system

Abstract

The system according to this embodiment aims to streamline task management and ensure the smooth progress of daily tasks. [Solution] The system according to the embodiment comprises an automation unit, an analysis unit, a processing unit, and a learning unit. The automation unit automates tasks. The analysis unit analyzes data from tasks automated by the automation unit. The processing unit performs natural language processing based on the data obtained by the analysis unit. The learning unit performs self-learning based on the data obtained by the processing unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the efficiency of task management has not been sufficiently improved, and there is room for improvement.

[0005] The system according to the embodiment aims to improve the efficiency of task management and smoothly progress daily tasks.

Means for Solving the Problems

[0006] The system according to the embodiment includes an automation unit, an analysis unit, a processing unit, and a learning unit. The automation unit automates tasks. The analysis unit analyzes the data of the tasks automated by the automation unit. The processing unit performs natural language processing based on the data obtained by the analysis unit. The learning unit performs self-learning based on the data obtained by the processing unit. [Effects of the Invention]

[0007] The system according to this embodiment can streamline task management and allow daily tasks to proceed smoothly. [Brief explanation of the drawing]

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

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

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0028] (Example of form 1) The TaskOrbit AI system, according to an embodiment of the present invention, is a smart task management agent that puts daily task management on track. The TaskOrbit AI system supports work and personal efficiency through schedule organization, priority optimization, and reminder notifications. The TaskOrbit AI system is an advanced artificial intelligence platform for business process automation, an AI-powered solution that automates repetitive tasks such as data entry and document processing. Using cutting-edge technologies such as machine learning and natural language processing, the TaskOrbit AI system automates repetitive tasks, improving accuracy and reducing human error. The TaskOrbit AI system is a cloud-based solution, available across various industries, and designed to improve productivity and efficiency. Its goal is to reduce the time and effort required for repetitive tasks, allowing employees to focus on specialized tasks. The TaskOrbit AI system uses machine learning algorithms to analyze data and automate tasks. It uses natural language processing to parse and process text data. The TaskOrbit AI system can integrate with other platforms and can be customized to different business needs using customized APIs. The TaskOrbit AI system includes various components such as machine learning, natural language processing, and data mining. The TaskOrbit AI system offers seamless integration with many other platforms, enabling business process automation, data collection and analysis, or improved customer support. The TaskOrbit AI system incorporates security features, providing the highest level of data protection. It consists of multiple components, including data extraction, data processing, and data storage. The TaskOrbit AI system integrates with other platforms such as CRM and ERP, enabling the automation and improvement of business processes.TaskOrbit AI systems improve productivity by automating highly repetitive tasks. TaskOrbit AI systems automate business data analysis, providing accurate analysis and insights. Using natural language processing, TaskOrbit AI systems can resolve customer requests and problems, handling issues quickly and accurately. TaskOrbit AI systems continuously learn and adapt to the business using machine learning algorithms. TaskOrbit AI systems have data extraction capabilities, allowing them to ingest and analyze vast amounts of data. TaskOrbit AI systems have data processing capabilities, enabling fast and efficient data processing. TaskOrbit AI systems have data storage capabilities, providing fast and secure data storage. TaskOrbit AI systems help businesses save time and reduce errors. Implementing TaskOrbit AI systems has a positive impact on businesses, improving customer satisfaction through time savings and reduced errors. Implementing TaskOrbit AI systems allows employees to automate repetitive tasks, freeing up time for more complex tasks. As AI technology evolves, TaskOrbit AI systems will continuously improve, offering more advanced features and benefits. This enables TaskOrbit AI systems to streamline daily task management and automate business processes.

[0029] The TaskOrbit AI system according to this embodiment comprises an automation unit, an analysis unit, a processing unit, and a learning unit. The automation unit automates tasks. For example, the automation unit automates tasks such as schedule management, data entry, and report generation. The automation unit can automate tasks using AI. For example, to automate schedule management tasks, the automation unit works with a calendar application to automatically add or modify schedules. To automate data entry tasks, the automation unit uses OCR technology to convert paper documents into digital data and inputs it into a database. To automate report generation tasks, the automation unit extracts necessary data from the database and generates reports according to a standard format. The analysis unit analyzes data from tasks automated by the automation unit. For example, the analysis unit analyzes data using methods such as statistical analysis and the application of machine learning algorithms. The analysis unit can analyze data using AI. For example, to perform statistical analysis, the analysis unit analyzes the distribution and trends of data and detects outliers. The analysis unit applies machine learning algorithms to perform data clustering and classification. The analysis unit analyzes the correlation between data and constructs a predictive model. The processing unit performs natural language processing based on the data obtained by the analysis unit. The processing unit performs natural language processing using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The processing unit can perform natural language processing using AI. For example, to perform morphological analysis, the processing unit divides text data into words and tags the parts of speech. To perform grammatical analysis, the processing unit analyzes the structure of sentences and identifies grammatical elements such as subjects, predicates, and objects. To perform semantic analysis, the processing unit understands the meaning of text data and generates appropriate responses according to the context. The learning unit performs self-learning based on the data obtained by the processing unit. The learning unit performs self-learning using algorithms such as reinforcement learning and deep learning. The learning unit can perform self-learning using AI. For example, to perform reinforcement learning, the learning unit has an agent interact with the environment and receive rewards to advance learning. To perform deep learning, the learning unit constructs a multi-layered neural network and trains the model using a large amount of data.The learning unit provides feedback on the results of self-learning, improving the overall system performance. As a result, the TaskOrbit AI system according to this embodiment enables efficient task management by performing task automation, data analysis, natural language processing, and self-learning.

[0030] The Automation Department automates tasks. For example, it automates tasks such as schedule management, data entry, and report generation. The Automation Department can use AI to automate tasks. Specifically, to automate schedule management tasks, the Automation Department integrates with calendar applications, analyzes the user's schedule, and suggests the optimal schedule. For example, when a user adds a meeting, the Automation Department automatically adjusts the time to avoid conflicts with other appointments. It can also utilize a reminder function to notify important appointments in advance. For automating data entry tasks, it uses OCR technology to convert paper documents into digital data and inputs it into a database. For example, it scans paper documents such as invoices and contracts and converts them into text data using OCR technology, reducing the effort required for manual data entry. Furthermore, to ensure data accuracy, it includes a function where AI automatically detects errors and suggests corrections. For automating report generation tasks, it extracts necessary data from the database and generates reports according to a standard format. For example, it automatically creates periodic performance reports based on sales data and customer data. This reduces the effort required for manual report creation, enabling the rapid and accurate provision of information. By efficiently automating these tasks, the automation unit can reduce the workload on users and improve productivity.

[0031] The analytics department analyzes data from tasks automated by the automation department. The analytics department analyzes data using methods such as statistical analysis and the application of machine learning algorithms. Specifically, to perform statistical analysis, the analytics department analyzes data distribution and trends to detect outliers. For example, it can analyze the distribution of sales data to detect abnormal increases or decreases in sales over a specific period. This allows for the identification of the cause of the abnormal data and the implementation of appropriate countermeasures. Furthermore, the analytics department applies machine learning algorithms to cluster and classify data. For example, it can cluster customer data and create segments based on customer purchasing behavior. This enables targeted marketing and the provision of personalized services. The analytics department can also analyze data correlations and build predictive models. For example, it can build a model to predict future sales based on historical sales data and advertising campaign data. This enables the development of effective marketing strategies and the optimization of inventory management. Through these data analyses, the analytics department can provide users with valuable insights and support their decision-making.

[0032] The processing unit performs natural language processing based on the data obtained by the analysis unit. The processing unit performs natural language processing using techniques such as morphological analysis, grammatical analysis, and semantic analysis. Specifically, to perform morphological analysis, the processing unit divides text data into words and tags them by part of speech. For example, it analyzes text entered by a user and identifies parts of speech such as nouns, verbs, and adjectives. This allows it to understand the structure of the text data and perform appropriate processing. In grammatical analysis, it analyzes the structure of a sentence and identifies grammatical elements such as subjects, predicates, and objects. For example, it analyzes the grammatical structure of a sentence entered by a user and accurately understands the meaning of the sentence. This improves the accuracy of natural language processing. In semantic analysis, it understands the meaning of text data and generates appropriate responses according to the context. For example, it analyzes the meaning of text data to generate appropriate answers to questions entered by a user. This enables natural dialogue with the user and supports effective communication. By making full use of these natural language processing techniques, the processing unit can generate appropriate responses to user input and improve the overall system performance.

[0033] The learning unit performs self-learning based on data obtained by the processing unit. The learning unit uses algorithms such as reinforcement learning and deep learning. Specifically, to perform reinforcement learning, the learning unit learns by having an agent interact with the environment and receive rewards. For example, the agent is rewarded each time it completes a task, allowing it to learn optimal actions. This enables the agent to learn how to complete tasks efficiently, improving the overall system performance. In deep learning, a multi-layered neural network is constructed, and the model is trained using a large amount of data. For example, in an image recognition task, a neural network is trained using a large amount of image data to build a highly accurate image recognition model. This allows the system to recognize complex patterns and perform advanced tasks. The learning unit feeds back the results of its self-learning, improving the overall system performance. For example, each time the learning unit learns new data, the system's performance improves, enabling more accurate predictions and responses. This allows the learning unit to continuously improve the system and provide high-quality services to users.

[0034] The security department provides security functions. For example, the security department provides security functions such as encryption, authentication, and access control. The security department can provide security functions using AI. For example, the security department applies the AES algorithm to encrypt data. The security department applies a two-factor authentication algorithm for user authentication. The security department sets access rights based on user roles for access control. This allows the security department to enhance data protection.

[0035] The integration unit integrates with other platforms. The integration unit integrates with other platforms through methods such as API integration and database integration. The integration unit can use AI to perform integration with other platforms. For example, the integration unit uses RESTful APIs to send and receive data for API integration. The integration unit applies ETL (Extract, Transform, Load) processes for database integration. The integration unit synchronizes data with other platforms to improve the efficiency of business processes. This enables the integration unit to achieve business process efficiency.

[0036] The extraction unit performs data extraction. The extraction unit extracts data using methods such as query-based extraction and filtering. The extraction unit can also use AI for data extraction. For example, to perform query-based extraction, the extraction unit uses SQL queries to extract the necessary data from the database. To perform filtering, the extraction unit selects data based on specific conditions. The extraction unit provides the data extraction results to the analysis unit, supporting efficient data analysis. This allows the extraction unit to efficiently obtain the necessary data.

[0037] The processing unit performs data processing. For example, the processing unit performs data processing using methods such as data cleaning and data transformation. The processing unit can also perform data processing using AI. For example, to perform data cleaning, the processing unit performs data imputation and removal of outliers. To perform data transformation, the processing unit transforms the data format and prepares it for analysis. The processing unit provides the data processing results to the analysis unit, supporting efficient data analysis. This enables the processing unit to achieve efficient data processing.

[0038] The storage unit performs data storage. The storage unit performs data storage using methods such as cloud storage and databases. The storage unit can also perform data storage using AI. For example, the storage unit can use cloud storage to save data and perform access control. The storage unit can use databases to save data and perform efficient data retrieval. The storage unit performs data backup and recovery, ensuring secure data storage. This enables the storage unit to ensure secure data storage.

[0039] The automation unit can apply different automation algorithms depending on the type of task to be automated. For example, the automation unit applies an automation algorithm using OCR technology to data entry tasks. For document processing tasks, it applies an automation algorithm using natural language processing technology. For schedule management tasks, it applies an automation algorithm using calendar synchronization technology. In this way, the automation unit can improve the accuracy of automation by applying the appropriate automation algorithm according to the type of task.

[0040] The automation unit can optimize the timing of automation based on the frequency of the tasks to be automated. For example, the automation unit can set daily tasks to be automated regularly. It can set weekly tasks to be automated at the beginning of the week. It can set monthly tasks to be automated at the beginning of the month. In this way, the automation unit can achieve efficient task management by optimizing the timing of automation based on the frequency of tasks.

[0041] The automation unit can monitor the execution results of automated tasks in real time and modify the automation process as needed. For example, if an error occurs during task execution, the automation unit detects the error in real time and corrects the automation process. If the task execution results are not as expected, the automation unit analyzes the results in real time and adjusts the automation process. If new requirements arise during task execution, the automation unit reflects the requirements in real time and modifies the automation process. In this way, the automation unit can improve the accuracy of automation by monitoring task execution results in real time and making corrections as needed.

[0042] The automation unit can apply different automation methods depending on the execution environment of the task to be automated. For example, in an on-premises environment, the automation unit applies an automation method that utilizes local resources. In a cloud environment, the automation unit applies an automation method that utilizes cloud resources. In a hybrid environment, the automation unit applies an automation method that combines on-premises and cloud resources. This allows the automation unit to improve the efficiency of automation by applying the appropriate automation method according to the task's execution environment.

[0043] The analysis unit can apply different analysis algorithms depending on the type of data being analyzed. For example, it can apply a natural language processing algorithm to text data, a statistical analysis algorithm to numerical data, and an image recognition algorithm to image data. This allows the analysis unit to improve the accuracy of its analysis by applying the appropriate analysis algorithm according to the type of data.

[0044] The analysis unit can refer to past analysis data to improve the accuracy of its analysis results. For example, the analysis unit can correct current analysis results based on past analysis data. The analysis unit can refer to past analysis data to extract trends and patterns. The analysis unit can utilize past analysis data to improve the accuracy of its analysis algorithms. In this way, the analysis unit can improve the accuracy of its analysis results by referring to past analysis data.

[0045] The analysis department can optimize the timing of data acquisition and perform real-time data analysis. For example, the analysis department optimizes the timing of data acquisition to perform real-time data analysis. The analysis department adjusts the timing of data acquisition to improve the accuracy of analysis results. The analysis department supports rapid decision-making by optimizing the timing of data acquisition. In this way, the analysis department can achieve real-time data analysis by optimizing the timing of data acquisition.

[0046] The analysis department can integrate analysis results with other systems to perform comprehensive data analysis. For example, the analysis department can integrate analysis results with a CRM system to perform comprehensive analysis of customer data. The analysis department can integrate analysis results with an ERP system to perform comprehensive analysis of business processes. The analysis department can integrate analysis results with a BI tool to perform comprehensive business intelligence analysis. In this way, the analysis department can achieve comprehensive data analysis by integrating with other systems.

[0047] The processing unit can apply different natural language processing algorithms depending on the type of text data being processed. For example, the processing unit can apply a summarization algorithm to news articles, a sentiment analysis algorithm to customer inquiries, and a topic modeling algorithm to product reviews. This allows the processing unit to improve the accuracy of processing by applying the appropriate natural language processing algorithm according to the type of text data.

[0048] The processing unit can refer to past processing data to improve the accuracy of the processing results. For example, the processing unit corrects the current processing results based on past processing data. The processing unit refers to past processing data and extracts trends and patterns. The processing unit utilizes past processing data to improve the accuracy of the natural language processing algorithm. In this way, the processing unit can improve the accuracy of the processing results by referring to past processing data.

[0049] The processing unit can optimize the timing of acquiring text data to be processed, enabling real-time natural language processing. For example, the processing unit optimizes the timing of text data acquisition and performs real-time natural language processing. The processing unit adjusts the timing of text data acquisition to improve the accuracy of processing results. The processing unit supports rapid decision-making by optimizing the timing of text data acquisition. Thus, by optimizing the timing of text data acquisition, the processing unit can achieve real-time natural language processing.

[0050] The processing unit can integrate its processing results with other systems to perform comprehensive data processing. For example, it can integrate its processing results with a CRM system to perform comprehensive processing of customer data. It can integrate its processing results with an ERP system to perform comprehensive processing of business processes. It can integrate its processing results with a BI tool to perform comprehensive business intelligence processing. In this way, the processing unit can achieve comprehensive data processing by integrating with other systems.

[0051] The learning unit can apply different learning algorithms depending on the type of data being trained. For example, the learning unit applies a natural language processing algorithm to text data, a statistical learning algorithm to numerical data, and an image recognition algorithm to image data. This allows the learning unit to improve the accuracy of its learning by applying the appropriate learning algorithm according to the type of data.

[0052] The learning unit can refer to past training data to improve the accuracy of the learning results. For example, the learning unit corrects the current learning results based on past training data. The learning unit refers to past training data and extracts trends and patterns. The learning unit improves the accuracy of the learning algorithm by utilizing past training data. In this way, the learning unit can improve the accuracy of the learning results by referring to past training data.

[0053] The learning unit can optimize the timing of data acquisition for training and perform real-time data learning. For example, the learning unit optimizes the timing of data acquisition and performs real-time data learning. The learning unit adjusts the timing of data acquisition to improve the accuracy of the learning results. The learning unit optimizes the timing of data acquisition to support rapid decision-making. In this way, the learning unit can achieve real-time data learning by optimizing the timing of data acquisition.

[0054] The learning unit can integrate its learning results with other systems to perform comprehensive data learning. For example, the learning unit can integrate its learning results with a CRM system to perform comprehensive learning of customer data. The learning unit can integrate its learning results with an ERP system to perform comprehensive learning of business processes. The learning unit can integrate its learning results with a BI tool to perform comprehensive learning of business intelligence. In this way, the learning unit can achieve comprehensive data learning by integrating with other systems.

[0055] The security unit can apply different security algorithms depending on the type of security measure. For example, the security unit applies the AES algorithm for data encryption. The security unit applies the two-factor authentication algorithm for user authentication. The security unit applies the firewall algorithm for network security. In this way, the security unit can improve the accuracy of security by applying the appropriate security algorithm according to the type of security measure.

[0056] The security department can monitor the results of security measures in real time and modify security processes as needed. For example, if an error occurs during the execution of security measures, the security department can detect the error in real time and correct the security process. If the results of security measures are not as expected, the security department can analyze the results in real time and adjust the security process. If a new threat emerges during the execution of security measures, the security department can reflect the threat in real time and modify the security process. In this way, the security department can improve the accuracy of security by monitoring the results of security measures in real time and making corrections as needed.

[0057] The integration unit can apply different integration algorithms depending on the type of platform being integrated. For example, the integration unit applies a customer data integration algorithm to CRM systems, a business process integration algorithm to ERP systems, and a business intelligence integration algorithm to BI tools. This allows the integration unit to improve the accuracy of integration by applying the appropriate integration algorithm according to the type of platform.

[0058] The integration unit can monitor the results of the integration process in real time and modify the integration process as needed. For example, if an error occurs during the execution of the integration process, the integration unit can detect the error in real time and correct the integration process. If the results of the integration process are not as expected, the integration unit can analyze the results in real time and adjust the integration process. If new requirements arise during the execution of the integration process, the integration unit can reflect the requirements in real time and modify the integration process. In this way, the integration unit can improve the accuracy of the integration by monitoring the results of the integration process in real time and making corrections as needed.

[0059] The extraction unit can apply different extraction algorithms depending on the type of data being extracted. For example, the extraction unit can apply a natural language processing algorithm to text data, a statistical analysis algorithm to numerical data, and an image recognition algorithm to image data. By applying the appropriate extraction algorithm according to the type of data, the extraction unit can improve the accuracy of the extraction.

[0060] The extraction unit can monitor the results of the extraction process in real time and modify the extraction process as needed. For example, if an error occurs during the execution of the extraction process, the extraction unit can detect the error in real time and modify the extraction process. If the results of the extraction process are not as expected, the extraction unit can analyze the results in real time and adjust the extraction process. If new requirements arise during the execution of the extraction process, the extraction unit can reflect the requirements in real time and modify the extraction process. In this way, the extraction unit can improve the accuracy of the extraction by monitoring the results of the extraction process in real time and modifying them as needed.

[0061] The storage unit can apply different storage algorithms depending on the type of data being stored. For example, the storage unit applies a compression algorithm to text data, an image compression algorithm to image data, and a video compression algorithm to video data. By applying the appropriate storage algorithm according to the data type, the storage unit can improve the accuracy of storage.

[0062] The storage unit can monitor the results of the save process in real time and modify the save process as needed. For example, if an error occurs during the save process, the storage unit can detect the error in real time and modify the save process. If the results of the save process are not as expected, the storage unit can analyze the results in real time and adjust the save process. If new requirements arise during the save process, the storage unit can reflect the requirements in real time and modify the save process. In this way, the storage unit can improve the accuracy of saving by monitoring the results of the save process in real time and modifying them as needed.

[0063] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0064] The automation unit can automate tasks at the optimal time by referring to the user's past behavior history. For example, if a user checks their email every morning, it can automate related tasks to coincide with that time. If a user creates reports on weekends, it can automatically collect the necessary data beforehand. If a user submits expense reports at the end of the month, it can automatically prepare the necessary documents beforehand. In this way, the automation unit can optimize task automation based on the user's behavior patterns.

[0065] The analytics department can integrate information from different data sources to perform comprehensive analysis. For example, it can integrate and analyze customer data from CRM systems with business data from ERP systems; customer feedback from social media with sales data; and sensor data with inventory data. By integrating information from multiple data sources, the analytics department can achieve more accurate and comprehensive analysis.

[0066] The processing unit can process text data in different languages ​​in natural language processing. For example, it can apply an English natural language processing algorithm to English text data, a Japanese natural language processing algorithm to Japanese text data, and a Chinese natural language processing algorithm to Chinese text data. This allows the processing unit to improve processing accuracy by performing appropriate natural language processing on text data in different languages.

[0067] The learning unit can collect information from different data sources in real time and utilize it for training. For example, it can collect sensor data in real time and use it to train machine learning models. It can collect feedback from social media in real time and use it to train sentiment analysis models. It can collect transaction data in real time and use it to train prediction models. As a result, the learning unit can improve the accuracy of its learning models by utilizing data collected in real time.

[0068] The security department can apply different security levels to security measures. For example, it can apply strong encryption algorithms to highly confidential data, standard encryption algorithms to general data, and no encryption to publicly available data. This allows the security department to improve security accuracy by applying appropriate security measures according to the confidentiality of the data.

[0069] The following briefly describes the processing flow for example form 1.

[0070] Step 1: The automation department automates tasks. For example, the automation department automates tasks such as schedule management, data entry, and report generation. The automation department can automate these tasks using AI. Specifically, to automate schedule management tasks, it integrates with a calendar application to automatically add and modify schedules. To automate data entry tasks, it uses OCR technology to convert paper documents into digital data and input it into a database. To automate report generation tasks, it extracts necessary data from the database and generates reports according to a standard format. Step 2: The analysis unit analyzes the data from the automated tasks performed by the automation unit. For example, it analyzes the data using methods such as statistical analysis and the application of machine learning algorithms. The analysis unit can use AI to analyze the data. Specifically, it analyzes the distribution and trends of the data to perform statistical analysis and detects outliers. It applies machine learning algorithms to cluster and classify the data. It analyzes the correlation between data and builds predictive models. Step 3: The processing unit performs natural language processing based on the data obtained by the analysis unit. For example, it performs natural language processing using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The processing unit can perform natural language processing using AI. Specifically, to perform morphological analysis, it divides the text data into words and tags the parts of speech. To perform grammatical analysis, it analyzes the structure of sentences and identifies grammatical elements such as subjects, predicates, and objects. To perform semantic analysis, it understands the meaning of the text data and generates appropriate responses according to the context. Step 4: The learning unit performs self-learning based on the data obtained by the processing unit. For example, it performs self-learning using algorithms such as reinforcement learning and deep learning. The learning unit can perform self-learning using AI. Specifically, for reinforcement learning, the agent interacts with the environment and learns by receiving rewards. For deep learning, a multi-layered neural network is built and the model is trained using a large amount of data. The learning unit feeds back the results of self-learning to improve the overall performance of the system.

[0071] (Example of form 2) The TaskOrbit AI system, according to an embodiment of the present invention, is a smart task management agent that puts daily task management on track. The TaskOrbit AI system supports work and personal efficiency through schedule organization, priority optimization, and reminder notifications. The TaskOrbit AI system is an advanced artificial intelligence platform for business process automation, an AI-powered solution that automates repetitive tasks such as data entry and document processing. Using cutting-edge technologies such as machine learning and natural language processing, the TaskOrbit AI system automates repetitive tasks, improving accuracy and reducing human error. The TaskOrbit AI system is a cloud-based solution, available across various industries, and designed to improve productivity and efficiency. Its goal is to reduce the time and effort required for repetitive tasks, allowing employees to focus on specialized tasks. The TaskOrbit AI system uses machine learning algorithms to analyze data and automate tasks. It uses natural language processing to parse and process text data. The TaskOrbit AI system can integrate with other platforms and can be customized to different business needs using customized APIs. The TaskOrbit AI system includes various components such as machine learning, natural language processing, and data mining. The TaskOrbit AI system offers seamless integration with many other platforms, enabling business process automation, data collection and analysis, or improved customer support. The TaskOrbit AI system incorporates security features, providing the highest level of data protection. It consists of multiple components, including data extraction, data processing, and data storage. The TaskOrbit AI system integrates with other platforms such as CRM and ERP, enabling the automation and improvement of business processes.TaskOrbit AI systems improve productivity by automating highly repetitive tasks. TaskOrbit AI systems automate business data analysis, providing accurate analysis and insights. Using natural language processing, TaskOrbit AI systems can resolve customer requests and problems, handling issues quickly and accurately. TaskOrbit AI systems continuously learn and adapt to the business using machine learning algorithms. TaskOrbit AI systems have data extraction capabilities, allowing them to ingest and analyze vast amounts of data. TaskOrbit AI systems have data processing capabilities, enabling fast and efficient data processing. TaskOrbit AI systems have data storage capabilities, providing fast and secure data storage. TaskOrbit AI systems help businesses save time and reduce errors. Implementing TaskOrbit AI systems has a positive impact on businesses, improving customer satisfaction through time savings and reduced errors. Implementing TaskOrbit AI systems allows employees to automate repetitive tasks, freeing up time for more complex tasks. As AI technology evolves, TaskOrbit AI systems will continuously improve, offering more advanced features and benefits. This enables TaskOrbit AI systems to streamline daily task management and automate business processes.

[0072] The TaskOrbit AI system according to this embodiment comprises an automation unit, an analysis unit, a processing unit, and a learning unit. The automation unit automates tasks. For example, the automation unit automates tasks such as schedule management, data entry, and report generation. The automation unit can automate tasks using AI. For example, to automate schedule management tasks, the automation unit works with a calendar application to automatically add or modify schedules. To automate data entry tasks, the automation unit uses OCR technology to convert paper documents into digital data and inputs it into a database. To automate report generation tasks, the automation unit extracts necessary data from the database and generates reports according to a standard format. The analysis unit analyzes data from tasks automated by the automation unit. For example, the analysis unit analyzes data using methods such as statistical analysis and the application of machine learning algorithms. The analysis unit can analyze data using AI. For example, to perform statistical analysis, the analysis unit analyzes the distribution and trends of data and detects outliers. The analysis unit applies machine learning algorithms to perform data clustering and classification. The analysis unit analyzes the correlation between data and constructs a predictive model. The processing unit performs natural language processing based on the data obtained by the analysis unit. The processing unit performs natural language processing using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The processing unit can perform natural language processing using AI. For example, to perform morphological analysis, the processing unit divides text data into words and tags the parts of speech. To perform grammatical analysis, the processing unit analyzes the structure of sentences and identifies grammatical elements such as subjects, predicates, and objects. To perform semantic analysis, the processing unit understands the meaning of text data and generates appropriate responses according to the context. The learning unit performs self-learning based on the data obtained by the processing unit. The learning unit performs self-learning using algorithms such as reinforcement learning and deep learning. The learning unit can perform self-learning using AI. For example, to perform reinforcement learning, the learning unit has an agent interact with the environment and receive rewards to advance learning. To perform deep learning, the learning unit constructs a multi-layered neural network and trains the model using a large amount of data.The learning unit provides feedback on the results of self-learning, improving the overall system performance. As a result, the TaskOrbit AI system according to this embodiment enables efficient task management by performing task automation, data analysis, natural language processing, and self-learning.

[0073] The Automation Department automates tasks. For example, it automates tasks such as schedule management, data entry, and report generation. The Automation Department can use AI to automate tasks. Specifically, to automate schedule management tasks, the Automation Department integrates with calendar applications, analyzes the user's schedule, and suggests the optimal schedule. For example, when a user adds a meeting, the Automation Department automatically adjusts the time to avoid conflicts with other appointments. It can also utilize a reminder function to notify important appointments in advance. For automating data entry tasks, it uses OCR technology to convert paper documents into digital data and inputs it into a database. For example, it scans paper documents such as invoices and contracts and converts them into text data using OCR technology, reducing the effort required for manual data entry. Furthermore, to ensure data accuracy, it includes a function where AI automatically detects errors and suggests corrections. For automating report generation tasks, it extracts necessary data from the database and generates reports according to a standard format. For example, it automatically creates periodic performance reports based on sales data and customer data. This reduces the effort required for manual report creation, enabling the rapid and accurate provision of information. By efficiently automating these tasks, the automation unit can reduce the workload on users and improve productivity.

[0074] The analytics department analyzes data from tasks automated by the automation department. The analytics department analyzes data using methods such as statistical analysis and the application of machine learning algorithms. Specifically, to perform statistical analysis, the analytics department analyzes data distribution and trends to detect outliers. For example, it can analyze the distribution of sales data to detect abnormal increases or decreases in sales over a specific period. This allows for the identification of the cause of the abnormal data and the implementation of appropriate countermeasures. Furthermore, the analytics department applies machine learning algorithms to cluster and classify data. For example, it can cluster customer data and create segments based on customer purchasing behavior. This enables targeted marketing and the provision of personalized services. The analytics department can also analyze data correlations and build predictive models. For example, it can build a model to predict future sales based on historical sales data and advertising campaign data. This enables the development of effective marketing strategies and the optimization of inventory management. Through these data analyses, the analytics department can provide users with valuable insights and support their decision-making.

[0075] The processing unit performs natural language processing based on the data obtained by the analysis unit. The processing unit performs natural language processing using techniques such as morphological analysis, grammatical analysis, and semantic analysis. Specifically, to perform morphological analysis, the processing unit divides text data into words and tags them by part of speech. For example, it analyzes text entered by a user and identifies parts of speech such as nouns, verbs, and adjectives. This allows it to understand the structure of the text data and perform appropriate processing. In grammatical analysis, it analyzes the structure of a sentence and identifies grammatical elements such as subjects, predicates, and objects. For example, it analyzes the grammatical structure of a sentence entered by a user and accurately understands the meaning of the sentence. This improves the accuracy of natural language processing. In semantic analysis, it understands the meaning of text data and generates appropriate responses according to the context. For example, it analyzes the meaning of text data to generate appropriate answers to questions entered by a user. This enables natural dialogue with the user and supports effective communication. By making full use of these natural language processing techniques, the processing unit can generate appropriate responses to user input and improve the overall system performance.

[0076] The learning unit performs self-learning based on data obtained by the processing unit. The learning unit uses algorithms such as reinforcement learning and deep learning. Specifically, to perform reinforcement learning, the learning unit learns by having an agent interact with the environment and receive rewards. For example, the agent is rewarded each time it completes a task, allowing it to learn optimal actions. This enables the agent to learn how to complete tasks efficiently, improving the overall system performance. In deep learning, a multi-layered neural network is constructed, and the model is trained using a large amount of data. For example, in an image recognition task, a neural network is trained using a large amount of image data to build a highly accurate image recognition model. This allows the system to recognize complex patterns and perform advanced tasks. The learning unit feeds back the results of its self-learning, improving the overall system performance. For example, each time the learning unit learns new data, the system's performance improves, enabling more accurate predictions and responses. This allows the learning unit to continuously improve the system and provide high-quality services to users.

[0077] The security department provides security functions. For example, the security department provides security functions such as encryption, authentication, and access control. The security department can provide security functions using AI. For example, the security department applies the AES algorithm to encrypt data. The security department applies a two-factor authentication algorithm for user authentication. The security department sets access rights based on user roles for access control. This allows the security department to enhance data protection.

[0078] The integration unit integrates with other platforms. The integration unit integrates with other platforms through methods such as API integration and database integration. The integration unit can use AI to perform integration with other platforms. For example, the integration unit uses RESTful APIs to send and receive data for API integration. The integration unit applies ETL (Extract, Transform, Load) processes for database integration. The integration unit synchronizes data with other platforms to improve the efficiency of business processes. This enables the integration unit to achieve business process efficiency.

[0079] The extraction unit performs data extraction. The extraction unit extracts data using methods such as query-based extraction and filtering. The extraction unit can also use AI for data extraction. For example, to perform query-based extraction, the extraction unit uses SQL queries to extract the necessary data from the database. To perform filtering, the extraction unit selects data based on specific conditions. The extraction unit provides the data extraction results to the analysis unit, supporting efficient data analysis. This allows the extraction unit to efficiently obtain the necessary data.

[0080] The processing unit performs data processing. For example, the processing unit performs data processing using methods such as data cleaning and data transformation. The processing unit can also perform data processing using AI. For example, to perform data cleaning, the processing unit performs data imputation and removal of outliers. To perform data transformation, the processing unit transforms the data format and prepares it for analysis. The processing unit provides the data processing results to the analysis unit, supporting efficient data analysis. This enables the processing unit to achieve efficient data processing.

[0081] The storage unit performs data storage. The storage unit performs data storage using methods such as cloud storage and databases. The storage unit can also perform data storage using AI. For example, the storage unit can use cloud storage to save data and perform access control. The storage unit can use databases to save data and perform efficient data retrieval. The storage unit performs data backup and recovery, ensuring secure data storage. This enables the storage unit to ensure secure data storage.

[0082] The automation unit can estimate the user's emotions and adjust the priority of task automation based on the estimated emotions. For example, if the user is stressed, the automation unit will prioritize automating high-priority tasks to reduce the user's burden. If the user is relaxed, the automation unit will automate tasks according to normal priorities. If the user is in a hurry, the automation unit will postpone time-consuming tasks and prioritize automating tasks that can be completed quickly. In this way, the automation unit can reduce the user's burden by adjusting the priority of task automation based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0083] The automation unit can apply different automation algorithms depending on the type of task to be automated. For example, the automation unit applies an automation algorithm using OCR technology to data entry tasks. For document processing tasks, it applies an automation algorithm using natural language processing technology. For schedule management tasks, it applies an automation algorithm using calendar synchronization technology. In this way, the automation unit can improve the accuracy of automation by applying the appropriate automation algorithm according to the type of task.

[0084] The automation unit can optimize the timing of automation based on the frequency of the tasks to be automated. For example, the automation unit can set daily tasks to be automated regularly. It can set weekly tasks to be automated at the beginning of the week. It can set monthly tasks to be automated at the beginning of the month. In this way, the automation unit can achieve efficient task management by optimizing the timing of automation based on the frequency of tasks.

[0085] The automation unit can estimate the user's emotions and adjust the content of the tasks to be automated based on the estimated emotions. For example, if the user is stressed, the automation unit will prioritize automating simple tasks to reduce the user's burden. If the user is relaxed, the automation unit will automate tasks according to the usual task content. If the user is in a hurry, the automation unit will prioritize automating tasks that can be completed quickly. In this way, the automation unit can reduce the user's burden by adjusting the content of tasks based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0086] The automation unit can monitor the execution results of automated tasks in real time and modify the automation process as needed. For example, if an error occurs during task execution, the automation unit detects the error in real time and corrects the automation process. If the task execution results are not as expected, the automation unit analyzes the results in real time and adjusts the automation process. If new requirements arise during task execution, the automation unit reflects the requirements in real time and modifies the automation process. In this way, the automation unit can improve the accuracy of automation by monitoring task execution results in real time and making corrections as needed.

[0087] The automation unit can apply different automation methods depending on the execution environment of the task to be automated. For example, in an on-premises environment, the automation unit applies an automation method that utilizes local resources. In a cloud environment, the automation unit applies an automation method that utilizes cloud resources. In a hybrid environment, the automation unit applies an automation method that combines on-premises and cloud resources. This allows the automation unit to improve the efficiency of automation by applying the appropriate automation method according to the task's execution environment.

[0088] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is nervous, the analysis unit provides a simple and highly visible display method. If the user is relaxed, the analysis unit provides a display method that includes detailed information. If the user is in a hurry, the analysis unit provides a display method that gets straight to the point. In this way, the analysis unit can achieve a user-friendly display by adjusting the display method of the analysis results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0089] The analysis unit can apply different analysis algorithms depending on the type of data being analyzed. For example, it can apply a natural language processing algorithm to text data, a statistical analysis algorithm to numerical data, and an image recognition algorithm to image data. This allows the analysis unit to improve the accuracy of its analysis by applying the appropriate analysis algorithm according to the type of data.

[0090] The analysis unit can refer to past analysis data to improve the accuracy of its analysis results. For example, the analysis unit can correct current analysis results based on past analysis data. The analysis unit can refer to past analysis data to extract trends and patterns. The analysis unit can utilize past analysis data to improve the accuracy of its analysis algorithms. In this way, the analysis unit can improve the accuracy of its analysis results by referring to past analysis data.

[0091] The analysis unit can estimate the user's emotions and adjust the importance of the analysis results based on the estimated emotions. For example, if the user is stressed, the analysis unit will prioritize displaying high-importance analysis results. If the user is relaxed, the analysis unit will display analysis results according to normal importance. If the user is in a hurry, the analysis unit will prioritize displaying analysis results that require immediate attention. In this way, the analysis unit can prioritize displaying important information by adjusting the importance of analysis results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The analysis department can optimize the timing of data acquisition and perform real-time data analysis. For example, the analysis department optimizes the timing of data acquisition to perform real-time data analysis. The analysis department adjusts the timing of data acquisition to improve the accuracy of analysis results. The analysis department supports rapid decision-making by optimizing the timing of data acquisition. In this way, the analysis department can achieve real-time data analysis by optimizing the timing of data acquisition.

[0093] The analysis department can integrate analysis results with other systems to perform comprehensive data analysis. For example, the analysis department can integrate analysis results with a CRM system to perform comprehensive analysis of customer data. The analysis department can integrate analysis results with an ERP system to perform comprehensive analysis of business processes. The analysis department can integrate analysis results with a BI tool to perform comprehensive business intelligence analysis. In this way, the analysis department can achieve comprehensive data analysis by integrating with other systems.

[0094] The processing unit can estimate the user's emotions and adjust the natural language processing results based on the estimated emotions. For example, if the user is nervous, the processing unit provides simple and easy-to-read natural language processing results. If the user is relaxed, the processing unit provides natural language processing results that include detailed information. If the user is in a hurry, the processing unit provides natural language processing results that get straight to the point. In this way, the processing unit can provide results that are easy for the user to understand by adjusting the natural language processing results based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0095] The processing unit can apply different natural language processing algorithms depending on the type of text data being processed. For example, the processing unit can apply a summarization algorithm to news articles, a sentiment analysis algorithm to customer inquiries, and a topic modeling algorithm to product reviews. This allows the processing unit to improve the accuracy of processing by applying the appropriate natural language processing algorithm according to the type of text data.

[0096] The processing unit can refer to past processing data to improve the accuracy of the processing results. For example, the processing unit corrects the current processing results based on past processing data. The processing unit refers to past processing data and extracts trends and patterns. The processing unit utilizes past processing data to improve the accuracy of the natural language processing algorithm. In this way, the processing unit can improve the accuracy of the processing results by referring to past processing data.

[0097] The processing unit can estimate the user's emotions and adjust the display method of the processing results based on the estimated emotions. For example, if the user is nervous, the processing unit provides a simple and highly visible display method. If the user is relaxed, the processing unit provides a display method that includes detailed information. If the user is in a hurry, the processing unit provides a display method that gets straight to the point. In this way, the processing unit can achieve a user-friendly display by adjusting the display method of the processing results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The processing unit can optimize the timing of acquiring text data to be processed, enabling real-time natural language processing. For example, the processing unit optimizes the timing of text data acquisition and performs real-time natural language processing. The processing unit adjusts the timing of text data acquisition to improve the accuracy of processing results. The processing unit supports rapid decision-making by optimizing the timing of text data acquisition. Thus, by optimizing the timing of text data acquisition, the processing unit can achieve real-time natural language processing.

[0099] The processing unit can integrate its processing results with other systems to perform comprehensive data processing. For example, it can integrate its processing results with a CRM system to perform comprehensive processing of customer data. It can integrate its processing results with an ERP system to perform comprehensive processing of business processes. It can integrate its processing results with a BI tool to perform comprehensive business intelligence processing. In this way, the processing unit can achieve comprehensive data processing by integrating with other systems.

[0100] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is stressed, the learning unit will prioritize selecting simple training data. If the user is relaxed, the learning unit will select normal training data. If the user is in a hurry, the learning unit will prioritize selecting data that can be learned quickly. In this way, the learning unit can reduce the user's burden by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0101] The learning unit can apply different learning algorithms depending on the type of data being trained. For example, the learning unit applies a natural language processing algorithm to text data, a statistical learning algorithm to numerical data, and an image recognition algorithm to image data. This allows the learning unit to improve the accuracy of its learning by applying the appropriate learning algorithm according to the type of data.

[0102] The learning unit can refer to past training data to improve the accuracy of the learning results. For example, the learning unit corrects the current learning results based on past training data. The learning unit refers to past training data and extracts trends and patterns. The learning unit improves the accuracy of the learning algorithm by utilizing past training data. In this way, the learning unit can improve the accuracy of the learning results by referring to past training data.

[0103] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit will reduce the learning frequency to alleviate the burden. If the user is relaxed, the learning unit will perform learning at the normal frequency. If the user is in a hurry, the learning unit will increase the learning frequency to accelerate learning. In this way, the learning unit can reduce the user's burden by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The learning unit can optimize the timing of data acquisition for training and perform real-time data learning. For example, the learning unit optimizes the timing of data acquisition and performs real-time data learning. The learning unit adjusts the timing of data acquisition to improve the accuracy of the learning results. The learning unit optimizes the timing of data acquisition to support rapid decision-making. In this way, the learning unit can achieve real-time data learning by optimizing the timing of data acquisition.

[0105] The learning unit can integrate its learning results with other systems to perform comprehensive data learning. For example, the learning unit can integrate its learning results with a CRM system to perform comprehensive learning of customer data. The learning unit can integrate its learning results with an ERP system to perform comprehensive learning of business processes. The learning unit can integrate its learning results with a BI tool to perform comprehensive learning of business intelligence. In this way, the learning unit can achieve comprehensive data learning by integrating with other systems.

[0106] The security department can estimate the user's emotions and adjust the priority of security measures based on those emotions. For example, if the user is feeling anxious, the security department will prioritize high-priority security measures. If the user is relaxed, the security department will implement security measures according to normal priorities. If the user is in a hurry, the security department will prioritize security measures that require immediate attention. In this way, the security department can prioritize important security measures by adjusting the priority of security measures based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0107] The security unit can apply different security algorithms depending on the type of security measure. For example, the security unit applies the AES algorithm for data encryption. The security unit applies the two-factor authentication algorithm for user authentication. The security unit applies the firewall algorithm for network security. In this way, the security unit can improve the accuracy of security by applying the appropriate security algorithm according to the type of security measure.

[0108] The security department can estimate the user's emotions and adjust security measures based on those emotions. For example, if the user is feeling anxious, the security department will implement strong security measures to provide reassurance. If the user is relaxed, the security department will implement standard security measures. If the user is in a hurry, the security department will implement security measures that require a quick response. In this way, the security department can provide reassurance to the user by adjusting security measures based on their emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0109] The security department can monitor the results of security measures in real time and modify security processes as needed. For example, if an error occurs during the execution of security measures, the security department can detect the error in real time and correct the security process. If the results of security measures are not as expected, the security department can analyze the results in real time and adjust the security process. If a new threat emerges during the execution of security measures, the security department can reflect the threat in real time and modify the security process. In this way, the security department can improve the accuracy of security by monitoring the results of security measures in real time and making corrections as needed.

[0110] The integration unit can estimate the user's emotions and select a platform for integration based on those emotions. For example, if the user is stressed, the integration unit will prioritize a user-friendly platform. If the user is relaxed, the integration unit will follow normal platform selection criteria. If the user is in a hurry, the integration unit will prioritize a platform that can be integrated quickly. This allows the integration unit to reduce the user's burden by selecting a platform for integration based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0111] The integration unit can apply different integration algorithms depending on the type of platform being integrated. For example, the integration unit applies a customer data integration algorithm to CRM systems, a business process integration algorithm to ERP systems, and a business intelligence integration algorithm to BI tools. This allows the integration unit to improve the accuracy of integration by applying the appropriate integration algorithm according to the type of platform.

[0112] The integration unit can estimate the user's emotions and adjust the content of the integration process based on the estimated emotions. For example, if the user is stressed, the integration unit will prioritize a simpler integration process. If the user is relaxed, the integration unit will perform a normal integration process. If the user is in a hurry, the integration unit will prioritize a process that can be integrated quickly. In this way, the integration unit can reduce the user's burden by adjusting the content of the integration process based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0113] The integration unit can monitor the results of the integration process in real time and modify the integration process as needed. For example, if an error occurs during the execution of the integration process, the integration unit can detect the error in real time and correct the integration process. If the results of the integration process are not as expected, the integration unit can analyze the results in real time and adjust the integration process. If new requirements arise during the execution of the integration process, the integration unit can reflect the requirements in real time and modify the integration process. In this way, the integration unit can improve the accuracy of the integration by monitoring the results of the integration process in real time and making corrections as needed.

[0114] The extraction unit can estimate the user's emotions and adjust the priority of the data to be extracted based on the estimated user emotions. For example, if the user is stressed, the extraction unit will prioritize extracting high-priority data. If the user is relaxed, the extraction unit will extract data according to normal priorities. If the user is in a hurry, the extraction unit will prioritize extracting data that can be extracted quickly. In this way, the extraction unit can prioritize the extraction of important data by adjusting the priority of the data to be extracted based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0115] The extraction unit can apply different extraction algorithms depending on the type of data being extracted. For example, the extraction unit can apply a natural language processing algorithm to text data, a statistical analysis algorithm to numerical data, and an image recognition algorithm to image data. By applying the appropriate extraction algorithm according to the type of data, the extraction unit can improve the accuracy of the extraction.

[0116] The extraction unit can estimate the user's emotions and adjust the content of the data extracted based on the estimated emotions. For example, if the user is stressed, the extraction unit will prioritize extracting simple data. If the user is relaxed, the extraction unit will extract data according to normal data content. If the user is in a hurry, the extraction unit will prioritize extracting data that can be extracted quickly. In this way, the extraction unit can reduce the burden on the user by adjusting the content of the data extracted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0117] The extraction unit can monitor the results of the extraction process in real time and modify the extraction process as needed. For example, if an error occurs during the execution of the extraction process, the extraction unit can detect the error in real time and modify the extraction process. If the results of the extraction process are not as expected, the extraction unit can analyze the results in real time and adjust the extraction process. If new requirements arise during the execution of the extraction process, the extraction unit can reflect the requirements in real time and modify the extraction process. In this way, the extraction unit can improve the accuracy of the extraction by monitoring the results of the extraction process in real time and modifying them as needed.

[0118] The storage unit can estimate the user's emotions and adjust how data is stored based on those emotions. For example, if the user is feeling anxious, the storage unit will frequently back up the data to provide reassurance. If the user is relaxed, the storage unit will follow the normal storage method. If the user is in a hurry, the storage unit will prioritize methods that allow for quick storage. In this way, the storage unit can provide reassurance to the user by adjusting how data is stored based on their emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0119] The storage unit can apply different storage algorithms depending on the type of data being stored. For example, the storage unit applies a compression algorithm to text data, an image compression algorithm to image data, and a video compression algorithm to video data. By applying the appropriate storage algorithm according to the data type, the storage unit can improve the accuracy of storage.

[0120] The storage unit can estimate the user's emotions and adjust the content of the data it stores based on the estimated emotions. For example, if the user is feeling anxious, the storage unit will prioritize storing important data. If the user is relaxed, the storage unit will store data according to normal data content. If the user is in a hurry, the storage unit will prioritize storing data that can be saved quickly. In this way, the storage unit can reduce the user's burden by adjusting the content of the data it stores based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0121] The storage unit can monitor the results of the save process in real time and modify the save process as needed. For example, if an error occurs during the save process, the storage unit can detect the error in real time and modify the save process. If the results of the save process are not as expected, the storage unit can analyze the results in real time and adjust the save process. If new requirements arise during the save process, the storage unit can reflect the requirements in real time and modify the save process. In this way, the storage unit can improve the accuracy of saving by monitoring the results of the save process in real time and modifying them as needed.

[0122] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0123] The automation unit can estimate the user's emotions and adjust the timing of task automation based on those emotions. For example, if the user is stressed, it prioritizes automating high-priority tasks to reduce the user's burden. If the user is relaxed, it automates tasks according to normal priorities. If the user is in a hurry, it prioritizes automating tasks that can be completed quickly. In this way, the automation unit can reduce the user's burden by adjusting the timing of task automation based on the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, among other methods.

[0124] The analysis unit can estimate the user's emotions and adjust the notification method of the analysis results based on the estimated emotions. For example, if the user is nervous, a simple and highly visible notification method is provided. If the user is relaxed, a notification method containing detailed information is provided. If the user is in a hurry, a notification method that gets straight to the point is provided. In this way, the analysis unit can create notifications that are easy for the user to understand by adjusting the notification method of the analysis results based on the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc.

[0125] The processing unit can estimate the user's emotions and adjust the level of detail in the natural language processing results based on the estimated emotions. For example, if the user is nervous, it provides simple and highly visual natural language processing results. If the user is relaxed, it provides natural language processing results that include detailed information. If the user is in a hurry, it provides natural language processing results that get straight to the point. In this way, the processing unit can provide results that are easy for the user to understand by adjusting the level of detail in the natural language processing results based on the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc.

[0126] The learning unit can estimate the user's emotions and select training data based on those emotions. For example, if the user is stressed, it will prioritize selecting simple training data. If the user is relaxed, it will select normal training data. If the user is in a hurry, it will prioritize selecting data that allows for quick learning. In this way, the learning unit can reduce the user's burden by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc.

[0127] The security department can estimate a user's emotions and adjust the priority of security measures based on those emotions. For example, if a user is feeling anxious, high-priority security measures will be prioritized. If a user is relaxed, security measures will be implemented according to the usual priorities. If a user is in a hurry, security measures requiring immediate attention will be prioritized. In this way, the security department can prioritize important security measures by adjusting the priority of security measures based on the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, among other methods.

[0128] The automation unit can automate tasks at the optimal time by referring to the user's past behavior history. For example, if a user checks their email every morning, it can automate related tasks to coincide with that time. If a user creates reports on weekends, it can automatically collect the necessary data beforehand. If a user submits expense reports at the end of the month, it can automatically prepare the necessary documents beforehand. In this way, the automation unit can optimize task automation based on the user's behavior patterns.

[0129] The analytics department can integrate information from different data sources to perform comprehensive analysis. For example, it can integrate and analyze customer data from CRM systems with business data from ERP systems; customer feedback from social media with sales data; and sensor data with inventory data. By integrating information from multiple data sources, the analytics department can achieve more accurate and comprehensive analysis.

[0130] The processing unit can process text data in different languages ​​in natural language processing. For example, it can apply an English natural language processing algorithm to English text data, a Japanese natural language processing algorithm to Japanese text data, and a Chinese natural language processing algorithm to Chinese text data. This allows the processing unit to improve processing accuracy by performing appropriate natural language processing on text data in different languages.

[0131] The learning unit can collect information from different data sources in real time and utilize it for training. For example, it can collect sensor data in real time and use it to train machine learning models. It can collect feedback from social media in real time and use it to train sentiment analysis models. It can collect transaction data in real time and use it to train prediction models. As a result, the learning unit can improve the accuracy of its learning models by utilizing data collected in real time.

[0132] The security department can apply different security levels to security measures. For example, it can apply strong encryption algorithms to highly confidential data, standard encryption algorithms to general data, and no encryption to publicly available data. This allows the security department to improve security accuracy by applying appropriate security measures according to the confidentiality of the data.

[0133] The following briefly describes the processing flow for example form 2.

[0134] Step 1: The automation department automates tasks. For example, the automation department automates tasks such as schedule management, data entry, and report generation. The automation department can automate these tasks using AI. Specifically, to automate schedule management tasks, it integrates with a calendar application to automatically add and modify schedules. To automate data entry tasks, it uses OCR technology to convert paper documents into digital data and input it into a database. To automate report generation tasks, it extracts necessary data from the database and generates reports according to a standard format. Step 2: The analysis unit analyzes the data from the automated tasks performed by the automation unit. For example, it analyzes the data using methods such as statistical analysis and the application of machine learning algorithms. The analysis unit can use AI to analyze the data. Specifically, it analyzes the distribution and trends of the data to perform statistical analysis and detects outliers. It applies machine learning algorithms to cluster and classify the data. It analyzes the correlation between data and builds predictive models. Step 3: The processing unit performs natural language processing based on the data obtained by the analysis unit. For example, it performs natural language processing using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The processing unit can perform natural language processing using AI. Specifically, to perform morphological analysis, it divides the text data into words and tags the parts of speech. To perform grammatical analysis, it analyzes the structure of sentences and identifies grammatical elements such as subjects, predicates, and objects. To perform semantic analysis, it understands the meaning of the text data and generates appropriate responses according to the context. Step 4: The learning unit performs self-learning based on the data obtained by the processing unit. For example, it performs self-learning using algorithms such as reinforcement learning and deep learning. The learning unit can perform self-learning using AI. Specifically, for reinforcement learning, the agent interacts with the environment and learns by receiving rewards. For deep learning, a multi-layered neural network is built and the model is trained using a large amount of data. The learning unit feeds back the results of self-learning to improve the overall performance of the system.

[0135] 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.

[0136] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0137] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0138] Each of the multiple elements described above, including the automation unit, analysis unit, processing unit, learning unit, security unit, integration unit, extraction unit, processing unit, and storage unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the automation unit is implemented by the control unit 46A of the smart device 14 and automates tasks such as schedule management and data input. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes data by applying statistical analysis and machine learning algorithms. The processing unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs natural language processing. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs reinforcement learning and deep learning. The security unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs encryption and authentication. The integration unit is implemented by the control unit 46A of the smart device 14 and integrates with other platforms. The extraction unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs data extraction. The storage unit is implemented by the specific processing unit 290 of the data processing device 12 and performs data storage. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0139] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0140] 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.

[0141] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0142] 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.

[0143] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0145] 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.

[0146] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0147] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0148] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0149] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0150] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0151] 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.

[0152] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0153] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0154] Each of the multiple elements described above, including the automation unit, analysis unit, processing unit, learning unit, security unit, integration unit, extraction unit, processing unit, and storage unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the automation unit is implemented by the control unit 46A of the smart glasses 214 and automates tasks such as schedule management and data input. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes data by applying statistical analysis and machine learning algorithms. The processing unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs natural language processing. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs reinforcement learning and deep learning. The security unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs encryption and authentication. The integration unit is implemented by the control unit 46A of the smart glasses 214 and integrates with other platforms. The extraction unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs data extraction. The storage unit is implemented by the specific processing unit 290 of the data processing device 12 and performs data storage. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0155] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0156] 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.

[0157] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0158] 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.

[0159] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0161] 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.

[0162] 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.

[0163] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0164] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0165] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0166] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0167] 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.

[0168] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0169] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0170] Each of the multiple elements described above, including the automation unit, analysis unit, processing unit, learning unit, security unit, integration unit, extraction unit, processing unit, and storage unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the automation unit is implemented by the control unit 46A of the headset terminal 314 and automates tasks such as schedule management and data input. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes data by applying statistical analysis and machine learning algorithms. The processing unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs natural language processing. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs reinforcement learning and deep learning. The security unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs encryption and authentication. The integration unit is implemented by the control unit 46A of the headset terminal 314 and integrates with other platforms. The extraction unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs data extraction. The storage unit is implemented by the specific processing unit 290 of the data processing device 12 and performs data storage. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0171] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0172] 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.

[0173] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0174] 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.

[0175] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0176] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0177] 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.

[0178] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0179] 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.

[0180] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0181] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0182] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0183] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0184] 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.

[0185] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0186] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0187] Each of the multiple elements described above, including the automation unit, analysis unit, processing unit, learning unit, security unit, integration unit, extraction unit, processing unit, and storage unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the automation unit is implemented by the control unit 46A of the robot 414 and automates tasks such as schedule management and data input. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes data by applying statistical analysis and machine learning algorithms. The processing unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs natural language processing. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs reinforcement learning and deep learning. The security unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs encryption and authentication. The integration unit is implemented by the control unit 46A of the robot 414 and integrates with other platforms. The extraction unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs data extraction. The storage unit is implemented by the specific processing unit 290 of the data processing device 12 and performs data storage. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0188] 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.

[0189] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0190] 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.

[0191] 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.

[0192] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0193] 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."

[0194] 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.

[0195] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0204] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0205] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0206] (Note 1) The automation unit performs task automation, An analysis unit that analyzes data from tasks automated by the aforementioned automation unit, A processing unit that performs natural language processing based on the data obtained by the analysis unit, A learning unit that performs self-learning based on the data obtained by the processing unit, Equipped with A system characterized by the following features. (Note 2) Equipped with a security unit that provides security functions. The system described in Appendix 1, characterized by the features described herein. (Note 3) It features an integration unit for integrating with other platforms. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes an extraction unit that performs data extraction. The system described in Appendix 1, characterized by the features described herein. (Note 5) A processing unit for data processing is provided. The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes a storage unit for data storage. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned automation unit, It estimates the user's emotions and adjusts the priority of task automation based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned automation unit, Depending on the type of task to be automated, different automation algorithms should be applied. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned automation unit, Optimize the timing of automation based on the frequency of the tasks to be automated. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned automation unit, It estimates the user's emotions and adjusts the automated tasks based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned automation unit, Monitor the execution results of automated tasks in real time and modify the automated process as needed. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned automation unit, Depending on the execution environment of the task to be automated, different automation methods should be applied. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit is It estimates the user's emotions and adjusts how the analysis results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit is Depending on the type of data being analyzed, different analytical algorithms should be applied. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit is To improve the accuracy of the analysis results, we refer to past analysis data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit is It estimates the user's emotions and adjusts the importance of the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit is Optimize the timing of data acquisition for analysis and perform real-time data analysis. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit is The analysis results are integrated with other systems to perform comprehensive data analysis. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned processing unit, It estimates the user's emotions and adjusts the natural language processing results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned processing unit, Depending on the type of text data being processed, different natural language processing algorithms are applied. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned processing unit, To improve the accuracy of the processing results, we refer to past processing data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned processing unit, It estimates the user's emotions and adjusts how the processing results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned processing unit, Optimize the timing of acquiring text data to be processed and perform natural language processing in real time. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned processing unit, The processing results are integrated with other systems to perform comprehensive data processing. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned learning unit, Depending on the type of data being used for training, different learning algorithms should be applied. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned learning unit, To improve the accuracy of the learning results, we refer to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned learning unit, Optimize the timing of data acquisition for training and perform data learning in real time. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned learning unit, The learning results are integrated with other systems to perform comprehensive data learning. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned security unit is It estimates user sentiment and adjusts security measures priorities based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned security unit is Depending on the type of security measure, different security algorithms will be applied. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned security unit is The system estimates user sentiment and adjusts security measures based on that estimated sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned security unit is The results of security measures are monitored in real time, and security processes are modified as needed. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned integration unit is The system estimates user sentiment and selects a platform for integration based on that estimated sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned integration unit is Depending on the type of platform being integrated, different integration algorithms are applied. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned integration unit is It estimates the user's emotions and adjusts the content of the integration process based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned integration unit is The results of the integration process are monitored in real time, and the process is modified as needed. The system described in Appendix 3, characterized by the features described herein. (Note 39) The extraction unit is It estimates the user's emotions and adjusts the priority of the data extracted based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 40) The extraction unit is Depending on the type of data to be extracted, a different extraction algorithm will be applied. The system described in Appendix 4, characterized by the features described herein. (Note 41) The extraction unit is It estimates the user's emotions and adjusts the content of the data extracted based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 42) The extraction unit is The extraction process results are monitored in real time, and the extraction process is modified as needed. The system described in Appendix 4, characterized by the features described herein. (Note 43) The aforementioned storage unit is We estimate the user's emotions and adjust how data is stored based on those estimated emotions. The system described in Appendix 5, characterized by the features described herein. (Note 44) The aforementioned storage unit is Depending on the type of data to be saved, a different saving algorithm will be applied. The system described in Appendix 5, characterized by the features described herein. (Note 45) The aforementioned storage unit is It estimates the user's emotions and adjusts the content of the data stored based on the estimated user emotions. The system described in Appendix 5, characterized by the features described herein. (Note 46) The aforementioned storage unit is The results of the save process are monitored in real time, and the save process is modified as needed. The system described in Appendix 5, characterized by the features described herein. [Explanation of Symbols]

[0207] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The automation unit performs task automation, An analysis unit that analyzes data from tasks automated by the aforementioned automation unit, A processing unit that performs natural language processing based on the data obtained by the analysis unit, A learning unit that performs self-learning based on the data obtained by the processing unit, Equipped with A system characterized by the following features.

2. Equipped with a security unit that provides security functions. The system according to feature 1.

3. It features an integration unit for integrating with other platforms. The system according to feature 1.

4. It includes an extraction unit that performs data extraction. The system according to feature 1.

5. It includes a storage unit for data storage. The system according to feature 1.

6. The aforementioned automation unit, It estimates the user's emotions and adjusts the priority of task automation based on the estimated user emotions. The system according to feature 1.

7. The aforementioned automation unit, Depending on the type of task to be automated, different automation algorithms should be applied. The system according to feature 1.

8. The aforementioned automation unit, Optimize the timing of automation based on the frequency of the tasks to be automated. The system according to feature 1.

Images