system

Abstract

We provide the system. [Solution] means of collecting information, A means of constructing a machine learning model using collected information, Support means for providing task assistance based on constructed machine learning models, An analytical method for analyzing and improving the execution data of task support, A condition diagnostic means for acquiring information from mechanical devices and identifying abnormalities, A means for proposing maintenance and management methods based on the condition diagnosis results, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In certain industries that require specialized knowledge, it is often difficult to secure appropriate personnel, and there is a demand for business support to improve productivity. On the other hand, in conventional technologies, it has not been easy to efficiently teach AI industry-specific knowledge and utilize it as an immediate combat force in actual business. As a result, there is a problem that the efficiency and quality of business decline due to the lack of specialized knowledge.

Means for Solving the Problems

[0005] To address this challenge, we have developed data collection methods for gathering data from specific industries and training methods for training machine learning models based on the collected data. Using the models obtained through this training, we have developed support tools to assist with business operations, enabling AI to streamline tasks with practical expertise. Furthermore, we have incorporated analytical tools to analyze the results of business support and improve the models, ensuring continuous improvement in performance. This compensates for the lack of expertise in specific industries and enables advanced business support.

[0006] A "data collection method" is a system for efficiently collecting relevant data from a specific industry.

[0007] "Training methods" refer to the process of training a machine learning model based on collected data to improve its performance.

[0008] "Support measures" refer to methods that utilize trained machine learning models to provide support for specific tasks and improve operational efficiency.

[0009] "Analysis methods" refer to the process of monitoring the performance of the AI ​​model by analyzing the results of business support, and making improvements as needed.

[0010] A "machine learning model" is an algorithm that learns patterns based on large amounts of data and uses them to make predictions and decisions. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4]This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled 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.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled 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, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention is an industry-specific AI agent system aimed at improving operational efficiency and leveraging expertise in specific industries. The system consists of a server, terminals, and users, each performing a specific function.

[0033] The server first collects the necessary data from industry specialists using APIs and other digital means. This may include text data, images, and audio data. After collection, the server analyzes this data through machine learning algorithms and performs training. This allows the AI ​​agent to acquire specialized knowledge.

[0034] The trained AI model is implemented into an AI agent running on the device. The support tools within the device utilize the AI ​​agent to assist client companies with their business operations. For example, the device analyzes user operation logs and suggests business processes that can be automated. Furthermore, the AI ​​agent can respond to user inquiries in real time through the device.

[0035] Users operate the terminal to utilize the system and streamline their work. For example, if a user consults an AI agent about proposed revisions to a design document, the AI ​​agent will provide the user with an appropriate answer based on relevant literature and a database of past cases. This allows users to perform advanced tasks even without specialized knowledge.

[0036] Through analytical means, the server continuously monitors the performance of the AI ​​agent and optimizes the model. This ensures that the AI ​​agent provides effective and efficient support for business operations. This process enables the application of critical expertise in specific industries and improves the productivity of businesses.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] The server uses APIs provided by industry specialists to collect the necessary data into the database. The data is stored in industry-standard formats and organized by category.

[0040] Step 2:

[0041] The server then starts training a machine learning model using the collected data. The training method combines supervised and unsupervised learning to teach the model industry-specific knowledge and patterns.

[0042] Step 3:

[0043] The server deploys the trained machine learning model to the terminal. The terminal then uses this model to function as an AI agent, preparing to perform specified business support tasks.

[0044] Step 4:

[0045] Users provide business-related data and inquiries to an AI agent through their device. The AI ​​agent analyzes the user's input and generates quick and accurate responses.

[0046] Step 5:

[0047] The device provides the user with responses and action suggestions generated by an AI agent. The user then proceeds with their tasks based on the provided information and provides feedback as needed.

[0048] Step 6:

[0049] The server analyzes performance data from terminals related to business support. Based on this analysis, it plans improvements and retraining of the AI ​​model to enhance system efficiency.

[0050] (Example 1)

[0051] 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."

[0052] Traditional industry-specific support systems operate with separate functions for data collection, model training, user support, and performance optimization, making seamless integration and efficiency improvements difficult. This challenge needs to be addressed to achieve automation and increased efficiency through consistent information utilization.

[0053] 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.

[0054] In this invention, the server includes data collection means for collecting necessary information from specialized institutions using digital means, data preprocessing means for preprocessing the collected information, and training means for training a machine learning structure based on the preprocessed information. This enables coordinated information processing and model optimization, thereby improving the efficiency and automation of business support.

[0055] "Data collection means" refers to the function of obtaining necessary information from specialized institutions using digital means.

[0056] "Data preprocessing means" refers to functions that clean and format information in order to improve the quality of collected information.

[0057] A "training method" is a function that executes a process to train a machine learning structure based on pre-processed information.

[0058] "Support tools" are functions that implement pre-trained machine learning structures to assist users with their work.

[0059] "Analysis tools" refer to functions for evaluating and optimizing the performance of user support activities.

[0060] "Preprocessing means" refers to a function that performs a process to improve the quality of collected information and prepare it for training.

[0061] An "automated response system" is a function that generates a quick and appropriate response based on user input.

[0062] This invention is an industry-specific AI agent system aimed at improving operational efficiency and leveraging expertise in specific industries. The system consists of a server, terminals, and users, with each component performing a specific function.

[0063] The server first collects necessary information from specialized organizations using APIs and other digital means. The information collected is diverse, including text data, images, and audio data. For example, the server obtains industry technical papers and market trend data via the internet. In this process, the server uses HTTP requests and collects data through secure access authentication.

[0064] Next, the server preprocesses the collected information to improve its quality. This involves analyzing the information using programming languages ​​such as Python or R, removing noise, and extracting important keywords. The preprocessed information is then used to train the machine learning model.

[0065] The server uses machine learning frameworks such as TENSORFLOW® or PyTorch to perform training using pre-processed information. The trained structure is then implemented on the terminal. The terminal utilizes this trained AI agent to prepare to provide optimal support tailored to the user's tasks.

[0066] The device interacts with the user using a pre-trained AI model. In this process, the device provides appropriate information in real time based on the user's prompts. For example, if the user inputs "I would like advice on designing a new product," the device extracts information from a database of past cases and relevant literature and presents it to the user.

[0067] Users can improve work efficiency by receiving assistance from AI agents through their devices. In particular, even users lacking specialized knowledge can perform tasks effectively with the AI ​​agent's suggestions. Furthermore, the server continuously analyzes the performance of work assistance provided by the devices and optimizes the machine learning model to improve the overall system's effectiveness. This optimization process ensures that the AI ​​agents are always receiving the latest information and algorithmic optimizations.

[0068] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0069] Step 1:

[0070] The server collects necessary information via APIs from specialized organizations. Inputs include URLs and API keys of industry-related data sources. The server uses this information to send HTTP requests and retrieve industry-related information in various formats, such as text data, images, and audio files. Output is a raw, unprocessed dataset.

[0071] Step 2:

[0072] The server preprocesses the collected raw data. The input is the unprocessed dataset obtained in the previous step. The server cleans the data, for example, by removing unnecessary symbols from text data and extracting important keywords. For image data, resolution adjustments and noise reduction are performed. The output is a preprocessed dataset with improved quality.

[0073] Step 3:

[0074] The server trains a machine learning model using preprocessed data. The input is a preprocessed dataset. The server uses frameworks such as TensorFlow or PyTorch to apply a recurrent neural network (RNN) to text data and a convolutional neural network (CNN) to image data. The output is the trained AI model.

[0075] Step 4:

[0076] A pre-trained AI model is implemented on the device. The input is the pre-trained AI model provided by the server. The device receives the model, verifies its operation, and prepares the user interface. The output is a device environment with an AI agent that the user can interact with.

[0077] Step 5:

[0078] The user interacts with the AI ​​agent through the device. The input is a prompt from the user. Based on this input, the device uses a trained AI model to perform analysis and generate appropriate information and advice. The output is a specific answer or suggestion to the user.

[0079] Step 6:

[0080] The server monitors and optimizes the performance of the AI ​​agent in supporting business operations. Inputs include activity logs and performance metrics from the terminal. The server analyzes this data to determine whether model improvements or training with new data are necessary. Outputs include the optimized AI model and any updates to it.

[0081] (Application Example 1)

[0082] 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."

[0083] In the manufacturing industry, the maintenance of machinery and equipment is often inefficient and time-consuming due to the need for specialized knowledge and judgment. Furthermore, failure to perform maintenance at the appropriate time can lead to equipment failure and decreased productivity. This invention aims to solve these problems by providing a system that evaluates equipment status in real time and offers an optimal maintenance plan.

[0084] 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.

[0085] In this invention, the server includes collection means for collecting information, construction means for building a machine learning model using the collected information, and condition diagnosis means for acquiring information from mechanical devices and identifying anomalies. This makes it possible for on-site staff to quickly and accurately grasp the status of equipment and perform efficient maintenance and management, even without specialized knowledge.

[0086] "Information" refers to data and knowledge, and in particular, the material that systems use for analysis and processing.

[0087] "Information gathering means" refers to a mechanism or device used to acquire necessary information.

[0088] "Construction method" refers to a method or process for generating or training a machine learning model based on collected information.

[0089] "Support measures" are auxiliary methods or systems used to streamline specific tasks or processes.

[0090] An "analytical means" is a mechanism established to analyze information in detail and to understand and evaluate its content.

[0091] A "mechanical device" is a physical instrument or system designed to perform a specific task.

[0092] A "condition diagnosis means" is a technique or method for evaluating the current state of a device or system and detecting abnormalities.

[0093] A "proposal mechanism" is a mechanism for suggesting optimal actions or plans based on collected or analyzed information.

[0094] "Specialized knowledge" refers to advanced information and understanding of a particular field, which is necessary to perform tasks in that field.

[0095] "Reconstruction methods" refer to the process of updating or retraining existing machine learning models to adapt them to new data.

[0096] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user.

[0097] First, the server uses hardware such as sensors and cameras to collect condition information from mechanical equipment within the factory. This information is acquired in real time using IoT technology and transmitted to the cloud. The server uses the collected information to build machine learning models and train generative AI models. This process uses data analysis software and high-performance computing resources to efficiently process large amounts of data. The trained AI models identify equipment anomalies and enable condition diagnosis.

[0098] Next, the terminal functions as an interface that visually displays machine status information and AI analysis results to the user. This is often done using mobile devices such as smartphones or tablets, allowing users to access the information through intuitive operation. Maintenance suggestions generated from the AI ​​diagnostic results are presented to the user on the terminal. These suggestions include specific advice, such as, "This part is worn out and needs to be replaced within a week."

[0099] Users can take swift action based on the information presented, minimizing equipment downtime. Specifically, this could involve equipment maintenance personnel reviewing suggestions displayed on a terminal, revising processes, and preparing necessary parts and tools.

[0100] An example of a prompt for a generated AI model is, "Analyze this dataset to identify abnormal behavioral patterns. Specify where and why maintenance is needed." Using this prompt, the AI ​​model effectively provides the user with the necessary information.

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The server collects real-time status information from mechanical equipment within the factory. Using hardware such as sensors and cameras, it acquires machine operation data and transfers it to a database in the cloud. The input is machine sensor data, and the output is data storage in the cloud.

[0104] Step 2:

[0105] The server preprocesses the collected data. It performs data cleaning and noise reduction, transforming it into a format usable by machine learning models. This process removes outliers and normalizes the data as time series data. The input is raw data, and the output is clean, preprocessed data.

[0106] Step 3:

[0107] The server uses pre-processed data to train a generative AI model. It applies machine learning algorithms to learn patterns of normal and abnormal behavior. The input is clean data, and the output is the trained AI model.

[0108] Step 4:

[0109] The terminal runs an AI model on the server to provide real-time diagnostics. When new machine operation data is input, the AI ​​model analyzes it and determines whether or not there are any abnormalities. The input is new sensor data, and the output is the diagnostic result.

[0110] Step 5:

[0111] The terminal notifies the user through a visual user interface based on the diagnostic results of the AI ​​model. Field staff use this interface to check recommended maintenance actions. The input is the diagnostic results, and the output is a maintenance suggestion that the user can visually understand.

[0112] Step 6:

[0113] The user operates a terminal and develops a maintenance plan for the equipment based on the presented maintenance suggestions. Based on the suggested actions, they prepare the necessary parts and tools and carry out the actual maintenance. The input is the maintenance suggestion, and the output is the implementation of the maintenance action.

[0114] 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.

[0115] This invention aims to provide more precise and effective support by combining a system designed to assist with business operations with an emotion engine that recognizes user emotions. This system consists of three elements: a server, a terminal, and a user, each playing a specific role.

[0116] First, the server collects large-scale industry-specific data and uses it to train the AI ​​model. Furthermore, an emotion engine collects user emotional data, which is then used to enhance the AI ​​model. This enables adaptive work support that takes the user's emotional state into account.

[0117] Next, the device functions as an AI agent using a pre-trained model provided by the server. This device incorporates an emotion engine that acquires real-time emotional data from the user. Based on this data, it determines the user's emotional state while performing tasks and provides optimal support. For example, if the user is experiencing stress, it can adjust the workload accordingly and offer appropriate advice.

[0118] Users interact with the AI ​​agent via their device. By inputting specific instructions regarding their tasks, they can receive real-time support from the AI ​​agent. For example, when a user is preparing a presentation, the AI ​​agent can offer advice based on past successes. Furthermore, it can provide appropriate resources and point out areas for improvement based on emotional data.

[0119] Finally, the server continuously analyzes emotional data and uses it to improve and train the AI ​​model. This process allows the system to evolve over time, enhancing its ability to provide optimized work support for each user. In this way, the system of the present invention, which integrates an emotional engine, enables more advanced and personalized work support.

[0120] The following describes the processing flow.

[0121] Step 1:

[0122] The server configures access to collect data from trusted industry experts and gathers the necessary industry data. The collected data is formatted and securely stored on the server.

[0123] Step 2:

[0124] The server starts training a machine learning model using the collected data. The training process uses the latest algorithms to ensure the model's accuracy and applicability.

[0125] Step 3:

[0126] The server uses an emotion engine to analyze user sentiment data and recognize specific patterns. This data is incorporated into the model's training data, optimizing the model to enable personalized output.

[0127] Step 4:

[0128] The device downloads a pre-trained model and runs it as an AI agent in the user's environment. The emotion engine on the device evaluates the user's emotional state in real time and provides the results to the agent.

[0129] Step 5:

[0130] Users input tasks and information into the terminal to request work assistance. The AI ​​agent takes action to provide optimal work assistance based on the user's input and emotional data.

[0131] Step 6:

[0132] The device notifies the user of specific advice and task adjustments based on the assistance of an AI agent. The user's responses are continuously evaluated by an emotion engine to ensure the assistance is appropriate.

[0133] Step 7:

[0134] The server collects emotional and performance data transmitted from terminals and uses it to further improve the AI ​​model. This data is regularly analyzed and used to provide feedback to the training process.

[0135] (Example 2)

[0136] 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".

[0137] Current business support systems provide uniform support without considering the user's feelings, making it difficult to provide effective support that addresses the diverse needs and circumstances of each user. Furthermore, existing machine learning models suffer from insufficient variation in collected data, making it difficult to provide highly accurate support.

[0138] 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.

[0139] In this invention, the server includes information gathering means for collecting user information, including emotional data; learning means for training an artificial intelligence model using the collected information; and auxiliary means for providing individualized work support based on the trained artificial intelligence model. This enables the reflection of the user's emotional state in real time, resulting in personalized and effective work support.

[0140] "Emotional data" refers to data that indicates the user's emotional state, and includes information such as tone of voice, facial expressions, and physical reactions.

[0141] "Information gathering means" refers to a device or method configured to collect user information, including emotional data.

[0142] An "artificial intelligence model" is an algorithm or framework that is trained based on collected information and used to provide business support based on emotional data.

[0143] A "learning tool" is a device or method for training an artificial intelligence model using collected data and improving its capabilities.

[0144] "Auxiliary means" refers to a device or function used to provide individualized business support by utilizing a trained artificial intelligence model.

[0145] "Interface means" refers to connection methods or devices for receiving emotional data from the user in real time.

[0146] "Analysis means" refers to a device or method for analyzing data obtained during the process of providing business support and for improving the effectiveness of the support provided.

[0147] A "retraining device" is a device or method for continuously updating an artificial intelligence model and retraining it based on new data.

[0148] To implement this invention, three elements are necessary: ​​a server, a terminal, and a user. The server first employs information gathering means to collect user information, including emotional data. This means can collect information from various data sources, such as the user's voice data and facial expression data. The collected data is processed by a learning means that trains an artificial intelligence model using a deep learning framework such as TensorFlow. The trained model is then delivered from the server to the terminal.

[0149] The terminal integrates an interface for collecting emotional data in real time. For example, the terminal can use its built-in camera and microphone to detect the user's voice tone and facial expressions, and analyze their emotional state based on this data. Based on this analyzed emotional data, the terminal can individually tailor work support to the user, providing appropriate advice and resources.

[0150] Users interact directly with the AI ​​agent via their device. By using prompts to communicate specific requests regarding their work, they can receive support from the device. For example, by entering a prompt such as, "Please help me prepare materials for next week's project meeting," users can receive advice from the AI ​​agent based on past success stories.

[0151] Furthermore, the server has analytical means to analyze emotional data and support results obtained during the business support process, evaluate the effectiveness of the support, and use this to improve the next model update. Through retraining means, the artificial intelligence model is continuously improved, enabling the provision of more accurate support. In this way, this invention enables personalized business support that responds to the user's emotional state.

[0152] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0153] Step 1:

[0154] The server collects data from various sources, including voice and facial expressions, to gather user emotional data. This data is stored in a database and used in subsequent training processes. Inputs are voice files and image data, and output is structured emotional data. This provides foundational data for precisely measuring the user's emotional state.

[0155] Step 2:

[0156] The server trains an artificial intelligence model using the collected sentiment data. This process involves analyzing the data using a deep learning framework, performing pattern recognition and feature extraction. The input is structured sentiment data, and the output is the trained artificial intelligence model. This allows the model to learn how to interpret the sentiment data, enabling accurate sentiment analysis.

[0157] Step 3:

[0158] The server delivers the trained model to the terminal and integrates the model into the terminal. The terminal prepares to acquire sentiment data from the user in real time using an interface. The input is the trained model data, and the output is the readiness state of the user's terminal for sentiment data processing. This allows the terminal to instantly determine the user's emotional state.

[0159] Step 4:

[0160] The device acquires audio and video data from the user in real time and analyzes it using a trained model. During this process, it senses changes in voice tone and facial expressions to estimate the user's emotional state. The input is the user's audio and video data, and the output is estimated emotional state information. This allows for the preparation of appropriate support for the user's work.

[0161] Step 5:

[0162] The device provides users with work-related support and advice based on analyzed emotional data. For example, it can suggest relaxation techniques to users experiencing stress. The input is estimated emotional state information, and the output is personalized support. This allows users to receive effective and appropriate support.

[0163] Step 6:

[0164] The server analyzes the effectiveness of daily work support and uses this information to improve the artificial intelligence model. By continuously collecting and analyzing user feedback and sentiment data, the model's accuracy is enhanced. The input is user feedback and support result data, and the output is the improved artificial intelligence model. This allows the system to evolve and increase its ability to provide support that is even more optimized for individual users.

[0165] (Application Example 2)

[0166] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0167] In modern home environments, there are limited means to effectively address residents' emotional needs and reduce stress. In particular, there is a need for a system that can grasp the emotional state of individual residents in real time and suggest appropriate relaxation methods. However, conventional technologies have not sufficiently automated the process of emotional recognition and the response based on that recognition, resulting in limited effectiveness.

[0168] 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.

[0169] In this invention, the server includes an information gathering means, an emotional data analysis means, and a resident care suggestion means. This makes it possible to precisely grasp the emotional state of each resident and provide stress reduction and relaxation support according to that state.

[0170] "Information gathering means" refers to devices or technologies that have the function of collecting data and collect various emotional data in the home environment.

[0171] A "machine learning model" is a mathematical model used by computers to perform specific tasks based on experience, and is designed to recognize data patterns and make predictions.

[0172] "Training methods" refer to the process of training a machine learning model using collected data, and are procedures for improving the accuracy of the model.

[0173] "Support tools" refer to functions that assist with tasks or operations based on trained machine learning models, and are methods for providing specific advice or suggestions.

[0174] "Analysis methods" refer to the process of analyzing performance data related to business support and using it to make improvements, playing a role in improving the overall efficiency of the system.

[0175] "Emotional data analysis means" refers to a function that analyzes emotional data in real time and determines the emotional state of residents, and is a technology that uses sensors and algorithms.

[0176] The "resident care suggestion tool" is a function that, based on analyzed emotional data, makes suggestions to support residents in reducing stress and promoting relaxation.

[0177] This system utilizes a new form of home robot to care for the emotions of its residents. A server collects large amounts of information, including emotional data, and uses this to train a machine learning model. TensorFlow is used as the software for analyzing the emotional data, and an algorithm written in Python identifies emotional patterns.

[0178] The home robot, which serves as the terminal, is equipped with emotion sensors and an inference engine, and monitors the resident's emotional state in real time. It analyzes this emotional data and suggests optimal relaxation methods tailored to the resident's stress level and emotional state. This includes suggesting music and rest options that match their emotions.

[0179] Through this system, users can receive emotional support in their daily lives. For example, when a user returns home from work, the system detects stress and plays relaxing music to create a comfortable environment. Furthermore, the generative AI model associated with this system can be further improved based on the following example prompts.

[0180] Examples of prompts to input into a generative AI model:

[0181] "Design a home-use emotion-recognizing robot that can detect the stress levels of its inhabitants and suggest relaxation methods."

[0182] In this way, the present invention adapts to the emotional state of residents in complex home environments and provides effective support tailored to individual needs.

[0183] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0184] Step 1:

[0185] The server receives emotional data collected from within the home and integrates it using data collection methods. The input to this process is raw data sent from sensors, and the output is an integrated emotional dataset. As part of data processing, this data is converted into a format compatible with the centralized management system. Specific operations include integrating timestamps for each emotional data point and converting between different data formats.

[0186] Step 2:

[0187] The server performs the following process: it trains a machine learning model using TensorFlow with the collected sentiment data. The input is the sentiment dataset integrated in step 1, and the output is the updated machine learning model. The data computation involves learning each sentiment pattern through the neural network and improving the model's accuracy. Specific operations include optimizing model parameters and evaluating accuracy.

[0188] Step 3:

[0189] The home robot, acting as a terminal, receives a trained machine learning model from a server and monitors the resident's emotional state in real time. This system utilizes emotional data analysis. The input is raw data obtained in real time from emotion sensors, and the output is the result of determining the resident's emotional state. Data processing involves applying an emotion classification algorithm to categorize emotions. Specific actions include the robot providing voice notifications based on the recognized emotions.

[0190] Step 4:

[0191] The user accepts stress reduction and relaxation methods suggested by the device. The resident care suggestion system functions, with input being data on the emotional state determined in step 3, and output being specific relaxation methods provided to the user. Data processing leads to the selection of appropriate music and action suggestions. Specific actions include the robot selecting and starting playback of music, or providing verbal explanations of rest suggestions.

[0192] 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.

[0193] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0194] 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.

[0195] [Second Embodiment]

[0196] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0197] 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.

[0198] 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).

[0199] 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.

[0200] 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.

[0201] 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).

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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".

[0208] This invention is an industry-specific AI agent system aimed at improving operational efficiency and leveraging expertise in specific industries. The system consists of a server, terminals, and users, each performing a specific function.

[0209] The server first collects the necessary data from industry specialists using APIs and other digital means. This may include text data, images, and audio data. After collection, the server analyzes this data through machine learning algorithms and performs training. This allows the AI ​​agent to acquire specialized knowledge.

[0210] The trained AI model is implemented into an AI agent running on the device. The support tools within the device utilize the AI ​​agent to assist client companies with their business operations. For example, the device analyzes user operation logs and suggests business processes that can be automated. Furthermore, the AI ​​agent can respond to user inquiries in real time through the device.

[0211] Users operate the terminal to utilize the system and streamline their work. For example, if a user consults an AI agent about proposed revisions to a design document, the AI ​​agent will provide the user with an appropriate answer based on relevant literature and a database of past cases. This allows users to perform advanced tasks even without specialized knowledge.

[0212] Through analytical means, the server continuously monitors the performance of the AI ​​agent and optimizes the model. This ensures that the AI ​​agent provides effective and efficient support for business operations. This process enables the application of critical expertise in specific industries and improves the productivity of businesses.

[0213] The following describes the processing flow.

[0214] Step 1:

[0215] The server uses APIs provided by industry specialists to collect the necessary data into the database. The data is stored in industry-standard formats and organized by category.

[0216] Step 2:

[0217] The server then starts training a machine learning model using the collected data. The training method combines supervised and unsupervised learning to teach the model industry-specific knowledge and patterns.

[0218] Step 3:

[0219] The server deploys the trained machine learning model to the terminal. The terminal then uses this model to function as an AI agent, preparing to perform specified business support tasks.

[0220] Step 4:

[0221] Users provide business-related data and inquiries to an AI agent through their device. The AI ​​agent analyzes the user's input and generates quick and accurate responses.

[0222] Step 5:

[0223] The device provides the user with responses and action suggestions generated by an AI agent. The user then proceeds with their tasks based on the provided information and provides feedback as needed.

[0224] Step 6:

[0225] The server analyzes performance data from terminals related to business support. Based on this analysis, it plans improvements and retraining of the AI ​​model to enhance system efficiency.

[0226] (Example 1)

[0227] 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."

[0228] Traditional industry-specific support systems operate with separate functions for data collection, model training, user support, and performance optimization, making seamless integration and efficiency improvements difficult. This challenge needs to be addressed to achieve automation and increased efficiency through consistent information utilization.

[0229] 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.

[0230] In this invention, the server includes data collection means for collecting necessary information from specialized institutions using digital means, data preprocessing means for preprocessing the collected information, and training means for training a machine learning structure based on the preprocessed information. This enables coordinated information processing and model optimization, thereby improving the efficiency and automation of business support.

[0231] "Data collection means" refers to the function of obtaining necessary information from specialized institutions using digital means.

[0232] "Data preprocessing means" refers to functions that clean and format information in order to improve the quality of collected information.

[0233] A "training method" is a function that executes a process to train a machine learning structure based on pre-processed information.

[0234] "Support tools" are functions that implement pre-trained machine learning structures to assist users with their work.

[0235] "Analysis tools" refer to functions for evaluating and optimizing the performance of user support activities.

[0236] "Preprocessing means" refers to a function that performs a process to improve the quality of collected information and prepare it for training.

[0237] An "automated response system" is a function that generates a quick and appropriate response based on user input.

[0238] This invention is an industry-specific AI agent system aimed at improving operational efficiency and leveraging expertise in specific industries. The system consists of a server, terminals, and users, with each component performing a specific function.

[0239] The server first collects necessary information from specialized organizations using APIs and other digital means. The information collected is diverse, including text data, images, and audio data. For example, the server obtains industry technical papers and market trend data via the internet. In this process, the server uses HTTP requests and collects data through secure access authentication.

[0240] Next, the server preprocesses the collected information to improve its quality. This involves analyzing the information using programming languages ​​such as Python or R, removing noise, and extracting important keywords. The preprocessed information is then used to train the machine learning model.

[0241] The server uses machine learning frameworks such as TensorFlow and PyTorch to perform training using pre-processed information. The trained structure is then implemented on the terminal. The terminal then utilizes this trained AI agent to prepare to provide optimal support tailored to the user's tasks.

[0242] The device interacts with the user using a pre-trained AI model. In this process, the device provides appropriate information in real time based on the user's prompts. For example, if the user inputs "I would like advice on designing a new product," the device extracts information from a database of past cases and relevant literature and presents it to the user.

[0243] Users can improve work efficiency by receiving assistance from AI agents through their devices. In particular, even users lacking specialized knowledge can perform tasks effectively with the AI ​​agent's suggestions. Furthermore, the server continuously analyzes the performance of work assistance provided by the devices and optimizes the machine learning model to improve the overall system's effectiveness. This optimization process ensures that the AI ​​agents are always receiving the latest information and algorithmic optimizations.

[0244] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0245] Step 1:

[0246] The server collects necessary information via APIs from specialized organizations. Inputs include URLs and API keys of industry-related data sources. The server uses this information to send HTTP requests and retrieve industry-related information in various formats, such as text data, images, and audio files. Output is a raw, unprocessed dataset.

[0247] Step 2:

[0248] The server preprocesses the collected raw data. The input is the unprocessed dataset obtained in the previous step. The server cleans the data, for example, by removing unnecessary symbols from text data and extracting important keywords. For image data, resolution adjustments and noise reduction are performed. The output is a preprocessed dataset with improved quality.

[0249] Step 3:

[0250] The server trains a machine learning model using preprocessed data. The input is a preprocessed dataset. The server uses frameworks such as TensorFlow or PyTorch to apply a recurrent neural network (RNN) to text data and a convolutional neural network (CNN) to image data. The output is the trained AI model.

[0251] Step 4:

[0252] A pre-trained AI model is implemented on the device. The input is the pre-trained AI model provided by the server. The device receives the model, verifies its operation, and prepares the user interface. The output is a device environment with an AI agent that the user can interact with.

[0253] Step 5:

[0254] The user interacts with the AI ​​agent through the device. The input is a prompt from the user. Based on this input, the device uses a trained AI model to perform analysis and generate appropriate information and advice. The output is a specific answer or suggestion to the user.

[0255] Step 6:

[0256] The server monitors and optimizes the performance of the AI ​​agent in supporting business operations. Inputs include activity logs and performance metrics from the terminal. The server analyzes this data to determine whether model improvements or training with new data are necessary. Outputs include the optimized AI model and any updates to it.

[0257] (Application Example 1)

[0258] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0259] In the manufacturing industry, the maintenance of machinery and equipment is often inefficient and time-consuming due to the need for specialized knowledge and judgment. Furthermore, failure to perform maintenance at the appropriate time can lead to equipment failure and decreased productivity. This invention aims to solve these problems by providing a system that evaluates equipment status in real time and offers an optimal maintenance plan.

[0260] 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.

[0261] In this invention, the server includes collection means for collecting information, construction means for building a machine learning model using the collected information, and condition diagnosis means for acquiring information from mechanical devices and identifying anomalies. This makes it possible for on-site staff to quickly and accurately grasp the status of equipment and perform efficient maintenance and management, even without specialized knowledge.

[0262] "Information" refers to data and knowledge, and in particular, the material that systems use for analysis and processing.

[0263] "Information gathering means" refers to a mechanism or device used to acquire necessary information.

[0264] "Construction method" refers to a method or process for generating or training a machine learning model based on collected information.

[0265] "Support measures" are auxiliary methods or systems used to streamline specific tasks or processes.

[0266] An "analytical means" is a mechanism established to analyze information in detail and to understand and evaluate its content.

[0267] A "mechanical device" is a physical instrument or system designed to perform a specific task.

[0268] A "condition diagnosis means" is a technique or method for evaluating the current state of a device or system and detecting abnormalities.

[0269] A "proposal mechanism" is a mechanism for suggesting optimal actions or plans based on collected or analyzed information.

[0270] "Specialized knowledge" refers to advanced information and understanding of a particular field, which is necessary to perform tasks in that field.

[0271] "Reconstruction methods" refer to the process of updating or retraining existing machine learning models to adapt them to new data.

[0272] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user.

[0273] First, the server uses hardware such as sensors and cameras to collect condition information from mechanical equipment within the factory. This information is acquired in real time using IoT technology and transmitted to the cloud. The server uses the collected information to build machine learning models and train generative AI models. This process uses data analysis software and high-performance computing resources to efficiently process large amounts of data. The trained AI models identify equipment anomalies and enable condition diagnosis.

[0274] Next, the terminal functions as an interface that visually displays machine status information and AI analysis results to the user. This is often done using mobile devices such as smartphones or tablets, allowing users to access the information through intuitive operation. Maintenance suggestions generated from the AI ​​diagnostic results are presented to the user on the terminal. These suggestions include specific advice, such as, "This part is worn out and needs to be replaced within a week."

[0275] Users can take swift action based on the information presented, minimizing equipment downtime. Specifically, this could involve equipment maintenance personnel reviewing suggestions displayed on a terminal, revising processes, and preparing necessary parts and tools.

[0276] An example of a prompt for a generated AI model is, "Analyze this dataset to identify abnormal behavioral patterns. Specify where and why maintenance is needed." Using this prompt, the AI ​​model effectively provides the user with the necessary information.

[0277] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0278] Step 1:

[0279] The server collects status information in real time from mechanical equipment within the factory. Using hardware such as sensors and cameras, it acquires machine operation data and transfers it to a database in the cloud. The input is machine sensor data, and the output is data storage in the cloud.

[0280] Step 2:

[0281] The server preprocesses the collected data. It performs data cleaning and noise removal, and processes it into a form that can be used by the machine learning model. In this process, outliers in the data are removed and it is normalized as time series data. The input is raw data, and the output is clean data that has been preprocessed.

[0282] Step 3:

[0283] The server uses the preprocessed data to train a generative AI model. It applies machine learning algorithms to learn the patterns of normal and abnormal operations. The input is clean data, and the output is a trained AI model.

[0284] Step 4:

[0285] The terminal executes the AI model on the server to provide real-time diagnosis. When new operation data of the machine is input, the AI model analyzes it and determines whether there is an abnormality. The input is new sensor data, and the output is the diagnosis result.

[0286] Step 5:

[0287] The terminal notifies the user through a visual user interface based on the diagnosis result of the AI model. The on-site staff uses this interface to check the recommended maintenance actions. The input is the diagnosis result, and the output is a maintenance proposal that the user can visually recognize.

[0288] Step 6:

[0289] The user operates the terminal and formulates a facility maintenance plan based on the presented maintenance proposal. Based on the proposed actions, the necessary parts and tools are prepared and the actual maintenance is carried out. The input is the maintenance proposal, and the output is the implementation of maintenance actions.

[0290] 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.

[0291] This invention aims to provide more precise and effective support by combining a system designed to assist with business operations with an emotion engine that recognizes user emotions. This system consists of three elements: a server, a terminal, and a user, each playing a specific role.

[0292] First, the server collects large-scale industry-specific data and uses it to train the AI ​​model. Furthermore, an emotion engine collects user emotional data, which is then used to enhance the AI ​​model. This enables adaptive work support that takes the user's emotional state into account.

[0293] Next, the device functions as an AI agent using a pre-trained model provided by the server. This device incorporates an emotion engine that acquires real-time emotional data from the user. Based on this data, it determines the user's emotional state while performing tasks and provides optimal support. For example, if the user is experiencing stress, it can adjust the workload accordingly and offer appropriate advice.

[0294] Users interact with the AI ​​agent via their device. By inputting specific instructions regarding their tasks, they can receive real-time support from the AI ​​agent. For example, when a user is preparing a presentation, the AI ​​agent can offer advice based on past successes. Furthermore, it can provide appropriate resources and point out areas for improvement based on emotional data.

[0295] Finally, the server continuously analyzes emotional data and uses it to improve and train the AI ​​model. This process allows the system to evolve over time, enhancing its ability to provide optimized work support for each user. In this way, the system of the present invention, which integrates an emotional engine, enables more advanced and personalized work support.

[0296] The following describes the processing flow.

[0297] Step 1:

[0298] The server configures access to collect data from trusted industry experts and gathers the necessary industry data. The collected data is formatted and securely stored on the server.

[0299] Step 2:

[0300] The server starts training a machine learning model using the collected data. The training process uses the latest algorithms to ensure the model's accuracy and applicability.

[0301] Step 3:

[0302] The server uses an emotion engine to analyze user sentiment data and recognize specific patterns. This data is incorporated into the model's training data, optimizing the model to enable personalized output.

[0303] Step 4:

[0304] The device downloads a pre-trained model and runs it as an AI agent in the user's environment. The emotion engine on the device evaluates the user's emotional state in real time and provides the results to the agent.

[0305] Step 5:

[0306] The user inputs tasks and information into the terminal and requests business support. Based on the user's input and sentiment data, the AI agent executes actions to provide optimal business support.

[0307] Step 6:

[0308] Based on the support of the AI agent, the terminal notifies the user of specific advice and task adjustments. Continuously evaluate the user's reaction with the sentiment engine to confirm that the support content is appropriate.

[0309] Step 7:

[0310] The server collects the sentiment and business performance data sent from the terminal and uses it to further improve the AI model. Regularly analyze this data and provide feedback to the training process.

[0311] (Example 2)

[0312] Next, Example 2 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".

[0313] In the current business support system, it is difficult to provide effective support corresponding to different needs and situations for each user because it provides uniform support without considering the user's sentiment. In addition, existing machine learning models have the problem that it is difficult to provide high-precision support because the variations in the collected data are insufficient.

[0314] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0315] In this invention, the server includes information gathering means for collecting user information, including emotional data; learning means for training an artificial intelligence model using the collected information; and auxiliary means for providing individualized work support based on the trained artificial intelligence model. This enables the reflection of the user's emotional state in real time, resulting in personalized and effective work support.

[0316] "Emotional data" refers to data that indicates the user's emotional state, and includes information such as tone of voice, facial expressions, and physical reactions.

[0317] "Information gathering means" refers to a device or method configured to collect user information, including emotional data.

[0318] An "artificial intelligence model" is an algorithm or framework that is trained based on collected information and used to provide business support based on emotional data.

[0319] A "learning tool" is a device or method for training an artificial intelligence model using collected data and improving its capabilities.

[0320] "Auxiliary means" refers to a device or function used to provide individualized business support by utilizing a trained artificial intelligence model.

[0321] "Interface means" refers to connection methods or devices for receiving emotional data from the user in real time.

[0322] "Analysis means" refers to a device or method for analyzing data obtained during the process of providing business support and for improving the effectiveness of the support provided.

[0323] A "retraining device" is a device or method for continuously updating an artificial intelligence model and retraining it based on new data.

[0324] To implement this invention, three elements are necessary: ​​a server, a terminal, and a user. The server first employs information gathering means to collect user information, including emotional data. This means can collect information from various data sources, such as the user's voice data and facial expression data. The collected data is processed by a learning means that trains an artificial intelligence model using a deep learning framework such as TensorFlow. The trained model is then delivered from the server to the terminal.

[0325] The terminal integrates an interface for collecting emotional data in real time. For example, the terminal can use its built-in camera and microphone to detect the user's voice tone and facial expressions, and analyze their emotional state based on this data. Based on this analyzed emotional data, the terminal can individually tailor work support to the user, providing appropriate advice and resources.

[0326] Users interact directly with the AI ​​agent via their device. By using prompts to communicate specific requests regarding their work, they can receive support from the device. For example, by entering a prompt such as, "Please help me prepare materials for next week's project meeting," users can receive advice from the AI ​​agent based on past success stories.

[0327] Furthermore, the server has analytical means to analyze emotional data and support results obtained during the business support process, evaluate the effectiveness of the support, and use this to improve the next model update. Through retraining means, the artificial intelligence model is continuously improved, enabling the provision of more accurate support. In this way, this invention enables personalized business support that responds to the user's emotional state.

[0328] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0329] Step 1:

[0330] The server collects data from various sources, including voice and facial expressions, to gather user emotional data. This data is stored in a database and used in subsequent training processes. Inputs are voice files and image data, and output is structured emotional data. This provides foundational data for precisely measuring the user's emotional state.

[0331] Step 2:

[0332] The server trains an artificial intelligence model using the collected sentiment data. This process involves analyzing the data using a deep learning framework, performing pattern recognition and feature extraction. The input is structured sentiment data, and the output is the trained artificial intelligence model. This allows the model to learn how to interpret the sentiment data, enabling accurate sentiment analysis.

[0333] Step 3:

[0334] The server delivers the trained model to the terminal and integrates the model into the terminal. The terminal prepares to acquire sentiment data from the user in real time using an interface. The input is the trained model data, and the output is the readiness state of the user's terminal for sentiment data processing. This allows the terminal to instantly determine the user's emotional state.

[0335] Step 4:

[0336] The device acquires audio and video data from the user in real time and analyzes it using a trained model. During this process, it senses changes in voice tone and facial expressions to estimate the user's emotional state. The input is the user's audio and video data, and the output is estimated emotional state information. This allows for the preparation of appropriate support for the user's work.

[0337] Step 5:

[0338] The device provides users with work-related support and advice based on analyzed emotional data. For example, it can suggest relaxation techniques to users experiencing stress. The input is estimated emotional state information, and the output is personalized support. This allows users to receive effective and appropriate support.

[0339] Step 6:

[0340] The server analyzes the effectiveness of daily work support and uses this information to improve the artificial intelligence model. By continuously collecting and analyzing user feedback and sentiment data, the model's accuracy is enhanced. The input is user feedback and support result data, and the output is the improved artificial intelligence model. This allows the system to evolve and increase its ability to provide support that is even more optimized for individual users.

[0341] (Application Example 2)

[0342] 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."

[0343] In modern home environments, there are limited means to effectively address residents' emotional needs and reduce stress. In particular, there is a need for a system that can grasp the emotional state of individual residents in real time and suggest appropriate relaxation methods. However, conventional technologies have not sufficiently automated the process of emotional recognition and the response based on that recognition, resulting in limited effectiveness.

[0344] 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.

[0345] In this invention, the server includes an information gathering means, an emotional data analysis means, and a resident care suggestion means. This makes it possible to precisely grasp the emotional state of each resident and provide stress reduction and relaxation support according to that state.

[0346] "Information gathering means" refers to devices or technologies that have the function of collecting data and collect various emotional data in the home environment.

[0347] A "machine learning model" is a mathematical model used by computers to perform specific tasks based on experience, and is designed to recognize data patterns and make predictions.

[0348] "Training methods" refer to the process of training a machine learning model using collected data, and are procedures for improving the accuracy of the model.

[0349] "Support tools" refer to functions that assist with tasks or operations based on trained machine learning models, and are methods for providing specific advice or suggestions.

[0350] "Analysis methods" refer to the process of analyzing performance data related to business support and using it to make improvements, playing a role in improving the overall efficiency of the system.

[0351] "Emotional data analysis means" refers to a function that analyzes emotional data in real time and determines the emotional state of residents, and is a technology that uses sensors and algorithms.

[0352] The "resident care suggestion tool" is a function that, based on analyzed emotional data, makes suggestions to support residents in reducing stress and promoting relaxation.

[0353] This system utilizes a new form of home robot to care for the emotions of its residents. A server collects large amounts of information, including emotional data, and uses this to train a machine learning model. TensorFlow is used as the software for analyzing the emotional data, and an algorithm written in Python identifies emotional patterns.

[0354] The home robot, which serves as the terminal, is equipped with emotion sensors and an inference engine, and monitors the resident's emotional state in real time. It analyzes this emotional data and suggests optimal relaxation methods tailored to the resident's stress level and emotional state. This includes suggesting music and rest options that match their emotions.

[0355] Through this system, users can receive emotional support in their daily lives. For example, when a user returns home from work, the system detects stress and plays relaxing music to create a comfortable environment. Furthermore, the generative AI model associated with this system can be further improved based on the following example prompts.

[0356] Examples of prompts to input into a generative AI model:

[0357] "Design a home-use emotion-recognizing robot that can detect the stress levels of its inhabitants and suggest relaxation methods."

[0358] In this way, the present invention adapts to the emotional state of residents in complex home environments and provides effective support tailored to individual needs.

[0359] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0360] Step 1:

[0361] The server receives emotional data collected from within the home and integrates it using data collection methods. The input to this process is raw data sent from sensors, and the output is an integrated emotional dataset. As part of data processing, this data is converted into a format compatible with the centralized management system. Specific operations include integrating timestamps for each emotional data point and converting between different data formats.

[0362] Step 2:

[0363] The server performs the following process: it trains a machine learning model using TensorFlow with the collected sentiment data. The input is the sentiment dataset integrated in step 1, and the output is the updated machine learning model. The data computation involves learning each sentiment pattern through the neural network and improving the model's accuracy. Specific operations include optimizing model parameters and evaluating accuracy.

[0364] Step 3:

[0365] The home robot, acting as a terminal, receives a trained machine learning model from a server and monitors the resident's emotional state in real time. This system utilizes emotional data analysis. The input is raw data obtained in real time from emotion sensors, and the output is the result of determining the resident's emotional state. Data processing involves applying an emotion classification algorithm to categorize emotions. Specific actions include the robot providing voice notifications based on the recognized emotions.

[0366] Step 4:

[0367] The user accepts stress reduction and relaxation methods suggested by the device. The resident care suggestion system functions, with input being data on the emotional state determined in step 3, and output being specific relaxation methods provided to the user. Data processing leads to the selection of appropriate music and action suggestions. Specific actions include the robot selecting and starting playback of music, or providing verbal explanations of rest suggestions.

[0368] 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.

[0369] 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.

[0370] 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.

[0371] [Third Embodiment]

[0372] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0373] 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.

[0374] 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).

[0375] 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.

[0376] 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.

[0377] 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).

[0378] 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.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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".

[0384] This invention is an industry-specific AI agent system aimed at improving operational efficiency and leveraging expertise in specific industries. The system consists of a server, terminals, and users, each performing a specific function.

[0385] The server first collects the necessary data from industry specialists using APIs and other digital means. This may include text data, images, and audio data. After collection, the server analyzes this data through machine learning algorithms and performs training. This allows the AI ​​agent to acquire specialized knowledge.

[0386] The trained AI model is implemented into an AI agent running on the device. The support tools within the device utilize the AI ​​agent to assist client companies with their business operations. For example, the device analyzes user operation logs and suggests business processes that can be automated. Furthermore, the AI ​​agent can respond to user inquiries in real time through the device.

[0387] Users operate the terminal to utilize the system and streamline their work. For example, if a user consults an AI agent about proposed revisions to a design document, the AI ​​agent will provide the user with an appropriate answer based on relevant literature and a database of past cases. This allows users to perform advanced tasks even without specialized knowledge.

[0388] Through analytical means, the server continuously monitors the performance of the AI ​​agent and optimizes the model. This ensures that the AI ​​agent provides effective and efficient support for business operations. This process enables the application of critical expertise in specific industries and improves the productivity of businesses.

[0389] The following describes the processing flow.

[0390] Step 1:

[0391] The server uses APIs provided by industry specialists to collect the necessary data into the database. The data is stored in industry-standard formats and organized by category.

[0392] Step 2:

[0393] The server then starts training a machine learning model using the collected data. The training method combines supervised and unsupervised learning to teach the model industry-specific knowledge and patterns.

[0394] Step 3:

[0395] The server deploys the trained machine learning model to the terminal. The terminal then uses this model to function as an AI agent, preparing to perform specified business support tasks.

[0396] Step 4:

[0397] Users provide business-related data and inquiries to an AI agent through their device. The AI ​​agent analyzes the user's input and generates quick and accurate responses.

[0398] Step 5:

[0399] The device provides the user with responses and action suggestions generated by an AI agent. The user then proceeds with their tasks based on the provided information and provides feedback as needed.

[0400] Step 6:

[0401] The server analyzes performance data from terminals related to business support. Based on this analysis, it plans improvements and retraining of the AI ​​model to enhance system efficiency.

[0402] (Example 1)

[0403] 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."

[0404] Traditional industry-specific support systems operate with separate functions for data collection, model training, user support, and performance optimization, making seamless integration and efficiency improvements difficult. This challenge needs to be addressed to achieve automation and increased efficiency through consistent information utilization.

[0405] 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.

[0406] In this invention, the server includes data collection means for collecting necessary information from specialized institutions using digital means, data preprocessing means for preprocessing the collected information, and training means for training a machine learning structure based on the preprocessed information. This enables coordinated information processing and model optimization, thereby improving the efficiency and automation of business support.

[0407] "Data collection means" refers to the function of obtaining necessary information from specialized institutions using digital means.

[0408] "Data preprocessing means" refers to functions that clean and format information in order to improve the quality of collected information.

[0409] A "training method" is a function that executes a process to train a machine learning structure based on pre-processed information.

[0410] "Support tools" are functions that implement pre-trained machine learning structures to assist users with their work.

[0411] "Analysis tools" refer to functions for evaluating and optimizing the performance of user support activities.

[0412] "Preprocessing means" refers to a function that performs a process to improve the quality of collected information and prepare it for training.

[0413] An "automated response system" is a function that generates a quick and appropriate response based on user input.

[0414] This invention is an industry-specific AI agent system aimed at improving operational efficiency and leveraging expertise in specific industries. The system consists of a server, terminals, and users, with each component performing a specific function.

[0415] The server first collects necessary information from specialized organizations using APIs and other digital means. The information collected is diverse, including text data, images, and audio data. For example, the server obtains industry technical papers and market trend data via the internet. In this process, the server uses HTTP requests and collects data through secure access authentication.

[0416] Next, the server preprocesses the collected information to improve its quality. This involves analyzing the information using programming languages ​​such as Python or R, removing noise, and extracting important keywords. The preprocessed information is then used to train the machine learning model.

[0417] The server uses machine learning frameworks such as TensorFlow and PyTorch to perform training using pre-processed information. The trained structure is then implemented on the terminal. The terminal then utilizes this trained AI agent to prepare to provide optimal support tailored to the user's tasks.

[0418] The device interacts with the user using a pre-trained AI model. In this process, the device provides appropriate information in real time based on the user's prompts. For example, if the user inputs "I would like advice on designing a new product," the device extracts information from a database of past cases and relevant literature and presents it to the user.

[0419] Users can improve work efficiency by receiving assistance from AI agents through their devices. In particular, even users lacking specialized knowledge can perform tasks effectively with the AI ​​agent's suggestions. Furthermore, the server continuously analyzes the performance of work assistance provided by the devices and optimizes the machine learning model to improve the overall system's effectiveness. This optimization process ensures that the AI ​​agents are always receiving the latest information and algorithmic optimizations.

[0420] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0421] Step 1:

[0422] The server collects necessary information via APIs from specialized organizations. Inputs include URLs and API keys of industry-related data sources. The server uses this information to send HTTP requests and retrieve industry-related information in various formats, such as text data, images, and audio files. Output is a raw, unprocessed dataset.

[0423] Step 2:

[0424] The server preprocesses the collected raw data. The input is the unprocessed dataset obtained in the previous step. The server cleans the data, for example, by removing unnecessary symbols from text data and extracting important keywords. For image data, resolution adjustments and noise reduction are performed. The output is a preprocessed dataset with improved quality.

[0425] Step 3:

[0426] The server trains a machine learning model using preprocessed data. The input is a preprocessed dataset. The server uses frameworks such as TensorFlow or PyTorch to apply a recurrent neural network (RNN) to text data and a convolutional neural network (CNN) to image data. The output is the trained AI model.

[0427] Step 4:

[0428] A pre-trained AI model is implemented on the device. The input is the pre-trained AI model provided by the server. The device receives the model, verifies its operation, and prepares the user interface. The output is a device environment with an AI agent that the user can interact with.

[0429] Step 5:

[0430] The user interacts with the AI ​​agent through the device. The input is a prompt from the user. Based on this input, the device uses a trained AI model to perform analysis and generate appropriate information and advice. The output is a specific answer or suggestion to the user.

[0431] Step 6:

[0432] The server monitors and optimizes the performance of the AI ​​agent in supporting business operations. Inputs include activity logs and performance metrics from the terminal. The server analyzes this data to determine whether model improvements or training with new data are necessary. Outputs include the optimized AI model and any updates to it.

[0433] (Application Example 1)

[0434] 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."

[0435] In the manufacturing industry, the maintenance of machinery and equipment is often inefficient and time-consuming due to the need for specialized knowledge and judgment. Furthermore, failure to perform maintenance at the appropriate time can lead to equipment failure and decreased productivity. This invention aims to solve these problems by providing a system that evaluates equipment status in real time and offers an optimal maintenance plan.

[0436] 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.

[0437] In this invention, the server includes collection means for collecting information, construction means for building a machine learning model using the collected information, and condition diagnosis means for acquiring information from mechanical devices and identifying anomalies. This makes it possible for on-site staff to quickly and accurately grasp the status of equipment and perform efficient maintenance and management, even without specialized knowledge.

[0438] "Information" refers to data and knowledge, and in particular, the material that systems use for analysis and processing.

[0439] "Information gathering means" refers to a mechanism or device used to acquire necessary information.

[0440] "Construction method" refers to a method or process for generating or training a machine learning model based on collected information.

[0441] "Support measures" are auxiliary methods or systems used to streamline specific tasks or processes.

[0442] An "analytical means" is a mechanism established to analyze information in detail and to understand and evaluate its content.

[0443] A "mechanical device" is a physical instrument or system designed to perform a specific task.

[0444] A "condition diagnosis means" is a technique or method for evaluating the current state of a device or system and detecting abnormalities.

[0445] A "proposal mechanism" is a mechanism for suggesting optimal actions or plans based on collected or analyzed information.

[0446] "Specialized knowledge" refers to advanced information and understanding of a particular field, which is necessary to perform tasks in that field.

[0447] "Reconstruction methods" refer to the process of updating or retraining existing machine learning models to adapt them to new data.

[0448] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user.

[0449] First, the server uses hardware such as sensors and cameras to collect condition information from mechanical equipment within the factory. This information is acquired in real time using IoT technology and transmitted to the cloud. The server uses the collected information to build machine learning models and train generative AI models. This process uses data analysis software and high-performance computing resources to efficiently process large amounts of data. The trained AI models identify equipment anomalies and enable condition diagnosis.

[0450] Next, the terminal functions as an interface that visually displays machine status information and AI analysis results to the user. This is often done using mobile devices such as smartphones or tablets, allowing users to access the information through intuitive operation. Maintenance suggestions generated from the AI ​​diagnostic results are presented to the user on the terminal. These suggestions include specific advice, such as, "This part is worn out and needs to be replaced within a week."

[0451] Users can take swift action based on the information presented, minimizing equipment downtime. Specifically, this could involve equipment maintenance personnel reviewing suggestions displayed on a terminal, revising processes, and preparing necessary parts and tools.

[0452] An example of a prompt for a generated AI model is, "Analyze this dataset to identify abnormal behavioral patterns. Specify where and why maintenance is needed." Using this prompt, the AI ​​model effectively provides the user with the necessary information.

[0453] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0454] Step 1:

[0455] The server collects status information in real time from mechanical equipment within the factory. Using hardware such as sensors and cameras, it acquires machine operation data and transfers it to a database in the cloud. The input is machine sensor data, and the output is data storage in the cloud.

[0456] Step 2:

[0457] The server preprocesses the collected data. It performs data cleaning and noise reduction, transforming it into a format usable by machine learning models. This process removes outliers and normalizes the data as time series data. The input is raw data, and the output is clean, preprocessed data.

[0458] Step 3:

[0459] The server uses pre-processed data to train a generative AI model. It applies machine learning algorithms to learn patterns of normal and abnormal behavior. The input is clean data, and the output is the trained AI model.

[0460] Step 4:

[0461] The terminal runs an AI model on the server to provide real-time diagnostics. When new machine operation data is input, the AI ​​model analyzes it and determines whether or not there are any abnormalities. The input is new sensor data, and the output is the diagnostic result.

[0462] Step 5:

[0463] The terminal notifies the user through a visual user interface based on the diagnostic results of the AI ​​model. Field staff use this interface to check recommended maintenance actions. The input is the diagnostic results, and the output is a maintenance suggestion that the user can visually understand.

[0464] Step 6:

[0465] The user operates a terminal and develops a maintenance plan for the equipment based on the presented maintenance suggestions. Based on the suggested actions, they prepare the necessary parts and tools and carry out the actual maintenance. The input is the maintenance suggestion, and the output is the implementation of the maintenance action.

[0466] 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.

[0467] This invention aims to provide more precise and effective support by combining a system designed to assist with business operations with an emotion engine that recognizes user emotions. This system consists of three elements: a server, a terminal, and a user, each playing a specific role.

[0468] First, the server collects large-scale industry-specific data and uses it to train the AI ​​model. Furthermore, an emotion engine collects user emotional data, which is then used to enhance the AI ​​model. This enables adaptive work support that takes the user's emotional state into account.

[0469] Next, the device functions as an AI agent using a pre-trained model provided by the server. This device incorporates an emotion engine that acquires real-time emotional data from the user. Based on this data, it determines the user's emotional state while performing tasks and provides optimal support. For example, if the user is experiencing stress, it can adjust the workload accordingly and offer appropriate advice.

[0470] Users interact with the AI ​​agent via their device. By inputting specific instructions regarding their tasks, they can receive real-time support from the AI ​​agent. For example, when a user is preparing a presentation, the AI ​​agent can offer advice based on past successes. Furthermore, it can provide appropriate resources and point out areas for improvement based on emotional data.

[0471] Finally, the server continuously analyzes emotional data and uses it to improve and train the AI ​​model. This process allows the system to evolve over time, enhancing its ability to provide optimized work support for each user. In this way, the system of the present invention, which integrates an emotional engine, enables more advanced and personalized work support.

[0472] The following describes the processing flow.

[0473] Step 1:

[0474] The server configures access to collect data from trusted industry experts and gathers the necessary industry data. The collected data is formatted and securely stored on the server.

[0475] Step 2:

[0476] The server starts training a machine learning model using the collected data. The training process uses the latest algorithms to ensure the model's accuracy and applicability.

[0477] Step 3:

[0478] The server uses an emotion engine to analyze user sentiment data and recognize specific patterns. This data is incorporated into the model's training data, optimizing the model to enable personalized output.

[0479] Step 4:

[0480] The device downloads a pre-trained model and runs it as an AI agent in the user's environment. The emotion engine on the device evaluates the user's emotional state in real time and provides the results to the agent.

[0481] Step 5:

[0482] Users input tasks and information into the terminal to request work assistance. The AI ​​agent takes action to provide optimal work assistance based on the user's input and emotional data.

[0483] Step 6:

[0484] The device notifies the user of specific advice and task adjustments based on the assistance of an AI agent. The user's responses are continuously evaluated by an emotion engine to ensure the assistance is appropriate.

[0485] Step 7:

[0486] The server collects emotional and performance data transmitted from terminals and uses it to further improve the AI ​​model. This data is regularly analyzed and used to provide feedback to the training process.

[0487] (Example 2)

[0488] 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."

[0489] Current business support systems provide uniform support without considering the user's feelings, making it difficult to provide effective support that addresses the diverse needs and circumstances of each user. Furthermore, existing machine learning models suffer from insufficient variation in collected data, making it difficult to provide highly accurate support.

[0490] 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.

[0491] In this invention, the server includes information gathering means for collecting user information, including emotional data; learning means for training an artificial intelligence model using the collected information; and auxiliary means for providing individualized work support based on the trained artificial intelligence model. This enables the reflection of the user's emotional state in real time, resulting in personalized and effective work support.

[0492] "Emotional data" refers to data that indicates the user's emotional state, and includes information such as tone of voice, facial expressions, and physical reactions.

[0493] "Information gathering means" refers to a device or method configured to collect user information, including emotional data.

[0494] An "artificial intelligence model" is an algorithm or framework that is trained based on collected information and used to provide business support based on emotional data.

[0495] A "learning tool" is a device or method for training an artificial intelligence model using collected data and improving its capabilities.

[0496] "Auxiliary means" refers to a device or function used to provide individualized business support by utilizing a trained artificial intelligence model.

[0497] "Interface means" refers to connection methods or devices for receiving emotional data from the user in real time.

[0498] "Analysis means" refers to a device or method for analyzing data obtained during the process of providing business support and for improving the effectiveness of the support provided.

[0499] A "retraining device" is a device or method for continuously updating an artificial intelligence model and retraining it based on new data.

[0500] To implement this invention, three elements are necessary: ​​a server, a terminal, and a user. The server first employs information gathering means to collect user information, including emotional data. This means can collect information from various data sources, such as the user's voice data and facial expression data. The collected data is processed by a learning means that trains an artificial intelligence model using a deep learning framework such as TensorFlow. The trained model is then delivered from the server to the terminal.

[0501] The terminal integrates an interface for collecting emotional data in real time. For example, the terminal can use its built-in camera and microphone to detect the user's voice tone and facial expressions, and analyze their emotional state based on this data. Based on this analyzed emotional data, the terminal can individually tailor work support to the user, providing appropriate advice and resources.

[0502] Users interact directly with the AI ​​agent via their device. By using prompts to communicate specific requests regarding their work, they can receive support from the device. For example, by entering a prompt such as, "Please help me prepare materials for next week's project meeting," users can receive advice from the AI ​​agent based on past success stories.

[0503] Furthermore, the server has analytical means to analyze emotional data and support results obtained during the business support process, evaluate the effectiveness of the support, and use this to improve the next model update. Through retraining means, the artificial intelligence model is continuously improved, enabling the provision of more accurate support. In this way, this invention enables personalized business support that responds to the user's emotional state.

[0504] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0505] Step 1:

[0506] The server collects data from various sources, including voice and facial expressions, to gather user emotional data. This data is stored in a database and used in subsequent training processes. Inputs are voice files and image data, and output is structured emotional data. This provides foundational data for precisely measuring the user's emotional state.

[0507] Step 2:

[0508] The server trains an artificial intelligence model using the collected sentiment data. This process involves analyzing the data using a deep learning framework, performing pattern recognition and feature extraction. The input is structured sentiment data, and the output is the trained artificial intelligence model. This allows the model to learn how to interpret the sentiment data, enabling accurate sentiment analysis.

[0509] Step 3:

[0510] The server delivers the trained model to the terminal and integrates the model into the terminal. The terminal prepares to acquire sentiment data from the user in real time using an interface. The input is the trained model data, and the output is the readiness state of the user's terminal for sentiment data processing. This allows the terminal to instantly determine the user's emotional state.

[0511] Step 4:

[0512] The device acquires audio and video data from the user in real time and analyzes it using a trained model. During this process, it senses changes in voice tone and facial expressions to estimate the user's emotional state. The input is the user's audio and video data, and the output is estimated emotional state information. This allows for the preparation of appropriate support for the user's work.

[0513] Step 5:

[0514] The device provides users with work-related support and advice based on analyzed emotional data. For example, it can suggest relaxation techniques to users experiencing stress. The input is estimated emotional state information, and the output is personalized support. This allows users to receive effective and appropriate support.

[0515] Step 6:

[0516] The server analyzes the effectiveness of daily work support and uses this information to improve the artificial intelligence model. By continuously collecting and analyzing user feedback and sentiment data, the model's accuracy is enhanced. The input is user feedback and support result data, and the output is the improved artificial intelligence model. This allows the system to evolve and increase its ability to provide support that is even more optimized for individual users.

[0517] (Application Example 2)

[0518] 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."

[0519] In modern home environments, there are limited means to effectively address residents' emotional needs and reduce stress. In particular, there is a need for a system that can grasp the emotional state of individual residents in real time and suggest appropriate relaxation methods. However, conventional technologies have not sufficiently automated the process of emotional recognition and the response based on that recognition, resulting in limited effectiveness.

[0520] 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.

[0521] In this invention, the server includes an information gathering means, an emotional data analysis means, and a resident care suggestion means. This makes it possible to precisely grasp the emotional state of each resident and provide stress reduction and relaxation support according to that state.

[0522] "Information gathering means" refers to devices or technologies that have the function of collecting data and collect various emotional data in the home environment.

[0523] A "machine learning model" is a mathematical model used by computers to perform specific tasks based on experience, and is designed to recognize data patterns and make predictions.

[0524] "Training methods" refer to the process of training a machine learning model using collected data, and are procedures for improving the accuracy of the model.

[0525] "Support tools" refer to functions that assist with tasks or operations based on trained machine learning models, and are methods for providing specific advice or suggestions.

[0526] "Analysis methods" refer to the process of analyzing performance data related to business support and using it to make improvements, playing a role in improving the overall efficiency of the system.

[0527] "Emotional data analysis means" refers to a function that analyzes emotional data in real time and determines the emotional state of residents, and is a technology that uses sensors and algorithms.

[0528] The "resident care suggestion tool" is a function that, based on analyzed emotional data, makes suggestions to support residents in reducing stress and promoting relaxation.

[0529] This system utilizes a new form of home robot to care for the emotions of its residents. A server collects large amounts of information, including emotional data, and uses this to train a machine learning model. TensorFlow is used as the software for analyzing the emotional data, and an algorithm written in Python identifies emotional patterns.

[0530] The home robot, which serves as the terminal, is equipped with emotion sensors and an inference engine, and monitors the resident's emotional state in real time. It analyzes this emotional data and suggests optimal relaxation methods tailored to the resident's stress level and emotional state. This includes suggesting music and rest options that match their emotions.

[0531] Through this system, users can receive emotional support in their daily lives. For example, when a user returns home from work, the system detects stress and plays relaxing music to create a comfortable environment. Furthermore, the generative AI model associated with this system can be further improved based on the following example prompts.

[0532] Examples of prompts to input into a generative AI model:

[0533] "Design a home-use emotion-recognizing robot that can detect the stress levels of its inhabitants and suggest relaxation methods."

[0534] In this way, the present invention adapts to the emotional state of residents in complex home environments and provides effective support tailored to individual needs.

[0535] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0536] Step 1:

[0537] The server receives emotional data collected from within the home and integrates it using data collection methods. The input to this process is raw data sent from sensors, and the output is an integrated emotional dataset. As part of data processing, this data is converted into a format compatible with the centralized management system. Specific operations include integrating timestamps for each emotional data point and converting between different data formats.

[0538] Step 2:

[0539] The server performs the following process: it trains a machine learning model using TensorFlow with the collected sentiment data. The input is the sentiment dataset integrated in step 1, and the output is the updated machine learning model. The data computation involves learning each sentiment pattern through the neural network and improving the model's accuracy. Specific operations include optimizing model parameters and evaluating accuracy.

[0540] Step 3:

[0541] The home robot, acting as a terminal, receives a trained machine learning model from a server and monitors the resident's emotional state in real time. This system utilizes emotional data analysis. The input is raw data obtained in real time from emotion sensors, and the output is the result of determining the resident's emotional state. Data processing involves applying an emotion classification algorithm to categorize emotions. Specific actions include the robot providing voice notifications based on the recognized emotions.

[0542] Step 4:

[0543] The user accepts stress reduction and relaxation methods suggested by the device. The resident care suggestion system functions, with input being data on the emotional state determined in step 3, and output being specific relaxation methods provided to the user. Data processing leads to the selection of appropriate music and action suggestions. Specific actions include the robot selecting and starting playback of music, or providing verbal explanations of rest suggestions.

[0544] 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.

[0545] 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.

[0546] 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.

[0547] [Fourth Embodiment]

[0548] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0549] 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.

[0550] 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).

[0551] 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.

[0552] 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.

[0553] 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).

[0554] 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.

[0555] 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.

[0556] 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.

[0557] 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.

[0558] 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.

[0559] 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.

[0560] 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".

[0561] This invention is an industry-specific AI agent system aimed at improving operational efficiency and leveraging expertise in specific industries. The system consists of a server, terminals, and users, each performing a specific function.

[0562] The server first collects the necessary data from industry specialists using APIs and other digital means. This may include text data, images, and audio data. After collection, the server analyzes this data through machine learning algorithms and performs training. This allows the AI ​​agent to acquire specialized knowledge.

[0563] The trained AI model is implemented into an AI agent running on the device. The support tools within the device utilize the AI ​​agent to assist client companies with their business operations. For example, the device analyzes user operation logs and suggests business processes that can be automated. Furthermore, the AI ​​agent can respond to user inquiries in real time through the device.

[0564] Users operate the terminal to utilize the system and streamline their work. For example, if a user consults an AI agent about proposed revisions to a design document, the AI ​​agent will provide the user with an appropriate answer based on relevant literature and a database of past cases. This allows users to perform advanced tasks even without specialized knowledge.

[0565] Through analytical means, the server continuously monitors the performance of the AI ​​agent and optimizes the model. This ensures that the AI ​​agent provides effective and efficient support for business operations. This process enables the application of critical expertise in specific industries and improves the productivity of businesses.

[0566] The following describes the processing flow.

[0567] Step 1:

[0568] The server uses APIs provided by industry specialists to collect the necessary data into the database. The data is stored in industry-standard formats and organized by category.

[0569] Step 2:

[0570] The server then starts training a machine learning model using the collected data. The training method combines supervised and unsupervised learning to teach the model industry-specific knowledge and patterns.

[0571] Step 3:

[0572] The server deploys the trained machine learning model to the terminal. The terminal then uses this model to function as an AI agent, preparing to perform specified business support tasks.

[0573] Step 4:

[0574] Users provide business-related data and inquiries to an AI agent through their device. The AI ​​agent analyzes the user's input and generates quick and accurate responses.

[0575] Step 5:

[0576] The device provides the user with responses and action suggestions generated by an AI agent. The user then proceeds with their tasks based on the provided information and provides feedback as needed.

[0577] Step 6:

[0578] The server analyzes performance data from terminals related to business support. Based on this analysis, it plans improvements and retraining of the AI ​​model to enhance system efficiency.

[0579] (Example 1)

[0580] 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".

[0581] Traditional industry-specific support systems operate with separate functions for data collection, model training, user support, and performance optimization, making seamless integration and efficiency improvements difficult. This challenge needs to be addressed to achieve automation and increased efficiency through consistent information utilization.

[0582] 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.

[0583] In this invention, the server includes data collection means for collecting necessary information from specialized institutions using digital means, data preprocessing means for preprocessing the collected information, and training means for training a machine learning structure based on the preprocessed information. This enables coordinated information processing and model optimization, thereby improving the efficiency and automation of business support.

[0584] "Data collection means" refers to the function of obtaining necessary information from specialized institutions using digital means.

[0585] "Data preprocessing means" refers to functions that clean and format information in order to improve the quality of collected information.

[0586] A "training method" is a function that executes a process to train a machine learning structure based on pre-processed information.

[0587] "Support tools" are functions that implement pre-trained machine learning structures to assist users with their work.

[0588] "Analysis tools" refer to functions for evaluating and optimizing the performance of user support activities.

[0589] "Preprocessing means" refers to a function that performs a process to improve the quality of collected information and prepare it for training.

[0590] An "automated response system" is a function that generates a quick and appropriate response based on user input.

[0591] This invention is an industry-specific AI agent system aimed at improving operational efficiency and leveraging expertise in specific industries. The system consists of a server, terminals, and users, with each component performing a specific function.

[0592] The server first collects necessary information from specialized organizations using APIs and other digital means. The information collected is diverse, including text data, images, and audio data. For example, the server obtains industry technical papers and market trend data via the internet. In this process, the server uses HTTP requests and collects data through secure access authentication.

[0593] Next, the server preprocesses the collected information to improve its quality. This involves analyzing the information using programming languages ​​such as Python or R, removing noise, and extracting important keywords. The preprocessed information is then used to train the machine learning model.

[0594] The server uses machine learning frameworks such as TensorFlow and PyTorch to perform training using pre-processed information. The trained structure is then implemented on the terminal. The terminal then utilizes this trained AI agent to prepare to provide optimal support tailored to the user's tasks.

[0595] The device interacts with the user using a pre-trained AI model. In this process, the device provides appropriate information in real time based on the user's prompts. For example, if the user inputs "I would like advice on designing a new product," the device extracts information from a database of past cases and relevant literature and presents it to the user.

[0596] Users can improve work efficiency by receiving assistance from AI agents through their devices. In particular, even users lacking specialized knowledge can perform tasks effectively with the AI ​​agent's suggestions. Furthermore, the server continuously analyzes the performance of work assistance provided by the devices and optimizes the machine learning model to improve the overall system's effectiveness. This optimization process ensures that the AI ​​agents are always receiving the latest information and algorithmic optimizations.

[0597] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0598] Step 1:

[0599] The server collects necessary information via APIs from specialized organizations. Inputs include URLs and API keys of industry-related data sources. The server uses this information to send HTTP requests and retrieve industry-related information in various formats, such as text data, images, and audio files. Output is a raw, unprocessed dataset.

[0600] Step 2:

[0601] The server preprocesses the collected raw data. The input is the unprocessed dataset obtained in the previous step. The server cleans the data, for example, by removing unnecessary symbols from text data and extracting important keywords. For image data, resolution adjustments and noise reduction are performed. The output is a preprocessed dataset with improved quality.

[0602] Step 3:

[0603] The server trains a machine learning model using preprocessed data. The input is a preprocessed dataset. The server uses frameworks such as TensorFlow or PyTorch to apply a recurrent neural network (RNN) to text data and a convolutional neural network (CNN) to image data. The output is the trained AI model.

[0604] Step 4:

[0605] A pre-trained AI model is implemented on the device. The input is the pre-trained AI model provided by the server. The device receives the model, verifies its operation, and prepares the user interface. The output is a device environment with an AI agent that the user can interact with.

[0606] Step 5:

[0607] The user interacts with the AI ​​agent through the device. The input is a prompt from the user. Based on this input, the device uses a trained AI model to perform analysis and generate appropriate information and advice. The output is a specific answer or suggestion to the user.

[0608] Step 6:

[0609] The server monitors and optimizes the performance of the AI ​​agent in supporting business operations. Inputs include activity logs and performance metrics from the terminal. The server analyzes this data to determine whether model improvements or training with new data are necessary. Outputs include the optimized AI model and any updates to it.

[0610] (Application Example 1)

[0611] 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".

[0612] In the manufacturing industry, the maintenance of machinery and equipment is often inefficient and time-consuming due to the need for specialized knowledge and judgment. Furthermore, failure to perform maintenance at the appropriate time can lead to equipment failure and decreased productivity. This invention aims to solve these problems by providing a system that evaluates equipment status in real time and offers an optimal maintenance plan.

[0613] 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.

[0614] In this invention, the server includes collection means for collecting information, construction means for building a machine learning model using the collected information, and condition diagnosis means for acquiring information from mechanical devices and identifying anomalies. This makes it possible for on-site staff to quickly and accurately grasp the status of equipment and perform efficient maintenance and management, even without specialized knowledge.

[0615] "Information" refers to data and knowledge, and in particular, the material that systems use for analysis and processing.

[0616] "Information gathering means" refers to a mechanism or device used to acquire necessary information.

[0617] "Construction method" refers to a method or process for generating or training a machine learning model based on collected information.

[0618] "Support measures" are auxiliary methods or systems used to streamline specific tasks or processes.

[0619] An "analytical means" is a mechanism established to analyze information in detail and to understand and evaluate its content.

[0620] A "mechanical device" is a physical instrument or system designed to perform a specific task.

[0621] A "condition diagnosis means" is a technique or method for evaluating the current state of a device or system and detecting abnormalities.

[0622] A "proposal mechanism" is a mechanism for suggesting optimal actions or plans based on collected or analyzed information.

[0623] "Specialized knowledge" refers to advanced information and understanding of a particular field, which is necessary to perform tasks in that field.

[0624] "Reconstruction methods" refer to the process of updating or retraining existing machine learning models to adapt them to new data.

[0625] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user.

[0626] First, the server uses hardware such as sensors and cameras to collect condition information from mechanical equipment within the factory. This information is acquired in real time using IoT technology and transmitted to the cloud. The server uses the collected information to build machine learning models and train generative AI models. This process uses data analysis software and high-performance computing resources to efficiently process large amounts of data. The trained AI models identify equipment anomalies and enable condition diagnosis.

[0627] Next, the terminal functions as an interface that visually displays machine status information and AI analysis results to the user. This is often done using mobile devices such as smartphones or tablets, allowing users to access the information through intuitive operation. Maintenance suggestions generated from the AI ​​diagnostic results are presented to the user on the terminal. These suggestions include specific advice, such as, "This part is worn out and needs to be replaced within a week."

[0628] Users can take swift action based on the information presented, minimizing equipment downtime. Specifically, this could involve equipment maintenance personnel reviewing suggestions displayed on a terminal, revising processes, and preparing necessary parts and tools.

[0629] An example of a prompt for a generated AI model is, "Analyze this dataset to identify abnormal behavioral patterns. Specify where and why maintenance is needed." Using this prompt, the AI ​​model effectively provides the user with the necessary information.

[0630] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0631] Step 1:

[0632] The server collects status information in real time from mechanical equipment within the factory. Using hardware such as sensors and cameras, it acquires machine operation data and transfers it to a database in the cloud. The input is machine sensor data, and the output is data storage in the cloud.

[0633] Step 2:

[0634] The server preprocesses the collected data. It performs data cleaning and noise reduction, transforming it into a format usable by machine learning models. This process removes outliers and normalizes the data as time series data. The input is raw data, and the output is clean, preprocessed data.

[0635] Step 3:

[0636] The server uses pre-processed data to train a generative AI model. It applies machine learning algorithms to learn patterns of normal and abnormal behavior. The input is clean data, and the output is the trained AI model.

[0637] Step 4:

[0638] The terminal runs an AI model on the server to provide real-time diagnostics. When new machine operation data is input, the AI ​​model analyzes it and determines whether or not there are any abnormalities. The input is new sensor data, and the output is the diagnostic result.

[0639] Step 5:

[0640] The terminal notifies the user through a visual user interface based on the diagnostic results of the AI ​​model. Field staff use this interface to check recommended maintenance actions. The input is the diagnostic results, and the output is a maintenance suggestion that the user can visually understand.

[0641] Step 6:

[0642] The user operates a terminal and develops a maintenance plan for the equipment based on the presented maintenance suggestions. Based on the suggested actions, they prepare the necessary parts and tools and carry out the actual maintenance. The input is the maintenance suggestion, and the output is the implementation of the maintenance action.

[0643] 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.

[0644] This invention aims to provide more precise and effective support by combining a system designed to assist with business operations with an emotion engine that recognizes user emotions. This system consists of three elements: a server, a terminal, and a user, each playing a specific role.

[0645] First, the server collects large-scale industry-specific data and uses it to train the AI ​​model. Furthermore, an emotion engine collects user emotional data, which is then used to enhance the AI ​​model. This enables adaptive work support that takes the user's emotional state into account.

[0646] Next, the device functions as an AI agent using a pre-trained model provided by the server. This device incorporates an emotion engine that acquires real-time emotional data from the user. Based on this data, it determines the user's emotional state while performing tasks and provides optimal support. For example, if the user is experiencing stress, it can adjust the workload accordingly and offer appropriate advice.

[0647] Users interact with the AI ​​agent via their device. By inputting specific instructions regarding their tasks, they can receive real-time support from the AI ​​agent. For example, when a user is preparing a presentation, the AI ​​agent can offer advice based on past successes. Furthermore, it can provide appropriate resources and point out areas for improvement based on emotional data.

[0648] Finally, the server continuously analyzes emotional data and uses it to improve and train the AI ​​model. This process allows the system to evolve over time, enhancing its ability to provide optimized work support for each user. In this way, the system of the present invention, which integrates an emotional engine, enables more advanced and personalized work support.

[0649] The following describes the processing flow.

[0650] Step 1:

[0651] The server configures access to collect data from trusted industry experts and gathers the necessary industry data. The collected data is formatted and securely stored on the server.

[0652] Step 2:

[0653] The server starts training a machine learning model using the collected data. The training process uses the latest algorithms to ensure the model's accuracy and applicability.

[0654] Step 3:

[0655] The server uses an emotion engine to analyze user sentiment data and recognize specific patterns. This data is incorporated into the model's training data, optimizing the model to enable personalized output.

[0656] Step 4:

[0657] The device downloads a pre-trained model and runs it as an AI agent in the user's environment. The emotion engine on the device evaluates the user's emotional state in real time and provides the results to the agent.

[0658] Step 5:

[0659] Users input tasks and information into the terminal to request work assistance. The AI ​​agent takes action to provide optimal work assistance based on the user's input and emotional data.

[0660] Step 6:

[0661] The device notifies the user of specific advice and task adjustments based on the assistance of an AI agent. The user's responses are continuously evaluated by an emotion engine to ensure the assistance is appropriate.

[0662] Step 7:

[0663] The server collects emotional and performance data transmitted from terminals and uses it to further improve the AI ​​model. This data is regularly analyzed and used to provide feedback to the training process.

[0664] (Example 2)

[0665] 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".

[0666] Current business support systems provide uniform support without considering the user's feelings, making it difficult to provide effective support that addresses the diverse needs and circumstances of each user. Furthermore, existing machine learning models suffer from insufficient variation in collected data, making it difficult to provide highly accurate support.

[0667] 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.

[0668] In this invention, the server includes information gathering means for collecting user information, including emotional data; learning means for training an artificial intelligence model using the collected information; and auxiliary means for providing individualized work support based on the trained artificial intelligence model. This enables the reflection of the user's emotional state in real time, resulting in personalized and effective work support.

[0669] "Emotional data" refers to data that indicates the user's emotional state, and includes information such as tone of voice, facial expressions, and physical reactions.

[0670] "Information gathering means" refers to a device or method configured to collect user information, including emotional data.

[0671] An "artificial intelligence model" is an algorithm or framework that is trained based on collected information and used to provide business support based on emotional data.

[0672] A "learning tool" is a device or method for training an artificial intelligence model using collected data and improving its capabilities.

[0673] "Auxiliary means" refers to a device or function used to provide individualized business support by utilizing a trained artificial intelligence model.

[0674] "Interface means" refers to connection methods or devices for receiving emotional data from the user in real time.

[0675] "Analysis means" refers to a device or method for analyzing data obtained during the process of providing business support and for improving the effectiveness of the support provided.

[0676] A "retraining device" is a device or method for continuously updating an artificial intelligence model and retraining it based on new data.

[0677] To implement this invention, three elements are necessary: ​​a server, a terminal, and a user. The server first employs information gathering means to collect user information, including emotional data. This means can collect information from various data sources, such as the user's voice data and facial expression data. The collected data is processed by a learning means that trains an artificial intelligence model using a deep learning framework such as TensorFlow. The trained model is then delivered from the server to the terminal.

[0678] The terminal integrates an interface for collecting emotional data in real time. For example, the terminal can use its built-in camera and microphone to detect the user's voice tone and facial expressions, and analyze their emotional state based on this data. Based on this analyzed emotional data, the terminal can individually tailor work support to the user, providing appropriate advice and resources.

[0679] Users interact directly with the AI ​​agent via their device. By using prompts to communicate specific requests regarding their work, they can receive support from the device. For example, by entering a prompt such as, "Please help me prepare materials for next week's project meeting," users can receive advice from the AI ​​agent based on past success stories.

[0680] Furthermore, the server has analytical means to analyze emotional data and support results obtained during the business support process, evaluate the effectiveness of the support, and use this to improve the next model update. Through retraining means, the artificial intelligence model is continuously improved, enabling the provision of more accurate support. In this way, this invention enables personalized business support that responds to the user's emotional state.

[0681] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0682] Step 1:

[0683] The server collects data from various sources, including voice and facial expressions, to gather user emotional data. This data is stored in a database and used in subsequent training processes. Inputs are voice files and image data, and output is structured emotional data. This provides foundational data for precisely measuring the user's emotional state.

[0684] Step 2:

[0685] The server trains an artificial intelligence model using the collected sentiment data. This process involves analyzing the data using a deep learning framework, performing pattern recognition and feature extraction. The input is structured sentiment data, and the output is the trained artificial intelligence model. This allows the model to learn how to interpret the sentiment data, enabling accurate sentiment analysis.

[0686] Step 3:

[0687] The server delivers the trained model to the terminal and integrates the model into the terminal. The terminal prepares to acquire sentiment data from the user in real time using an interface. The input is the trained model data, and the output is the readiness state of the user's terminal for sentiment data processing. This allows the terminal to instantly determine the user's emotional state.

[0688] Step 4:

[0689] The device acquires audio and video data from the user in real time and analyzes it using a trained model. During this process, it senses changes in voice tone and facial expressions to estimate the user's emotional state. The input is the user's audio and video data, and the output is estimated emotional state information. This allows for the preparation of appropriate support for the user's work.

[0690] Step 5:

[0691] The device provides users with work-related support and advice based on analyzed emotional data. For example, it can suggest relaxation techniques to users experiencing stress. The input is estimated emotional state information, and the output is personalized support. This allows users to receive effective and appropriate support.

[0692] Step 6:

[0693] The server analyzes the effectiveness of daily work support and uses this information to improve the artificial intelligence model. By continuously collecting and analyzing user feedback and sentiment data, the model's accuracy is enhanced. The input is user feedback and support result data, and the output is the improved artificial intelligence model. This allows the system to evolve and increase its ability to provide support that is even more optimized for individual users.

[0694] (Application Example 2)

[0695] 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".

[0696] In modern home environments, there are limited means to effectively address residents' emotional needs and reduce stress. In particular, there is a need for a system that can grasp the emotional state of individual residents in real time and suggest appropriate relaxation methods. However, conventional technologies have not sufficiently automated the process of emotional recognition and the response based on that recognition, resulting in limited effectiveness.

[0697] 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.

[0698] In this invention, the server includes an information gathering means, an emotional data analysis means, and a resident care suggestion means. This makes it possible to precisely grasp the emotional state of each resident and provide stress reduction and relaxation support according to that state.

[0699] "Information gathering means" refers to devices or technologies that have the function of collecting data and collect various emotional data in the home environment.

[0700] A "machine learning model" is a mathematical model used by computers to perform specific tasks based on experience, and is designed to recognize data patterns and make predictions.

[0701] "Training methods" refer to the process of training a machine learning model using collected data, and are procedures for improving the accuracy of the model.

[0702] "Support tools" refer to functions that assist with tasks or operations based on trained machine learning models, and are methods for providing specific advice or suggestions.

[0703] "Analysis methods" refer to the process of analyzing performance data related to business support and using it to make improvements, playing a role in improving the overall efficiency of the system.

[0704] "Emotional data analysis means" refers to a function that analyzes emotional data in real time and determines the emotional state of residents, and is a technology that uses sensors and algorithms.

[0705] The "resident care suggestion tool" is a function that, based on analyzed emotional data, makes suggestions to support residents in reducing stress and promoting relaxation.

[0706] This system utilizes a new form of home robot to care for the emotions of its residents. A server collects large amounts of information, including emotional data, and uses this to train a machine learning model. TensorFlow is used as the software for analyzing the emotional data, and an algorithm written in Python identifies emotional patterns.

[0707] The home robot, which serves as the terminal, is equipped with emotion sensors and an inference engine, and monitors the resident's emotional state in real time. It analyzes this emotional data and suggests optimal relaxation methods tailored to the resident's stress level and emotional state. This includes suggesting music and rest options that match their emotions.

[0708] Through this system, users can receive emotional support in their daily lives. For example, when a user returns home from work, the system detects stress and plays relaxing music to create a comfortable environment. Furthermore, the generative AI model associated with this system can be further improved based on the following example prompts.

[0709] Examples of prompts to input into a generative AI model:

[0710] "Design a home-use emotion-recognizing robot that can detect the stress levels of its inhabitants and suggest relaxation methods."

[0711] In this way, the present invention adapts to the emotional state of residents in complex home environments and provides effective support tailored to individual needs.

[0712] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0713] Step 1:

[0714] The server receives emotional data collected from within the home and integrates it using data collection methods. The input to this process is raw data sent from sensors, and the output is an integrated emotional dataset. As part of data processing, this data is converted into a format compatible with the centralized management system. Specific operations include integrating timestamps for each emotional data point and converting between different data formats.

[0715] Step 2:

[0716] The server performs the following process: it trains a machine learning model using TensorFlow with the collected sentiment data. The input is the sentiment dataset integrated in step 1, and the output is the updated machine learning model. The data computation involves learning each sentiment pattern through the neural network and improving the model's accuracy. Specific operations include optimizing model parameters and evaluating accuracy.

[0717] Step 3:

[0718] The home robot, acting as a terminal, receives a trained machine learning model from a server and monitors the resident's emotional state in real time. This system utilizes emotional data analysis. The input is raw data obtained in real time from emotion sensors, and the output is the result of determining the resident's emotional state. Data processing involves applying an emotion classification algorithm to categorize emotions. Specific actions include the robot providing voice notifications based on the recognized emotions.

[0719] Step 4:

[0720] The user accepts stress reduction and relaxation methods suggested by the device. The resident care suggestion system functions, with input being data on the emotional state determined in step 3, and output being specific relaxation methods provided to the user. Data processing leads to the selection of appropriate music and action suggestions. Specific actions include the robot selecting and starting playback of music, or providing verbal explanations of rest suggestions.

[0721] 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.

[0722] 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.

[0723] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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."

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] The following is further disclosed regarding the embodiments described above.

[0743] (Claim 1)

[0744] Data collection means for collecting data,

[0745] Training methods for training machine learning models using collected data,

[0746] Support tools for providing business support based on trained machine learning models,

[0747] Analytical tools for analyzing and improving performance data in business support,

[0748] A system that includes this.

[0749] (Claim 2)

[0750] The system according to claim 1, comprising means for collecting data from institutions with specialized knowledge.

[0751] (Claim 3)

[0752] The system according to claim 1, further comprising means for retraining a machine learning model to periodically update it.

[0753] "Example 1"

[0754] (Claim 1)

[0755] Data collection means for collecting necessary information from specialized institutions using digital means,

[0756] Data preprocessing means for preprocessing collected information,

[0757] A training method for training a machine learning structure based on preprocessed information,

[0758] A support mechanism to assist user activities by implementing a pre-trained machine learning structure,

[0759] Analytical tools for evaluating and optimizing the performance of activity support,

[0760] A system that includes this.

[0761] (Claim 2)

[0762] The system according to claim 1, comprising preprocessing means for improving the quality of collected information.

[0763] (Claim 3)

[0764] The system according to claim 1, further comprising an automated response means for generating a response in real time based on user input.

[0765] "Application Example 1"

[0766] (Claim 1)

[0767] means of collecting information,

[0768] A means of constructing a machine learning model using collected information,

[0769] Support means for providing task assistance based on constructed machine learning models,

[0770] An analytical method for analyzing and improving the execution data of task support,

[0771] A condition diagnostic means for acquiring information from mechanical devices and identifying abnormalities,

[0772] A means for proposing maintenance and management methods based on the condition diagnosis results,

[0773] A system that includes this.

[0774] (Claim 2)

[0775] The system according to claim 1, comprising means for collecting information from organizations possessing specific expertise.

[0776] (Claim 3)

[0777] The system according to claim 1, further comprising means for periodically rebuilding a machine learning model.

[0778] "Example 2 of combining an emotion engine"

[0779] (Claim 1)

[0780] Information collection means for collecting user information, including emotional data,

[0781] A learning method for training an artificial intelligence model using collected information,

[0782] A means of providing support for individual tasks based on a trained artificial intelligence model,

[0783] An interface means for receiving emotional data from the user in real time via an information gathering device,

[0784] Analytical methods for analyzing and improving the effectiveness of support provided during the business support process,

[0785] A system that includes this.

[0786] (Claim 2)

[0787] The system according to claim 1, comprising means for collecting information from external professional organizations.

[0788] (Claim 3)

[0789] The system according to claim 1, further comprising means for retraining to continuously update an artificial intelligence model.

[0790] "Application example 2 when combining with an emotional engine"

[0791] (Claim 1)

[0792] Information gathering means for collecting data,

[0793] Training methods for training machine learning models using collected data,

[0794] Support tools for providing business support based on trained machine learning models,

[0795] Analytical tools for analyzing and improving performance data in business support,

[0796] An analytical means for analyzing emotional data in real time and determining emotional states,

[0797] Based on the analyzed emotional data, proposed methods for supporting stress reduction and relaxation among residents,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, comprising means for collecting data from institutions with specialized knowledge.

[0801] (Claim 3)

[0802] The system according to claim 1, further comprising means for retraining a machine learning model to periodically update it. [Explanation of Symbols]

[0803] 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. means of collecting information, A means of constructing a machine learning model using collected information, Support means for providing task assistance based on constructed machine learning models, An analytical method for analyzing and improving the execution data of task support, A condition diagnostic means for acquiring information from mechanical devices and identifying abnormalities, A means for proposing maintenance and management methods based on the condition diagnosis results, A system that includes this.

2. The system according to claim 1, comprising means for collecting information from organizations possessing specific expertise.

3. The system according to claim 1, further comprising means for periodically rebuilding a machine learning model.

Images