libraries such as TensorFlow and PyTorch.

[0833] Automated Program Generation and Emotion Recognition

[0834] The server generates the optimal automation program based on the operation data. It also uses technologies such as OpenCV to analyze data acquired from cameras and microphones and recognize the driver's emotional state. Based on this emotional state, the automation program and navigation are adjusted.

[0835] Voice recognition and operation execution

[0836] The driver can input voice commands into the vehicle's in-vehicle device, and the server will interpret the voice commands through speech recognition means and perform the corresponding operations, using the Google Speech-to-Text API.

[0837] feedback

[0838] The in-vehicle device provides real-time feedback to the driver on the results of the maneuver, allowing the driver to issue additional voice commands or corrective actions if necessary.

[0839] Specific examples

[0840] For example, if a driver issues the voice command "Go home," the system will:

[0841] 1. Voice command recognition:

[0842] Driver: "Going home."

[0843] In-vehicle device: Google Speech-to-Text converts voice commands into text

[0844] 2. Navigation adjustment:

[0845] Server: Analyzes the text data and generates a route to home

[0846] Emotional state analysis: if the driver is tired, add optimal rest stops to the route

[0847] 3. Feedback:

[0848] In-vehicle device: Provides voice feedback to the driver on route guidance

[0849] Example prompt sentence:

[0850] User: I want to go home

[0851] System: Searching for a route to your home. Please wait.

[0852] System (feedback): Your route is planned. It looks like you might need a break along the way, so we've added appropriate stops. Please resume driving.

[0853] In this way, the system effectively automates driver operations and also adjusts the in-car environment and navigation according to the driver's emotional state, providing a more comfortable and safer driving experience.

[0854] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0855] Step 1:

[0856] Recording of operation and emotional data

[0857] Subject: Terminal

[0858] The terminal (vehicle-mounted device) records the driver's operations and voice commands in real time. The terminal also uses cameras and sensors to collect the driver's facial expressions and voice. Input data includes steering wheel operations, pedal operations, touchscreen operations, facial expressions, and voice. This data is temporarily stored locally and prepared for real-time analysis as needed.

[0859] Step 2:

[0860] Data transmission and analysis

[0861] Subject: Terminal

[0862] The device sends the recorded operation data and emotion data to the server. The input data includes the operation log and emotion data collected in step 1. The server analyzes the received data and generates an automation program using generative artificial intelligence (e.g., TensorFlow, PyTorch). Data analysis includes splitting time-series data and feature extraction. The output after analysis is the initial script for the automation program.

[0863] Step 3:

[0864] Generating automation programs

[0865] Subject: Server

[0866] The server uses generative artificial intelligence to generate an automation program based on the analytical data. The analytical data obtained in step 2 is used as input. The generative AI model generates program code, creating operating procedures and scripts during the generation process. The output is program code containing automated operating procedures.

[0867] Step 4:

[0868] Emotion recognition and process regulation

[0869] Subject: Server

[0870] The server uses emotion recognition means (e.g., OpenCV) to recognize the driver's emotional state from the collected facial and voice data. The emotional data collected in steps 1 and 2 is used as input. Based on the results of the emotional state analysis, the automation program and navigation plan are adjusted. The output is an automated program adjusted according to the emotional state.

[0871] Step 5:

[0872] Entering and recognizing voice commands

[0873] Subject: User

[0874] The user (driver) inputs voice commands to the vehicle's onboard device. The input data is the voice command. The server uses a voice recognition method (e.g., Google Speech-to-Text) to convert the voice command into text data. The text data is then analyzed and integrated into the automation program. The output is an operation instruction based on the analyzed voice command.

[0875] Step 6:

[0876] Running an automation program

[0877] Subject: Terminal

[0878] The device executes the automation program received from the server. The input data includes the adjusted automation program and the analysis results of the voice commands. The device automatically executes the operation procedures, performing navigation, adjusting the in-car environment, etc. The output is the execution result of the automated operation.

[0879] Step 7:

[0880] Providing Feedback

[0881] Subject: Terminal

[0882] The terminal provides real-time feedback on the results of the operation to the user. The input data are the execution results and, if necessary, additional instructions from the user. The terminal analyzes this data and determines the next operation steps or necessary adjustments. The output is a report of the operation results to the user and a suggestion for the next operation step.

[0883] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0884] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0885] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0886] [Third embodiment]

[0887] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0888] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0889] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[0890] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0891] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0892] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0893] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0894] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0895] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0896] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0897] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0898] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0899] This invention is a system that automates a user's computer operations using generative artificial intelligence, machine learning models, and speech recognition means. The system records the user's operations, generates an automation program based on the records, and learns the user's work patterns to propose and execute an optimal process. Specific embodiments for implementing this system are described below.

[0900] Overall system configuration

[0901] The system mainly consists of a terminal, a server, and a user. The terminal is a device operated by the user, and performs functions such as recording computer operations, performing voice recognition, and running automation programs. The server mainly hosts generative artificial intelligence and machine learning models, analyzes the user's computer operations, and generates automation programs. The user is the entity that performs the computer operations and interacts with the system through an interface.

[0902] Program processing

[0903] 1. Recording user actions

[0904] The terminal records the user's computer operations in real time, including mouse clicks, keyboard input, screen scrolling, etc. The terminal records these operations in detail and sends them to the server.

[0905] 2. Data submission and analysis

[0906] The device sends the recorded operation data to a server, which uses generative artificial intelligence to analyze the operation and create an automation program based on the received data. The generated program code is then formatted and presented to the user as a procedure manual.

[0907] 3. User confirmation and correction

[0908] The user checks the instructions provided through the terminal. If necessary, the user can modify the operating procedures and program code. The modified instructions are then sent back to the server, where further analysis and program modification are performed.

[0909] 4. Optimization using machine learning models

[0910] The device continuously records the user's operation patterns and sends them to the server. The transmitted data is analyzed by a machine learning model to learn the user's operation patterns. Based on the learning results, an optimal automated process is designed and proposed to the user. The user can then approve or modify the proposal.

[0911] 5. Voice recognition and operation execution

[0912] The user inputs voice commands into the terminal. The server analyzes the voice commands using a voice recognition means and integrates the corresponding operations into an automated program. The terminal executes the integrated program and automates the user's computer operations. The execution results are fed back to the user in real time.

[0913] Specific examples

[0914] For example, consider the operation of a system that automates the daily tasks of updating Excel files and sending them by email.

[0915] Recording operations

[0916] First, the user commands the device to "start recording operations" by voice. The device enters recording mode and records all operations performed by the user. The series of operations performed by the user, such as opening an Excel file, entering data, saving the file, and sending it by email, are recorded.

[0917] Data analysis and program generation

[0918] The device sends the recorded data to a server, which uses generative artificial intelligence to analyze the operations and generate an automation program based on the Excel operating procedures. The generated program is presented to the user as a textual instruction manual.

[0919] User confirmation and correction

[0920] The user checks the procedure manual and issues correction instructions as necessary. The correction instructions are sent via the terminal to the server, where the data is reanalyzed and corrected.

[0921] Machine learning optimization

[0922] The device continuously records the operation patterns of Excel files and the server learns from them. Based on the learning results, the server proposes the optimal operation procedure and presents it to the user.

[0923] Speech recognition and automatic execution

[0924] The user issues a voice command such as "Update and send the Excel file." The device analyzes the voice command using a voice recognition system and executes the instructed operation. The entire process, from updating the Excel file to sending the email, is carried out automatically, and the results are fed back to the user.

[0925] In this way, by using this system, users can efficiently automate computer operations, resulting in a significant improvement in work efficiency.

[0926] The processing flow will be explained below.

[0927] Step 1:

[0928] The user commands the device to "start recording operations" by voice. The device switches to recording mode and gets ready.

[0929] Step 2:

[0930] The device captures all of the user's computer operations (mouse clicks, keyboard input, window movement and scrolling, etc.) in real time and temporarily stores them in storage.

[0931] Step 3:

[0932] When the user completes the operation, the terminal stops recording and sends the captured data to the server.

[0933] Step 4:

[0934] The server inputs the received operation data into the multimodal AI, which analyzes the operation data and generates the corresponding program code.

[0935] Step 5:

[0936] The server then formats the generated code and presents it to the user as a procedure manual, who can then review the manual and provide corrections if necessary.

[0937] Step 6:

[0938] If there are any correction instructions, the terminal sends them to the server, which then reanalyzes the program based on the instructions and generates new program code.

[0939] Step 7:

[0940] The device continuously records the user's operation patterns and periodically sends them to the server, which then updates the machine learning model based on the data sent and learns the user's operation patterns.

[0941] Step 8:

[0942] The machine learning model then proposes the optimal automation process based on the results of its learning, which the server then presents to the user, who can then approve or modify it.

[0943] Step 9:

[0944] The user issues a voice command to the device to perform a specific operation, and the device uses voice recognition AI to analyze the voice command and determine the corresponding operation.

[0945] Step 10:

[0946] The server then integrates the voice command into an automated program based on the analysis results, and the terminal executes the automated program to perform the specified operation.

[0947] Step 11:

[0948] The device provides real-time feedback to the user on the results of the operation, and if necessary, instructions for correction are issued, and further improvements are made based on those instructions.

[0949] Example 1

[0950] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0951] Many of the computer operations that users perform on a daily basis are repetitive and therefore time-consuming and labor-intensive. Furthermore, while these operations should be automated efficiently, conventional automation technologies have been unable to fully understand users' operation patterns, making it difficult to generate appropriate automation programs. Furthermore, when users use voice commands to perform operations, the coordination between voice recognition and automation is often insufficient, preventing smooth operation.

[0952] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0953] In this invention, the server includes means for understanding a user's computer operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn the user's work patterns and design an optimal automation process, and voice recognition means for understanding the user's voice commands and executing automated operations based on the voice commands, thereby enabling the server to accurately capture the user's operation patterns and generate and execute automation programs in real time.

[0954] "Generative AI" refers to AI that has the ability to generate new information and answers based on data.

[0955] "Computer operation" includes user actions for operating a computer or related device, such as mouse clicks, keyboard input, and screen scrolling.

[0956] "Means for generating a program" refers to the device or software that analyzes the user's operations and controls the process of generating program code for automation.

[0957] A "work pattern" refers to a set of computer operations that a user performs to accomplish a specific task.

[0958] An "optimal automated process" refers to an automated procedure that is designed to analyze a user's work patterns and enable the user to perform the work efficiently.

[0959] A "machine learning model" refers to an algorithm or statistical model that learns from data and makes predictions and judgments.

[0960] "Voice command" refers to a command given by a user to give instructions to a computer or related device using voice.

[0961] "Voice recognition means" refers to technology or devices for analyzing a user's voice commands and executing appropriate instructions or operations.

[0962] "Means for recording and transmitting in real time" refers to a process in which every time a user performs a computer operation, that operation is immediately recorded and transmitted to a server.

[0963] A "procedure" is a document that details each step in accomplishing a specific task.

[0964] "Interface" refers to the means or methods by which a user interacts with a system and inputs or displays data.

[0965] This invention is a system for automating user computer operations and improving business efficiency. The system is mainly composed of terminals, a server, and users. Each component and its operation will be specifically described below.

[0966] 1. Recording user actions

[0967] The device is responsible for recording the user's computer operations in real time. This includes mouse clicks, keyboard input, and screen scrolling. When a user operates an Excel file, all specific operations such as opening and closing it, entering data, and saving are recorded. For voice commands, the device uses the Google Speech-to-Text API to convert the voice into text data.

[0968] 2. Data submission and analysis

[0969] The device sends the recorded operation data to the server, using a secure communication protocol (e.g., HTTPS) to ensure the data is transmitted safely.

[0970] The server analyzes the received data using generative artificial intelligence such as OpenAI's GPT-3 model, which allows it to understand the user's operational procedures and generate an automated program.

[0971] The generated program code is formatted as a procedure and the details are presented to the user.

[0972] 3. User confirmation and correction

[0973] The user checks the presented procedure manual through the terminal and makes corrections as necessary. Using the interface, the user inputs the specific corrections. Based on this, the server analyzes the data again and corrects the program.

[0974] 4. Optimization using machine learning models

[0975] The device continuously records the user's operation patterns and periodically sends the data to a server. The server then analyzes the data using machine learning models such as TensorFlow and Scikit-learn to learn the user's operation patterns. Based on the results of this learning, optimal automation procedures are designed and proposed to the user.

[0976] 5. Voice recognition and operation execution

[0977] The user inputs a voice command to the terminal, such as "Update and send the Excel file." The terminal uses a voice recognition means to analyze the voice command and transmits it to the server.

[0978] The server integrates the automation program based on the analysis results and sends the determined commands to the terminal, which then executes the operations according to the received commands and provides the results to the user in real time.

[0979] As a concrete example, consider a situation where you want to automate the task of entering sales data into specific cells in an Excel file every day, saving the file, and sending it by email.

[0980] For example, by inputting a prompt such as, "Generate a program that will automate the task of entering sales data into specific cells in an Excel file every day, saving the file, and sending it by email," into the generation AI, the entire series of operations above will be automated.

[0981] In this way, by using this system, users can efficiently automate computer operations and greatly improve business efficiency.

[0982] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0983] Step 1:

[0984] The user inputs a voice command to the terminal saying, "Start recording operations."

[0985] Input: Voice commands given by the user

[0986] Processing: The device uses a voice recognition method (e.g., Google Speech-to-Text API) to parse the voice command and convert it into text data. If the voice command is recognized as an instruction to start recording mode, the device enters recording mode.

[0987] Output: Recording mode is started

[0988] Step 2:

[0989] A user opens an Excel file, enters sales data into specific cells, saves the file, and performs other operations.

[0990] Input: User-operated computer operations (mouse clicks, keyboard input, screen scrolling, etc.)

[0991] Processing: The device records these operations in real time and stores detailed operations in a log.

[0992] Output: Recorded operation log

[0993] Step 3:

[0994] The terminal transmits the recorded operation data to the server.

[0995] Input: Recorded operation log

[0996] Processing: The terminal sends the operation log to the server using a secure communication protocol (e.g., HTTPS).

[0997] Output: Operation log sent to the server

[0998] Step 4:

[0999] The server analyzes the received operation data and generates an automation program using generative artificial intelligence (e.g., OpenAI's GPT-3).

[1000] Input: Operation log sent to the server

[1001] Processing: The server uses generative artificial intelligence to generate an automated program by analyzing the operation log. This program is created by imitating the user's computer operations.

[1002] Output: Generated automation program

[1003] Step 5:

[1004] The server formats the generated program code as a procedure manual and sends it to the terminal.

[1005] Input: Generated automation program

[1006] Processing: The server formats the program code into a user-friendly instruction manual that the user can later review and modify.

[1007] Output: Automation program in the form of a procedure manual

[1008] Step 6:

[1009] The terminal displays the procedure manual to the user.

[1010] Input: Automation program in the form of a procedure manual

[1011] Processing: The terminal displays the procedure manual on the screen and asks the user for confirmation. The user checks the contents and, if necessary, inputs correction instructions through the interface.

[1012] Output: User checks the procedure manual and gives instructions for correction

[1013] Step 7:

[1014] The terminal transmits the user's correction instructions to the server.

[1015] Input: User correction instructions

[1016] Processing: The terminal sends correction instructions to the server, and the server re-analyzes the data.

[1017] Output: Correction instructions sent to the server

[1018] Step 8:

[1019] The server reanalyzes the program code based on the modification instructions and generates a modified automation program.

[1020] Input: Correction instructions sent to the server

[1021] Processing: The server re-analyzes the program code based on the correction instructions and generates an optimized automation program.

[1022] Output: Modified automation program

[1023] Step 9:

[1024] The terminal receives the modified automation program from the server and prepares it for execution.

[1025] Input: Modified automation program

[1026] Processing: The device checks whether the operation is executed correctly based on the received program. Once preparation is complete, the user can start the operation by entering a voice command.

[1027] Output: An automated program ready to run

[1028] Step 10:

[1029] The user inputs a voice command into the terminal saying, "Update and send the Excel file."

[1030] Input: Voice commands given by the user

[1031] Processing: The terminal uses voice recognition means to analyze the voice command, convert it into text data, and send it to the server.

[1032] Output: Voice command sent to the server

[1033] Step 11:

[1034] The server sends instructions to the terminal to execute an automated program based on the voice command.

[1035] Input: Voice command sent to the server

[1036] Processing: The server selects the appropriate automated program based on the voice command and sends the instructions to the terminal.

[1037] Output: Instructions to run the automation program

[1038] Step 12:

[1039] Based on the instructions received, the device automatically performs a series of operations, from updating the Excel file to sending an email.

[1040] Input: Instruction to run the automation program

[1041] Processing: The device opens an Excel file, enters sales data into designated cells, saves the file, and sends it by email.

[1042] Output: automated operations and feedback of the operation results

[1043] Step 13:

[1044] The terminal provides the execution results to the user in real time.

[1045] Input: Automated operation results

[1046] Processing: The device displays detailed results to the user, including whether the operation was successful or an error occurred.

[1047] Output: Real-time feedback of the operation results

[1048] (Application example 1)

[1049] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1050] Operating robots in factories requires a high level of specialized knowledge, and it takes time and training to operate them efficiently. Furthermore, workers tend to tire and make mistakes when performing the same operations every time. Consistent operation is also required even when different workers operate the robots, but this is difficult to achieve. There is a need to solve these issues, improve work efficiency, and reduce errors.

[1051] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1052] In this invention, the server includes means for understanding user operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn user work patterns and design an optimal automation process, means for understanding user voice commands and executing automated operations based on the voice commands, means for recording operations on a terminal and sending the recording to the server, means for presenting the generated program code and instructions to the user, means for continuously learning the operation history and proposing optimal operations, and means for executing operations based on voice recognition and providing feedback on the results. This enables more efficient and consistent robot operation in factories and reduces human error.

[1053] "Generative artificial intelligence" is a technology that generates models based on data and analyzes and automates user operations.

[1054] "User operation" refers to a series of actions or commands performed to operate a machine such as an industrial robot.

[1055] An "automation program" is software code that is generated to automatically perform a user operation.

[1056] A "machine learning model" is a statistical model that learns from data and proposes optimal operating processes.

[1057] A "voice command" is a command that a user issues to a system or machine using voice.

[1058] "Voice recognition means" refers to technology for analyzing a user's voice command and performing the corresponding operation.

[1059] An "operation record" is data that stores a series of actions performed by a user and is used for later analysis and learning.

[1060] A "procedure manual" is a document that describes in detail the operating procedure and is presented to the user.

[1061] "Continuous learning" means that the machine learning model constantly learns the optimal operation process based on recorded operation data.

[1062] "Feedback" refers to communicating to the user the results of an operation that has been performed.

[1063] This invention embodies a system that improves the efficiency and automation of industrial robot operations. This system uses generative artificial intelligence, machine learning models, and voice recognition functions to automate user operations, reducing operational errors and improving efficiency.

[1064] The terminal is a device for recording the user's robot operation in real time, recording detailed actions such as mouse clicks, keyboard input, and touch operations. The recorded data is then sent to a server, which hosts a generative artificial intelligence (AI) that analyzes the user's input and generates an optimal automation program.

[1065] The generated program is presented to the user as a text-formatted instruction manual. The user checks this manual, and if any corrections are necessary, they send the correction instructions to the server again via their terminal. The server reanalyzes the program based on these correction instructions and generates an optimized program.

[1066] Furthermore, the server continuously learns user operation data and proposes optimal operation processes, thereby enabling optimized operations that always reflect the latest operation patterns.Users can also easily operate the system through voice commands, and the server uses voice recognition means to analyze these voice commands and immediately execute the corresponding operations.

[1067] For example, consider a factory worker using a robot to record the operation of placing parts on an assembly line. The user gives a voice command to the terminal to record the operation, then starts operating the robot. Once the operation recording is complete, the terminal sends the data to a server, which then uses generative artificial intelligence to generate an automation program.

[1068] As an example of a prompt sentence, consider the voice command "Place new parts on the assembly line." The server analyzes this voice command and automatically controls the robot to execute the specified operation. As a result, the series of tasks from placing parts to moving on to the next step is automated.

[1069] The hardware required is a device (e.g., a tablet or PC) for user operation, a server for saving and transmitting operation records, and a microphone for inputting voice commands.The software required is a voice recognition library (e.g., speech_recognition), a machine learning model (e.g., a homemade AI model), and a server communication library.

[1070] This will enable more efficient and consistent robot operation in factories, and reduce human error.

[1071] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1072] Step 1:

[1073] The user inputs a voice command into the terminal to start operation recording. Specifically, the voice command "Start operation recording" is issued through the microphone. The input data is voice, and the terminal converts this voice command into text using voice recognition software. The output is the start of operation recording mode.

[1074] Step 2:

[1075] The device records a series of user operations in detail. Operation data (mouse clicks, keyboard input, touch operations, etc.) is saved in a log in real time. The input data is the user's operation, and the device compiles this as an operation record. The output is the operation record data.

[1076] Step 3:

[1077] The terminal sends the recorded operation data to the server. The server receives this data. The input data is the operation record data, which the server stores in the database. The output is the operation record stored in the database.

[1078] Step 4:

[1079] The server analyzes the received operation data and generates an optimal automation program using generative artificial intelligence. The input data is the operation record data, which the server analyzes and executes an algorithm to generate the automation program. The output is the generated automation program code.

[1080] Step 5:

[1081] The server sends the generated program code to the terminal as a procedure manual and presents it to the user. The input data is the automation program code, which the server formats in procedure manual format. The output is a procedure manual that the user can check.

[1082] Step 6:

[1083] The user checks the procedure manual and, if any corrections are necessary, sends the correction instructions to the server via the terminal. The input data is the correction instructions, which the terminal sends to the server. The output is the transmission of the correction instructions.

[1084] Step 7:

[1085] The server receives the modification instructions and reanalyzes and modifies the automation program. The input data are the modification instructions, which the server uses for further analysis. The output is the modified automation program code.

[1086] Step 8:

[1087] The server continuously learns from the user's operation data and proposes the optimal operation process. The input data is the newly recorded operation data, and the server updates the machine learning model. The output is the proposed optimized operation process.

[1088] Step 9:

[1089] The user then executes the generated program by again inputting voice commands into the terminal. Specifically, the user inputs a specific prompt through the microphone, such as "Place the new part on the assembly line." The input data is voice, which the terminal converts into text using voice recognition software and sends to the server. The output is the automated operation to be executed.

[1090] Step 10:

[1091] The server analyzes the voice commands and executes the corresponding automated program. The input data is the text of the voice commands, which the server matches with the automated program and executes. The output is the result of the automated operation.

[1092] Step 11:

[1093] The execution results are fed back to the user through the terminal. The input data is the execution results, which the server sends to the terminal. The output is feedback information that the user can check.

[1094] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1095] This invention is a system that automates a user's computer operations using generative artificial intelligence, a machine learning model, a speech recognition means, and an emotion engine. This system not only records and analyzes the user's operations and generates an automation program, but also recognizes the user's emotional state and adjusts operating procedures and processes based on that. Specific embodiments for implementing this system are described below.

[1096] Overall system configuration

[1097] The system mainly consists of a terminal, a server, and a user. The terminal is a device operated by the user, and performs tasks such as recording computer operations, performing voice recognition, recognizing emotions using an emotion engine, and running automation programs. The server mainly hosts generative artificial intelligence and machine learning models, analyzes the user's computer operations, and generates automation programs. The user is the entity that interacts with the system via an interface and performs computer operations.

[1098] Program processing

[1099] The specific processing flow of the program and the operation at each step will be explained below.

[1100] 1. Recording user actions

[1101] The terminal records the user's computer operations in real time, including mouse clicks, keyboard input, and screen scrolling.

[1102] 2. Data submission and analysis

[1103] The device sends the recorded operation data to a server, which then inputs the received data into a generative artificial intelligence (AI) system, analyzes it, and generates an automation program. The generated program code is then formatted and presented to the user as a procedure manual.

[1104] 3. User confirmation and correction

[1105] The user checks the procedure manual provided through the terminal. If necessary, the user can modify the operation procedure or program code and send the modification instructions to the server. The server then reanalyzes the program based on the modification instructions and generates new program code.

[1106] 4. Optimization using machine learning models

[1107] The device continuously records the user's operation patterns and sends them to the server. The server uses the data to update the machine learning model and learns the user's operation patterns. Based on the learning results, an optimal automated process is designed and proposed to the user. The user can then approve or modify the proposal.

[1108] 5. Emotion Recognition by Emotion Engine

[1109] The device uses an emotion engine to recognize the user's emotional state in real time, which is analyzed based on data collected through sensors such as cameras and microphones.

[1110] 6. Emotion-based process adjustment

[1111] The server receives the emotional data analyzed by the emotion engine and adjusts the automation process based on the user's emotional state. For example, if the system detects that the user is fatigued, it will simplify the operation procedure or suggest that the user take a break.

[1112] 7. Voice recognition and operation execution

[1113] The user inputs voice commands to the terminal to perform specific operations. The server analyzes the voice commands using a voice recognition means and integrates the corresponding operations into an automation program. The terminal executes the integrated program and automates the user's computer operations.

[1114] 8. Operation Feedback

[1115] The device provides real-time feedback to the user on the results of the operations performed, and if necessary, instructions are given for correction, which are then used to make further improvements.

[1116] Specific examples

[1117] For example, consider the operation of a system that automates the daily tasks of updating Excel files and sending them by email.

[1118] Recording operations

[1119] The user first commands the device to "start recording operations." The device then enters recording mode and records all operations performed by the user. The series of operations performed by the user, including opening an Excel file, entering data, saving the file, and sending it by email, are recorded.

[1120] Data analysis and program generation

[1121] The device sends the recorded data to a server, which uses generative artificial intelligence to analyze the operations and generate an automation program based on the Excel operating procedures. The generated program is presented to the user as a textual instruction manual.

[1122] User confirmation and correction

[1123] The user checks the procedure manual and issues correction instructions as necessary. The terminal sends the correction instructions to the server, which reanalyzes the program and generates new program code.

[1124] Emotion recognition and operational adjustment

[1125] The device uses an emotion engine to recognize the user's emotions from their facial expressions and voice. For example, if the user is feeling stressed, the server will adjust the device to simplify the operation procedure.

[1126] Speech recognition and automatic execution

[1127] The user issues a voice command such as "Update and send the Excel file." The device analyzes the command using voice recognition and executes the specified operation. The results of the operation are fed back to the user in real time.

[1128] In this way, this system allows users to automate computer operations efficiently and respond flexibly to their emotional state, resulting in a significant improvement in the user's work efficiency and a more comfortable working environment.

[1129] The processing flow will be explained below.

[1130] Step 1:

[1131] The user commands the terminal by voice, "Start recording my operations." The terminal switches to recording mode and prepares for computer operations.

[1132] Step 2:

[1133] The terminal captures the user's computer operations in real time and temporarily stores data such as mouse clicks, keyboard input, and window operations.

[1134] Step 3:

[1135] When the user completes the operation, the terminal stops recording and sends the captured data to the server.

[1136] Step 4:

[1137] The server inputs the received operation data into the generative AI, analyzes it, and generates an automation program. The server then formats the generated program code and presents it to the user as a procedure manual.

[1138] Step 5:

[1139] The user checks the procedure manual through the terminal and issues instructions to correct the operation procedures or program code as necessary. The correction instructions are sent from the terminal to the server.

[1140] Step 6:

[1141] The server re-analyzes the program based on the correction instructions, generates new program code, and presents the corrected procedure manual or program code to the user again.

[1142] Step 7:

[1143] The device continuously records the user's operation patterns and sends them to the server, which then updates the machine learning model and learns the user's operation patterns.

[1144] Step 8:

[1145] The machine learning model designs the optimal automated process, which the server presents to the user, who can then approve or modify the proposal via their device.

[1146] Step 9:

[1147] The device uses an emotion engine to recognize the user's emotional state in real time and collect emotion data.

[1148] Step 10:

[1149] The server receives the emotional data analyzed by the emotion engine and adjusts the automated process based on the user's emotional state, for example, simplifying the operation procedure if the user is tired.

[1150] Step 11:

[1151] The user issues a voice command to the terminal to perform a specific operation, and the terminal uses a voice recognition means to analyze the voice command and determine the corresponding operation.

[1152] Step 12:

[1153] The server integrates operations corresponding to the voice commands into an automated program, and the terminal executes the automated program to automate the user's computer operations.

[1154] Step 13:

[1155] The device provides real-time feedback to the user on the results of the operation, and if necessary, instructions for correction are issued again, and further improvements are made based on those instructions.

[1156] Example 2

[1157] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1158] In conventional systems, it is difficult to automate user computer operations, and each individual operation procedure must be set manually, resulting in reduced work efficiency. Furthermore, because dynamic adjustments based on the user's work patterns and emotional state are not made, users are prone to accumulate stress and fatigue, leading to frequent operational errors. The present invention aims to solve these problems.

[1159] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1160] In this invention, the server includes means for understanding a user's computer operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn the user's work patterns and design an optimal automation process, voice recognition means for understanding the user's voice commands and executing automated operations based on the voice commands, means for recognizing the user's emotional state in real time and adjusting the automation process based on the emotional state, and means for recording the user's computer operations and presenting the user with program code and instructions generated based on the recorded operation data. This makes it possible to automate the user's operations efficiently and flexibly and adjust the process optimally according to the user's emotional state.

[1161] "Generative AI" is AI that understands a user's computer operations and generates a program to automate those operations.

[1162] A "machine learning model" is a learning algorithm that learns user work patterns and designs optimal automation processes.

[1163] "Voice recognition means" refers to technology for understanding a user's voice commands and performing automated operations based on the voice commands.

[1164] An "emotion engine" is a system that recognizes a user's emotional state in real time and adjusts automated processes based on this.

[1165] "Camera and Microphone" are video and audio sensors used to collect the user's emotional state.

[1166] "Computer operation" refers to all operations that a user performs using a computer.

[1167] "Operation data" is data that records the user's computer operations.

[1168] "Program code" means source code generated for automation by generative artificial intelligence.

[1169] A "procedure manual" is a document of operating procedures that is presented to the user based on the generated program code.

[1170] The "modification interface" is a user interface that allows a user to make modifications to the generated program code and procedure manual.

[1171] MODE FOR CARRYING OUT THE INVENTION

[1172] This invention is a system that automates user computer operations using generative artificial intelligence, machine learning models, speech recognition means, and an emotion engine. This system not only records and analyzes user operations and generates automation programs, but also recognizes the user's emotional state and adjusts operating procedures and processes based on that.

[1173] The system mainly consists of a server, a terminal, and a user. The terminal is a device operated by the user, and performs tasks such as recording computer operations, performing voice recognition, recognizing emotions using an emotion engine, and running automation programs. The server mainly hosts generative artificial intelligence and machine learning models, analyzes the user's computer operations, and generates automation programs. The user is the entity that interacts with the system via an interface and performs computer operations.

[1174] Specifically, the device records the user's actions and sends the data to a server. The server then analyzes the actions using a generative AI model (such as ChatGPT) and generates the necessary programs. The device can also monitor the user's emotional state in real time and send that information to the server. The server then analyzes the emotional state using an emotion engine (such as the Affectiva SDK) and adjusts the automation process as needed.

[1175] Specific examples

[1176] For example, consider the case where the user wants to automate the daily task of updating an Excel file and sending it by email. First, the user commands the device to "start recording operations." At this time, the device enters recording mode and records all operations performed by the user. Operations such as the user opening the Excel file, entering data, saving the file, and sending it by email are recorded.

[1177] The recorded data is sent from the device to a server, which then uses a generative AI model to analyze the operation and generate an automation program. The generated program is presented to the user as a procedure manual, which the user can review and provide correction instructions as needed.

[1178] The device then uses an emotion engine to monitor the user's emotional state. For example, if the device detects that the user is feeling stressed, the server can make adjustments, such as simplifying the operation procedure.

[1179] Finally, the user can issue a voice command such as "Update and send the Excel file." The device will interpret the command using a voice recognition method (e.g., Google Cloud Speech-to-Text API) and execute the automated operation, providing real-time feedback to the user.

[1180] Prompt Sentence Examples

[1181] Here are some examples of prompts to input to a generative AI model:

[1182] "Create a program to automatically update Excel data and send emails daily. Follow these steps:

[1183] 1. Open the Excel file

[1184] 2. Enter your data

[1185] 3. Save the file

[1186] 4. Send the saved file by email.

[1187] By using this system, users can efficiently automate computer operations and optimally adjust processes according to their emotional state, significantly improving their work efficiency and providing a more comfortable working environment.

[1188] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1189] Step 1:

[1190] Recording user actions

[1191] When the user starts operating the computer, the terminal enters the recording mode by issuing a command to "start recording the operation."

[1192] Input: User actions such as mouse clicks, keyboard input, and screen scrolling.

[1193] Data processing: Record the entered operations in a log file.

[1194] Output: Recorded operation data.

[1195] Specific actions: Everything a user does, from opening Excel, entering data, saving, and emailing, is recorded.

[1196] Step 2:

[1197] Data transmission and analysis

[1198] The terminal transmits the recorded operation data to the server periodically or after the operation is completed.

[1199] Input: Recorded operation data.

[1200] Data processing: Input the operational data into a generative AI model (e.g., ChatGPT) and perform analysis.

[1201] Output: Program code for the automation process.

[1202] Specific operation: After the data is sent to the server, the generative AI model analyzes the operation procedures and creates an automation program based on the Excel operation procedures.

[1203] Step 3:

[1204] User confirmation and correction

[1205] The user checks the procedure manual presented via the terminal.

[1206] Input: Presented instructions and generated program code.

[1207] Data processing: The user makes corrections and sends the correction instructions to the server via their device. The server reuses the generative AI model and regenerates the program code.

[1208] Output: Updated program code and instructions.

[1209] Specific operation: When the user instructs "This step is unnecessary, so please delete it," the server generates a new procedure manual and program based on the instruction.

[1210] Step 4:

[1211] Optimization with machine learning models

[1212] The terminal continuously records the user's operation patterns and transmits them to the server.

[1213] Input: Continuously recorded operational data.

[1214] Data processing: Using machine learning models (e.g., TensorFlow) to learn operational patterns.

[1215] Output: A recommendation of the best automation process for the user.

[1216] What it does: It collects data over a long period of time and then the server suggests to the user, "We've optimized it so that you can perform all operations with just one click."

[1217] Step 5:

[1218] Emotion recognition by emotion engine

[1219] The device uses an emotion engine (e.g., Affectiva SDK) to recognize the user's emotional state in real time.

[1220] Input: User facial and voice data collected through camera and microphone.

[1221] Data processing: The emotion engine analyzes facial expressions and voice to determine the emotional state.

[1222] Output: The user's real-time emotional state.

[1223] Specific operation: If the user shows signs of fatigue during operation, the emotion engine will recognize the state as "fatigue."

[1224] Step 6:

[1225] Emotion-based process adjustment

[1226] The server adjusts the automation process based on the emotion data received from the emotion engine.

[1227] Input: Emotional state data from the emotion engine.

[1228] Data processing: Adjusting automated processes, simplifying steps or suggesting breaks where necessary.

[1229] Output: A coordinated automated process.

[1230] Specific operation: The server suggests, "Would you like to take a break?" and presents instructions to simplify the operation procedure.

[1231] Step 7:

[1232] Voice recognition and operation execution

[1233] The user issues a voice command, which the terminal recognizes.

[1234] Input: Voice command.

[1235] Data processing: The voice is analyzed using a speech recognition tool (e.g., Google Cloud Speech-to-Text API) and sent to a server, which then integrates the instructions into an automated program and returns instructions for execution.

[1236] Output: Execution of automated operations based on voice commands.

[1237] Specific operation: When a user commands, "Update and send the Excel file," the device analyzes the voice and generates an execution command on the server, after which the Excel file is automatically updated and an email is sent.

[1238] Step 8:

[1239] Operation feedback

[1240] The terminal provides the user with real-time feedback on the results of the operation.

[1241] Input: The result of running an automated program.

[1242] Data processing: Analyze the execution results and provide feedback to the user.

[1243] Output: Feedback information.

[1244] Specific operation: When the user commands, "Check if the operation was successful," the device displays the execution results and gives feedback that "All operations were successful."

[1245] (Application example 2)

[1246] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1247] In modern self-driving vehicles, automation of driver operations and voice commands, and environmental adjustments based on real-time emotion recognition have not yet been fully realized. Therefore, reducing the burden on the driver and improving safety are issues. In addition, the generation of automated programs based on the analysis of operation data and the interface for modifying them are not yet fully developed, so an efficient automated system is required.

[1248] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1249] In this invention, the server includes means for understanding user operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn the user's work patterns and design an optimal automation process, voice recognition means for understanding the user's voice commands and executing automated operations based on the voice commands, means for recording, analyzing, and automating the driver's operations and voice commands, and means for recognizing the driver's emotional state in real time and adjusting the in-vehicle environment and navigation based on that state. This makes it possible to efficiently automate the driver's operations and further adjust the in-vehicle environment and navigation based on the driver's emotional state.

[1250] "Generative AI" is an AI technology that understands user operations and generates programs to automate those operations.

[1251] A "machine learning model" is an algorithm or method for learning user work patterns and designing optimal automation processes.

[1252] "Voice recognition means" refers to technology for understanding a user's voice commands and performing automated operations based on the voice commands.

[1253] The "operation recording means" is a function for recording user operations and voice commands, analyzing them, and automating them.

[1254] "Emotion recognition means" is a technology that recognizes the driver's emotional state in real time and adjusts the in-car environment and navigation based on that state.

[1255] An "autonomous vehicle" is a vehicle that drives autonomously without the need for manual operation by a driver.

[1256] The "user interface" refers to a screen or input means that allows the user to modify the generated program code and procedure manual.

[1257] This invention relates to a system that records, analyzes, and automates driver operations and voice commands of an autonomous vehicle. This system has a function of supporting comfortable driving by the driver using generative artificial intelligence, machine learning models, voice recognition means, and emotion recognition means. Detailed embodiments of the system are described below.

[1258] Overall system configuration

[1259] The system mainly consists of an in-vehicle device, a server, and a driver. The in-vehicle device records the driver's operations and voice commands and collects data for emotion recognition. The server hosts generative artificial intelligence and machine learning models, analyzes operation data, and generates automated programs. The driver interacts with the system via an interface and is the entity that performs driving operations.

[1260] System Program

[1261] Operation recording means

[1262] The in-vehicle device records the driver's actions and voice commands in real time, including steering, pedal operation, touchscreen operation, etc. It also uses cameras and sensors to collect the driver's facial expressions and voice.

[1263] Data transmission and analysis

[1264] The vehicle-mounted device sends the recorded operation data to a server, which then inputs the received data into a generative artificial intelligence system, analyzes it, and generates an automation program. This uses machine learning libraries such as TensorFlow and PyTorch.

[1265] Automated Program Generation and Emotion Recognition

[1266] The server generates the optimal automation program based on the operation data. It also uses technologies such as OpenCV to analyze data acquired from cameras and microphones and recognize the driver's emotional state. Based on this emotional state, the automation program and navigation are adjusted.

[1267] Voice recognition and operation execution

[1268] The driver can input voice commands into the vehicle's in-vehicle device, and the server will interpret the voice commands through speech recognition means and perform the corresponding operations, using the Google Speech-to-Text API.

[1269] feedback

[1270] The in-vehicle device provides real-time feedback to the driver on the results of the maneuver, allowing the driver to issue additional voice commands or corrective actions if necessary.

[1271] Specific examples

[1272] For example, if a driver issues the voice command "Go home," the system will:

[1273] 1. Voice command recognition:

[1274] Driver: "Going home."

[1275] In-vehicle device: Google Speech-to-Text converts voice commands into text

[1276] 2. Navigation adjustment:

[1277] Server: Analyzes the text data and generates a route to home

[1278] Emotional state analysis: if the driver is tired, add optimal rest stops to the route

[1279] 3. Feedback:

[1280] In-vehicle device: Provides voice feedback to the driver on route guidance

[1281] Example prompt sentence:

[1282] User: I want to go home

[1283] System: Searching for a route to your home. Please wait.

[1284] System (feedback): Your route is planned. It looks like you might need a break along the way, so we've added appropriate stops. Please resume driving.

[1285] In this way, the system effectively automates driver operations and also adjusts the in-car environment and navigation according to the driver's emotional state, providing a more comfortable and safer driving experience.

[1286] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1287] Step 1:

[1288] Recording of operation and emotional data

[1289] Subject: Terminal

[1290] The terminal (vehicle-mounted device) records the driver's operations and voice commands in real time. The terminal also uses cameras and sensors to collect the driver's facial expressions and voice. Input data includes steering wheel operations, pedal operations, touchscreen operations, facial expressions, and voice. This data is temporarily stored locally and prepared for real-time analysis as needed.

[1291] Step 2:

[1292] Data transmission and analysis

[1293] Subject: Terminal

[1294] The device sends the recorded operation data and emotion data to the server. The input data includes the operation log and emotion data collected in step 1. The server analyzes the received data and generates an automation program using generative artificial intelligence (e.g., TensorFlow, PyTorch). Data analysis includes splitting time-series data and feature extraction. The output after analysis is the initial script for the automation program.

[1295] Step 3:

[1296] Generating automation programs

[1297] Subject: Server

[1298] The server uses generative artificial intelligence to generate an automation program based on the analytical data. The analytical data obtained in step 2 is used as input. The generative AI model generates program code, creating operating procedures and scripts during the generation process. The output is program code containing automated operating procedures.

[1299] Step 4:

[1300] Emotion recognition and process regulation

[1301] Subject: Server

[1302] The server uses emotion recognition means (e.g., OpenCV) to recognize the driver's emotional state from the collected facial and voice data. The emotional data collected in steps 1 and 2 is used as input. Based on the results of the emotional state analysis, the automation program and navigation plan are adjusted. The output is an automated program adjusted according to the emotional state.

[1303] Step 5:

[1304] Entering and recognizing voice commands

[1305] Subject: User

[1306] The user (driver) inputs voice commands to the vehicle's onboard device. The input data is the voice command. The server uses a voice recognition method (e.g., Google Speech-to-Text) to convert the voice command into text data. The text data is then analyzed and integrated into the automation program. The output is an operation instruction based on the analyzed voice command.

[1307] Step 6:

[1308] Running an automation program

[1309] Subject: Terminal

[1310] The device executes the automation program received from the server. The input data includes the adjusted automation program and the analysis results of the voice commands. The device automatically executes the operation procedures, performing navigation, adjusting the in-car environment, etc. The output is the execution result of the automated operation.

[1311] Step 7:

[1312] Providing Feedback

[1313] Subject: Terminal

[1314] The terminal provides real-time feedback on the results of the operation to the user. The input data are the execution results and, if necessary, additional instructions from the user. The terminal analyzes this data and determines the next operation steps or necessary adjustments. The output is a report of the operation results to the user and a suggestion for the next operation step.

[1315] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1316] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1317] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1318] [Fourth embodiment]

[1319] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1320] 7, a 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.

[1321] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[1322] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1323] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1324] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1325] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1326] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1327] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1328] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1329] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1330] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1331] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1332] This invention is a system that automates a user's computer operations using generative artificial intelligence, machine learning models, and speech recognition means. The system records the user's operations, generates an automation program based on the records, and learns the user's work patterns to propose and execute an optimal process. Specific embodiments for implementing this system are described below.

[1333] Overall system configuration

[1334] The system mainly consists of a terminal, a server, and a user. The terminal is a device operated by the user, and performs functions such as recording computer operations, performing voice recognition, and running automation programs. The server mainly hosts generative artificial intelligence and machine learning models, analyzes the user's computer operations, and generates automation programs. The user is the entity that performs the computer operations and interacts with the system through an interface.

[1335] Program processing

[1336] 1. Recording user actions

[1337] The terminal records the user's computer operations in real time, including mouse clicks, keyboard input, screen scrolling, etc. The terminal records these operations in detail and sends them to the server.

[1338] 2. Data submission and analysis

[1339] The device sends the recorded operation data to a server, which uses generative artificial intelligence to analyze the operation and create an automation program based on the received data. The generated program code is then formatted and presented to the user as a procedure manual.

[1340] 3. User confirmation and correction

[1341] The user checks the instructions provided through the terminal. If necessary, the user can modify the operating procedures and program code. The modified instructions are then sent back to the server, where further analysis and program modification are performed.

[1342] 4. Optimization using machine learning models

[1343] The device continuously records the user's operation patterns and sends them to the server. The transmitted data is analyzed by a machine learning model to learn the user's operation patterns. Based on the learning results, an optimal automated process is designed and proposed to the user. The user can then approve or modify the proposal.

[1344] 5. Voice recognition and operation execution

[1345] The user inputs voice commands into the terminal. The server analyzes the voice commands using a voice recognition means and integrates the corresponding operations into an automated program. The terminal executes the integrated program and automates the user's computer operations. The execution results are fed back to the user in real time.

[1346] Specific examples

[1347] For example, consider the operation of a system that automates the daily tasks of updating Excel files and sending them by email.

[1348] Recording operations

[1349] First, the user commands the device to "start recording operations" by voice. The device enters recording mode and records all operations performed by the user. The series of operations performed by the user, such as opening an Excel file, entering data, saving the file, and sending it by email, are recorded.

[1350] Data analysis and program generation

[1351] The device sends the recorded data to a server, which uses generative artificial intelligence to analyze the operations and generate an automation program based on the Excel operating procedures. The generated program is presented to the user as a textual instruction manual.

[1352] User confirmation and correction

[1353] The user checks the procedure manual and issues correction instructions as necessary. The correction instructions are sent via the terminal to the server, where the data is reanalyzed and corrected.

[1354] Machine learning optimization

[1355] The device continuously records the operation patterns of Excel files and the server learns from them. Based on the learning results, the server proposes the optimal operation procedure and presents it to the user.

[1356] Speech recognition and automatic execution

[1357] The user issues a voice command such as "Update and send the Excel file." The device analyzes the voice command using a voice recognition system and executes the instructed operation. The entire process, from updating the Excel file to sending the email, is carried out automatically, and the results are fed back to the user.

[1358] In this way, by using this system, users can efficiently automate computer operations, resulting in a significant improvement in work efficiency.

[1359] The processing flow will be explained below.

[1360] Step 1:

[1361] The user commands the device to "start recording operations" by voice. The device switches to recording mode and gets ready.

[1362] Step 2:

[1363] The device captures all of the user's computer operations (mouse clicks, keyboard input, window movement and scrolling, etc.) in real time and temporarily stores them in storage.

[1364] Step 3:

[1365] When the user completes the operation, the terminal stops recording and sends the captured data to the server.

[1366] Step 4:

[1367] The server inputs the received operation data into the multimodal AI, which analyzes the operation data and generates the corresponding program code.

[1368] Step 5:

[1369] The server then formats the generated code and presents it to the user as a procedure manual, who can then review the manual and provide corrections if necessary.

[1370] Step 6:

[1371] If there are any correction instructions, the terminal sends them to the server, which then reanalyzes the program based on the instructions and generates new program code.

[1372] Step 7:

[1373] The device continuously records the user's operation patterns and periodically sends them to the server, which then updates the machine learning model based on the data sent and learns the user's operation patterns.

[1374] Step 8:

[1375] The machine learning model then proposes the optimal automation process based on the results of its learning, which the server then presents to the user, who can then approve or modify it.

[1376] Step 9:

[1377] The user issues a voice command to the device to perform a specific operation, and the device uses voice recognition AI to analyze the voice command and determine the corresponding operation.

[1378] Step 10:

[1379] The server then integrates the voice command into an automated program based on the analysis results, and the terminal executes the automated program to perform the specified operation.

[1380] Step 11:

[1381] The device provides real-time feedback to the user on the results of the operation, and if necessary, instructions for correction are issued, and further improvements are made based on those instructions.

[1382] Example 1

[1383] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1384] Many of the computer operations that users perform on a daily basis are repetitive and therefore time-consuming and labor-intensive. Furthermore, while these operations should be automated efficiently, conventional automation technologies have been unable to fully understand users' operation patterns, making it difficult to generate appropriate automation programs. Furthermore, when users use voice commands to perform operations, the coordination between voice recognition and automation is often insufficient, preventing smooth operation.

[1385] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1386] In this invention, the server includes means for understanding a user's computer operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn the user's work patterns and design an optimal automation process, and voice recognition means for understanding the user's voice commands and executing automated operations based on the voice commands, thereby enabling the server to accurately capture the user's operation patterns and generate and execute automation programs in real time.

[1387] "Generative AI" refers to AI that has the ability to generate new information and answers based on data.

[1388] "Computer operation" includes user actions for operating a computer or related device, such as mouse clicks, keyboard input, and screen scrolling.

[1389] "Means for generating a program" refers to the device or software that analyzes the user's operations and controls the process of generating program code for automation.

[1390] A "work pattern" refers to a set of computer operations that a user performs to accomplish a specific task.

[1391] An "optimal automated process" refers to an automated procedure that is designed to analyze a user's work patterns and enable the user to perform the work efficiently.

[1392] A "machine learning model" refers to an algorithm or statistical model that learns from data and makes predictions and judgments.

[1393] "Voice command" refers to a command given by a user to give instructions to a computer or related device using voice.

[1394] "Voice recognition means" refers to technology or devices for analyzing a user's voice commands and executing appropriate instructions or operations.

[1395] "Means for recording and transmitting in real time" refers to a process in which every time a user performs a computer operation, that operation is immediately recorded and transmitted to a server.

[1396] A "procedure" is a document that details each step in accomplishing a specific task.

[1397] "Interface" refers to the means or methods by which a user interacts with a system and inputs or displays data.

[1398] This invention is a system for automating user computer operations and improving business efficiency. The system is mainly composed of terminals, a server, and users. Each component and its operation will be specifically described below.

[1399] 1. Recording user actions

[1400] The device is responsible for recording the user's computer operations in real time. This includes mouse clicks, keyboard input, and screen scrolling. When a user operates an Excel file, all specific operations such as opening and closing it, entering data, and saving are recorded. For voice commands, the device uses the Google Speech-to-Text API to convert the voice into text data.

[1401] 2. Data submission and analysis

[1402] The device sends the recorded operation data to the server, using a secure communication protocol (e.g., HTTPS) to ensure the data is transmitted safely.

[1403] The server analyzes the received data using generative artificial intelligence such as OpenAI's GPT-3 model, which allows it to understand the user's operational procedures and generate an automated program.

[1404] The generated program code is formatted as a procedure and the details are presented to the user.

[1405] 3. User confirmation and correction

[1406] The user checks the presented procedure manual through the terminal and makes corrections as necessary. Using the interface, the user inputs the specific corrections. Based on this, the server analyzes the data again and corrects the program.

[1407] 4. Optimization using machine learning models

[1408] The device continuously records the user's operation patterns and periodically sends the data to a server. The server then analyzes the data using machine learning models such as TensorFlow and Scikit-learn to learn the user's operation patterns. Based on the results of this learning, optimal automation procedures are designed and proposed to the user.

[1409] 5. Voice recognition and operation execution

[1410] The user inputs a voice command to the terminal, such as "Update and send the Excel file." The terminal uses a voice recognition means to analyze the voice command and transmits it to the server.

[1411] The server integrates the automation program based on the analysis results and sends the determined commands to the terminal, which then executes the operations according to the received commands and provides the results to the user in real time.

[1412] As a concrete example, consider a situation where you want to automate the task of entering sales data into specific cells in an Excel file every day, saving the file, and sending it by email.

[1413] For example, by inputting a prompt such as, "Generate a program that will automate the task of entering sales data into specific cells in an Excel file every day, saving the file, and sending it by email," into the generation AI, the entire series of operations above will be automated.

[1414] In this way, by using this system, users can efficiently automate computer operations and greatly improve business efficiency.

[1415] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1416] Step 1:

[1417] The user inputs a voice command to the terminal saying, "Start recording operations."

[1418] Input: Voice commands given by the user

[1419] Processing: The device uses a voice recognition method (e.g., Google Speech-to-Text API) to parse the voice command and convert it into text data. If the voice command is recognized as an instruction to start recording mode, the device enters recording mode.

[1420] Output: Recording mode is started

[1421] Step 2:

[1422] A user opens an Excel file, enters sales data into specific cells, saves the file, and performs other operations.

[1423] Input: User-operated computer operations (mouse clicks, keyboard input, screen scrolling, etc.)

[1424] Processing: The device records these operations in real time and stores detailed operations in a log.

[1425] Output: Recorded operation log

[1426] Step 3:

[1427] The terminal transmits the recorded operation data to the server.

[1428] Input: Recorded operation log

[1429] Processing: The terminal sends the operation log to the server using a secure communication protocol (e.g., HTTPS).

[1430] Output: Operation log sent to the server

[1431] Step 4:

[1432] The server analyzes the received operation data and generates an automation program using generative artificial intelligence (e.g., OpenAI's GPT-3).

[1433] Input: Operation log sent to the server

[1434] Processing: The server uses generative artificial intelligence to generate an automated program by analyzing the operation log. This program is created by imitating the user's computer operations.

[1435] Output: Generated automation program

[1436] Step 5:

[1437] The server formats the generated program code as a procedure manual and sends it to the terminal.

[1438] Input: Generated automation program

[1439] Processing: The server formats the program code into a user-friendly instruction manual that the user can later review and modify.

[1440] Output: Automation program in the form of a procedure manual

[1441] Step 6:

[1442] The terminal displays the procedure manual to the user.

[1443] Input: Automation program in the form of a procedure manual

[1444] Processing: The terminal displays the procedure manual on the screen and asks the user for confirmation. The user checks the contents and, if necessary, inputs correction instructions through the interface.

[1445] Output: User checks the procedure manual and gives instructions for correction

[1446] Step 7:

[1447] The terminal transmits the user's correction instructions to the server.

[1448] Input: User correction instructions

[1449] Processing: The terminal sends correction instructions to the server, and the server re-analyzes the data.

[1450] Output: Correction instructions sent to the server

[1451] Step 8:

[1452] The server reanalyzes the program code based on the modification instructions and generates a modified automation program.

[1453] Input: Correction instructions sent to the server

[1454] Processing: The server re-analyzes the program code based on the correction instructions and generates an optimized automation program.

[1455] Output: Modified automation program

[1456] Step 9:

[1457] The terminal receives the modified automation program from the server and prepares it for execution.

[1458] Input: Modified automation program

[1459] Processing: The device checks whether the operation is executed correctly based on the received program. Once preparation is complete, the user can start the operation by entering a voice command.

[1460] Output: An automated program ready to run

[1461] Step 10:

[1462] The user inputs a voice command into the terminal saying, "Update and send the Excel file."

[1463] Input: Voice commands given by the user

[1464] Processing: The terminal uses voice recognition means to analyze the voice command, convert it into text data, and send it to the server.

[1465] Output: Voice command sent to the server

[1466] Step 11:

[1467] The server sends instructions to the terminal to execute an automated program based on the voice command.

[1468] Input: Voice command sent to the server

[1469] Processing: The server selects the appropriate automated program based on the voice command and sends the instructions to the terminal.

[1470] Output: Instructions to run the automation program

[1471] Step 12:

[1472] Based on the instructions received, the device automatically performs a series of operations, from updating the Excel file to sending an email.

[1473] Input: Instruction to run the automation program

[1474] Processing: The device opens an Excel file, enters sales data into designated cells, saves the file, and sends it by email.

[1475] Output: automated operations and feedback of the operation results

[1476] Step 13:

[1477] The terminal provides the execution results to the user in real time.

[1478] Input: Automated operation results

[1479] Processing: The device displays detailed results to the user, including whether the operation was successful or an error occurred.

[1480] Output: Real-time feedback of the operation results

[1481] (Application example 1)

[1482] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1483] Operating robots in factories requires a high level of specialized knowledge, and it takes time and training to operate them efficiently. Furthermore, workers tend to tire and make mistakes when performing the same operations every time. Consistent operation is also required even when different workers operate the robots, but this is difficult to achieve. There is a need to solve these issues, improve work efficiency, and reduce errors.

[1484] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1485] In this invention, the server includes means for understanding user operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn user work patterns and design an optimal automation process, means for understanding user voice commands and executing automated operations based on the voice commands, means for recording operations on a terminal and sending the recording to the server, means for presenting the generated program code and instructions to the user, means for continuously learning the operation history and proposing optimal operations, and means for executing operations based on voice recognition and providing feedback on the results. This enables more efficient and consistent robot operation in factories and reduces human error.

[1486] "Generative artificial intelligence" is a technology that generates models based on data and analyzes and automates user operations.

[1487] "User operation" refers to a series of actions or commands performed to operate a machine such as an industrial robot.

[1488] An "automation program" is software code that is generated to automatically perform a user operation.

[1489] A "machine learning model" is a statistical model that learns from data and proposes optimal operating processes.

[1490] A "voice command" is a command that a user issues to a system or machine using voice.

[1491] "Voice recognition means" refers to technology for analyzing a user's voice command and performing the corresponding operation.

[1492] An "operation record" is data that stores a series of actions performed by a user and is used for later analysis and learning.

[1493] A "procedure manual" is a document that describes in detail the operating procedure and is presented to the user.

[1494] "Continuous learning" means that the machine learning model constantly learns the optimal operation process based on recorded operation data.

[1495] "Feedback" refers to communicating to the user the results of an operation that has been performed.

[1496] This invention embodies a system that improves the efficiency and automation of industrial robot operations. This system uses generative artificial intelligence, machine learning models, and voice recognition functions to automate user operations, reducing operational errors and improving efficiency.

[1497] The terminal is a device for recording the user's robot operation in real time, recording detailed actions such as mouse clicks, keyboard input, and touch operations. The recorded data is then sent to a server, which hosts a generative artificial intelligence (AI) that analyzes the user's input and generates an optimal automation program.

[1498] The generated program is presented to the user as a text-formatted instruction manual. The user checks this manual, and if any corrections are necessary, they send the correction instructions to the server again via their terminal. The server reanalyzes the program based on these correction instructions and generates an optimized program.

[1499] Furthermore, the server continuously learns user operation data and proposes optimal operation processes, thereby enabling optimized operations that always reflect the latest operation patterns.Users can also easily operate the system through voice commands, and the server uses voice recognition means to analyze these voice commands and immediately execute the corresponding operations.

[1500] For example, consider a factory worker using a robot to record the operation of placing parts on an assembly line. The user gives a voice command to the terminal to record the operation, then starts operating the robot. Once the operation recording is complete, the terminal sends the data to a server, which then uses generative artificial intelligence to generate an automation program.

[1501] As an example of a prompt sentence, consider the voice command "Place new parts on the assembly line." The server analyzes this voice command and automatically controls the robot to execute the specified operation. As a result, the series of tasks from placing parts to moving on to the next step is automated.

[1502] The hardware required is a device (e.g., a tablet or PC) for user operation, a server for saving and transmitting operation records, and a microphone for inputting voice commands.The software required is a voice recognition library (e.g., speech_recognition), a machine learning model (e.g., a homemade AI model), and a server communication library.

[1503] This will enable more efficient and consistent robot operation in factories, and reduce human error.

[1504] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1505] Step 1:

[1506] The user inputs a voice command into the terminal to start operation recording. Specifically, the voice command "Start operation recording" is issued through the microphone. The input data is voice, and the terminal converts this voice command into text using voice recognition software. The output is the start of operation recording mode.

[1507] Step 2:

[1508] The device records a series of user operations in detail. Operation data (mouse clicks, keyboard input, touch operations, etc.) is saved in a log in real time. The input data is the user's operation, and the device compiles this as an operation record. The output is the operation record data.

[1509] Step 3:

[1510] The terminal sends the recorded operation data to the server. The server receives this data. The input data is the operation record data, which the server stores in the database. The output is the operation record stored in the database.

[1511] Step 4:

[1512] The server analyzes the received operation data and generates an optimal automation program using generative artificial intelligence. The input data is the operation record data, which the server analyzes and executes an algorithm to generate the automation program. The output is the generated automation program code.

[1513] Step 5:

[1514] The server sends the generated program code to the terminal as a procedure manual and presents it to the user. The input data is the automation program code, which the server formats in procedure manual format. The output is a procedure manual that the user can check.

[1515] Step 6:

[1516] The user checks the procedure manual and, if any corrections are necessary, sends the correction instructions to the server via the terminal. The input data is the correction instructions, which the terminal sends to the server. The output is the transmission of the correction instructions.

[1517] Step 7:

[1518] The server receives the modification instructions and reanalyzes and modifies the automation program. The input data are the modification instructions, which the server uses for further analysis. The output is the modified automation program code.

[1519] Step 8:

[1520] The server continuously learns from the user's operation data and proposes the optimal operation process. The input data is the newly recorded operation data, and the server updates the machine learning model. The output is the proposed optimized operation process.

[1521] Step 9:

[1522] The user then executes the generated program by again inputting voice commands into the terminal. Specifically, the user inputs a specific prompt through the microphone, such as "Place the new part on the assembly line." The input data is voice, which the terminal converts into text using voice recognition software and sends to the server. The output is the automated operation to be executed.

[1523] Step 10:

[1524] The server analyzes the voice commands and executes the corresponding automated program. The input data is the text of the voice commands, which the server matches with the automated program and executes. The output is the result of the automated operation.

[1525] Step 11:

[1526] The execution results are fed back to the user through the terminal. The input data is the execution results, which the server sends to the terminal. The output is feedback information that the user can check.

[1527] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1528] This invention is a system that automates a user's computer operations using generative artificial intelligence, a machine learning model, a speech recognition means, and an emotion engine. This system not only records and analyzes the user's operations and generates an automation program, but also recognizes the user's emotional state and adjusts operating procedures and processes based on that. Specific embodiments for implementing this system are described below.

[1529] Overall system configuration

[1530] The system mainly consists of a terminal, a server, and a user. The terminal is a device operated by the user, and performs tasks such as recording computer operations, performing voice recognition, recognizing emotions using an emotion engine, and running automation programs. The server mainly hosts generative artificial intelligence and machine learning models, analyzes the user's computer operations, and generates automation programs. The user is the entity that interacts with the system via an interface and performs computer operations.

[1531] Program processing

[1532] The specific processing flow of the program and the operation at each step will be explained below.

[1533] 1. Recording user actions

[1534] The terminal records the user's computer operations in real time, including mouse clicks, keyboard input, and screen scrolling.

[1535] 2. Data submission and analysis

[1536] The device sends the recorded operation data to a server, which then inputs the received data into a generative artificial intelligence (AI) system, analyzes it, and generates an automation program. The generated program code is then formatted and presented to the user as a procedure manual.

[1537] 3. User confirmation and correction

[1538] The user checks the procedure manual provided through the terminal. If necessary, the user can modify the operation procedure or program code and send the modification instructions to the server. The server then reanalyzes the program based on the modification instructions and generates new program code.

[1539] 4. Optimization using machine learning models

[1540] The device continuously records the user's operation patterns and sends them to the server. The server uses the data to update the machine learning model and learns the user's operation patterns. Based on the learning results, an optimal automated process is designed and proposed to the user. The user can then approve or modify the proposal.

[1541] 5. Emotion Recognition by Emotion Engine

[1542] The device uses an emotion engine to recognize the user's emotional state in real time, which is analyzed based on data collected through sensors such as cameras and microphones.

[1543] 6. Emotion-based process adjustment

[1544] The server receives the emotional data analyzed by the emotion engine and adjusts the automation process based on the user's emotional state. For example, if the system detects that the user is fatigued, it will simplify the operation procedure or suggest that the user take a break.

[1545] 7. Voice recognition and operation execution

[1546] The user inputs voice commands to the terminal to perform specific operations. The server analyzes the voice commands using a voice recognition means and integrates the corresponding operations into an automation program. The terminal executes the integrated program and automates the user's computer operations.

[1547] 8. Operation Feedback

[1548] The device provides real-time feedback to the user on the results of the operations performed, and if necessary, instructions are given for correction, which are then used to make further improvements.

[1549] Specific examples

[1550] For example, consider the operation of a system that automates the daily tasks of updating Excel files and sending them by email.

[1551] Recording operations

[1552] The user first commands the device to "start recording operations." The device then enters recording mode and records all operations performed by the user. The series of operations performed by the user, including opening an Excel file, entering data, saving the file, and sending it by email, are recorded.

[1553] Data analysis and program generation

[1554] The device sends the recorded data to a server, which uses generative artificial intelligence to analyze the operations and generate an automation program based on the Excel operating procedures. The generated program is presented to the user as a textual instruction manual.

[1555] User confirmation and correction

[1556] The user checks the procedure manual and issues correction instructions as necessary. The terminal sends the correction instructions to the server, which reanalyzes the program and generates new program code.

[1557] Emotion recognition and operational adjustment

[1558] The device uses an emotion engine to recognize the user's emotions from their facial expressions and voice. For example, if the user is feeling stressed, the server will adjust the device to simplify the operation procedure.

[1559] Speech recognition and automatic execution

[1560] The user issues a voice command such as "Update and send the Excel file." The device analyzes the command using voice recognition and executes the specified operation. The results of the operation are fed back to the user in real time.

[1561] In this way, this system allows users to automate computer operations efficiently and respond flexibly to their emotional state, resulting in a significant improvement in the user's work efficiency and a more comfortable working environment.

[1562] The processing flow will be explained below.

[1563] Step 1:

[1564] The user commands the terminal by voice, "Start recording my operations." The terminal switches to recording mode and prepares for computer operations.

[1565] Step 2:

[1566] The terminal captures the user's computer operations in real time and temporarily stores data such as mouse clicks, keyboard input, and window operations.

[1567] Step 3:

[1568] When the user completes the operation, the terminal stops recording and sends the captured data to the server.

[1569] Step 4:

[1570] The server inputs the received operation data into the generative AI, analyzes it, and generates an automation program. The server then formats the generated program code and presents it to the user as a procedure manual.

[1571] Step 5:

[1572] The user checks the procedure manual through the terminal and issues instructions to correct the operation procedures or program code as necessary. The correction instructions are sent from the terminal to the server.

[1573] Step 6:

[1574] The server re-analyzes the program based on the correction instructions, generates new program code, and presents the corrected procedure manual or program code to the user again.

[1575] Step 7:

[1576] The device continuously records the user's operation patterns and sends them to the server, which then updates the machine learning model and learns the user's operation patterns.

[1577] Step 8:

[1578] The machine learning model designs the optimal automated process, which the server presents to the user, who can then approve or modify the proposal via their device.

[1579] Step 9:

[1580] The device uses an emotion engine to recognize the user's emotional state in real time and collect emotion data.

[1581] Step 10:

[1582] The server receives the emotional data analyzed by the emotion engine and adjusts the automated process based on the user's emotional state, for example, simplifying the operation procedure if the user is tired.

[1583] Step 11:

[1584] The user issues a voice command to the terminal to perform a specific operation, and the terminal uses a voice recognition means to analyze the voice command and determine the corresponding operation.

[1585] Step 12:

[1586] The server integrates operations corresponding to the voice commands into an automated program, and the terminal executes the automated program to automate the user's computer operations.

[1587] Step 13:

[1588] The device provides real-time feedback to the user on the results of the operation, and if necessary, instructions for correction are issued again, and further improvements are made based on those instructions.

[1589] Example 2

[1590] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1591] In conventional systems, it is difficult to automate user computer operations, and each individual operation procedure must be set manually, resulting in reduced work efficiency. Furthermore, because dynamic adjustments based on the user's work patterns and emotional state are not made, users are prone to accumulate stress and fatigue, leading to frequent operational errors. The present invention aims to solve these problems.

[1592] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1593] In this invention, the server includes means for understanding a user's computer operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn the user's work patterns and design an optimal automation process, voice recognition means for understanding the user's voice commands and executing automated operations based on the voice commands, means for recognizing the user's emotional state in real time and adjusting the automation process based on the emotional state, and means for recording the user's computer operations and presenting the user with program code and instructions generated based on the recorded operation data. This makes it possible to automate the user's operations efficiently and flexibly and adjust the process optimally according to the user's emotional state.

[1594] "Generative AI" is AI that understands a user's computer operations and generates a program to automate those operations.

[1595] A "machine learning model" is a learning algorithm that learns user work patterns and designs optimal automation processes.

[1596] "Voice recognition means" refers to technology for understanding a user's voice commands and performing automated operations based on the voice commands.

[1597] An "emotion engine" is a system that recognizes a user's emotional state in real time and adjusts automated processes based on this.

[1598] "Camera and Microphone" are video and audio sensors used to collect the user's emotional state.

[1599] "Computer operation" refers to all operations that a user performs using a computer.

[1600] "Operation data" is data that records the user's computer operations.

[1601] "Program code" means source code generated for automation by generative artificial intelligence.

[1602] A "procedure manual" is a document of operating procedures that is presented to the user based on the generated program code.

[1603] The "modification interface" is a user interface that allows a user to make modifications to the generated program code and procedure manual.

[1604] MODE FOR CARRYING OUT THE INVENTION

[1605] This invention is a system that automates user computer operations using generative artificial intelligence, machine learning models, speech recognition means, and an emotion engine. This system not only records and analyzes user operations and generates automation programs, but also recognizes the user's emotional state and adjusts operating procedures and processes based on that.

[1606] The system mainly consists of a server, a terminal, and a user. The terminal is a device operated by the user, and performs tasks such as recording computer operations, performing voice recognition, recognizing emotions using an emotion engine, and running automation programs. The server mainly hosts generative artificial intelligence and machine learning models, analyzes the user's computer operations, and generates automation programs. The user is the entity that interacts with the system via an interface and performs computer operations.

[1607] Specifically, the device records the user's actions and sends the data to a server. The server then analyzes the actions using a generative AI model (such as ChatGPT) and generates the necessary programs. The device can also monitor the user's emotional state in real time and send that information to the server. The server then analyzes the emotional state using an emotion engine (such as the Affectiva SDK) and adjusts the automation process as needed.

[1608] Specific examples

[1609] For example, consider the case where the user wants to automate the daily task of updating an Excel file and sending it by email. First, the user commands the device to "start recording operations." At this time, the device enters recording mode and records all operations performed by the user. Operations such as the user opening the Excel file, entering data, saving the file, and sending it by email are recorded.

[1610] The recorded data is sent from the device to a server, which then uses a generative AI model to analyze the operation and generate an automation program. The generated program is presented to the user as a procedure manual, which the user can review and provide correction instructions as needed.

[1611] The device then uses an emotion engine to monitor the user's emotional state. For example, if the device detects that the user is feeling stressed, the server can make adjustments, such as simplifying the operation procedure.

[1612] Finally, the user can issue a voice command such as "Update and send the Excel file." The device will interpret the command using a voice recognition method (e.g., Google Cloud Speech-to-Text API) and execute the automated operation, providing real-time feedback to the user.

[1613] Prompt Sentence Examples

[1614] Here are some examples of prompts to input to a generative AI model:

[1615] "Create a program to automatically update Excel data and send emails daily. Follow these steps:

[1616] 1. Open the Excel file

[1617] 2. Enter your data

[1618] 3. Save the file

[1619] 4. Send the saved file by email.

[1620] By using this system, users can efficiently automate computer operations and optimally adjust processes according to their emotional state, significantly improving their work efficiency and providing a more comfortable working environment.

[1621] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1622] Step 1:

[1623] Recording user actions

[1624] When the user starts operating the computer, the terminal enters the recording mode by issuing a command to "start recording the operation."

[1625] Input: User actions such as mouse clicks, keyboard input, and screen scrolling.

[1626] Data processing: Record the entered operations in a log file.

[1627] Output: Recorded operation data.

[1628] Specific actions: Everything a user does, from opening Excel, entering data, saving, and emailing, is recorded.

[1629] Step 2:

[1630] Data transmission and analysis

[1631] The terminal transmits the recorded operation data to the server periodically or after the operation is completed.

[1632] Input: Recorded operation data.

[1633] Data processing: Input the operational data into a generative AI model (e.g., ChatGPT) and perform analysis.

[1634] Output: Program code for the automation process.

[1635] Specific operation: After the data is sent to the server, the generative AI model analyzes the operation procedures and creates an automation program based on the Excel operation procedures.

[1636] Step 3:

[1637] User confirmation and correction

[1638] The user checks the procedure manual presented via the terminal.

[1639] Input: Presented instructions and generated program code.

[1640] Data processing: The user makes corrections and sends the correction instructions to the server via their device. The server reuses the generative AI model and regenerates the program code.

[1641] Output: Updated program code and instructions.

[1642] Specific operation: When the user instructs "This step is unnecessary, so please delete it," the server generates a new procedure manual and program based on the instruction.

[1643] Step 4:

[1644] Optimization with machine learning models

[1645] The terminal continuously records the user's operation patterns and transmits them to the server.

[1646] Input: Continuously recorded operational data.

[1647] Data processing: Using machine learning models (e.g., TensorFlow) to learn operational patterns.

[1648] Output: A recommendation of the best automation process for the user.

[1649] What it does: It collects data over a long period of time and then the server suggests to the user, "We've optimized it so that you can perform all operations with just one click."

[1650] Step 5:

[1651] Emotion recognition by emotion engine

[1652] The device uses an emotion engine (e.g., Affectiva SDK) to recognize the user's emotional state in real time.

[1653] Input: User facial and voice data collected through camera and microphone.

[1654] Data processing: The emotion engine analyzes facial expressions and voice to determine the emotional state.

[1655] Output: The user's real-time emotional state.

[1656] Specific operation: If the user shows signs of fatigue during operation, the emotion engine will recognize the state as "fatigue."

[1657] Step 6:

[1658] Emotion-based process adjustment

[1659] The server adjusts the automation process based on the emotion data received from the emotion engine.

[1660] Input: Emotional state data from the emotion engine.

[1661] Data processing: Adjusting automated processes, simplifying steps or suggesting breaks where necessary.

[1662] Output: A coordinated automated process.

[1663] Specific operation: The server suggests, "Would you like to take a break?" and presents instructions to simplify the operation procedure.

[1664] Step 7:

[1665] Voice recognition and operation execution

[1666] The user issues a voice command, which the terminal recognizes.

[1667] Input: Voice command.

[1668] Data processing: The voice is analyzed using a speech recognition tool (e.g., Google Cloud Speech-to-Text API) and sent to a server, which then integrates the instructions into an automated program and returns instructions for execution.

[1669] Output: Execution of automated operations based on voice commands.

[1670] Specific operation: When a user commands, "Update and send the Excel file," the device analyzes the voice and generates an execution command on the server, after which the Excel file is automatically updated and an email is sent.

[1671] Step 8:

[1672] Operation feedback

[1673] The terminal provides the user with real-time feedback on the results of the operation.

[1674] Input: The result of running an automated program.

[1675] Data processing: Analyze the execution results and provide feedback to the user.

[1676] Output: Feedback information.

[1677] Specific operation: When the user commands, "Check if the operation was successful," the device displays the execution results and gives feedback that "All operations were successful."

[1678] (Application example 2)

[1679] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1680] In modern self-driving vehicles, automation of driver operations and voice commands, and environmental adjustments based on real-time emotion recognition have not yet been fully realized. Therefore, reducing the burden on the driver and improving safety are issues. In addition, the generation of automated programs based on the analysis of operation data and the interface for modifying them are not yet fully developed, so an efficient automated system is required.

[1681] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1682] In this invention, the server includes means for understanding user operations using generative artificial intelligence and generating a program for automating the operations, means for using a machine learning model to learn the user's work patterns and design an optimal automation process, voice recognition means for understanding the user's voice commands and executing automated operations based on the voice commands, means for recording, analyzing, and automating the driver's operations and voice commands, and means for recognizing the driver's emotional state in real time and adjusting the in-vehicle environment and navigation based on that state. This makes it possible to efficiently automate the driver's operations and further adjust the in-vehicle environment and navigation based on the driver's emotional state.

[1683] "Generative AI" is an AI technology that understands user operations and generates programs to automate those operations.

[1684] A "machine learning model" is an algorithm or method for learning user work patterns and designing optimal automation processes.

[1685] "Voice recognition means" refers to technology for understanding a user's voice commands and performing automated operations based on the voice commands.

[1686] The "operation recording means" is a function for recording user operations and voice commands, analyzing them, and automating them.

[1687] "Emotion recognition means" is a technology that recognizes the driver's emotional state in real time and adjusts the in-car environment and navigation based on that state.

[1688] An "autonomous vehicle" is a vehicle that drives autonomously without the need for manual operation by a driver.

[1689] The "user interface" refers to a screen or input means that allows the user to modify the generated program code and procedure manual.

[1690] This invention relates to a system that records, analyzes, and automates driver operations and voice commands of an autonomous vehicle. This system has a function of supporting comfortable driving by the driver using generative artificial intelligence, machine learning models, voice recognition means, and emotion recognition means. Detailed embodiments of the system are described below.

[1691] Overall system configuration

[1692] The system mainly consists of an in-vehicle device, a server, and a driver. The in-vehicle device records the driver's operations and voice commands and collects data for emotion recognition. The server hosts generative artificial intelligence and machine learning models, analyzes operation data, and generates automated programs. The driver interacts with the system via an interface and is the entity that performs driving operations.

[1693] System Program

[1694] Operation recording means

[1695] The in-vehicle device records the driver's actions and voice commands in real time, including steering, pedal operation, touchscreen operation, etc. It also uses cameras and sensors to collect the driver's facial expressions and voice.

[1696] Data transmission and analysis

[1697] The vehicle-mounted device sends the recorded operation data to a server, which then inputs the received data into a generative artificial intelligence system, analyzes it, and generates an automation program. This uses machine learning libraries such as TensorFlow and PyTorch.

[1698] Automated Program Generation and Emotion Recognition

[1699] The server generates the optimal automation program based on the operation data. It also uses technologies such as OpenCV to analyze data acquired from cameras and microphones and recognize the driver's emotional state. Based on this emotional state, the automation program and navigation are adjusted.

[1700] Voice recognition and operation execution

[1701] The driver can input voice commands into the vehicle's in-vehicle device, and the server will interpret the voice commands through speech recognition means and perform the corresponding operations, using the Google Speech-to-Text API.

[1702] feedback

[1703] The in-vehicle device provides real-time feedback to the driver on the results of the maneuver, allowing the driver to issue additional voice commands or corrective actions if necessary.

[1704] Specific examples

[1705] For example, if a driver issues the voice command "Go home," the system will:

[1706] 1. Voice command recognition:

[1707] Driver: "Going home."

[1708] In-vehicle device: Google Speech-to-Text converts voice commands into text

[1709] 2. Navigation adjustment:

[1710] Server: Analyzes the text data and generates a route to home

[1711] Emotional state analysis: if the driver is tired, add optimal rest stops to the route

[1712] 3. Feedback:

[1713] In-vehicle device: Provides voice feedback to the driver on route guidance

[1714] Example prompt sentence:

[1715] User: I want to go home

[1716] System: Searching for a route to your home. Please wait.

[1717] System (feedback): Your route is planned. It looks like you might need a break along the way, so we've added appropriate stops. Please resume driving.

[1718] In this way, the system effectively automates driver operations and also adjusts the in-car environment and navigation according to the driver's emotional state, providing a more comfortable and safer driving experience.

[1719] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1720] Step 1:

[1721] Recording of operation and emotional data

[1722] Subject: Terminal

[1723] The terminal (vehicle-mounted device) records the driver's operations and voice commands in real time. The terminal also uses cameras and sensors to collect the driver's facial expressions and voice. Input data includes steering wheel operations, pedal operations, touchscreen operations, facial expressions, and voice. This data is temporarily stored locally and prepared for real-time analysis as needed.

[1724] Step 2:

[1725] Data transmission and analysis

[1726] Subject: Terminal

[1727] The device sends the recorded operation data and emotion data to the server. The input data includes the operation log and emotion data collected in step 1. The server analyzes the received data and generates an automation program using generative artificial intelligence (e.g., TensorFlow, PyTorch). Data analysis includes splitting time-series data and feature extraction. The output after analysis is the initial script for the automation program.

[1728] Step 3:

[1729] Generating automation programs

[1730] Subject: Server

[1731] The server uses generative artificial intelligence to generate an automation program based on the analytical data. The analytical data obtained in step 2 is used as input. The generative AI model generates program code, creating operating procedures and scripts during the generation process. The output is program code containing automated operating procedures.

[1732] Step 4:

[1733] Emotion recognition and process regulation

[1734] Subject: Server

[1735] The server uses emotion recognition means (e.g., OpenCV) to recognize the driver's emotional state from the collected facial and voice data. The emotional data collected in steps 1 and 2 is used as input. Based on the results of the emotional state analysis, the automation program and navigation plan are adjusted. The output is an automated program adjusted according to the emotional state.

[1736] Step 5:

[1737] Entering and recognizing voice commands

[1738] Subject: User

[1739] The user (driver) inputs voice commands to the vehicle's onboard device. The input data is the voice command. The server uses a voice recognition method (e.g., Google Speech-to-Text) to convert the voice command into text data. The text data is then analyzed and integrated into the automation program. The output is an operation instruction based on the analyzed voice command.

[1740] Step 6:

[1741] Running an automation program

[1742] Subject: Terminal

[1743] The device executes the automation program received from the server. The input data includes the adjusted automation program and the analysis results of the voice commands. The device automatically executes the operation procedures, performing navigation, adjusting the in-car environment, etc. The output is the execution result of the automated operation.

[1744] Step 7:

[1745] Providing Feedback

[1746] Subject: Terminal

[1747] The terminal provides real-time feedback on the results of the operation to the user. The input data are the execution results and, if necessary, additional instructions from the user. The terminal analyzes this data and determines the next operation steps or necessary adjustments. The output is a report of the operation results to the user and a suggestion for the next operation step.

[1748] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1749] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1750] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1751] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1752] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1753] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1754] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1755] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1756] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1757] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1758] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1759] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1760] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1761] 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.

[1762] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1763] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1764] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1765] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1766] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1767] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1768] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1769] The following is further disclosed regarding the above embodiment.

[1770] (Claim 1)

[1771] means for understanding a user's computer operation using generative artificial intelligence and generating a program for automating said operation;

[1772] A means for using a machine learning model to learn user work patterns and design an optimal automation process;

[1773] a voice recognition means for understanding a user's voice commands and performing automated operations based on the voice commands;

[1774] A system including:

[1775] (Claim 2)

[1776] 2. The system according to claim 1, further comprising means for recording a user's computer operations and presenting to the user a program code generated based on the recorded operations.

[1777] (Claim 3)

[1778] 10. The system of claim 1, further comprising means for providing an interface for a user to modify the generated program code and instructions.

[1779] "Example 1"

[1780] (Claim 1)

[1781] means for understanding a user's computer operation using generative artificial intelligence and generating a program for automating said operation;

[1782] A means for using a machine learning model to learn user work patterns and design an optimal automation process;

[1783] a voice recognition means for understanding a user's voice commands and performing automated operations based on the voice commands;

[1784] means for recording a user's computer operations in real time and transmitting the records to a server;

[1785] a means for presenting the generated program code to a user as a procedure manual and providing an interface for the user to confirm and modify the procedure manual;

[1786] A system including:

[1787] (Claim 2)

[1788] 2. The system according to claim 1, further comprising means for recording a user's computer operations and presenting to the user a program code generated based on the recorded operations.

[1789] (Claim 3)

[1790] 10. The system of claim 1, further comprising means for providing an interface for a user to modify the generated program code and instructions.

[1791] "Application Example 1"

[1792] (Claim 1)

[1793] A means for understanding a user's operation using generative artificial intelligence and generating a program for automating the operation;

[1794] A means for using a machine learning model to learn user work patterns and design an optimal automation process;

[1795] a voice recognition means for understanding a user's voice commands and performing automated operations based on the voice commands;

[1796] A means for recording an operation record on a terminal and transmitting the record to a server;

[1797] means for presenting the generated program code and instructions to a user;

[1798] A means to continuously learn operation history and suggest optimal operations,

[1799] A means for performing an operation based on speech recognition and providing feedback on the result;

[1800] A system including:

[1801] (Claim 2)

[1802] 2. The system according to claim 1, further comprising means for optimizing the operation of the industrial robot using the user's operation record data.

[1803] (Claim 3)

[1804] 2. The system according to claim 1, further comprising means for continuously recording the operation history of the industrial robot and providing a voice recognition interface for a user to instruct the robot operation through voice commands.

[1805] "Example 2: Combining Emotion Engines"

[1806] (Claim 1)

[1807] means for understanding a user's computer operation using generative artificial intelligence and generating a program for automating said operation;

[1808] A means for using a machine learning model to learn user work patterns and design an optimal automation process;

[1809] a voice recognition means for understanding a user's voice commands and performing automated operations based on the voice commands;

[1810] means for recognizing the emotional state of a user in real time and adjusting the automated process based on the emotional state;

[1811] means for recording a user's computer operations and presenting to the user a program code and a procedure manual generated based on the recorded operation data;

[1812] A system including:

[1813] (Claim 2)

[1814] 10. The system of claim 1, further comprising means for using an emotion engine to collect and analyze the user's emotional state through a camera and a microphone.

[1815] (Claim 3)

[1816] 2. The system according to claim 1, further comprising: means for providing an interface for a user to modify the generated program code and procedure manual; and means for regenerating the automation program based on the modification instructions.

[1817] "Application example 2 when combining emotion engines"

[1818] (Claim 1)

[1819] A means for understanding a user's operation using generative artificial intelligence and generating a program for automating the operation;

[1820] A means for using a machine learning model to learn user work patterns and design an optimal automation process;

[1821] a voice recognition means for understanding a user's voice commands and performing automated operations based on the voice commands;

[1822] A means to record, analyze, and automate driver operations and voice commands, and

[1823] A means of recognizing the driver's emotional state in real time and adjusting the in-car environment and navigation based on that state; and

[1824] A system including:

[1825] (Claim 2)

[1826] 2. The system according to claim 1, further comprising means for recording a user's computer operations and presenting to the user a program code generated based on the recorded operations.

[1827] (Claim 3)

[1828] 10. The system of claim 1, further comprising means for providing an interface for a user to modify the generated program code and instructions. [Explanation of symbols]

[1829] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for understanding a user's computer operation using generative artificial intelligence and generating a program for automating said operation; A means for using a machine learning model to learn user work patterns and design an optimal automation process; a voice recognition means for understanding a user's voice commands and performing automated operations based on the voice commands; A system including:

2. 2. The system according to claim 1, further comprising means for recording a user's computer operations and presenting to the user a program code generated based on the recorded operations.

3. 2. The system of claim 1, further comprising means for providing an interface for a user to modify the generated program code and procedures.

Images