system

Abstract

Provide a system. 【Solution means】 Means for acquiring user operation information, Means for analyzing the acquired operation information and converting it into text information, Means for learning the user's operation pattern based on the converted text information, Means for automating work using the learned operation pattern, Means for acquiring and analyzing voice input information, Means for performing an automated process based on the analyzed voice information, Means for generating feedback information for the user, A system including.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Many modern operations require complex operations that require expertise and a series of tasks across different applications, and it is difficult to automate them efficiently. Conventional automation tools are limited to specific processes or applications, and there is a problem that it is difficult to learn and automate different operation patterns for each user. In addition, since the mechanism for effectively reflecting voice commands in business automation is insufficient, improvement of user convenience and further efficiency are required.

Means for Solving the Problems

[0005] This invention provides means for acquiring user operation information, analyzing it, and converting it into text information. Furthermore, it provides means for learning user operation patterns based on the converted information and automating tasks using the results. It also provides means for acquiring and analyzing voice input information to execute automated processing based on user voice commands. By utilizing both operation patterns and voice commands, it achieves automation and optimization, generates feedback information for the user, and improves work efficiency.

[0006] "User operation information" refers to data that shows a series of operations and procedures performed by a user on a computer.

[0007] "Means of acquisition" refers to methods or devices for sensing specific information and collecting it as data.

[0008] "Means of analysis" refers to the techniques and methods used to analyze acquired data and information and convert them into a specific format or meaning.

[0009] "Text information" refers to data in the form of characters or sentences.

[0010] An "operation pattern" refers to a sequence or tendency of operations that a user repeatedly performs when carrying out a particular task or process.

[0011] "Means of learning" refer to methods and mechanisms for identifying regularities and patterns from data and information, and for memorizing and applying them.

[0012] "Means of automation" refer to methods and technologies that reduce human intervention and allow machines or software to autonomously perform specific processes.

[0013] "Voice input information" refers to commands and data entered via voice.

[0014] "Feedback information" refers to the information and reactions provided by a system or device to a user.

[0015] "Optimization proposal" means that the system proposes an efficient process or method according to specific goals and conditions.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention is a system that automates and streamlines operations performed by users on a computer. The main components of the system consist of a terminal, a server, and related software modules.

[0038] The terminal is a computer that the user typically operates and is connected to a network. The terminal is equipped with software to capture user actions in real time. This software acquires user action information such as mouse clicks, keystrokes, and screen changes, and stores this information as data.

[0039] The server is responsible for receiving and analyzing user interaction information sent from terminals. The server is equipped with multimodal AI, which can convert a series of user actions into text information. Specifically, it records the user's actions, such as aggregating data using spreadsheet software, as text and programs those steps. This converted text information is stored in a database and used for further analysis and automation.

[0040] User operation patterns are learned by a machine learning model running on the server. This model recognizes sequences of operations that users frequently perform and uses those patterns to build automated processes. For example, it can learn the steps a user takes to create a weekly report and automatically generate that report.

[0041] Furthermore, this system also features voice recognition capabilities, allowing users to give instructions to their devices via a microphone. Voice input is sent to a server and analyzed by a voice recognition AI. Based on this analysis, the server executes the user's intended actions. For example, if a user gives a voice command such as "Show me next week's schedule," the schedule management software will automatically operate based on that instruction.

[0042] In this way, the system will be implemented to streamline users' work and provide an environment where they can focus on creative activities by tracing and learning user actions and automating operations through voice commands as needed.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The terminal launches software to capture user actions. When the user performs any action on the computer, the terminal records the details of that action (e.g., click location and input content) in real time.

[0046] Step 2:

[0047] The terminal transmits recorded operation information to a server via the internet. This makes the user's actions available on the server.

[0048] Step 3:

[0049] The server inputs the operation information received from the terminal into the multimodal AI module and converts the operation into text data. This text records the specific steps the user took in language.

[0050] Step 4:

[0051] The server inputs text data of user operations into a machine learning model, which analyzes and learns from the user's operation patterns. This model captures regularities when similar operations are repeated and generates an optimal automated process.

[0052] Step 5:

[0053] The user inputs voice commands into the terminal via the microphone. The terminal then sends these voice commands to the server as digital audio data.

[0054] Step 6:

[0055] The server uses speech recognition AI to analyze the audio data and convert it into text commands. Based on the converted text commands, it then invokes the necessary automation scripts.

[0056] Step 7:

[0057] The server executes automated processes based on the converted text instructions and learned operation patterns. This allows the user's intended task to be performed automatically.

[0058] Step 8:

[0059] The server provides the user with feedback on the execution results and processing details. If requested by the user, it will provide more detailed explanations and suggestions for the next action.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] In many modern work environments, users spend a significant amount of time on repetitive operations and routine tasks. The inefficiency of these tasks hinders productivity improvements and poses a major challenge, especially in environments where automation is not widespread. Furthermore, there is a lack of established methods for reliably interpreting and executing voice commands when users wish to guide them through operations. In addition, there is a lack of mechanisms to provide appropriate feedback to users, and improvements to intuitive operation are needed.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for acquiring user operation information, means for analyzing the acquired operation information and converting it into text information, and means for learning the user's operation patterns based on the converted text information. This enables efficient automation of repetitive operations and interpretation and execution of instructions using speech recognition technology. Furthermore, it enables the provision of a more intuitive and user-friendly interface through user feedback.

[0065] "User operation information" refers to the history and data of operations performed by a user on a computer or device, such as mouse clicks, keystrokes, and screen changes.

[0066] "Text information" refers to information written in strings, generated as a result of analyzing user interaction data.

[0067] An "operation pattern" refers to a series of actions that are recognized as a pattern, which are similar operations or procedures that a user repeatedly performs.

[0068] "Automation" is the process of enabling a system to automatically perform operations or procedures that were previously done manually by a user.

[0069] "Voice input information" refers to information about voice commands uttered by the user through a device such as a microphone.

[0070] "Feedback information" refers to information about the results and status of operations that a system returns to the user.

[0071] This invention is a system that automates user operations and improves operational efficiency. The system consists of a terminal, a server, and associated software modules.

[0072] A terminal is a computer device used by users on a daily basis and is connected to a network. The terminal is equipped with software that captures user actions in real time. This software acquires and stores operational data such as mouse clicks, keystrokes, and screen changes.

[0073] The server is responsible for receiving and analyzing user interaction information sent from the terminal. The server implements multimodal AI, including a generative AI model, which converts the received data into text. This converted data is stored in a database and used for learning interaction patterns and automating processes.

[0074] User operation patterns are learned by machine learning algorithms on the server. These algorithms can identify frequently performed user actions and generate suggestions for automating those sequences of actions. For example, it can learn the procedure for creating weekly reports and automatically generate similar reports.

[0075] Furthermore, users can give voice commands via the device's microphone. The voice input is sent to the server, where speech recognition technology analyzes the commands. Based on the analysis, the server automatically performs operations according to the user's intent. For example, if the user says, "Show me next week's schedule," the server will display the relevant information via the schedule management software.

[0076] A concrete example is the weekly Friday routine task of "retrieving data from a specified range in a spreadsheet, adding a cover page, and saving it as a PDF." An example of a prompt message used when automating this operation would be, "Extract data from the specified range in the spreadsheet, format it, and save it in PDF format."

[0077] In this way, this system supports business operations by efficiently tracing user actions and automating processes.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The device monitors user actions and captures operational information such as mouse clicks, keystrokes, and screen changes in real time. It receives user interface input and saves operation logs as digital data as output. A specific example of its operation is recording information when a user clicks a cell in a spreadsheet and enters a number.

[0081] Step 2:

[0082] The terminal sends the captured operation data to the server. In this step, operation log data is used as input, and data is transferred to the server via the network as output. Specifically, the terminal packets the data "'100' was entered into cell A1" and sends it.

[0083] Step 3:

[0084] The server analyzes the received operation data and uses a generation AI model to convert the operation details into text information. Here, it takes received data as input and generates operation instructions in text format as output. Specifically, the server converts a sum calculation operation in a spreadsheet into text, such as "Calculate the sum of cells A1 to A10."

[0085] Step 4:

[0086] The server stores the converted text information in a database and learns user operation patterns using a machine learning algorithm. It uses the converted operation history as input and records each user's operation patterns in the database as output. Specifically, the server learns and records the "procedures for data aggregation work that is usually performed on Mondays."

[0087] Step 5:

[0088] The user provides voice commands via the device's microphone. The server receives the voice data and interprets the commands using voice recognition AI. In this step, the input is voice data, and the output is the analyzed command content. For example, if the user says, "Show me next week's schedule," the command content will be expressed as text.

[0089] Step 6:

[0090] The server executes automated processes based on analyzed operation information and voice commands. Using the analysis results as input, it generates a state where the system automatically performs the operation intended by the user as output. Specifically, the server operates scheduling software and displays next week's schedule on the screen.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] Improving work efficiency is crucial in complex and diverse operations such as those in logistics centers. However, current systems lack sufficient development of efficiency methods utilizing eye-tracking information, and an environment where workers can give instructions without using their hands is not in place. As a result, logistics operations become complicated, and working hours increase.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes means for acquiring user operation information, means for acquiring and analyzing voice input information, and means for acquiring user gaze information in real time. This enables workers to perform their tasks efficiently using gaze and voice.

[0096] "User operation information" refers to input data generated when a user operates a computing device, and includes information such as keystrokes, mouse clicks, and screen changes.

[0097] "Text information" refers to information obtained by analyzing user interaction data and representing it as formatted string data.

[0098] "Operation patterns" refer to data that identifies the regularity and trends in a series of operations that a user repeatedly performs.

[0099] "Voice input information" refers to voice data generated when a user gives instructions to a device using their voice.

[0100] "Eye-gaze information" refers to data about visual focus and direction of gaze obtained by monitoring the user's eye movements.

[0101] "Real-time" refers to a state in which user actions and inputs are processed immediately.

[0102] "Feedback information" refers to data that includes responses and instructions that a system returns in response to user actions or inputs.

[0103] "Automated processing" refers to actions that automatically perform tasks or operations without human intervention, based on predefined rules or learned patterns.

[0104] "Optimization suggestions" refer to information that analyzes a user's past actions and input data to suggest more efficient procedures and methods.

[0105] A "network" is a communication line or system used to transmit information between multiple computing devices.

[0106] This invention is a system that automates user operations with the aim of improving the efficiency of operations in logistics centers and the like. This system mainly consists of a server, terminals, and an interface device (e.g., smart glasses) for acquiring eye-tracking and voice data.

[0107] The server receives user operation information, voice input information, and eye-tracking information, and analyzes them in real time. Operation information is captured on the terminal and converted into text information. Natural Language Processing (NLP) technology is used for this conversion. Voice input information is analyzed through speech recognition software and converted into the necessary instruction data. Eye-tracking information is acquired in real time using eye-tracking technology and transmitted to the server.

[0108] On the server, user operation patterns and eye movements are learned, enabling automated processing based on this data. In particular, machine learning algorithms recognize operation patterns and propose more efficient workflows. This reduces manual work for users, minimizes errors, and allows tasks to proceed quickly. Generative AI models are used to generate decisions and feedback during automation, providing users with appropriate information.

[0109] As a concrete example, a worker can visually confirm the products on the shelves and give a voice command such as "Show the next shipping list," at which point the server automatically issues a shipping instruction, and the next action is displayed on smart glasses. This allows the worker to continue working efficiently without using their hands.

[0110] An example of a prompt message would be: "Generate an application that streamlines logistics operations using human eye movement and voice commands. Include a flow that sends gaze data and voice information to a server and automates the processing."

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The server receives user action information sent from the terminal. Keystrokes, mouse clicks, and screen change information are provided as input. Natural Language Processing (NLP) technology is used to convert this data into text information, and the formatted text data is output.

[0114] Step 2:

[0115] The server receives voice input information in real time and analyzes it using speech recognition software. Voice data is provided as input and converted into text instruction data. The output is a textual representation of the analyzed voice instruction. The server uses a generative AI model to understand the user's intent and generate appropriate instructions.

[0116] Step 3:

[0117] The device acquires gaze information in real time via smart glasses and transmits it to the server. The input is the user's gaze tracking data. The server analyzes the gaze information and uses computer vision technology to recognize fixation on specific objects. The output is the identification of objects based on the user's gaze.

[0118] Step 4:

[0119] The server optimizes the workflow by applying machine learning algorithms based on operation patterns, voice input information, and eye-tracking data. Inputs consist of text data and eye-tracking data generated in the previous stage. Outputs include instructions to be executed and optimized work procedures.

[0120] Step 5:

[0121] The user receives feedback information from the server and follows instructions displayed via smart glasses. The output is a real-time work guide displayed on the smart glasses via the network. Cloud computing technology is used to provide this feedback in a timely manner.

[0122] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0123] This invention is a system that acquires not only user operation information but also emotional information to optimize business automation and feedback. This system consists of a terminal, a server, and an emotional engine.

[0124] The terminal is a computer used for the user's normal tasks, capturing operation information and acquiring emotional states. When the user operates the PC, the terminal records that operation information (e.g., clicks, keystrokes) in real time. In addition, the built-in emotion engine recognizes the user's emotional state based on voice and video data. This information is transmitted to the server via the network.

[0125] The server analyzes operation information and sentiment information based on data sent from the terminal. First, operation information is converted to text using multimodal AI, and the server learns the user's operation patterns based on this text data. For example, it evaluates the user's operation of creating a monthly report and explores ways to make it more efficient. This learning makes it possible to automate repetitive tasks.

[0126] Meanwhile, the emotion engine analyzes the emotional information acquired by the user to determine their emotional state during the interaction and reflects the results back to the server. The analyzed emotional information indicates various emotional states, such as whether the user is stressed or satisfied. This information can be used to automate processes and personalize feedback.

[0127] User feedback is based on information generated by the server. For example, if a user shows high levels of stress, feedback will be provided that offers more concise explanations and support. Furthermore, the application interface is adjusted based on emotional information, and adaptive support is provided according to the user's emotional state.

[0128] Thus, the present invention provides a more human-friendly system environment by performing automation and feedback that takes user emotional information into account. This system is expected to not only improve user work efficiency but also significantly increase user satisfaction.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The user begins working on the terminal, and the terminal collects user activity information in real time. The terminal detects mouse clicks and keyboard inputs and saves these events as time-series data.

[0132] Step 2:

[0133] The device uses an emotion engine to acquire emotional information through the user's face and voice. By analyzing the user's facial expressions and voice tone, it identifies their current emotional state.

[0134] Step 3:

[0135] The collected operational and emotional information is transmitted to the server via the network. The terminal verifies that the data has been transmitted accurately.

[0136] Step 4:

[0137] The server passes the received operation information to the multimodal AI, which converts it into text information. The server analyzes this text information to recognize and learn the user's operation patterns.

[0138] Step 5:

[0139] The server processes emotional information and evaluates the user's stress level and satisfaction. It uses an emotional evaluation algorithm to obtain a quantified or categorized emotional state.

[0140] Step 6:

[0141] The server combines learned operation patterns with evaluated emotional states to design an automated task process. The server creates the automated procedure and saves it in a format that can be executed the next time the user interacts with the system.

[0142] Step 7:

[0143] The next time the user performs a similar action, the server executes an automated procedure. It considers emotional information and adjusts the user interface as needed to facilitate smooth operation.

[0144] Step 8:

[0145] The server provides users with feedback based on their actions and emotions. For example, if the server determines that a user is experiencing a lot of stress, it will suggest simplifying the operation or improving the explanation.

[0146] (Example 2)

[0147] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0148] In today's work environment, there is a demand for work efficiency and feedback that takes into account not only user operation information but also their emotional state. However, conventional systems are insufficient in providing automation and feedback that takes such complex information into account, making it difficult to improve user work efficiency and satisfaction.

[0149] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0150] In this invention, the server includes means for acquiring user operation information, means for analyzing the operation information and converting it into text information, and means for acquiring and analyzing the user's emotional state using audio data and video data. This makes it possible to learn the user's operation patterns and provide adaptive feedback and automation based on emotional information.

[0151] "User operation information" refers to data about user actions such as clicks and keystrokes when using a computer.

[0152] "Text information" refers to data in string format that is obtained by converting the analyzed user operation information.

[0153] An "operation pattern" is a characteristic behavior that indicates the continuity or regularity of a user's specific operations.

[0154] "Automation" refers to the process of automatically executing tasks using learned operation patterns through a program.

[0155] "Voice data" refers to data that electronically records the voice spoken by the user.

[0156] "Video data" refers to data that visually records the user's facial expressions and movements.

[0157] "Emotional state" refers to information about emotions such as joy, sadness, and stress, which represent the user's psychological state.

[0158] "Feedback" refers to advice and information provided based on the user's actions and emotional state.

[0159] This invention is a system that optimizes the automation and feedback of tasks based on user operation information and emotional information. This system consists of a terminal, a server, and an engine equipped with emotional analysis capabilities.

[0160] First, the user uses the terminal to perform their daily tasks. Capture software is installed on the terminal to acquire operation information, recording digital inputs such as clicks and keystrokes. Simultaneously, the terminal is equipped with hardware for acquiring audio and video information, such as a camera and microphone, and audio and video data are collected using this. Based on the collected data, the sentiment analysis engine identifies the user's emotional state in real time. Common libraries and modules, such as image processing libraries and speech recognition libraries, are used for this sentiment analysis.

[0161] Next, the information collected by the terminal is transmitted to the server via the network. The server converts the received operation information into text data using multimodal AI and learns the user's operation patterns from it. This learning is performed by a natural language processing engine, and foundational data is created for automating certain repetitive tasks. Specifically, this includes templating reports that users repeatedly create and automatically applying formatting.

[0162] The server also analyzes emotional information and evaluates the user's psychological state. Based on criteria such as stress level and satisfaction, personalized feedback is generated. The feedback is sent to the device as a pop-up notification to help the user work more efficiently. For example, if a high level of stress is detected, the device may suggest taking a break from work or recommend refreshments.

[0163] A concrete example of a prompt message would be: "Analyze the user's operation patterns while they are creating the report and suggest ways to automate the work process. Also, analyze their emotional state and provide appropriate feedback if the user is experiencing stress."

[0164] In this way, this system can improve user productivity and satisfaction.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] Users perform their tasks using a terminal. The terminal acquires user operation information. This input includes action information such as clicks and keystrokes. The terminal records this input in real time and stores it as an operation log. Specifically, it performs keyboard input capture and mouse event monitoring.

[0168] Step 2:

[0169] The device uses a microphone and camera to acquire audio and video data as input. Based on this data, the built-in emotion analysis engine processes the data. Specifically, it analyzes the tone of the voice and the facial expressions in the images to identify the user's emotional state. This processing outputs data indicating the emotional state.

[0170] Step 3:

[0171] The device collects operational and emotional information and transmits it to a server via the network. Security is considered during this transmission, and encryption protocols are used. As a result, real-time operational and emotional data is transmitted to the server.

[0172] Step 4:

[0173] The server analyzes the received operation information and converts it into text data. It uses natural language processing techniques to analyze the operation log as input and identify user operation patterns. Based on this analysis, the operation patterns are output in text format. Specifically, certain operation sequences are extracted as patterns.

[0174] Step 5:

[0175] The server analyzes emotional information and evaluates the user's emotional state. This input uses an emotional analysis model to assess stress and satisfaction levels. The analysis results output emotional evaluation data. This evaluation serves as foundational data for reducing the user's psychological burden.

[0176] Step 6:

[0177] The server processes the automation of tasks and optimizes feedback based on the analyzed operation patterns and emotional information. For example, it generates scripts to automate repetitive operations and creates appropriate feedback based on the emotional state. The output of this process is the automated operation process and personalized feedback information.

[0178] Step 7:

[0179] The server sends the generated feedback information to the terminal. The terminal provides this information to the user at an appropriate time. Specific actions include displaying an alert as a pop-up notification on the user's screen and providing suggestions for improving work methods through a reminder function.

[0180] (Application Example 2)

[0181] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0182] In modern retail store customer service, staff are required to quickly and accurately understand customers' emotional states and respond accordingly to enhance customer satisfaction. However, traditional systems struggle to properly acquire emotional information and provide automated feedback based on it, often relying on subjective judgments by staff. This results in inconsistent service quality and limits the potential for improving the customer experience.

[0183] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0184] In this invention, the server includes means for acquiring user operation information, means for acquiring video and audio information to recognize emotional states, and means for optimizing automated processing and feedback based on the estimated emotional state. This enables staff to provide appropriate service in response to customer emotions and improve the customer experience.

[0185] "Means for acquiring user operation information" refers to a device or mechanism for recording operations performed by a user, such as acquiring operation data like clicks, taps, and key inputs.

[0186] "Means for analyzing operation information and converting it into text information" refers to the function of a device or software that analyzes acquired user operation information and converts its contents into a string of characters.

[0187] "Means for learning operation patterns" refers to a device or program that learns user behavior patterns based on converted text information and predicts future operations.

[0188] "Means of automating work" refers to the function of a device or software that uses learned user operation patterns to mechanically perform repetitive tasks.

[0189] "Means for acquiring video and audio information to recognize emotional states" refers to a device or mechanism that collects video and audio data using cameras, microphones, etc., in order to estimate emotions from the user's facial expressions and voice.

[0190] "Means for estimating emotional state" refers to software functions that analyze acquired video and audio information to determine the user's emotional state.

[0191] "Means for optimizing automated processing and feedback" refers to the function of a device or software for adjusting and optimizing automated processing and user feedback in accordance with the estimated emotional state.

[0192] "Means for generating emotion-based feedback information" refers to a function that generates information related to the user's emotional state and presents it to the user or the system.

[0193] The system for implementing this invention collects and analyzes user emotional state and interaction information to improve customer service in physical stores, and optimizes feedback based on this information. This system mainly consists of smart glasses as a terminal, a server, and an emotion engine.

[0194] A user wearing smart glasses (for example, a store employee) captures a customer's face with a camera and records their voice via a microphone. The emotion engine within the device estimates the user's emotional state in real time based on this video and audio information. This data is transmitted to a server via the network.

[0195] The server analyzes the operation and emotional information sent by the user. This analysis utilizes an emotional analysis engine and multimodal AI, enabling the system to learn the user's operation patterns and estimate their emotional state based on past data. This allows the system to generate appropriate feedback tailored to the customer's emotions and display instructions in real time on the smart glasses.

[0196] As a concrete example of this system, consider a case where staff at a flower shop use smart glasses. If a customer is looking for a specific flower but shows a dissatisfied expression, feedback will be displayed on the screen based on the analysis of their emotional state, stating, "It would be desirable to respond to this customer in a more cheerful tone and suggest a new spring arrangement."

[0197] By using a generative AI model, it is possible to provide prompts that include advice on customer service styles. Examples of specific prompts include: "What customer service style would you recommend when a particular customer is expressing dissatisfaction? What services or products should I suggest?"

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The device uses the smart glasses' camera to capture the customer's face within the user's field of view and acquires video data related to the customer's facial expressions. This input includes real-time video data. The output is formatted video data for use in sentiment analysis.

[0201] Step 2:

[0202] The device uses the microphone in the smart glasses to record customer conversations and acquire audio data. This input includes customer audio data, including the surrounding sound environment. The output is audio data converted into a format suitable for speech analysis.

[0203] Step 3:

[0204] The device analyzes acquired video and audio data in real time using its built-in emotion engine to estimate the customer's emotional state. Based on the input data, it analyzes facial expressions and tone of voice, and then estimates the emotion. The output is information about the customer's current emotional state.

[0205] Step 4:

[0206] The terminal transmits the emotional state data obtained as an analysis result to the server via the network. This transmission process includes both emotional information and operational information. The output is the dataset necessary for analysis on the server.

[0207] Step 5:

[0208] The server uses multimodal AI to compare the received data with past customer service patterns and emotional data. This process combines the input emotional state and interaction patterns for data processing. The output is insightful data used to generate feedback.

[0209] Step 6:

[0210] The server uses a generative AI model to generate appropriate feedback information based on the input insight data. This process generates feedback that includes various customer service suggestions. The output is specific feedback information displayed on the terminal.

[0211] Step 7:

[0212] The terminal displays feedback information sent from the server on the smart glasses' screen. This information serves as a guide for the user to take customer service actions that respond to customer emotions in real time. The output is the feedback information displayed on the smart glasses.

[0213] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0214] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0215] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0216] [Second Embodiment]

[0217] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0218] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0219] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0220] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0221] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0222] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0223] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0224] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0225] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0226] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0227] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0228] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0229] This invention is a system that automates and streamlines operations performed by users on a computer. The main components of the system consist of a terminal, a server, and related software modules.

[0230] The terminal is a computer that the user typically operates and is connected to a network. The terminal is equipped with software to capture user actions in real time. This software acquires user action information such as mouse clicks, keystrokes, and screen changes, and stores this information as data.

[0231] The server is responsible for receiving and analyzing user interaction information sent from terminals. The server is equipped with multimodal AI, which can convert a series of user actions into text information. Specifically, it records the user's actions, such as aggregating data using spreadsheet software, as text and programs those steps. This converted text information is stored in a database and used for further analysis and automation.

[0232] User operation patterns are learned by a machine learning model running on the server. This model recognizes sequences of operations that users frequently perform and uses those patterns to build automated processes. For example, it can learn the steps a user takes to create a weekly report and automatically generate that report.

[0233] Furthermore, this system also features voice recognition capabilities, allowing users to give instructions to their devices via a microphone. Voice input is sent to a server and analyzed by a voice recognition AI. Based on this analysis, the server executes the user's intended actions. For example, if a user gives a voice command such as "Show me next week's schedule," the schedule management software will automatically operate based on that instruction.

[0234] In this way, the system will be implemented to streamline users' work and provide an environment where they can focus on creative activities by tracing and learning user actions and automating operations through voice commands as needed.

[0235] The following describes the processing flow.

[0236] Step 1:

[0237] The terminal launches software to capture user actions. When the user performs any action on the computer, the terminal records the details of that action (e.g., click location and input content) in real time.

[0238] Step 2:

[0239] The terminal transmits recorded operation information to a server via the internet. This makes the user's actions available on the server.

[0240] Step 3:

[0241] The server inputs the operation information received from the terminal into the multimodal AI module and converts the operation into text data. This text records the specific steps the user took in language.

[0242] Step 4:

[0243] The server inputs text data of user operations into a machine learning model, which analyzes and learns from the user's operation patterns. This model captures regularities when similar operations are repeated and generates an optimal automated process.

[0244] Step 5:

[0245] The user inputs voice commands into the terminal via the microphone. The terminal then sends these voice commands to the server as digital audio data.

[0246] Step 6:

[0247] The server uses speech recognition AI to analyze the audio data and convert it into text commands. Based on the converted text commands, it then invokes the necessary automation scripts.

[0248] Step 7:

[0249] The server executes automated processes based on the converted text instructions and learned operation patterns. This allows the user's intended task to be performed automatically.

[0250] Step 8:

[0251] The server provides the user with feedback on the execution results and processing details. If requested by the user, it will provide more detailed explanations and suggestions for the next action.

[0252] (Example 1)

[0253] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0254] In many modern work environments, users spend a significant amount of time on repetitive operations and routine tasks. The inefficiency of these tasks hinders productivity improvements and poses a major challenge, especially in environments where automation is not widespread. Furthermore, there is a lack of established methods for reliably interpreting and executing voice commands when users wish to guide them through operations. In addition, there is a lack of mechanisms to provide appropriate feedback to users, and improvements to intuitive operation are needed.

[0255] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0256] In this invention, the server includes means for acquiring user operation information, means for analyzing the acquired operation information and converting it into text information, and means for learning the user's operation patterns based on the converted text information. This enables efficient automation of repetitive operations and interpretation and execution of instructions using speech recognition technology. Furthermore, it enables the provision of a more intuitive and user-friendly interface through user feedback.

[0257] "User operation information" refers to the history and data of operations performed by a user on a computer or device, such as mouse clicks, keystrokes, and screen changes.

[0258] "Text information" refers to information written in strings, generated as a result of analyzing user interaction data.

[0259] An "operation pattern" refers to a series of actions that are recognized as a pattern, which are similar operations or procedures that a user repeatedly performs.

[0260] "Automation" is the process of enabling a system to automatically perform operations or procedures that were previously done manually by a user.

[0261] "Voice input information" refers to information about voice commands uttered by the user through a device such as a microphone.

[0262] "Feedback information" refers to information about the results and status of operations that a system returns to the user.

[0263] This invention is a system that automates user operations and improves operational efficiency. The system consists of a terminal, a server, and associated software modules.

[0264] A terminal is a computer device used by users on a daily basis and is connected to a network. The terminal is equipped with software that captures user actions in real time. This software acquires and stores operational data such as mouse clicks, keystrokes, and screen changes.

[0265] The server is responsible for receiving and analyzing user interaction information sent from the terminal. The server implements multimodal AI, including a generative AI model, which converts the received data into text. This converted data is stored in a database and used for learning interaction patterns and automating processes.

[0266] User operation patterns are learned by machine learning algorithms on the server. These algorithms can identify frequently performed user actions and generate suggestions for automating those sequences of actions. For example, it can learn the procedure for creating weekly reports and automatically generate similar reports.

[0267] Furthermore, users can give voice commands via the device's microphone. The voice input is sent to the server, where speech recognition technology analyzes the commands. Based on the analysis, the server automatically performs operations according to the user's intent. For example, if the user says, "Show me next week's schedule," the server will display the relevant information via the schedule management software.

[0268] A concrete example is the weekly Friday routine task of "retrieving data from a specified range in a spreadsheet, adding a cover page, and saving it as a PDF." An example of a prompt message used when automating this operation would be, "Extract data from the specified range in the spreadsheet, format it, and save it in PDF format."

[0269] In this way, this system supports business operations by efficiently tracing user actions and automating processes.

[0270] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0271] Step 1:

[0272] The device monitors user actions and captures operational information such as mouse clicks, keystrokes, and screen changes in real time. It receives user interface input and saves operation logs as digital data as output. A specific example of its operation is recording information when a user clicks a cell in a spreadsheet and enters a number.

[0273] Step 2:

[0274] The terminal sends the captured operation data to the server. In this step, operation log data is used as input, and data is transferred to the server via the network as output. Specifically, the terminal packets the data "'100' was entered into cell A1" and sends it.

[0275] Step 3:

[0276] The server analyzes the received operation data and uses a generation AI model to convert the operation details into text information. Here, it takes received data as input and generates operation instructions in text format as output. Specifically, the server converts a sum calculation operation in a spreadsheet into text, such as "Calculate the sum of cells A1 to A10."

[0277] Step 4:

[0278] The server stores the converted text information in a database and learns user operation patterns using a machine learning algorithm. It uses the converted operation history as input and records each user's operation patterns in the database as output. Specifically, the server learns and records the "procedures for data aggregation work that is usually performed on Mondays."

[0279] Step 5:

[0280] The user provides voice commands via the device's microphone. The server receives the voice data and interprets the commands using voice recognition AI. In this step, the input is voice data, and the output is the analyzed command content. For example, if the user says, "Show me next week's schedule," the command content will be expressed as text.

[0281] Step 6:

[0282] The server executes automated processing based on the analyzed operation information and voice instructions. Using the analysis result as input, it generates a state where the system automatically performs the operation intended by the user as output. As a specific operation, the server operates the scheduling software and displays the schedule for next week on the screen.

[0283] (Application Example 1)

[0284] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] In complex and diverse operations such as a logistics center, it is very important to improve work efficiency. However, in the current system, efficiency improvement means using line-of-sight information have not been fully developed, and an environment where workers can give instructions without using their hands is not established. For this reason, there is a problem that logistics operations become complicated and working hours increase.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0287] In this invention, the server includes means for acquiring user operation information, means for acquiring and analyzing voice input information, and means for acquiring the user's line-of-sight information in real time. This enables workers to efficiently perform operations using their line of sight and voice.

[0288] "User operation information" is input data generated when a user operates a computing device, and includes information such as keystrokes, mouse clicks, and screen changes.

[0289] "Text information" is information expressed as formatted string data by analyzing user operation information.

[0290] "Operation pattern" is data that identifies the regularity and tendency of a series of operation procedures repeatedly performed by a user.

[0291] "Voice input information" refers to voice data generated when a user gives instructions to a device using their voice.

[0292] "Eye-gaze information" refers to data about visual focus and direction of gaze obtained by monitoring the user's eye movements.

[0293] "Real-time" refers to a state in which user actions and inputs are processed immediately.

[0294] "Feedback information" refers to data that includes responses and instructions that a system returns in response to user actions or inputs.

[0295] "Automated processing" refers to actions that automatically perform tasks or operations without human intervention, based on predefined rules or learned patterns.

[0296] "Optimization suggestions" refer to information that analyzes a user's past actions and input data to suggest more efficient procedures and methods.

[0297] A "network" is a communication line or system used to transmit information between multiple computing devices.

[0298] This invention is a system that automates user operations with the aim of improving the efficiency of operations in logistics centers and the like. This system mainly consists of a server, terminals, and an interface device (e.g., smart glasses) for acquiring eye-tracking and voice data.

[0299] The server receives user operation information, voice input information, and eye-tracking information, and analyzes them in real time. Operation information is captured on the terminal and converted into text information. Natural Language Processing (NLP) technology is used for this conversion. Voice input information is analyzed through speech recognition software and converted into the necessary instruction data. Eye-tracking information is acquired in real time using eye-tracking technology and transmitted to the server.

[0300] On the server, user operation patterns and eye movements are learned, enabling automated processing based on this data. In particular, machine learning algorithms recognize operation patterns and propose more efficient workflows. This reduces manual work for users, minimizes errors, and allows tasks to proceed quickly. Generative AI models are used to generate decisions and feedback during automation, providing users with appropriate information.

[0301] As a concrete example, a worker can visually confirm the products on the shelves and give a voice command such as "Show the next shipping list," at which point the server automatically issues a shipping instruction, and the next action is displayed on smart glasses. This allows the worker to continue working efficiently without using their hands.

[0302] An example of a prompt message would be: "Generate an application that streamlines logistics operations using human eye movement and voice commands. Include a flow that sends gaze data and voice information to a server and automates the processing."

[0303] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0304] Step 1:

[0305] The server receives the user's operation information sent from the terminal. As inputs, keystrokes, mouse clicks, and screen change information are provided. To convert this data into text information, Natural Language Processing (NLP) technology is utilized to output formatted text data.

[0306] Step 2:

[0307] The server receives real-time voice input information and analyzes it using speech recognition software. As input, voice data is provided, and it is converted into text instruction data. The output is the text representation of the analyzed voice instruction. The server uses a generated AI model to understand the user's intention and generate appropriate instructions.

[0308] Step 3:

[0309] The terminal obtains the line-of-sight information in real-time via smart glasses and transmits it to the server. The input is the user's line-of-sight tracking data. The server analyzes the line-of-sight information and uses computer vision technology to recognize fixation on a specific object. The output is the identification of the object by the user's line of sight.

[0310] Step 4:

[0311] Based on the operation pattern, voice input information, and line-of-sight information, the server applies machine learning algorithms to optimize the business process. The inputs are the text data and line-of-sight data generated in the previous stage. The output is the instruction content to be executed and the optimized business procedures.

[0312] Step 5:

[0313] The user receives feedback information from the server and follows instructions displayed via smart glasses. The output is a real-time work guide displayed on the smart glasses via the network. Cloud computing technology is used to provide this feedback in a timely manner.

[0314] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0315] This invention is a system that acquires not only user operation information but also emotional information to optimize business automation and feedback. This system consists of a terminal, a server, and an emotional engine.

[0316] The terminal is a computer used for the user's normal tasks, capturing operation information and acquiring emotional states. When the user operates the PC, the terminal records that operation information (e.g., clicks, keystrokes) in real time. In addition, the built-in emotion engine recognizes the user's emotional state based on voice and video data. This information is transmitted to the server via the network.

[0317] The server analyzes operation information and sentiment information based on data sent from the terminal. First, operation information is converted to text using multimodal AI, and the server learns the user's operation patterns based on this text data. For example, it evaluates the user's operation of creating a monthly report and explores ways to make it more efficient. This learning makes it possible to automate repetitive tasks.

[0318] Meanwhile, the emotion engine analyzes the emotional information acquired by the user to determine their emotional state during the interaction and reflects the results back to the server. The analyzed emotional information indicates various emotional states, such as whether the user is stressed or satisfied. This information can be used to automate processes and personalize feedback.

[0319] User feedback is based on information generated by the server. For example, if a user shows high levels of stress, feedback will be provided that offers more concise explanations and support. Furthermore, the application interface is adjusted based on emotional information, and adaptive support is provided according to the user's emotional state.

[0320] Thus, the present invention provides a more human-friendly system environment by performing automation and feedback that takes user emotional information into account. This system is expected to not only improve user work efficiency but also significantly increase user satisfaction.

[0321] The following describes the processing flow.

[0322] Step 1:

[0323] The user begins working on the terminal, and the terminal collects user activity information in real time. The terminal detects mouse clicks and keyboard inputs and saves these events as time-series data.

[0324] Step 2:

[0325] The device uses an emotion engine to acquire emotional information through the user's face and voice. By analyzing the user's facial expressions and voice tone, it identifies their current emotional state.

[0326] Step 3:

[0327] The collected operational and emotional information is transmitted to the server via the network. The terminal verifies that the data has been transmitted accurately.

[0328] Step 4:

[0329] The server passes the received operation information to the multimodal AI, which converts it into text information. The server analyzes this text information to recognize and learn the user's operation patterns.

[0330] Step 5:

[0331] The server processes emotional information and evaluates the user's stress level and satisfaction. It uses an emotional evaluation algorithm to obtain a quantified or categorized emotional state.

[0332] Step 6:

[0333] The server combines learned operation patterns with evaluated emotional states to design an automated task process. The server creates the automated procedure and saves it in a format that can be executed the next time the user interacts with the system.

[0334] Step 7:

[0335] The next time the user performs a similar action, the server executes an automated procedure. It considers emotional information and adjusts the user interface as needed to facilitate smooth operation.

[0336] Step 8:

[0337] The server provides users with feedback based on their actions and emotions. For example, if the server determines that a user is experiencing a lot of stress, it will suggest simplifying the operation or improving the explanation.

[0338] (Example 2)

[0339] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0340] In today's work environment, there is a demand for work efficiency and feedback that takes into account not only user operation information but also their emotional state. However, conventional systems are insufficient in providing automation and feedback that takes such complex information into account, making it difficult to improve user work efficiency and satisfaction.

[0341] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0342] In this invention, the server includes means for acquiring user operation information, means for analyzing the operation information and converting it into text information, and means for acquiring and analyzing the user's emotional state using audio data and video data. This makes it possible to learn the user's operation patterns and provide adaptive feedback and automation based on emotional information.

[0343] "User operation information" refers to data about user actions such as clicks and keystrokes when using a computer.

[0344] "Text information" refers to data in string format that is obtained by converting the analyzed user operation information.

[0345] An "operation pattern" is a characteristic behavior that indicates the continuity or regularity of a user's specific operations.

[0346] "Automation" refers to the process of automatically executing tasks using learned operation patterns through a program.

[0347] "Voice data" refers to data that electronically records the voice spoken by the user.

[0348] "Video data" refers to data that visually records the user's facial expressions and movements.

[0349] "Emotional state" refers to information about emotions such as joy, sadness, and stress, which represent the user's psychological state.

[0350] "Feedback" refers to advice and information provided based on the user's actions and emotional state.

[0351] This invention is a system that optimizes the automation and feedback of tasks based on user operation information and emotional information. This system consists of a terminal, a server, and an engine equipped with emotional analysis capabilities.

[0352] First, the user uses the terminal to perform their daily tasks. Capture software is installed on the terminal to acquire operation information, recording digital inputs such as clicks and keystrokes. Simultaneously, the terminal is equipped with hardware for acquiring audio and video information, such as a camera and microphone, and audio and video data are collected using this. Based on the collected data, the sentiment analysis engine identifies the user's emotional state in real time. Common libraries and modules, such as image processing libraries and speech recognition libraries, are used for this sentiment analysis.

[0353] Next, the information collected by the terminal is transmitted to the server via the network. The server converts the received operation information into text data using multimodal AI and learns the user's operation patterns from it. This learning is performed by a natural language processing engine, and foundational data is created for automating certain repetitive tasks. Specifically, this includes templating reports that users repeatedly create and automatically applying formatting.

[0354] The server also analyzes emotional information and evaluates the user's psychological state. Based on criteria such as stress level and satisfaction, personalized feedback is generated. The feedback is sent to the device as a pop-up notification to help the user work more efficiently. For example, if a high level of stress is detected, the device may suggest taking a break from work or recommend refreshments.

[0355] A concrete example of a prompt message would be: "Analyze the user's operation patterns while they are creating the report and suggest ways to automate the work process. Also, analyze their emotional state and provide appropriate feedback if the user is experiencing stress."

[0356] In this way, this system can improve user productivity and satisfaction.

[0357] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0358] Step 1:

[0359] Users perform their tasks using a terminal. The terminal acquires user operation information. This input includes action information such as clicks and keystrokes. The terminal records this input in real time and stores it as an operation log. Specifically, it performs keyboard input capture and mouse event monitoring.

[0360] Step 2:

[0361] The device uses a microphone and camera to acquire audio and video data as input. Based on this data, the built-in emotion analysis engine processes the data. Specifically, it analyzes the tone of the voice and the facial expressions in the images to identify the user's emotional state. This processing outputs data indicating the emotional state.

[0362] Step 3:

[0363] The device collects operational and emotional information and transmits it to a server via the network. Security is considered during this transmission, and encryption protocols are used. As a result, real-time operational and emotional data is transmitted to the server.

[0364] Step 4:

[0365] The server analyzes the received operation information and converts it into text data. It uses natural language processing techniques to analyze the operation log as input and identify user operation patterns. Based on this analysis, the operation patterns are output in text format. Specifically, certain operation sequences are extracted as patterns.

[0366] Step 5:

[0367] The server analyzes emotional information and evaluates the user's emotional state. This input uses an emotional analysis model to assess stress and satisfaction levels. The analysis results output emotional evaluation data. This evaluation serves as foundational data for reducing the user's psychological burden.

[0368] Step 6:

[0369] The server processes the automation of tasks and optimizes feedback based on the analyzed operation patterns and emotional information. For example, it generates scripts to automate repetitive operations and creates appropriate feedback based on the emotional state. The output of this process is the automated operation process and personalized feedback information.

[0370] Step 7:

[0371] The server sends the generated feedback information to the terminal. The terminal provides this information to the user at an appropriate time. Specific actions include displaying an alert as a pop-up notification on the user's screen and providing suggestions for improving work methods through a reminder function.

[0372] (Application Example 2)

[0373] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0374] In modern retail store customer service, staff are required to quickly and accurately understand customers' emotional states and respond accordingly to enhance customer satisfaction. However, traditional systems struggle to properly acquire emotional information and provide automated feedback based on it, often relying on subjective judgments by staff. This results in inconsistent service quality and limits the potential for improving the customer experience.

[0375] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0376] In this invention, the server includes means for acquiring user operation information, means for acquiring video and audio information to recognize emotional states, and means for optimizing automated processing and feedback based on the estimated emotional state. This enables staff to provide appropriate service in response to customer emotions and improve the customer experience.

[0377] "Means for acquiring user operation information" refers to a device or mechanism for recording operations performed by a user, such as acquiring operation data like clicks, taps, and key inputs.

[0378] "Means for analyzing operation information and converting it into text information" refers to the function of a device or software that analyzes acquired user operation information and converts its contents into a string of characters.

[0379] "Means for learning operation patterns" refers to a device or program that learns user behavior patterns based on converted text information and predicts future operations.

[0380] "Means of automating work" refers to the function of a device or software that uses learned user operation patterns to mechanically perform repetitive tasks.

[0381] "Means for acquiring video and audio information to recognize emotional states" refers to a device or mechanism that collects video and audio data using cameras, microphones, etc., in order to estimate emotions from the user's facial expressions and voice.

[0382] "Means for estimating emotional state" refers to software functions that analyze acquired video and audio information to determine the user's emotional state.

[0383] "Means for optimizing automated processing and feedback" refers to the function of a device or software for adjusting and optimizing automated processing and user feedback in accordance with the estimated emotional state.

[0384] "Means for generating emotion-based feedback information" refers to a function that generates information related to the user's emotional state and presents it to the user or the system.

[0385] The system for implementing this invention collects and analyzes user emotional state and interaction information to improve customer service in physical stores, and optimizes feedback based on this information. This system mainly consists of smart glasses as a terminal, a server, and an emotion engine.

[0386] A user wearing smart glasses (for example, a store employee) captures a customer's face with a camera and records their voice via a microphone. The emotion engine within the device estimates the user's emotional state in real time based on this video and audio information. This data is transmitted to a server via the network.

[0387] The server analyzes the operation and emotional information sent by the user. This analysis utilizes an emotional analysis engine and multimodal AI, enabling the system to learn the user's operation patterns and estimate their emotional state based on past data. This allows the system to generate appropriate feedback tailored to the customer's emotions and display instructions in real time on the smart glasses.

[0388] As a concrete example of this system, consider a case where staff at a flower shop use smart glasses. If a customer is looking for a specific flower but shows a dissatisfied expression, feedback will be displayed on the screen based on the analysis of their emotional state, stating, "It would be desirable to respond to this customer in a more cheerful tone and suggest a new spring arrangement."

[0389] By using a generative AI model, it is possible to provide prompts that include advice on customer service styles. Examples of specific prompts include: "What customer service style would you recommend when a particular customer is expressing dissatisfaction? What services or products should I suggest?"

[0390] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0391] Step 1:

[0392] The device uses the smart glasses' camera to capture the customer's face within the user's field of view and acquires video data related to the customer's facial expressions. This input includes real-time video data. The output is formatted video data for use in sentiment analysis.

[0393] Step 2:

[0394] The device uses the microphone in the smart glasses to record customer conversations and acquire audio data. This input includes customer audio data, including the surrounding sound environment. The output is audio data converted into a format suitable for speech analysis.

[0395] Step 3:

[0396] The device analyzes acquired video and audio data in real time using its built-in emotion engine to estimate the customer's emotional state. Based on the input data, it analyzes facial expressions and tone of voice, and then estimates the emotion. The output is information about the customer's current emotional state.

[0397] Step 4:

[0398] The terminal transmits the emotional state data obtained as an analysis result to the server via the network. This transmission process includes both emotional information and operational information. The output is the dataset necessary for analysis on the server.

[0399] Step 5:

[0400] The server uses multimodal AI to compare the received data with past customer service patterns and emotional data. This process combines the input emotional state and interaction patterns for data processing. The output is insightful data used to generate feedback.

[0401] Step 6:

[0402] The server uses a generative AI model to generate appropriate feedback information based on the input insight data. This process generates feedback that includes various customer service suggestions. The output is specific feedback information displayed on the terminal.

[0403] Step 7:

[0404] The terminal displays feedback information sent from the server on the smart glasses' screen. This information serves as a guide for the user to take customer service actions that respond to customer emotions in real time. The output is the feedback information displayed on the smart glasses.

[0405] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0406] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0407] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0408] [Third Embodiment]

[0409] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0410] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0411] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0412] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0413] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0414] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0415] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0416] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0417] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0418] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0419] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0420] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0421] This invention is a system that automates and streamlines operations performed by users on a computer. The main components of the system consist of a terminal, a server, and related software modules.

[0422] The terminal is a computer that the user typically operates and is connected to a network. The terminal is equipped with software to capture user actions in real time. This software acquires user action information such as mouse clicks, keystrokes, and screen changes, and stores this information as data.

[0423] The server is responsible for receiving and analyzing user interaction information sent from terminals. The server is equipped with multimodal AI, which can convert a series of user actions into text information. Specifically, it records the user's actions, such as aggregating data using spreadsheet software, as text and programs those steps. This converted text information is stored in a database and used for further analysis and automation.

[0424] User operation patterns are learned by a machine learning model running on the server. This model recognizes sequences of operations that users frequently perform and uses those patterns to build automated processes. For example, it can learn the steps a user takes to create a weekly report and automatically generate that report.

[0425] Furthermore, this system also features voice recognition capabilities, allowing users to give instructions to their devices via a microphone. Voice input is sent to a server and analyzed by a voice recognition AI. Based on this analysis, the server executes the user's intended actions. For example, if a user gives a voice command such as "Show me next week's schedule," the schedule management software will automatically operate based on that instruction.

[0426] In this way, the system will be implemented to streamline users' work and provide an environment where they can focus on creative activities by tracing and learning user actions and automating operations through voice commands as needed.

[0427] The following describes the processing flow.

[0428] Step 1:

[0429] The terminal launches software to capture user actions. When the user performs any action on the computer, the terminal records the details of that action (e.g., click location and input content) in real time.

[0430] Step 2:

[0431] The terminal transmits recorded operation information to a server via the internet. This makes the user's actions available on the server.

[0432] Step 3:

[0433] The server inputs the operation information received from the terminal into the multimodal AI module and converts the operation into text data. This text records the specific steps the user took in language.

[0434] Step 4:

[0435] The server inputs text data of user operations into a machine learning model, which analyzes and learns from the user's operation patterns. This model captures regularities when similar operations are repeated and generates an optimal automated process.

[0436] Step 5:

[0437] The user inputs voice commands into the terminal via the microphone. The terminal then sends these voice commands to the server as digital audio data.

[0438] Step 6:

[0439] The server uses speech recognition AI to analyze the audio data and convert it into text commands. Based on the converted text commands, it then invokes the necessary automation scripts.

[0440] Step 7:

[0441] The server executes automated processes based on the converted text instructions and learned operation patterns. This allows the user's intended task to be performed automatically.

[0442] Step 8:

[0443] The server provides the user with feedback on the execution results and processing details. If requested by the user, it will provide more detailed explanations and suggestions for the next action.

[0444] (Example 1)

[0445] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0446] In many modern work environments, users spend a significant amount of time on repetitive operations and routine tasks. The inefficiency of these tasks hinders productivity improvements and poses a major challenge, especially in environments where automation is not widespread. Furthermore, there is a lack of established methods for reliably interpreting and executing voice commands when users wish to guide them through operations. In addition, there is a lack of mechanisms to provide appropriate feedback to users, and improvements to intuitive operation are needed.

[0447] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0448] In this invention, the server includes means for acquiring user operation information, means for analyzing the acquired operation information and converting it into text information, and means for learning the user's operation patterns based on the converted text information. This enables efficient automation of repetitive operations and interpretation and execution of instructions using speech recognition technology. Furthermore, it enables the provision of a more intuitive and user-friendly interface through user feedback.

[0449] "User operation information" refers to the history and data of operations performed by a user on a computer or device, such as mouse clicks, keystrokes, and screen changes.

[0450] "Text information" refers to information written in strings, generated as a result of analyzing user interaction data.

[0451] An "operation pattern" refers to a series of actions that are recognized as a pattern, which are similar operations or procedures that a user repeatedly performs.

[0452] "Automation" is the process of enabling a system to automatically perform operations or procedures that were previously done manually by a user.

[0453] "Voice input information" refers to information about voice commands uttered by the user through a device such as a microphone.

[0454] "Feedback information" refers to information about the results and status of operations that a system returns to the user.

[0455] This invention is a system that automates user operations and improves operational efficiency. The system consists of a terminal, a server, and associated software modules.

[0456] A terminal is a computer device used by users on a daily basis and is connected to a network. The terminal is equipped with software that captures user actions in real time. This software acquires and stores operational data such as mouse clicks, keystrokes, and screen changes.

[0457] The server is responsible for receiving and analyzing user interaction information sent from the terminal. The server implements multimodal AI, including a generative AI model, which converts the received data into text. This converted data is stored in a database and used for learning interaction patterns and automating processes.

[0458] User operation patterns are learned by machine learning algorithms on the server. These algorithms can identify frequently performed user actions and generate suggestions for automating those sequences of actions. For example, it can learn the procedure for creating weekly reports and automatically generate similar reports.

[0459] Furthermore, users can give voice commands via the device's microphone. The voice input is sent to the server, where speech recognition technology analyzes the commands. Based on the analysis, the server automatically performs operations according to the user's intent. For example, if the user says, "Show me next week's schedule," the server will display the relevant information via the schedule management software.

[0460] A concrete example is the weekly Friday routine task of "retrieving data from a specified range in a spreadsheet, adding a cover page, and saving it as a PDF." An example of a prompt message used when automating this operation would be, "Extract data from the specified range in the spreadsheet, format it, and save it in PDF format."

[0461] In this way, this system supports business operations by efficiently tracing user actions and automating processes.

[0462] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0463] Step 1:

[0464] The device monitors user actions and captures operational information such as mouse clicks, keystrokes, and screen changes in real time. It receives user interface input and saves operation logs as digital data as output. A specific example of its operation is recording information when a user clicks a cell in a spreadsheet and enters a number.

[0465] Step 2:

[0466] The terminal sends the captured operation data to the server. In this step, operation log data is used as input, and data is transferred to the server via the network as output. Specifically, the terminal packets the data "'100' was entered into cell A1" and sends it.

[0467] Step 3:

[0468] The server analyzes the received operation data and uses a generation AI model to convert the operation details into text information. Here, it takes received data as input and generates operation instructions in text format as output. Specifically, the server converts a sum calculation operation in a spreadsheet into text, such as "Calculate the sum of cells A1 to A10."

[0469] Step 4:

[0470] The server stores the converted text information in a database and learns user operation patterns using a machine learning algorithm. It uses the converted operation history as input and records each user's operation patterns in the database as output. Specifically, the server learns and records the "procedures for data aggregation work that is usually performed on Mondays."

[0471] Step 5:

[0472] The user provides voice commands via the device's microphone. The server receives the voice data and interprets the commands using voice recognition AI. In this step, the input is voice data, and the output is the analyzed command content. For example, if the user says, "Show me next week's schedule," the command content will be expressed as text.

[0473] Step 6:

[0474] The server executes automated processes based on analyzed operation information and voice commands. Using the analysis results as input, it generates a state where the system automatically performs the operation intended by the user as output. Specifically, the server operates scheduling software and displays next week's schedule on the screen.

[0475] (Application Example 1)

[0476] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0477] Improving work efficiency is crucial in complex and diverse operations such as those in logistics centers. However, current systems lack sufficient development of efficiency methods utilizing eye-tracking information, and an environment where workers can give instructions without using their hands is not in place. As a result, logistics operations become complicated, and working hours increase.

[0478] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0479] In this invention, the server includes means for acquiring user operation information, means for acquiring and analyzing voice input information, and means for acquiring user gaze information in real time. This enables workers to perform their tasks efficiently using gaze and voice.

[0480] "User operation information" refers to input data generated when a user operates a computing device, and includes information such as keystrokes, mouse clicks, and screen changes.

[0481] "Text information" refers to information obtained by analyzing user interaction data and representing it as formatted string data.

[0482] "Operation patterns" refer to data that identifies the regularity and trends in a series of operations that a user repeatedly performs.

[0483] "Voice input information" refers to voice data generated when a user gives instructions to a device using their voice.

[0484] "Eye-gaze information" refers to data about visual focus and direction of gaze obtained by monitoring the user's eye movements.

[0485] "Real-time" refers to a state in which user actions and inputs are processed immediately.

[0486] "Feedback information" refers to data that includes responses and instructions that a system returns in response to user actions or inputs.

[0487] "Automated processing" refers to actions that automatically perform tasks or operations without human intervention, based on predefined rules or learned patterns.

[0488] "Optimization suggestions" refer to information that analyzes a user's past actions and input data to suggest more efficient procedures and methods.

[0489] A "network" is a communication line or system used to transmit information between multiple computing devices.

[0490] This invention is a system that automates user operations with the aim of improving the efficiency of operations in logistics centers and the like. This system mainly consists of a server, terminals, and an interface device (e.g., smart glasses) for acquiring eye-tracking and voice data.

[0491] The server receives user operation information, voice input information, and eye-tracking information, and analyzes them in real time. Operation information is captured on the terminal and converted into text information. Natural Language Processing (NLP) technology is used for this conversion. Voice input information is analyzed through speech recognition software and converted into the necessary instruction data. Eye-tracking information is acquired in real time using eye-tracking technology and transmitted to the server.

[0492] On the server, user operation patterns and eye movements are learned, enabling automated processing based on this data. In particular, machine learning algorithms recognize operation patterns and propose more efficient workflows. This reduces manual work for users, minimizes errors, and allows tasks to proceed quickly. Generative AI models are used to generate decisions and feedback during automation, providing users with appropriate information.

[0493] As a concrete example, a worker can visually confirm the products on the shelves and give a voice command such as "Show the next shipping list," at which point the server automatically issues a shipping instruction, and the next action is displayed on smart glasses. This allows the worker to continue working efficiently without using their hands.

[0494] An example of a prompt message would be: "Generate an application that streamlines logistics operations using human eye movement and voice commands. Include a flow that sends gaze data and voice information to a server and automates the processing."

[0495] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0496] Step 1:

[0497] The server receives user action information sent from the terminal. Keystrokes, mouse clicks, and screen change information are provided as input. Natural Language Processing (NLP) technology is used to convert this data into text information, and the formatted text data is output.

[0498] Step 2:

[0499] The server receives voice input information in real time and analyzes it using speech recognition software. Voice data is provided as input and converted into text instruction data. The output is a textual representation of the analyzed voice instruction. The server uses a generative AI model to understand the user's intent and generate appropriate instructions.

[0500] Step 3:

[0501] The device acquires gaze information in real time via smart glasses and transmits it to the server. The input is the user's gaze tracking data. The server analyzes the gaze information and uses computer vision technology to recognize fixation on specific objects. The output is the identification of objects based on the user's gaze.

[0502] Step 4:

[0503] The server optimizes the workflow by applying machine learning algorithms based on operation patterns, voice input information, and eye-tracking data. Inputs consist of text data and eye-tracking data generated in the previous stage. Outputs include instructions to be executed and optimized work procedures.

[0504] Step 5:

[0505] The user receives feedback information from the server and follows instructions displayed via smart glasses. The output is a real-time work guide displayed on the smart glasses via the network. Cloud computing technology is used to provide this feedback in a timely manner.

[0506] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0507] This invention is a system that acquires not only user operation information but also emotional information to optimize business automation and feedback. This system consists of a terminal, a server, and an emotional engine.

[0508] The terminal is a computer used for the user's normal tasks, capturing operation information and acquiring emotional states. When the user operates the PC, the terminal records that operation information (e.g., clicks, keystrokes) in real time. In addition, the built-in emotion engine recognizes the user's emotional state based on voice and video data. This information is transmitted to the server via the network.

[0509] The server analyzes operation information and sentiment information based on data sent from the terminal. First, operation information is converted to text using multimodal AI, and the server learns the user's operation patterns based on this text data. For example, it evaluates the user's operation of creating a monthly report and explores ways to make it more efficient. This learning makes it possible to automate repetitive tasks.

[0510] Meanwhile, the emotion engine analyzes the emotional information acquired by the user to determine their emotional state during the interaction and reflects the results back to the server. The analyzed emotional information indicates various emotional states, such as whether the user is stressed or satisfied. This information can be used to automate processes and personalize feedback.

[0511] User feedback is based on information generated by the server. For example, if a user shows high levels of stress, feedback will be provided that offers more concise explanations and support. Furthermore, the application interface is adjusted based on emotional information, and adaptive support is provided according to the user's emotional state.

[0512] Thus, the present invention provides a more human-friendly system environment by performing automation and feedback that takes user emotional information into account. This system is expected to not only improve user work efficiency but also significantly increase user satisfaction.

[0513] The following describes the processing flow.

[0514] Step 1:

[0515] The user begins working on the terminal, and the terminal collects user activity information in real time. The terminal detects mouse clicks and keyboard inputs and saves these events as time-series data.

[0516] Step 2:

[0517] The device uses an emotion engine to acquire emotional information through the user's face and voice. By analyzing the user's facial expressions and voice tone, it identifies their current emotional state.

[0518] Step 3:

[0519] The collected operational and emotional information is transmitted to the server via the network. The terminal verifies that the data has been transmitted accurately.

[0520] Step 4:

[0521] The server passes the received operation information to the multimodal AI, which converts it into text information. The server analyzes this text information to recognize and learn the user's operation patterns.

[0522] Step 5:

[0523] The server processes emotional information and evaluates the user's stress level and satisfaction. It uses an emotional evaluation algorithm to obtain a quantified or categorized emotional state.

[0524] Step 6:

[0525] The server combines learned operation patterns with evaluated emotional states to design an automated task process. The server creates the automated procedure and saves it in a format that can be executed the next time the user interacts with the system.

[0526] Step 7:

[0527] The next time the user performs a similar action, the server executes an automated procedure. It considers emotional information and adjusts the user interface as needed to facilitate smooth operation.

[0528] Step 8:

[0529] The server provides users with feedback based on their actions and emotions. For example, if the server determines that a user is experiencing a lot of stress, it will suggest simplifying the operation or improving the explanation.

[0530] (Example 2)

[0531] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0532] In today's work environment, there is a demand for work efficiency and feedback that takes into account not only user operation information but also their emotional state. However, conventional systems are insufficient in providing automation and feedback that takes such complex information into account, making it difficult to improve user work efficiency and satisfaction.

[0533] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0534] In this invention, the server includes means for acquiring user operation information, means for analyzing the operation information and converting it into text information, and means for acquiring and analyzing the user's emotional state using audio data and video data. This makes it possible to learn the user's operation patterns and provide adaptive feedback and automation based on emotional information.

[0535] "User operation information" refers to data about user actions such as clicks and keystrokes when using a computer.

[0536] "Text information" refers to data in string format that is obtained by converting the analyzed user operation information.

[0537] An "operation pattern" is a characteristic behavior that indicates the continuity or regularity of a user's specific operations.

[0538] "Automation" refers to the process of automatically executing tasks using learned operation patterns through a program.

[0539] "Voice data" refers to data that electronically records the voice spoken by the user.

[0540] "Video data" refers to data that visually records the user's facial expressions and movements.

[0541] "Emotional state" refers to information about emotions such as joy, sadness, and stress, which represent the user's psychological state.

[0542] "Feedback" refers to advice and information provided based on the user's actions and emotional state.

[0543] This invention is a system that optimizes the automation and feedback of tasks based on user operation information and emotional information. This system consists of a terminal, a server, and an engine equipped with emotional analysis capabilities.

[0544] First, the user uses the terminal to perform their daily tasks. Capture software is installed on the terminal to acquire operation information, recording digital inputs such as clicks and keystrokes. Simultaneously, the terminal is equipped with hardware for acquiring audio and video information, such as a camera and microphone, and audio and video data are collected using this. Based on the collected data, the sentiment analysis engine identifies the user's emotional state in real time. Common libraries and modules, such as image processing libraries and speech recognition libraries, are used for this sentiment analysis.

[0545] Next, the information collected by the terminal is transmitted to the server via the network. The server converts the received operation information into text data using multimodal AI and learns the user's operation patterns from it. This learning is performed by a natural language processing engine, and foundational data is created for automating certain repetitive tasks. Specifically, this includes templating reports that users repeatedly create and automatically applying formatting.

[0546] The server also analyzes emotional information and evaluates the user's psychological state. Based on criteria such as stress level and satisfaction, personalized feedback is generated. The feedback is sent to the device as a pop-up notification to help the user work more efficiently. For example, if a high level of stress is detected, the device may suggest taking a break from work or recommend refreshments.

[0547] A concrete example of a prompt message would be: "Analyze the user's operation patterns while they are creating the report and suggest ways to automate the work process. Also, analyze their emotional state and provide appropriate feedback if the user is experiencing stress."

[0548] In this way, this system can improve user productivity and satisfaction.

[0549] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0550] Step 1:

[0551] Users perform their tasks using a terminal. The terminal acquires user operation information. This input includes action information such as clicks and keystrokes. The terminal records this input in real time and stores it as an operation log. Specifically, it performs keyboard input capture and mouse event monitoring.

[0552] Step 2:

[0553] The device uses a microphone and camera to acquire audio and video data as input. Based on this data, the built-in emotion analysis engine processes the data. Specifically, it analyzes the tone of the voice and the facial expressions in the images to identify the user's emotional state. This processing outputs data indicating the emotional state.

[0554] Step 3:

[0555] The device collects operational and emotional information and transmits it to a server via the network. Security is considered during this transmission, and encryption protocols are used. As a result, real-time operational and emotional data is transmitted to the server.

[0556] Step 4:

[0557] The server analyzes the received operation information and converts it into text data. It uses natural language processing techniques to analyze the operation log as input and identify user operation patterns. Based on this analysis, the operation patterns are output in text format. Specifically, certain operation sequences are extracted as patterns.

[0558] Step 5:

[0559] The server analyzes emotional information and evaluates the user's emotional state. This input uses an emotional analysis model to assess stress and satisfaction levels. The analysis results output emotional evaluation data. This evaluation serves as foundational data for reducing the user's psychological burden.

[0560] Step 6:

[0561] The server processes the automation of tasks and optimizes feedback based on the analyzed operation patterns and emotional information. For example, it generates scripts to automate repetitive operations and creates appropriate feedback based on the emotional state. The output of this process is the automated operation process and personalized feedback information.

[0562] Step 7:

[0563] The server sends the generated feedback information to the terminal. The terminal provides this information to the user at an appropriate time. Specific actions include displaying an alert as a pop-up notification on the user's screen and providing suggestions for improving work methods through a reminder function.

[0564] (Application Example 2)

[0565] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0566] In modern retail store customer service, staff are required to quickly and accurately understand customers' emotional states and respond accordingly to enhance customer satisfaction. However, traditional systems struggle to properly acquire emotional information and provide automated feedback based on it, often relying on subjective judgments by staff. This results in inconsistent service quality and limits the potential for improving the customer experience.

[0567] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0568] In this invention, the server includes means for acquiring user operation information, means for acquiring video and audio information to recognize emotional states, and means for optimizing automated processing and feedback based on the estimated emotional state. This enables staff to provide appropriate service in response to customer emotions and improve the customer experience.

[0569] "Means for acquiring user operation information" refers to a device or mechanism for recording operations performed by a user, such as acquiring operation data like clicks, taps, and key inputs.

[0570] "Means for analyzing operation information and converting it into text information" refers to the function of a device or software that analyzes acquired user operation information and converts its contents into a string of characters.

[0571] "Means for learning operation patterns" refers to a device or program that learns user behavior patterns based on converted text information and predicts future operations.

[0572] "Means of automating work" refers to the function of a device or software that uses learned user operation patterns to mechanically perform repetitive tasks.

[0573] "Means for acquiring video and audio information to recognize emotional states" refers to a device or mechanism that collects video and audio data using cameras, microphones, etc., in order to estimate emotions from the user's facial expressions and voice.

[0574] "Means for estimating emotional state" refers to software functions that analyze acquired video and audio information to determine the user's emotional state.

[0575] "Means for optimizing automated processing and feedback" refers to the function of a device or software for adjusting and optimizing automated processing and user feedback in accordance with the estimated emotional state.

[0576] "Means for generating emotion-based feedback information" refers to a function that generates information related to the user's emotional state and presents it to the user or the system.

[0577] The system for implementing this invention collects and analyzes user emotional state and interaction information to improve customer service in physical stores, and optimizes feedback based on this information. This system mainly consists of smart glasses as a terminal, a server, and an emotion engine.

[0578] A user wearing smart glasses (for example, a store employee) captures a customer's face with a camera and records their voice via a microphone. The emotion engine within the device estimates the user's emotional state in real time based on this video and audio information. This data is transmitted to a server via the network.

[0579] The server analyzes the operation and emotional information sent by the user. This analysis utilizes an emotional analysis engine and multimodal AI, enabling the system to learn the user's operation patterns and estimate their emotional state based on past data. This allows the system to generate appropriate feedback tailored to the customer's emotions and display instructions in real time on the smart glasses.

[0580] As a concrete example of this system, consider a case where staff at a flower shop use smart glasses. If a customer is looking for a specific flower but shows a dissatisfied expression, feedback will be displayed on the screen based on the analysis of their emotional state, stating, "It would be desirable to respond to this customer in a more cheerful tone and suggest a new spring arrangement."

[0581] By using a generative AI model, it is possible to provide prompts that include advice on customer service styles. Examples of specific prompts include: "What customer service style would you recommend when a particular customer is expressing dissatisfaction? What services or products should I suggest?"

[0582] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0583] Step 1:

[0584] The device uses the smart glasses' camera to capture the customer's face within the user's field of view and acquires video data related to the customer's facial expressions. This input includes real-time video data. The output is formatted video data for use in sentiment analysis.

[0585] Step 2:

[0586] The device uses the microphone in the smart glasses to record customer conversations and acquire audio data. This input includes customer audio data, including the surrounding sound environment. The output is audio data converted into a format suitable for speech analysis.

[0587] Step 3:

[0588] The device analyzes acquired video and audio data in real time using its built-in emotion engine to estimate the customer's emotional state. Based on the input data, it analyzes facial expressions and tone of voice, and then estimates the emotion. The output is information about the customer's current emotional state.

[0589] Step 4:

[0590] The terminal transmits the emotional state data obtained as an analysis result to the server via the network. This transmission process includes both emotional information and operational information. The output is the dataset necessary for analysis on the server.

[0591] Step 5:

[0592] The server uses multimodal AI to compare the received data with past customer service patterns and emotional data. This process combines the input emotional state and interaction patterns for data processing. The output is insightful data used to generate feedback.

[0593] Step 6:

[0594] The server uses a generative AI model to generate appropriate feedback information based on the input insight data. This process generates feedback that includes various customer service suggestions. The output is specific feedback information displayed on the terminal.

[0595] Step 7:

[0596] The terminal displays feedback information sent from the server on the smart glasses' screen. This information serves as a guide for the user to take customer service actions that respond to customer emotions in real time. The output is the feedback information displayed on the smart glasses.

[0597] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0598] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0599] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0600] [Fourth Embodiment]

[0601] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0602] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0603] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0604] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0605] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0606] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0607] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0608] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0609] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0610] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0611] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0612] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0613] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0614] This invention is a system that automates and streamlines operations performed by users on a computer. The main components of the system consist of a terminal, a server, and related software modules.

[0615] The terminal is a computer that the user typically operates and is connected to a network. The terminal is equipped with software to capture user actions in real time. This software acquires user action information such as mouse clicks, keystrokes, and screen changes, and stores this information as data.

[0616] The server is responsible for receiving and analyzing user interaction information sent from terminals. The server is equipped with multimodal AI, which can convert a series of user actions into text information. Specifically, it records the user's actions, such as aggregating data using spreadsheet software, as text and programs those steps. This converted text information is stored in a database and used for further analysis and automation.

[0617] User operation patterns are learned by a machine learning model running on the server. This model recognizes sequences of operations that users frequently perform and uses those patterns to build automated processes. For example, it can learn the steps a user takes to create a weekly report and automatically generate that report.

[0618] Furthermore, this system also features voice recognition capabilities, allowing users to give instructions to their devices via a microphone. Voice input is sent to a server and analyzed by a voice recognition AI. Based on this analysis, the server executes the user's intended actions. For example, if a user gives a voice command such as "Show me next week's schedule," the schedule management software will automatically operate based on that instruction.

[0619] In this way, the system will be implemented to streamline users' work and provide an environment where they can focus on creative activities by tracing and learning user actions and automating operations through voice commands as needed.

[0620] The following describes the processing flow.

[0621] Step 1:

[0622] The terminal launches software to capture user actions. When the user performs any action on the computer, the terminal records the details of that action (e.g., click location and input content) in real time.

[0623] Step 2:

[0624] The terminal transmits recorded operation information to a server via the internet. This makes the user's actions available on the server.

[0625] Step 3:

[0626] The server inputs the operation information received from the terminal into the multimodal AI module and converts the operation into text data. This text records the specific steps the user took in language.

[0627] Step 4:

[0628] The server inputs text data of user operations into a machine learning model, which analyzes and learns from the user's operation patterns. This model captures regularities when similar operations are repeated and generates an optimal automated process.

[0629] Step 5:

[0630] The user inputs voice commands into the terminal via the microphone. The terminal then sends these voice commands to the server as digital audio data.

[0631] Step 6:

[0632] The server uses speech recognition AI to analyze the audio data and convert it into text commands. Based on the converted text commands, it then invokes the necessary automation scripts.

[0633] Step 7:

[0634] The server executes automated processes based on the converted text instructions and learned operation patterns. This allows the user's intended task to be performed automatically.

[0635] Step 8:

[0636] The server provides the user with feedback on the execution results and processing details. If requested by the user, it will provide more detailed explanations and suggestions for the next action.

[0637] (Example 1)

[0638] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0639] In many modern work environments, users spend a significant amount of time on repetitive operations and routine tasks. The inefficiency of these tasks hinders productivity improvements and poses a major challenge, especially in environments where automation is not widespread. Furthermore, there is a lack of established methods for reliably interpreting and executing voice commands when users wish to guide them through operations. In addition, there is a lack of mechanisms to provide appropriate feedback to users, and improvements to intuitive operation are needed.

[0640] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0641] In this invention, the server includes means for acquiring user operation information, means for analyzing the acquired operation information and converting it into text information, and means for learning the user's operation patterns based on the converted text information. This enables efficient automation of repetitive operations and interpretation and execution of instructions using speech recognition technology. Furthermore, it enables the provision of a more intuitive and user-friendly interface through user feedback.

[0642] "User operation information" refers to the history and data of operations performed by a user on a computer or device, such as mouse clicks, keystrokes, and screen changes.

[0643] "Text information" refers to information written in strings, generated as a result of analyzing user interaction data.

[0644] An "operation pattern" refers to a series of actions that are recognized as a pattern, which are similar operations or procedures that a user repeatedly performs.

[0645] "Automation" is the process of enabling a system to automatically perform operations or procedures that were previously done manually by a user.

[0646] "Voice input information" refers to information about voice commands uttered by the user through a device such as a microphone.

[0647] "Feedback information" refers to information about the results and status of operations that a system returns to the user.

[0648] This invention is a system that automates user operations and improves operational efficiency. The system consists of a terminal, a server, and associated software modules.

[0649] A terminal is a computer device used by users on a daily basis and is connected to a network. The terminal is equipped with software that captures user actions in real time. This software acquires and stores operational data such as mouse clicks, keystrokes, and screen changes.

[0650] The server is responsible for receiving and analyzing user interaction information sent from the terminal. The server implements multimodal AI, including a generative AI model, which converts the received data into text. This converted data is stored in a database and used for learning interaction patterns and automating processes.

[0651] User operation patterns are learned by machine learning algorithms on the server. These algorithms can identify frequently performed user actions and generate suggestions for automating those sequences of actions. For example, it can learn the procedure for creating weekly reports and automatically generate similar reports.

[0652] Furthermore, users can give voice commands via the device's microphone. The voice input is sent to the server, where speech recognition technology analyzes the commands. Based on the analysis, the server automatically performs operations according to the user's intent. For example, if the user says, "Show me next week's schedule," the server will display the relevant information via the schedule management software.

[0653] A concrete example is the weekly Friday routine task of "retrieving data from a specified range in a spreadsheet, adding a cover page, and saving it as a PDF." An example of a prompt message used when automating this operation would be, "Extract data from the specified range in the spreadsheet, format it, and save it in PDF format."

[0654] In this way, this system supports business operations by efficiently tracing user actions and automating processes.

[0655] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0656] Step 1:

[0657] The device monitors user actions and captures operational information such as mouse clicks, keystrokes, and screen changes in real time. It receives user interface input and saves operation logs as digital data as output. A specific example of its operation is recording information when a user clicks a cell in a spreadsheet and enters a number.

[0658] Step 2:

[0659] The terminal sends the captured operation data to the server. In this step, operation log data is used as input, and data is transferred to the server via the network as output. Specifically, the terminal packets the data "'100' was entered into cell A1" and sends it.

[0660] Step 3:

[0661] The server analyzes the received operation data and uses a generation AI model to convert the operation details into text information. Here, it takes received data as input and generates operation instructions in text format as output. Specifically, the server converts a sum calculation operation in a spreadsheet into text, such as "Calculate the sum of cells A1 to A10."

[0662] Step 4:

[0663] The server stores the converted text information in a database and learns user operation patterns using a machine learning algorithm. It uses the converted operation history as input and records each user's operation patterns in the database as output. Specifically, the server learns and records the "procedures for data aggregation work that is usually performed on Mondays."

[0664] Step 5:

[0665] The user provides voice commands via the device's microphone. The server receives the voice data and interprets the commands using voice recognition AI. In this step, the input is voice data, and the output is the analyzed command content. For example, if the user says, "Show me next week's schedule," the command content will be expressed as text.

[0666] Step 6:

[0667] The server executes automated processes based on analyzed operation information and voice commands. Using the analysis results as input, it generates a state where the system automatically performs the operation intended by the user as output. Specifically, the server operates scheduling software and displays next week's schedule on the screen.

[0668] (Application Example 1)

[0669] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0670] Improving work efficiency is crucial in complex and diverse operations such as those in logistics centers. However, current systems lack sufficient development of efficiency methods utilizing eye-tracking information, and an environment where workers can give instructions without using their hands is not in place. As a result, logistics operations become complicated, and working hours increase.

[0671] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0672] In this invention, the server includes means for acquiring user operation information, means for acquiring and analyzing voice input information, and means for acquiring user gaze information in real time. This enables workers to perform their tasks efficiently using gaze and voice.

[0673] "User operation information" refers to input data generated when a user operates a computing device, and includes information such as keystrokes, mouse clicks, and screen changes.

[0674] "Text information" refers to information obtained by analyzing user interaction data and representing it as formatted string data.

[0675] "Operation patterns" refer to data that identifies the regularity and trends in a series of operations that a user repeatedly performs.

[0676] "Voice input information" refers to voice data generated when a user gives instructions to a device using their voice.

[0677] "Eye-gaze information" refers to data about visual focus and direction of gaze obtained by monitoring the user's eye movements.

[0678] "Real-time" refers to a state in which user actions and inputs are processed immediately.

[0679] "Feedback information" refers to data that includes responses and instructions that a system returns in response to user actions or inputs.

[0680] "Automated processing" refers to actions that automatically perform tasks or operations without human intervention, based on predefined rules or learned patterns.

[0681] "Optimization suggestions" refer to information that analyzes a user's past actions and input data to suggest more efficient procedures and methods.

[0682] A "network" is a communication line or system used to transmit information between multiple computing devices.

[0683] This invention is a system that automates user operations with the aim of improving the efficiency of operations in logistics centers and the like. This system mainly consists of a server, terminals, and an interface device (e.g., smart glasses) for acquiring eye-tracking and voice data.

[0684] The server receives user operation information, voice input information, and eye-tracking information, and analyzes them in real time. Operation information is captured on the terminal and converted into text information. Natural Language Processing (NLP) technology is used for this conversion. Voice input information is analyzed through speech recognition software and converted into the necessary instruction data. Eye-tracking information is acquired in real time using eye-tracking technology and transmitted to the server.

[0685] On the server, user operation patterns and eye movements are learned, enabling automated processing based on this data. In particular, machine learning algorithms recognize operation patterns and propose more efficient workflows. This reduces manual work for users, minimizes errors, and allows tasks to proceed quickly. Generative AI models are used to generate decisions and feedback during automation, providing users with appropriate information.

[0686] As a concrete example, a worker can visually confirm the products on the shelves and give a voice command such as "Show the next shipping list," at which point the server automatically issues a shipping instruction, and the next action is displayed on smart glasses. This allows the worker to continue working efficiently without using their hands.

[0687] An example of a prompt message would be: "Generate an application that streamlines logistics operations using human eye movement and voice commands. Include a flow that sends gaze data and voice information to a server and automates the processing."

[0688] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0689] Step 1:

[0690] The server receives user action information sent from the terminal. Keystrokes, mouse clicks, and screen change information are provided as input. Natural Language Processing (NLP) technology is used to convert this data into text information, and the formatted text data is output.

[0691] Step 2:

[0692] The server receives voice input information in real time and analyzes it using speech recognition software. Voice data is provided as input and converted into text instruction data. The output is a textual representation of the analyzed voice instruction. The server uses a generative AI model to understand the user's intent and generate appropriate instructions.

[0693] Step 3:

[0694] The device acquires gaze information in real time via smart glasses and transmits it to the server. The input is the user's gaze tracking data. The server analyzes the gaze information and uses computer vision technology to recognize fixation on specific objects. The output is the identification of objects based on the user's gaze.

[0695] Step 4:

[0696] The server optimizes the workflow by applying machine learning algorithms based on operation patterns, voice input information, and eye-tracking data. Inputs consist of text data and eye-tracking data generated in the previous stage. Outputs include instructions to be executed and optimized work procedures.

[0697] Step 5:

[0698] The user receives feedback information from the server and follows instructions displayed via smart glasses. The output is a real-time work guide displayed on the smart glasses via the network. Cloud computing technology is used to provide this feedback in a timely manner.

[0699] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0700] This invention is a system that acquires not only user operation information but also emotional information to optimize business automation and feedback. This system consists of a terminal, a server, and an emotional engine.

[0701] The terminal is a computer used for the user's normal tasks, capturing operation information and acquiring emotional states. When the user operates the PC, the terminal records that operation information (e.g., clicks, keystrokes) in real time. In addition, the built-in emotion engine recognizes the user's emotional state based on voice and video data. This information is transmitted to the server via the network.

[0702] The server analyzes operation information and sentiment information based on data sent from the terminal. First, operation information is converted to text using multimodal AI, and the server learns the user's operation patterns based on this text data. For example, it evaluates the user's operation of creating a monthly report and explores ways to make it more efficient. This learning makes it possible to automate repetitive tasks.

[0703] Meanwhile, the emotion engine analyzes the emotional information acquired by the user to determine their emotional state during the interaction and reflects the results back to the server. The analyzed emotional information indicates various emotional states, such as whether the user is stressed or satisfied. This information can be used to automate processes and personalize feedback.

[0704] User feedback is based on information generated by the server. For example, if a user shows high levels of stress, feedback will be provided that offers more concise explanations and support. Furthermore, the application interface is adjusted based on emotional information, and adaptive support is provided according to the user's emotional state.

[0705] Thus, the present invention provides a more human-friendly system environment by performing automation and feedback that takes user emotional information into account. This system is expected to not only improve user work efficiency but also significantly increase user satisfaction.

[0706] The following describes the processing flow.

[0707] Step 1:

[0708] The user begins working on the terminal, and the terminal collects user activity information in real time. The terminal detects mouse clicks and keyboard inputs and saves these events as time-series data.

[0709] Step 2:

[0710] The device uses an emotion engine to acquire emotional information through the user's face and voice. By analyzing the user's facial expressions and voice tone, it identifies their current emotional state.

[0711] Step 3:

[0712] The collected operational and emotional information is transmitted to the server via the network. The terminal verifies that the data has been transmitted accurately.

[0713] Step 4:

[0714] The server passes the received operation information to the multimodal AI, which converts it into text information. The server analyzes this text information to recognize and learn the user's operation patterns.

[0715] Step 5:

[0716] The server processes emotional information and evaluates the user's stress level and satisfaction. It uses an emotional evaluation algorithm to obtain a quantified or categorized emotional state.

[0717] Step 6:

[0718] The server combines learned operation patterns with evaluated emotional states to design an automated task process. The server creates the automated procedure and saves it in a format that can be executed the next time the user interacts with the system.

[0719] Step 7:

[0720] The next time the user performs a similar action, the server executes an automated procedure. It considers emotional information and adjusts the user interface as needed to facilitate smooth operation.

[0721] Step 8:

[0722] The server provides users with feedback based on their actions and emotions. For example, if the server determines that a user is experiencing a lot of stress, it will suggest simplifying the operation or improving the explanation.

[0723] (Example 2)

[0724] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0725] In today's work environment, there is a demand for work efficiency and feedback that takes into account not only user operation information but also their emotional state. However, conventional systems are insufficient in providing automation and feedback that takes such complex information into account, making it difficult to improve user work efficiency and satisfaction.

[0726] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0727] In this invention, the server includes means for acquiring user operation information, means for analyzing the operation information and converting it into text information, and means for acquiring and analyzing the user's emotional state using audio data and video data. This makes it possible to learn the user's operation patterns and provide adaptive feedback and automation based on emotional information.

[0728] "User operation information" refers to data about user actions such as clicks and keystrokes when using a computer.

[0729] "Text information" refers to data in string format that is obtained by converting the analyzed user operation information.

[0730] An "operation pattern" is a characteristic behavior that indicates the continuity or regularity of a user's specific operations.

[0731] "Automation" refers to the process of automatically executing tasks using learned operation patterns through a program.

[0732] "Voice data" refers to data that electronically records the voice spoken by the user.

[0733] "Video data" refers to data that visually records the user's facial expressions and movements.

[0734] "Emotional state" refers to information about emotions such as joy, sadness, and stress, which represent the user's psychological state.

[0735] "Feedback" refers to advice and information provided based on the user's actions and emotional state.

[0736] This invention is a system that optimizes the automation and feedback of tasks based on user operation information and emotional information. This system consists of a terminal, a server, and an engine equipped with emotional analysis capabilities.

[0737] First, the user uses the terminal to perform their daily tasks. Capture software is installed on the terminal to acquire operation information, recording digital inputs such as clicks and keystrokes. Simultaneously, the terminal is equipped with hardware for acquiring audio and video information, such as a camera and microphone, and audio and video data are collected using this. Based on the collected data, the sentiment analysis engine identifies the user's emotional state in real time. Common libraries and modules, such as image processing libraries and speech recognition libraries, are used for this sentiment analysis.

[0738] Next, the information collected by the terminal is transmitted to the server via the network. The server converts the received operation information into text data using multimodal AI and learns the user's operation patterns from it. This learning is performed by a natural language processing engine, and foundational data is created for automating certain repetitive tasks. Specifically, this includes templating reports that users repeatedly create and automatically applying formatting.

[0739] The server also analyzes emotional information and evaluates the user's psychological state. Based on criteria such as stress level and satisfaction, personalized feedback is generated. The feedback is sent to the device as a pop-up notification to help the user work more efficiently. For example, if a high level of stress is detected, the device may suggest taking a break from work or recommend refreshments.

[0740] A concrete example of a prompt message would be: "Analyze the user's operation patterns while they are creating the report and suggest ways to automate the work process. Also, analyze their emotional state and provide appropriate feedback if the user is experiencing stress."

[0741] In this way, this system can improve user productivity and satisfaction.

[0742] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0743] Step 1:

[0744] Users perform their tasks using a terminal. The terminal acquires user operation information. This input includes action information such as clicks and keystrokes. The terminal records this input in real time and stores it as an operation log. Specifically, it performs keyboard input capture and mouse event monitoring.

[0745] Step 2:

[0746] The device uses a microphone and camera to acquire audio and video data as input. Based on this data, the built-in emotion analysis engine processes the data. Specifically, it analyzes the tone of the voice and the facial expressions in the images to identify the user's emotional state. This processing outputs data indicating the emotional state.

[0747] Step 3:

[0748] The device collects operational and emotional information and transmits it to a server via the network. Security is considered during this transmission, and encryption protocols are used. As a result, real-time operational and emotional data is transmitted to the server.

[0749] Step 4:

[0750] The server analyzes the received operation information and converts it into text data. It uses natural language processing techniques to analyze the operation log as input and identify user operation patterns. Based on this analysis, the operation patterns are output in text format. Specifically, certain operation sequences are extracted as patterns.

[0751] Step 5:

[0752] The server analyzes emotional information and evaluates the user's emotional state. This input uses an emotional analysis model to assess stress and satisfaction levels. The analysis results output emotional evaluation data. This evaluation serves as foundational data for reducing the user's psychological burden.

[0753] Step 6:

[0754] The server processes the automation of tasks and optimizes feedback based on the analyzed operation patterns and emotional information. For example, it generates scripts to automate repetitive operations and creates appropriate feedback based on the emotional state. The output of this process is the automated operation process and personalized feedback information.

[0755] Step 7:

[0756] The server sends the generated feedback information to the terminal. The terminal provides this information to the user at an appropriate time. Specific actions include displaying an alert as a pop-up notification on the user's screen and providing suggestions for improving work methods through a reminder function.

[0757] (Application Example 2)

[0758] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0759] In modern retail store customer service, staff are required to quickly and accurately understand customers' emotional states and respond accordingly to enhance customer satisfaction. However, traditional systems struggle to properly acquire emotional information and provide automated feedback based on it, often relying on subjective judgments by staff. This results in inconsistent service quality and limits the potential for improving the customer experience.

[0760] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0761] In this invention, the server includes means for acquiring user operation information, means for acquiring video and audio information to recognize emotional states, and means for optimizing automated processing and feedback based on the estimated emotional state. This enables staff to provide appropriate service in response to customer emotions and improve the customer experience.

[0762] "Means for acquiring user operation information" refers to a device or mechanism for recording operations performed by a user, such as acquiring operation data like clicks, taps, and key inputs.

[0763] "Means for analyzing operation information and converting it into text information" refers to the function of a device or software that analyzes acquired user operation information and converts its contents into a string of characters.

[0764] "Means for learning operation patterns" refers to a device or program that learns user behavior patterns based on converted text information and predicts future operations.

[0765] "Means of automating work" refers to the function of a device or software that uses learned user operation patterns to mechanically perform repetitive tasks.

[0766] "Means for acquiring video and audio information to recognize emotional states" refers to a device or mechanism that collects video and audio data using cameras, microphones, etc., in order to estimate emotions from the user's facial expressions and voice.

[0767] "Means for estimating emotional state" refers to software functions that analyze acquired video and audio information to determine the user's emotional state.

[0768] "Means for optimizing automated processing and feedback" refers to the function of a device or software for adjusting and optimizing automated processing and user feedback in accordance with the estimated emotional state.

[0769] "Means for generating emotion-based feedback information" refers to a function that generates information related to the user's emotional state and presents it to the user or the system.

[0770] The system for implementing this invention collects and analyzes user emotional state and interaction information to improve customer service in physical stores, and optimizes feedback based on this information. This system mainly consists of smart glasses as a terminal, a server, and an emotion engine.

[0771] A user wearing smart glasses (for example, a store employee) captures a customer's face with a camera and records their voice via a microphone. The emotion engine within the device estimates the user's emotional state in real time based on this video and audio information. This data is transmitted to a server via the network.

[0772] The server analyzes the operation and emotional information sent by the user. This analysis utilizes an emotional analysis engine and multimodal AI, enabling the system to learn the user's operation patterns and estimate their emotional state based on past data. This allows the system to generate appropriate feedback tailored to the customer's emotions and display instructions in real time on the smart glasses.

[0773] As a concrete example of this system, consider a case where staff at a flower shop use smart glasses. If a customer is looking for a specific flower but shows a dissatisfied expression, feedback will be displayed on the screen based on the analysis of their emotional state, stating, "It would be desirable to respond to this customer in a more cheerful tone and suggest a new spring arrangement."

[0774] By using a generative AI model, it is possible to provide prompts that include advice on customer service styles. Examples of specific prompts include: "What customer service style would you recommend when a particular customer is expressing dissatisfaction? What services or products should I suggest?"

[0775] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0776] Step 1:

[0777] The device uses the smart glasses' camera to capture the customer's face within the user's field of view and acquires video data related to the customer's facial expressions. This input includes real-time video data. The output is formatted video data for use in sentiment analysis.

[0778] Step 2:

[0779] The device uses the microphone in the smart glasses to record customer conversations and acquire audio data. This input includes customer audio data, including the surrounding sound environment. The output is audio data converted into a format suitable for speech analysis.

[0780] Step 3:

[0781] The device analyzes acquired video and audio data in real time using its built-in emotion engine to estimate the customer's emotional state. Based on the input data, it analyzes facial expressions and tone of voice, and then estimates the emotion. The output is information about the customer's current emotional state.

[0782] Step 4:

[0783] The terminal transmits the emotional state data obtained as an analysis result to the server via the network. This transmission process includes both emotional information and operational information. The output is the dataset necessary for analysis on the server.

[0784] Step 5:

[0785] The server uses multimodal AI to compare the received data with past customer service patterns and emotional data. This process combines the input emotional state and interaction patterns for data processing. The output is insightful data used to generate feedback.

[0786] Step 6:

[0787] The server uses a generative AI model to generate appropriate feedback information based on the input insight data. This process generates feedback that includes various customer service suggestions. The output is specific feedback information displayed on the terminal.

[0788] Step 7:

[0789] The terminal displays feedback information sent from the server on the smart glasses' screen. This information serves as a guide for the user to take customer service actions that respond to customer emotions in real time. The output is the feedback information displayed on the smart glasses.

[0790] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0791] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0792] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0793] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0794] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0795] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0796] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0797] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0798] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0799] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0800] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0801] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0802] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0803] 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.

[0804] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0805] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0806] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0807] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0808] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0809] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0810] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0811] The following is further disclosed regarding the embodiments described above.

[0812] (Claim 1)

[0813] A means of obtaining user operation information,

[0814] A means for analyzing acquired operation information and converting it into text information,

[0815] A means of learning user operation patterns based on converted text information,

[0816] A means of automating tasks using learned operation patterns,

[0817] A means for acquiring and analyzing voice input information,

[0818] A means of performing automated processing based on analyzed audio information,

[0819] A means for generating user feedback information,

[0820] A system that includes this.

[0821] (Claim 2)

[0822] The system according to claim 1, comprising means for recording user operation information and transmitting it via a network.

[0823] (Claim 3)

[0824] The system according to claim 1, comprising means for generating automated processing and optimization suggestions based on analyzed operation information and voice information.

[0825] "Example 1"

[0826] (Claim 1)

[0827] A means of obtaining user operation information,

[0828] A means for analyzing acquired operation information and converting it into text information,

[0829] A means of learning user operation patterns based on converted text information,

[0830] A means of automating tasks using learned operation patterns,

[0831] A means for acquiring and analyzing voice input information,

[0832] A means of performing automated processing based on analyzed audio information,

[0833] A means for generating user feedback information,

[0834] A means of analyzing user operation patterns using machine learning algorithms to recognize frequently performed operation procedures,

[0835] A means for interpreting voice commands from the user using speech recognition technology and automatically executing corresponding processes,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, comprising means for recording user operation information and transmitting it via a network.

[0839] (Claim 3)

[0840] The system according to claim 1, comprising means for generating automated processing and optimization suggestions based on analyzed operation information and voice information.

[0841] "Application Example 1"

[0842] (Claim 1)

[0843] A means of obtaining user operation information,

[0844] A means for analyzing acquired operation information and converting it into text information,

[0845] A means of learning user operation patterns based on converted text information,

[0846] A means of automating tasks using learned operation patterns,

[0847] A means for acquiring and analyzing voice input information,

[0848] A means of performing automated processing based on analyzed audio information,

[0849] A means of acquiring user eye-tracking information in real time,

[0850] A means for transmitting acquired gaze information via a network,

[0851] A means for generating user feedback information,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, comprising means for recording user operation information and gaze information and transmitting them via a network.

[0855] (Claim 3)

[0856] The system according to claim 1, comprising means for generating automated processing and optimization suggestions based on analyzed operation information, voice information, and gaze information.

[0857] "Example 2 of combining an emotion engine"

[0858] (Claim 1)

[0859] A means of obtaining user operation information,

[0860] A means for analyzing acquired operation information and converting it into text information,

[0861] A means of learning user operation patterns based on converted text information,

[0862] A means of automating tasks using learned operation patterns,

[0863] A method for acquiring and analyzing a user's emotional state using audio and video data,

[0864] A means of automating processing and individualizing feedback content based on analyzed emotional information,

[0865] A means of generating and providing feedback information to users,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, comprising means for recording user operation information and emotional information and transmitting them via a network.

[0869] (Claim 3)

[0870] The system according to claim 1, comprising means for optimizing automated processing and generating adaptive support in response to emotions based on analyzed operational information and emotional information.

[0871] "Application example 2 of combining emotional engines"

[0872] (Claim 1)

[0873] A means of obtaining user operation information,

[0874] A means for analyzing acquired operation information and converting it into text information,

[0875] A means of learning user operation patterns based on converted text information,

[0876] A means of automating tasks using learned operation patterns,

[0877] Means for acquiring video and audio information in order to recognize emotional states,

[0878] A means for analyzing acquired video and audio information to estimate emotional state,

[0879] Means for optimizing automated processing and feedback based on estimated emotional states,

[0880] A means for generating emotion-based feedback information for users,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, comprising means for recording user operation information and emotional information and transmitting them via a network.

[0884] (Claim 3)

[0885] The system according to claim 1, comprising means for generating automated processing and optimization suggestions based on analyzed operation information, voice information and emotion information. [Explanation of Symbols]

[0886] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining user operation information, A means for analyzing acquired operation information and converting it into text information, A means of learning user operation patterns based on converted text information, A means of automating tasks using learned operation patterns, A means for acquiring and analyzing voice input information, A means of performing automated processing based on analyzed audio information, A means for generating user feedback information, A system that includes this.

2. The system according to claim 1, further comprising means for recording user operation information and transmitting it via a network.

3. The system according to claim 1, comprising means for generating automated processing and optimization suggestions based on analyzed operation information and voice information.

Images