system

Abstract

The system according to this embodiment aims to optimize the workflow based on the operation status of the work PC and provide personalized support. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, an automation unit, a provision unit, an optimization unit, and a support unit. The collection unit records the operation status of the business PC. The analysis unit analyzes the operation status recorded by the collection unit. The automation unit automates tasks based on the analysis results obtained by the analysis unit. The provision unit provides the results of the tasks automated by the automation unit. The optimization unit optimizes the business flow based on the results provided by the provision unit. The support unit provides personalized support based on the business flow optimized by the optimization unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, optimizing the business process based on the operation status of the business PC and providing individualized support have not been sufficiently carried out, and there is room for improvement.

[0005] The system according to the embodiment aims to optimize the business process based on the operation status of the business PC and provide individualized support.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, an analysis unit, an automation unit, a data provision unit, an optimization unit, and a support unit. The data collection unit records the operation status of the business PC. The analysis unit analyzes the operation status recorded by the data collection unit. The automation unit automates tasks based on the analysis results obtained by the analysis unit. The data provision unit provides the results of the tasks automated by the automation unit. The optimization unit optimizes the business flow based on the results provided by the data provision unit. The support unit provides personalized support based on the business flow optimized by the optimization unit. [Effects of the Invention]

[0007] The system according to this embodiment can optimize the workflow based on the operation status of the work PC and provide personalized support. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An AI agent system according to an embodiment of the present invention is a system that comprehensively records the operation status of an employee's work PC and learns work patterns. Based on the accumulated data, this AI agent system automates or assists with the following tasks. First, the AI ​​agent system creates and prioritizes to-do lists. The AI ​​agent system analyzes the employee's work content and organizes tasks based on importance and urgency. Next, the AI ​​agent system creates and proposes email drafts. The AI ​​agent system learns the content of the employee's past emails and proposes appropriate wording. Furthermore, the AI ​​agent system automates data entry, processing, and analysis. The AI ​​agent system automates routine data processing to improve efficiency. In addition, the AI ​​agent system schedules meetings and notifies participants. The AI ​​agent system checks the employee's schedule and proposes the optimal meeting time. The AI ​​agent system also automatically creates and summarizes meeting minutes. The AI ​​agent system records the content of meetings and summarizes the key points. The AI ​​agent system also proposes automation and efficiency improvements for routine tasks. The AI ​​agent system analyzes the workflow and makes suggestions for efficiency improvements. Furthermore, the AI ​​agent system proposes optimization of the workflow. The AI ​​agent system optimizes and streamlines workflows. It learns employees' work styles and preferences, providing personalized support. This improves employee efficiency, eliminating inefficiencies and wasted time. It also reduces employee fatigue and decreased motivation caused by repetitive tasks. Furthermore, it prevents delays and quality declines due to labor shortages. The complexity of data management and analysis is also reduced, making it easier to visualize and optimize business processes. The AI ​​agent system achieves these tasks by utilizing text generation AI, natural language processing AI, data analysis AI, image / video generation AI, speech processing AI, and code generation AI. For example, text generation AI can automatically create and prioritize to-do lists, draft emails, automatically create and summarize meeting minutes, and generate suggestions for optimizing workflows.Natural language processing AI communicates with employees, analyzes and understands work patterns, and provides personalized support. Data analysis AI records and analyzes the usage of work PCs, provides insights for improving work efficiency, and learns employees' work styles and preferences. Image and video generation AI visualizes data and automatically creates presentation materials. Voice processing AI operates using voice commands and performs speech recognition and transcription of meetings. Code generation AI creates scripts to improve work efficiency and generates code for data processing and analysis. As a result, the AI ​​agent system can improve employee work efficiency and eliminate inefficiencies and wasted time.

[0029] The AI ​​agent system according to this embodiment comprises a collection unit, an analysis unit, an automation unit, a provision unit, an optimization unit, and a support unit. The collection unit records the operation status of the work PC. The collection unit records, for example, mouse movements, keyboard input, and application usage. The collection unit can comprehensively record the operation status of the work PC. For example, the collection unit records the operation status of the work PC in real time and stores it in a database. When recording the operation status, the collection unit can select the type of data to record according to the employee's work content. For example, in the case of data entry work, the collection unit focuses on recording data related to input speed and accuracy. When recording the operation status, the collection unit can improve the accuracy of the recording by referring to the employee's past operation history. For example, based on past operation history, the collection unit prioritizes recording frequently used operations. The collection unit can estimate the employee's emotions and adjust the frequency of recording the operation status based on the estimated emotions of the employee. For example, if the employee is feeling stressed, the collection unit reduces the frequency of recording the operation status to alleviate the workload. The data collection unit can prioritize recording highly relevant operations by considering the employee's geographical location when recording operational activity. For example, if the employee is in the office, the data collection unit will prioritize recording work-related operations. The data collection unit can also analyze the employee's social media activity and record relevant operations when recording operational activity. For example, if the employee uses social media during work hours, the data collection unit will record those operations. The analysis unit analyzes the operational activity recorded by the data collection unit. The analysis unit can analyze the recorded operational activity and learn work patterns. For example, the analysis unit can analyze operational activity using data aggregation methods and pattern recognition algorithms. The analysis unit can estimate the employee's emotions and adjust the analysis method based on the estimated emotions. For example, if the analysis unit is stressed, it will apply a simplified analysis method. When analyzing recorded operational activity, the analysis unit can apply different analysis algorithms depending on the employee's work content. For example, in the case of data entry work, the analysis unit will apply algorithms that analyze input speed and accuracy.The analysis department can improve the accuracy of its analysis of recorded operational activity by referring to employees' past work patterns. For example, the analysis department can focus on analyzing frequently occurring operations based on past work patterns. The analysis department can also consider employees' geographical location information when analyzing recorded operational activity. For example, the analysis department can focus on analyzing work-related operations when employees are in the office. The analysis department can improve the accuracy of its analysis by referring to relevant literature related to employees when analyzing recorded operational activity. For example, the analysis department can refer to work-related literature to aid in the analysis of operational activity. The automation department automates tasks based on the analysis results obtained by the analysis department. The automation department can automate tasks such as creating and prioritizing to-do lists, drafting and proposing emails, data entry, processing, and analysis. For example, the automation department analyzes employees' work content and organizes tasks based on importance and urgency. The automation department can estimate employees' emotions and adjust the automation method based on the estimated employee emotions. For example, the automation department can apply a simpler automation method if an employee is experiencing stress. The automation department can apply different automation algorithms depending on the employee's work content during automation. For example, for data entry tasks, the automation department can apply an automation algorithm that improves input speed and accuracy. The automation department can improve the accuracy of automation by referring to the employee's past work patterns. For example, based on past work patterns, the automation department prioritizes automating frequently occurring tasks. The automation department can estimate an employee's emotions and determine automation priorities based on the estimated emotions. For example, if an employee is experiencing stress, the automation department will postpone the automation of less important tasks. The automation department can consider the employee's geographical location during automation. For example, if an employee is in the office, the automation department will prioritize automating work-related tasks. The automation department can analyze an employee's social media activity during automation and automate related tasks. For example, if an employee uses social media during work hours, the automation department will automate that task.The Delivery Unit provides the results of tasks automated by the Automation Unit. The Delivery Unit can schedule meetings and notify participants, and automatically create and summarize meeting minutes. For example, the Delivery Unit can check employee schedules and suggest optimal meeting times. The Delivery Unit can estimate employee emotions and adjust how results are displayed based on the estimated emotions. For example, if an employee is stressed, the Delivery Unit provides a simple and highly visible display. When displaying results, the Delivery Unit can apply different display algorithms depending on the employee's work content. For example, for data entry tasks, the Delivery Unit visually displays results related to entry speed and accuracy. When displaying results, the Delivery Unit can improve display accuracy by referring to the employee's past work patterns. For example, based on past work patterns, the Delivery Unit focuses on displaying frequently occurring results. The Delivery Unit can estimate employee emotions and prioritize results based on the estimated emotions. For example, if an employee is stressed, the Delivery Unit postpones displaying less important results. The service provider can display results while considering the employee's geographical location. For example, if the employee is in the office, the service provider will prioritize displaying work-related results. The service provider can analyze the employee's social media activity and provide relevant results when displaying results. For example, if the service provider uses social media during work hours, it will display the results. The optimization service provider optimizes the workflow based on the results provided by the service provider. The optimization service provider can make optimization suggestions for the workflow. For example, the optimization service provider will suggest which parts of the workflow should be optimized based on optimization evaluation criteria. The optimization service provider can estimate the employee's emotions and adjust the workflow optimization method based on the estimated employee emotions. For example, if the optimization service provider is stressed, it will apply a simpler optimization method. When optimizing the workflow, the optimization service provider can apply different optimization algorithms depending on the employee's work content.For example, the optimization unit applies optimization algorithms to improve input speed and accuracy in the case of data entry tasks. The optimization unit can improve the accuracy of optimization by referencing employees' past work patterns when optimizing workflows. For example, it prioritizes optimizing frequently occurring tasks based on past work patterns. The optimization unit can estimate employees' emotions and determine the priority of workflow optimization based on the estimated emotions. For example, if an employee is stressed, the optimization unit will postpone the optimization of less important tasks. The optimization unit can consider employees' geographical location when optimizing workflows. For example, if an employee is in the office, the optimization unit prioritizes optimizing work-related tasks. The optimization unit can analyze employees' social media activity and optimize relevant workflows when optimizing workflows. For example, if an employee uses social media during work hours, the optimization unit optimizes that workflow. The support unit provides personalized support based on the workflows optimized by the optimization unit. The support unit can learn employees' work styles and preferences to provide personalized support. For example, the support department provides appropriate support based on the employee's job duties and preferences. The support department can estimate the employee's emotions and adjust the personalized support method based on the estimated emotions. For example, if the support department is stressed, it will apply a simpler support method. When providing personalized support, the support department can apply different support algorithms depending on the employee's job duties. For example, in the case of data entry, the support department will apply a support algorithm that improves input speed and accuracy. When providing personalized support, the support department can improve the accuracy of support by referring to the employee's past work patterns. For example, based on past work patterns, the support department will prioritize providing support for frequently occurring issues. The support department can estimate the employee's emotions and determine the priority of personalized support based on the estimated emotions.For example, the support department can postpone providing less important support if an employee is experiencing stress. The support department can also consider an employee's geographical location when providing personalized support. For example, if an employee is in the office, the support department can prioritize work-related support. The support department can also analyze an employee's social media activity when providing personalized support and provide relevant support. For example, if an employee is using social media during work hours, the support department can provide support for that. This allows the AI ​​agent system, according to the embodiment, to improve employee work efficiency and eliminate inefficiencies and wasted time.

[0030] The data collection unit records the operation status of work PCs. For example, it records mouse movements, keyboard input, and application usage. Specifically, it records details such as cursor movement paths, click frequency, and click location for mouse movements. For keyboard input, it records entered strings, input speed, and key press frequency. For application usage, it records which applications were launched, when, for how long they were used, and the operations performed within those applications. The data collection unit can comprehensively record the operation status of work PCs. For example, it can record the operation status of work PCs in real time and save it to a database. When recording operation status, the data collection unit can select the types of data to record according to the employee's work content. For example, in the case of data entry work, the data collection unit will focus on recording data related to input speed and accuracy. When recording operation status, the data collection unit can improve the accuracy of the recording by referring to the employee's past operation history. For example, based on past operation history, the data collection unit will prioritize recording frequently used operations. The data collection unit can estimate employees' emotions and adjust the frequency of recording their activity based on those emotions. For example, if an employee is stressed, the unit can reduce the frequency of recording their activity to alleviate their workload. When recording activity, the unit can prioritize recording highly relevant activity by considering the employee's geographical location. For example, if an employee is in the office, the unit will prioritize recording work-related activity. When recording activity, the unit can analyze employees' social media activity and record relevant activity. For example, if an employee uses social media during work hours, the unit will record that activity. This allows the unit to collect optimal data by comprehensively considering employees' work content, emotional state, geographical location, and social media activity. The unit can centrally manage this data and integrate it with other systems and departments as needed. For example, collected data can be stored on a cloud server and made accessible to the analysis and automation departments. Furthermore, by adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions are possible.This allows the data collection unit to collect data efficiently and effectively, improving the overall performance of the system.

[0031] The analysis unit analyzes the operational status recorded by the data collection unit. The analysis unit can learn work patterns by analyzing the recorded operational status. For example, the analysis unit analyzes operational status using data aggregation methods and pattern recognition algorithms. Specifically, the analysis unit uses machine learning algorithms to cluster employee operational patterns and extract common work patterns. This allows for the identification of areas for improvement to enhance employee work efficiency. The analysis unit can estimate employee emotions and adjust the analysis method based on the estimated emotions. For example, if an employee is stressed, the analysis unit applies a simplified analysis method. This reduces the burden on employees and maintains work efficiency. When analyzing recorded operational status, the analysis unit can apply different analysis algorithms depending on the employee's work content. For example, in the case of data entry work, the analysis unit applies algorithms that analyze input speed and accuracy. This allows for optimal analysis tailored to the work content. When analyzing recorded operational status, the analysis unit can improve the accuracy of the analysis by referring to the employee's past work patterns. For example, based on past work patterns, the analysis unit focuses on analyzing frequently occurring operations. This improves the accuracy of the analysis and enables more precise suggestions for business improvement. The analysis department can consider the geographical location of employees when analyzing recorded operational activity. For example, if an employee is in the office, the analysis department will focus on analyzing work-related operations. This allows for an optimal analysis that takes geographical factors into account. The analysis department can improve the accuracy of the analysis by referring to relevant literature related to employees when analyzing recorded operational activity. For example, the analysis department can refer to work-related literature and use it to aid in the analysis of operational activity. This allows the analysis department to conduct an optimal analysis by comprehensively considering the employee's work content, emotional state, geographical location, relevant literature, etc. This enables the analysis department to improve employee work efficiency and make concrete suggestions to eliminate inefficiencies and wasted time.

[0032] The automation department automates tasks based on the analysis results obtained by the analysis department. The automation department can automate tasks such as creating and prioritizing to-do lists, drafting and proposing emails, data entry, processing, and analysis. For example, the automation department analyzes employees' work and organizes tasks based on importance and urgency. Specifically, it analyzes employees' work, automatically adds high-priority tasks to to-do lists, and notifies employees. For email drafting, it learns from employees' past email content and automatically generates appropriate text. For data entry, processing, and analysis automation, it automates operations frequently performed by employees, improving work efficiency. The automation department can estimate employees' emotions and adjust the automation method based on the estimated emotions. For example, if an employee is stressed, the automation department applies a simpler automation method. This reduces the burden on employees and maintains work efficiency. During automation, the automation department can apply different automation algorithms depending on the employee's work. For example, for data entry tasks, the automation department applies an automation algorithm that improves input speed and accuracy. This allows for optimal automation tailored to the specific tasks. The automation unit can improve the accuracy of automation by referencing employees' past work patterns. For example, based on past work patterns, the automation unit prioritizes automating frequently occurring tasks. This improves automation accuracy and enables more efficient work execution. The automation unit can estimate employees' emotions and determine automation priorities based on these estimates. For example, if an employee is stressed, the automation unit will postpone the automation of less important tasks. This reduces the burden on employees and maintains work efficiency. The automation unit can consider employees' geographical location during automation. For example, if an employee is in the office, the automation unit prioritizes automating work-related tasks. This enables optimal automation that takes geographical factors into account. The automation unit can analyze employees' social media activity during automation and automate related tasks.For example, the automation department can automate tasks such as employees using social media during work hours. This allows the automation department to optimize automation by comprehensively considering factors such as the employee's work content, emotional state, geographical location, and social media activity. As a result, the automation department can improve employee work efficiency and make concrete suggestions to eliminate inefficiencies and wasted time.

[0033] The optimization unit optimizes business processes based on the results provided by the service provider. The optimization unit can propose optimizations for business processes. For example, the optimization unit proposes which parts of the business process should be optimized based on optimization evaluation criteria. Specifically, the optimization unit analyzes each step of the business process in detail and identifies bottlenecks. This allows it to make concrete improvement proposals to improve the overall efficiency of the business process. The optimization unit can estimate employee emotions and adjust the business process optimization method based on the estimated emotions. For example, if an employee is stressed, the optimization unit applies a simpler optimization method. This reduces the burden on employees and maintains work efficiency. When optimizing business processes, the optimization unit can apply different optimization algorithms depending on the employee's work content. For example, in the case of data entry tasks, the optimization unit applies optimization algorithms that improve input speed and accuracy. This allows for optimal optimization according to the work content. When optimizing business processes, the optimization unit can improve the accuracy of optimization by referring to the employee's past work patterns. For example, based on past work patterns, the optimization unit prioritizes optimizing frequently occurring tasks. This improves the accuracy of optimization and enables more efficient work execution. The optimization unit can estimate employee emotions and determine the priority of workflow optimization based on the estimated emotions. For example, if an employee is stressed, the optimization unit will postpone the optimization of less important tasks. This reduces the burden on employees and maintains work efficiency. The optimization unit can also consider employees' geographical location when optimizing workflows. For example, if an employee is in the office, the optimization unit will prioritize optimizing work-related tasks. This enables optimal optimization that takes geographical factors into account. The optimization unit can also analyze employees' social media activity when optimizing workflows and optimize the relevant workflows. For example, if an employee is using social media during work hours, the optimization unit will optimize that workflow.This allows the optimization unit to comprehensively consider employees' work content, emotional state, geographical location information, social media activity, and other factors to perform optimal optimization. As a result, the optimization unit can improve employee work efficiency and make concrete suggestions to eliminate inefficiencies and wasted time.

[0034] The support department provides personalized support based on the workflow optimized by the optimization department. The support department can learn employees' work styles and preferences to provide personalized support. For example, the support department provides appropriate support based on the employee's work content and preferences. Specifically, the support department analyzes the employee's work content and automatically provides the necessary tools and resources. It also provides advice on how to proceed with tasks and how to use tools, according to the employee's preferences. The support department can estimate the employee's emotions and adjust the personalized support method based on the estimated emotions. For example, if an employee is stressed, the support department applies a simpler support method. This reduces the employee's burden and maintains work efficiency. When providing personalized support, the support department can apply different support algorithms depending on the employee's work content. For example, in the case of data entry tasks, the support department applies a support algorithm that improves input speed and accuracy. This allows for optimal support tailored to the work content. When providing personalized support, the support department can improve the accuracy of support by referring to the employee's past work patterns. For example, the support department can prioritize frequently occurring support requests based on past work patterns. This improves the accuracy and effectiveness of support. The support department can estimate employee emotions and determine personalized support priorities based on those emotions. For example, if an employee is stressed, the support department will postpone providing less important support. This reduces the burden on employees and maintains work efficiency. When providing personalized support, the support department can take into account the employee's geographical location. For example, if an employee is in the office, the support department will prioritize work-related support. This allows for optimal support that takes geographical factors into account. When providing personalized support, the support department can analyze employees' social media activity and provide relevant support.For example, the support department can provide support if an employee uses social media during work hours. This allows the support department to provide optimal support by comprehensively considering factors such as the employee's work content, emotional state, geographical location, and social media activity. As a result, the support department can improve employee work efficiency and make concrete suggestions to eliminate inefficiencies and wasted time.

[0035] The data collection unit can comprehensively record the operation status of work PCs. For example, the data collection unit can record the operation status of work PCs in real time and store it in a database. When recording operation status, the data collection unit can select the type of data to record according to the employee's work content. For example, in the case of data entry work, the data collection unit will focus on recording data related to input speed and accuracy. When recording operation status, the data collection unit can improve the accuracy of the recording by referring to the employee's past operation history. For example, based on past operation history, the data collection unit will prioritize recording frequently used operations. The data collection unit can estimate the employee's emotions and adjust the frequency of recording operation status based on the estimated emotions of the employee. For example, if the data collection unit is feeling stressed, it will reduce the frequency of recording operation status to alleviate the workload. When recording operation status, the data collection unit can prioritize recording highly relevant operations by considering the employee's geographical location information. For example, if the data collection unit is in the office, it will prioritize recording work-related operations. When recording operation status, the data collection unit can analyze the employee's social media activity and record relevant operations. For example, the data collection unit records when employees use social media during work hours. This allows for the collection of detailed data by comprehensively recording the usage status of work PCs.

[0036] The analysis department can analyze recorded operational data and learn work patterns. For example, it can analyze operational data using data aggregation methods and pattern recognition algorithms. The analysis department can estimate employee emotions and adjust the analysis method based on the estimated emotions. For example, if an employee is stressed, the analysis department can apply a simplified analysis method. When analyzing recorded operational data, the analysis department can apply different analysis algorithms depending on the employee's work content. For example, in the case of data entry, the analysis department can apply algorithms that analyze input speed and accuracy. When analyzing recorded operational data, the analysis department can improve the accuracy of the analysis by referring to the employee's past work patterns. For example, based on past work patterns, the analysis department can focus on analyzing frequently occurring operations. When analyzing recorded operational data, the analysis department can consider the employee's geographical location. For example, if an employee is in the office, the analysis department can focus on analyzing work-related operations. When analyzing recorded operational data, the analysis department can improve the accuracy of the analysis by referring to the employee's relevant literature. For example, the analysis department refers to literature related to the work and uses it to analyze operational status. By learning work patterns, they can improve the efficiency of their work.

[0037] The automation unit can automate tasks such as creating and prioritizing to-do lists, drafting and proposing emails, data entry, processing, and analysis. For example, the automation unit can analyze employee work content and organize tasks based on importance and urgency. It can estimate employee emotions and adjust automation methods based on these estimations. For instance, if an employee is stressed, the automation unit applies a simpler automation method. During automation, the automation unit can apply different automation algorithms depending on the employee's work content. For example, for data entry tasks, the automation unit applies an algorithm that improves input speed and accuracy. During automation, the automation unit can improve the accuracy of automation by referring to the employee's past work patterns. For example, based on past work patterns, the automation unit prioritizes automating frequently occurring tasks. The automation unit can estimate employee emotions and determine automation priorities based on these estimations. For example, if an employee is stressed, the automation unit postpones the automation of less important tasks. The automation unit can also consider employee geographical location information during automation. For example, the automation department prioritizes automating work-related tasks when employees are in the office. During automation, the automation department can analyze employees' social media activity and automate related tasks. For instance, if an employee uses social media during work hours, the automation department will automate that task. This process of automating tasks can improve work efficiency.

[0038] The system can schedule meetings, notify participants, and automatically create and summarize meeting minutes. For example, it can check employee schedules and suggest optimal meeting times. It can estimate employee emotions and adjust how results are displayed based on the estimated emotions. For example, if an employee is stressed, it provides a simple and highly visible display. When displaying results, the system can apply different display algorithms depending on the employee's work content. For example, for data entry tasks, it visually displays results related to entry speed and accuracy. When displaying results, the system can improve display accuracy by referring to the employee's past work patterns. For example, based on past work patterns, it prioritizes frequently occurring results. The system can estimate employee emotions and prioritize results based on the estimated emotions. For example, if an employee is stressed, it postpones displaying less important results. When displaying results, the system can consider the employee's geographical location. For example, the service provider can prioritize displaying work-related results when an employee is in the office. When displaying results, the service provider can analyze employee social media activity and provide relevant results. For instance, if an employee is using social media during work hours, the service provider can display the results. This can improve work efficiency by automating meeting scheduling and minute creation.

[0039] The optimization unit can propose optimizations for business processes. For example, the optimization unit proposes which parts of the business process should be optimized based on optimization evaluation criteria. The optimization unit can estimate employee emotions and adjust the business process optimization method based on the estimated emotions. For example, if an employee is feeling stressed, the optimization unit will apply a simpler optimization method. When optimizing business processes, the optimization unit can apply different optimization algorithms depending on the employee's work content. For example, in the case of data entry tasks, the optimization unit will apply an optimization algorithm that improves input speed and accuracy. When optimizing business processes, the optimization unit can improve the accuracy of optimization by referring to the employee's past work patterns. For example, based on past work patterns, the optimization unit prioritizes optimizing frequently occurring tasks. The optimization unit can estimate employee emotions and determine the priority of business process optimization based on the estimated emotions. For example, if an employee is feeling stressed, the optimization unit will postpone the optimization of less important tasks. When optimizing business processes, the optimization unit can consider the employee's geographical location information. For example, the optimization unit prioritizes optimizing work-related tasks when employees are in the office. When optimizing workflows, the optimization unit can analyze employees' social media activity and optimize related workflows. For instance, if an employee uses social media during work hours, the optimization unit will optimize that workflow. This allows for improved work efficiency by suggesting workflow optimizations.

[0040] The support department can learn employees' work styles and preferences and provide personalized support. For example, the support department can provide appropriate support based on the employee's work content and preferences. The support department can estimate the employee's emotions and adjust the personalized support method based on the estimated emotions. For example, if the support department is stressed, it will apply a simpler support method. When providing personalized support, the support department can apply different support algorithms depending on the employee's work content. For example, for data entry tasks, the support department will apply a support algorithm that improves input speed and accuracy. When providing personalized support, the support department can improve the accuracy of support by referring to the employee's past work patterns. For example, based on past work patterns, the support department will prioritize providing support that occurs frequently. The support department can estimate the employee's emotions and determine the priority of personalized support based on the estimated emotions. For example, if the support department is stressed, it will postpone providing support of lower importance. When providing personalized support, the support department can take the employee's geographical location into consideration. For example, the support department prioritizes providing work-related support to employees when they are in the office. When providing personalized support, the support department can analyze employees' social media activity and provide relevant support. For instance, if an employee uses social media during work hours, the support department can provide support for that. This allows for increased work efficiency by providing support tailored to employees' work styles and preferences.

[0041] The data collection unit can select the type of data to record according to the employee's work content when recording operational status. For example, in the case of data entry, the data collection unit can focus on recording data related to input speed and accuracy. In the case of email correspondence, the data collection unit can record data related to the time and content of emails sent and received. In the case of meeting participation, the data collection unit can record data related to meeting participation time and content of comments. By recording data according to the content of the work, it is possible to improve work efficiency.

[0042] The data collection unit can improve the accuracy of recordings by referring to the employee's past operation history when recording operation status. For example, the data collection unit can prioritize recording frequently used operations based on past operation history. The data collection unit can analyze past operation errors and record them in detail if similar errors occur. The data collection unit can refer to past operation patterns and issue alerts if abnormal operations occur. In this way, the accuracy of recordings can be improved by referring to past operation history.

[0043] The data collection unit can prioritize recording highly relevant operations by considering the employee's geographical location when recording operation status. For example, if an employee is in the office, the data collection unit will prioritize recording work-related operations. If an employee is on a business trip, the data collection unit can focus on recording operations performed at the business trip location. If an employee is working remotely, the data collection unit can record operations performed at home in detail. By recording operations while considering geographical location, the system can improve work efficiency.

[0044] The data collection unit can analyze employees' social media activity and record relevant actions when recording operational status. For example, if an employee uses social media during work hours, the data collection unit can record that activity. The data collection unit can analyze work-related posts on social media and record relevant actions. The data collection unit can record work-related feedback obtained from social media activity. This allows for improved work efficiency by analyzing social media activity and recording actions.

[0045] The analysis department can apply different analysis algorithms to the recorded operational status depending on the employee's work content. For example, in the case of data entry, the analysis department can apply an algorithm that analyzes input speed and accuracy. In the case of email correspondence, the analysis department can apply an algorithm that analyzes the time it takes to send and receive emails and their content. In the case of meeting participation, the analysis department can apply an algorithm that analyzes the time spent at meetings and the content of what was said. By applying an analysis algorithm tailored to the work content, the department can improve the efficiency of operations.

[0046] The analysis department can improve the accuracy of its analysis by referring to employees' past work patterns when analyzing recorded operational status. For example, the analysis department can focus its analysis on frequently occurring operations based on past work patterns. The analysis department can analyze past work errors and conduct a detailed analysis if similar errors occur. The analysis department can refer to past work patterns and issue alerts if abnormal operations occur. This improves the accuracy of the analysis by referring to past work patterns.

[0047] The analysis department can take into account the geographical location of employees when analyzing recorded operational data. For example, if an employee is in the office, the analysis department will focus on analyzing work-related operations. If an employee is on a business trip, the analysis department can analyze operations performed at the business trip location. If an employee is working remotely, the analysis department can conduct a detailed analysis of operations performed at home. By considering geographical location during the analysis, the department can improve the efficiency of operations.

[0048] The analysis department can improve the accuracy of its analysis by referring to relevant employee literature when analyzing recorded operational status. For example, the analysis department can refer to work-related literature to aid in the analysis of operational status. Based on the knowledge gained from relevant literature, the analysis department can adjust its analysis algorithms. By referring to relevant literature, the analysis department can gain insights that lead to increased work efficiency. Thus, by referring to relevant literature, the accuracy of the analysis can be improved.

[0049] The automation unit can apply different automation algorithms depending on the employee's work content during automation. For example, in the case of data entry, the automation unit can apply an automation algorithm that improves input speed and accuracy. In the case of email correspondence, the automation unit can apply an algorithm that automates the sending and receiving time and content of emails. In the case of meeting participation, the automation unit can apply an algorithm that automates meeting scheduling and minute-taking. In this way, by applying automation algorithms tailored to the work content, the efficiency of work can be improved.

[0050] The automation unit can improve the accuracy of automation by referring to employees' past work patterns during the automation process. For example, the automation unit can prioritize the automation of frequently occurring tasks based on past work patterns. The automation unit can analyze past work errors and automate similar errors if they occur again. The automation unit can refer to past work patterns and issue alerts if an unusual task occurs. This allows the accuracy of automation to be improved by referring to past work patterns.

[0051] The automation unit can perform automation while taking into account the geographical location of employees. For example, if an employee is in the office, the automation unit will prioritize automating work-related tasks. If an employee is on a business trip, the automation unit can focus on automating tasks at the business trip location. If an employee is working remotely, the automation unit can automate tasks at home in detail. By considering geographical location when performing automation, the efficiency of operations can be improved.

[0052] The automation department can analyze employees' social media activity and automate related tasks during the automation process. For example, if an employee uses social media during work hours, the automation department can automate that task. The automation department can analyze work-related posts on social media and automate related tasks. The automation department can automate the process of obtaining work-related feedback from social media activity. This allows for increased work efficiency by analyzing social media activity and automating tasks.

[0053] The data delivery system can apply different display algorithms depending on the employee's work content when displaying the results it provides. For example, in the case of data entry, the system can visually display results related to input speed and accuracy. In the case of email correspondence, the system can display results related to email sending and receiving time and content. In the case of meeting participation, the system can display results related to meeting participation time and content of comments. By applying a display algorithm tailored to the work content, the system can improve work efficiency.

[0054] The data delivery unit can improve the accuracy of the displayed results by referring to employees' past work patterns. For example, the unit can focus on displaying frequently occurring results based on past work patterns. The unit can analyze past work errors and display them in detail when similar errors occur. The unit can refer to past work patterns and issue alerts when abnormal results occur. This improves the accuracy of the displayed results by referring to past work patterns.

[0055] The data delivery system can display results while taking into account the employee's geographical location. For example, if an employee is in the office, the system can prioritize displaying work-related results. If an employee is on a business trip, the system can focus on displaying results from their business trip location. If an employee is working remotely, the system can display detailed results from their home. By displaying results while considering geographical location, the system can improve work efficiency.

[0056] The service provider can analyze employees' social media activity and provide relevant results when displaying the results. For example, it can display results if an employee uses social media during work hours. The service provider can analyze work-related posts on social media and display relevant results. The service provider can display work-related feedback derived from social media activity. This allows for improved work efficiency by analyzing social media activity and providing results.

[0057] The optimization unit can apply different optimization algorithms depending on the employee's work content when optimizing business workflows. For example, in the case of data entry, the optimization unit can apply an optimization algorithm that improves input speed and accuracy. In the case of email correspondence, the optimization unit can apply an algorithm that optimizes the sending and receiving time and content of emails. In the case of meeting participation, the optimization unit can apply an algorithm that optimizes meeting scheduling and minute-taking. In this way, by applying an optimization algorithm tailored to the work content, business efficiency can be improved.

[0058] The optimization unit can improve the accuracy of optimization by referring to employees' past work patterns when optimizing business workflows. For example, the optimization unit can prioritize the optimization of frequently occurring tasks based on past work patterns. The optimization unit can analyze past work errors and optimize when similar errors occur. The optimization unit can refer to past work patterns and issue alerts when abnormal tasks occur. In this way, the accuracy of optimization can be improved by referring to past work patterns.

[0059] The optimization unit can optimize business workflows while considering employees' geographical location information. For example, if an employee is in the office, the optimization unit will prioritize optimizing work-related tasks. If an employee is on a business trip, the optimization unit can focus on optimizing tasks performed at the business trip location. If an employee is working remotely, the optimization unit can optimize tasks performed at home in detail. By considering geographical location information during optimization, business efficiency can be improved.

[0060] The optimization unit can analyze employees' social media activity and optimize related workflows when optimizing business processes. For example, if an employee uses social media during work hours, the optimization unit can optimize that workflow. The optimization unit can analyze work-related posts on social media and optimize related workflows. The optimization unit can optimize work-related feedback obtained from social media activity. In this way, by analyzing social media activity and optimizing workflows, business efficiency can be improved.

[0061] The support department can apply different support algorithms depending on the employee's work content when providing personalized support. For example, for data entry tasks, the support department can apply support algorithms that improve input speed and accuracy. For email correspondence tasks, the support department can apply algorithms that support email sending and receiving times and content. For meeting participation tasks, the support department can apply algorithms that support meeting scheduling and minute-taking. In this way, by applying support algorithms tailored to the work content, the efficiency of operations can be improved.

[0062] The support department can improve the accuracy of personalized support by referring to employees' past work patterns. For example, the support department can prioritize support for frequently occurring issues based on past work patterns. The support department can analyze past work errors and provide support when similar errors occur. The support department can refer to past work patterns and issue alerts when unusual work occurs. In this way, the accuracy of support can be improved by referring to past work patterns.

[0063] The support department can provide personalized support while taking into account the employee's geographical location. For example, if an employee is in the office, the support department can prioritize work-related support. If an employee is on a business trip, the support department can focus on providing support at their destination. If an employee is working remotely, the support department can provide detailed support at their home. By considering geographical location when providing support, the support department can improve operational efficiency.

[0064] The support department can analyze employees' social media activity and provide relevant support when providing personalized support. For example, if an employee uses social media during work hours, the support department can provide support. The support department can analyze work-related posts on social media and provide relevant support. The support department can provide support based on work-related feedback obtained from social media activity. This allows for increased work efficiency by analyzing social media activity and providing support accordingly.

[0065] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0066] The AI ​​agent system can also assess employees' skill levels and suggest appropriate training programs. For example, the data collection unit records employee work performance data and assesses skill levels. The analysis unit analyzes the skill data to identify employees' strengths and weaknesses. The automation unit automatically generates training programs based on skill levels and provides them to employees. This leads to improved employee skills and increased work efficiency.

[0067] AI agent systems can also include support functions to improve employees' communication skills. For example, the data collection unit records employee communication data and evaluates skill levels. The analysis unit analyzes the communication data to identify employees' strengths and weaknesses. The automation unit automatically generates training programs based on skill levels and provides them to employees. This leads to improved employee communication skills and increased work efficiency.

[0068] The AI ​​agent system can also monitor employee work performance in real time and provide immediate feedback. For example, the data collection unit records employee work data in real time and evaluates performance. The analysis unit analyzes the real-time data and generates immediate feedback. The delivery unit immediately provides the feedback to employees to improve their work performance. This enables real-time improvement of work performance.

[0069] The AI ​​agent system can also evaluate employee work performance and propose rewards and incentives. For example, the data collection unit records employee work data and evaluates performance. The analysis unit analyzes the performance data and generates reward and incentive proposals. The delivery unit provides these proposals to employees to improve their motivation. This ensures that rewards and incentives are proposed based on work performance.

[0070] The AI ​​agent system can also evaluate employee work performance and suggest career paths. For example, the data collection unit records employee work data and evaluates performance. The analysis unit analyzes the performance data and suggests career paths for employees. The delivery unit provides these career path suggestions to employees and supports their career growth. This ensures that career paths are suggested based on work performance.

[0071] The following briefly describes the processing flow for example form 1.

[0072] Step 1: The data collection unit records the operation status of work PCs. For example, it records mouse movements, keyboard input, application usage, etc., and saves them to a database in real time. The data collection unit selects the type of data to record according to the employee's work content and improves the accuracy of the recording by considering past operation history, employee sentiment, geographical location information, and social media activity. Step 2: The analysis unit analyzes the operational status recorded by the data collection unit. The analysis unit learns operational patterns and analyzes operational status using data aggregation methods and pattern recognition algorithms. The accuracy of the analysis is improved by considering employee sentiment, work content, past operational patterns, geographical location information, and relevant literature. Step 3: The automation department automates tasks based on the analysis results obtained by the analysis department. The automation department automates tasks such as creating and prioritizing to-do lists, drafting and proposing emails, data entry, processing, and analysis. The accuracy of automation is improved by considering employee sentiment, job content, past work patterns, geographical location information, and social media activity. Step 4: The delivery department provides the results of tasks automated by the automation department. The delivery department schedules meetings and notifies participants, and automatically creates and summarizes meeting minutes. It adjusts how the results are displayed, taking into account employee sentiment, job content, past work patterns, geographical location, and social media activity. Step 5: The Optimization Department optimizes the workflow based on the results provided by the Delivery Department. The Optimization Department proposes workflow optimizations and improves the accuracy of the optimization by considering employee sentiment, work content, past work patterns, geographical location information, and social media activity. Step 6: The support department provides personalized support based on the workflow optimized by the optimization department. The support department learns employees' work styles and preferences and provides personalized support that takes into account employees' emotions, work content, past work patterns, geographical location, and social media activity.

[0073] (Example of form 2) An AI agent system according to an embodiment of the present invention is a system that comprehensively records the operation status of an employee's work PC and learns work patterns. Based on the accumulated data, this AI agent system automates or assists with the following tasks. First, the AI ​​agent system creates and prioritizes to-do lists. The AI ​​agent system analyzes the employee's work content and organizes tasks based on importance and urgency. Next, the AI ​​agent system creates and proposes email drafts. The AI ​​agent system learns the content of the employee's past emails and proposes appropriate wording. Furthermore, the AI ​​agent system automates data entry, processing, and analysis. The AI ​​agent system automates routine data processing to improve efficiency. In addition, the AI ​​agent system schedules meetings and notifies participants. The AI ​​agent system checks the employee's schedule and proposes the optimal meeting time. The AI ​​agent system also automatically creates and summarizes meeting minutes. The AI ​​agent system records the content of meetings and summarizes the key points. The AI ​​agent system also proposes automation and efficiency improvements for routine tasks. The AI ​​agent system analyzes the workflow and makes suggestions for efficiency improvements. Furthermore, the AI ​​agent system proposes optimization of the workflow. The AI ​​agent system optimizes and streamlines workflows. It learns employees' work styles and preferences, providing personalized support. This improves employee efficiency, eliminating inefficiencies and wasted time. It also reduces employee fatigue and decreased motivation caused by repetitive tasks. Furthermore, it prevents delays and quality declines due to labor shortages. The complexity of data management and analysis is also reduced, making it easier to visualize and optimize business processes. The AI ​​agent system achieves these tasks by utilizing text generation AI, natural language processing AI, data analysis AI, image / video generation AI, speech processing AI, and code generation AI. For example, text generation AI can automatically create and prioritize to-do lists, draft emails, automatically create and summarize meeting minutes, and generate suggestions for optimizing workflows.Natural language processing AI communicates with employees, analyzes and understands work patterns, and provides personalized support. Data analysis AI records and analyzes the usage of work PCs, provides insights for improving work efficiency, and learns employees' work styles and preferences. Image and video generation AI visualizes data and automatically creates presentation materials. Voice processing AI operates using voice commands and performs speech recognition and transcription of meetings. Code generation AI creates scripts to improve work efficiency and generates code for data processing and analysis. As a result, the AI ​​agent system can improve employee work efficiency and eliminate inefficiencies and wasted time.

[0074] The AI ​​agent system according to this embodiment comprises a collection unit, an analysis unit, an automation unit, a provision unit, an optimization unit, and a support unit. The collection unit records the operation status of the work PC. The collection unit records, for example, mouse movements, keyboard input, and application usage. The collection unit can comprehensively record the operation status of the work PC. For example, the collection unit records the operation status of the work PC in real time and stores it in a database. When recording the operation status, the collection unit can select the type of data to record according to the employee's work content. For example, in the case of data entry work, the collection unit focuses on recording data related to input speed and accuracy. When recording the operation status, the collection unit can improve the accuracy of the recording by referring to the employee's past operation history. For example, based on past operation history, the collection unit prioritizes recording frequently used operations. The collection unit can estimate the employee's emotions and adjust the frequency of recording the operation status based on the estimated emotions of the employee. For example, if the employee is feeling stressed, the collection unit reduces the frequency of recording the operation status to alleviate the workload. The data collection unit can prioritize recording highly relevant operations by considering the employee's geographical location when recording operational activity. For example, if the employee is in the office, the data collection unit will prioritize recording work-related operations. The data collection unit can also analyze the employee's social media activity and record relevant operations when recording operational activity. For example, if the employee uses social media during work hours, the data collection unit will record those operations. The analysis unit analyzes the operational activity recorded by the data collection unit. The analysis unit can analyze the recorded operational activity and learn work patterns. For example, the analysis unit can analyze operational activity using data aggregation methods and pattern recognition algorithms. The analysis unit can estimate the employee's emotions and adjust the analysis method based on the estimated emotions. For example, if the analysis unit is stressed, it will apply a simplified analysis method. When analyzing recorded operational activity, the analysis unit can apply different analysis algorithms depending on the employee's work content. For example, in the case of data entry work, the analysis unit will apply algorithms that analyze input speed and accuracy.The analysis department can improve the accuracy of its analysis of recorded operational activity by referring to employees' past work patterns. For example, the analysis department can focus on analyzing frequently occurring operations based on past work patterns. The analysis department can also consider employees' geographical location information when analyzing recorded operational activity. For example, the analysis department can focus on analyzing work-related operations when employees are in the office. The analysis department can improve the accuracy of its analysis by referring to relevant literature related to employees when analyzing recorded operational activity. For example, the analysis department can refer to work-related literature to aid in the analysis of operational activity. The automation department automates tasks based on the analysis results obtained by the analysis department. The automation department can automate tasks such as creating and prioritizing to-do lists, drafting and proposing emails, data entry, processing, and analysis. For example, the automation department analyzes employees' work content and organizes tasks based on importance and urgency. The automation department can estimate employees' emotions and adjust the automation method based on the estimated employee emotions. For example, the automation department can apply a simpler automation method if an employee is experiencing stress. The automation department can apply different automation algorithms depending on the employee's work content during automation. For example, for data entry tasks, the automation department can apply an automation algorithm that improves input speed and accuracy. The automation department can improve the accuracy of automation by referring to the employee's past work patterns. For example, based on past work patterns, the automation department prioritizes automating frequently occurring tasks. The automation department can estimate an employee's emotions and determine automation priorities based on the estimated emotions. For example, if an employee is experiencing stress, the automation department will postpone the automation of less important tasks. The automation department can consider the employee's geographical location during automation. For example, if an employee is in the office, the automation department will prioritize automating work-related tasks. The automation department can analyze an employee's social media activity during automation and automate related tasks. For example, if an employee uses social media during work hours, the automation department will automate that task.The Delivery Unit provides the results of tasks automated by the Automation Unit. The Delivery Unit can schedule meetings and notify participants, and automatically create and summarize meeting minutes. For example, the Delivery Unit can check employee schedules and suggest optimal meeting times. The Delivery Unit can estimate employee emotions and adjust how results are displayed based on the estimated emotions. For example, if an employee is stressed, the Delivery Unit provides a simple and highly visible display. When displaying results, the Delivery Unit can apply different display algorithms depending on the employee's work content. For example, for data entry tasks, the Delivery Unit visually displays results related to entry speed and accuracy. When displaying results, the Delivery Unit can improve display accuracy by referring to the employee's past work patterns. For example, based on past work patterns, the Delivery Unit focuses on displaying frequently occurring results. The Delivery Unit can estimate employee emotions and prioritize results based on the estimated emotions. For example, if an employee is stressed, the Delivery Unit postpones displaying less important results. The service provider can display results while considering the employee's geographical location. For example, if the employee is in the office, the service provider will prioritize displaying work-related results. The service provider can analyze the employee's social media activity and provide relevant results when displaying results. For example, if the service provider uses social media during work hours, it will display the results. The optimization service provider optimizes the workflow based on the results provided by the service provider. The optimization service provider can make optimization suggestions for the workflow. For example, the optimization service provider will suggest which parts of the workflow should be optimized based on optimization evaluation criteria. The optimization service provider can estimate the employee's emotions and adjust the workflow optimization method based on the estimated employee emotions. For example, if the optimization service provider is stressed, it will apply a simpler optimization method. When optimizing the workflow, the optimization service provider can apply different optimization algorithms depending on the employee's work content.For example, the optimization unit applies optimization algorithms to improve input speed and accuracy in the case of data entry tasks. The optimization unit can improve the accuracy of optimization by referencing employees' past work patterns when optimizing workflows. For example, it prioritizes optimizing frequently occurring tasks based on past work patterns. The optimization unit can estimate employees' emotions and determine the priority of workflow optimization based on the estimated emotions. For example, if an employee is stressed, the optimization unit will postpone the optimization of less important tasks. The optimization unit can consider employees' geographical location when optimizing workflows. For example, if an employee is in the office, the optimization unit prioritizes optimizing work-related tasks. The optimization unit can analyze employees' social media activity and optimize relevant workflows when optimizing workflows. For example, if an employee uses social media during work hours, the optimization unit optimizes that workflow. The support unit provides personalized support based on the workflows optimized by the optimization unit. The support unit can learn employees' work styles and preferences to provide personalized support. For example, the support department provides appropriate support based on the employee's job duties and preferences. The support department can estimate the employee's emotions and adjust the personalized support method based on the estimated emotions. For example, if the support department is stressed, it will apply a simpler support method. When providing personalized support, the support department can apply different support algorithms depending on the employee's job duties. For example, in the case of data entry, the support department will apply a support algorithm that improves input speed and accuracy. When providing personalized support, the support department can improve the accuracy of support by referring to the employee's past work patterns. For example, based on past work patterns, the support department will prioritize providing support for frequently occurring issues. The support department can estimate the employee's emotions and determine the priority of personalized support based on the estimated emotions.For example, the support department can postpone providing less important support if an employee is experiencing stress. The support department can also consider an employee's geographical location when providing personalized support. For example, if an employee is in the office, the support department can prioritize work-related support. The support department can also analyze an employee's social media activity when providing personalized support and provide relevant support. For example, if an employee is using social media during work hours, the support department can provide support for that. This allows the AI ​​agent system, according to the embodiment, to improve employee work efficiency and eliminate inefficiencies and wasted time.

[0075] The data collection unit records the operation status of work PCs. For example, it records mouse movements, keyboard input, and application usage. Specifically, it records details such as cursor movement paths, click frequency, and click location for mouse movements. For keyboard input, it records entered strings, input speed, and key press frequency. For application usage, it records which applications were launched, when, for how long they were used, and the operations performed within those applications. The data collection unit can comprehensively record the operation status of work PCs. For example, it can record the operation status of work PCs in real time and save it to a database. When recording operation status, the data collection unit can select the types of data to record according to the employee's work content. For example, in the case of data entry work, the data collection unit will focus on recording data related to input speed and accuracy. When recording operation status, the data collection unit can improve the accuracy of the recording by referring to the employee's past operation history. For example, based on past operation history, the data collection unit will prioritize recording frequently used operations. The data collection unit can estimate employees' emotions and adjust the frequency of recording their activity based on those emotions. For example, if an employee is stressed, the unit can reduce the frequency of recording their activity to alleviate their workload. When recording activity, the unit can prioritize recording highly relevant activity by considering the employee's geographical location. For example, if an employee is in the office, the unit will prioritize recording work-related activity. When recording activity, the unit can analyze employees' social media activity and record relevant activity. For example, if an employee uses social media during work hours, the unit will record that activity. This allows the unit to collect optimal data by comprehensively considering employees' work content, emotional state, geographical location, and social media activity. The unit can centrally manage this data and integrate it with other systems and departments as needed. For example, collected data can be stored on a cloud server and made accessible to the analysis and automation departments. Furthermore, by adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions are possible.This allows the data collection unit to collect data efficiently and effectively, improving the overall performance of the system.

[0076] The analysis unit analyzes the operational status recorded by the data collection unit. The analysis unit can learn work patterns by analyzing the recorded operational status. For example, the analysis unit analyzes operational status using data aggregation methods and pattern recognition algorithms. Specifically, the analysis unit uses machine learning algorithms to cluster employee operational patterns and extract common work patterns. This allows for the identification of areas for improvement to enhance employee work efficiency. The analysis unit can estimate employee emotions and adjust the analysis method based on the estimated emotions. For example, if an employee is stressed, the analysis unit applies a simplified analysis method. This reduces the burden on employees and maintains work efficiency. When analyzing recorded operational status, the analysis unit can apply different analysis algorithms depending on the employee's work content. For example, in the case of data entry work, the analysis unit applies algorithms that analyze input speed and accuracy. This allows for optimal analysis tailored to the work content. When analyzing recorded operational status, the analysis unit can improve the accuracy of the analysis by referring to the employee's past work patterns. For example, based on past work patterns, the analysis unit focuses on analyzing frequently occurring operations. This improves the accuracy of the analysis and enables more precise suggestions for business improvement. The analysis department can consider the geographical location of employees when analyzing recorded operational activity. For example, if an employee is in the office, the analysis department will focus on analyzing work-related operations. This allows for an optimal analysis that takes geographical factors into account. The analysis department can improve the accuracy of the analysis by referring to relevant literature related to employees when analyzing recorded operational activity. For example, the analysis department can refer to work-related literature and use it to aid in the analysis of operational activity. This allows the analysis department to conduct an optimal analysis by comprehensively considering the employee's work content, emotional state, geographical location, relevant literature, etc. This enables the analysis department to improve employee work efficiency and make concrete suggestions to eliminate inefficiencies and wasted time.

[0077] The automation department automates tasks based on the analysis results obtained by the analysis department. The automation department can automate tasks such as creating and prioritizing to-do lists, drafting and proposing emails, data entry, processing, and analysis. For example, the automation department analyzes employees' work and organizes tasks based on importance and urgency. Specifically, it analyzes employees' work, automatically adds high-priority tasks to to-do lists, and notifies employees. For email drafting, it learns from employees' past email content and automatically generates appropriate text. For data entry, processing, and analysis automation, it automates operations frequently performed by employees, improving work efficiency. The automation department can estimate employees' emotions and adjust the automation method based on the estimated emotions. For example, if an employee is stressed, the automation department applies a simpler automation method. This reduces the burden on employees and maintains work efficiency. During automation, the automation department can apply different automation algorithms depending on the employee's work. For example, for data entry tasks, the automation department applies an automation algorithm that improves input speed and accuracy. This allows for optimal automation tailored to the specific tasks. The automation unit can improve the accuracy of automation by referencing employees' past work patterns. For example, based on past work patterns, the automation unit prioritizes automating frequently occurring tasks. This improves automation accuracy and enables more efficient work execution. The automation unit can estimate employees' emotions and determine automation priorities based on these estimates. For example, if an employee is stressed, the automation unit will postpone the automation of less important tasks. This reduces the burden on employees and maintains work efficiency. The automation unit can consider employees' geographical location during automation. For example, if an employee is in the office, the automation unit prioritizes automating work-related tasks. This enables optimal automation that takes geographical factors into account. The automation unit can analyze employees' social media activity during automation and automate related tasks.For example, the automation department can automate tasks such as employees using social media during work hours. This allows the automation department to optimize automation by comprehensively considering factors such as the employee's work content, emotional state, geographical location, and social media activity. As a result, the automation department can improve employee work efficiency and make concrete suggestions to eliminate inefficiencies and wasted time.

[0078] The optimization unit optimizes business processes based on the results provided by the service provider. The optimization unit can propose optimizations for business processes. For example, the optimization unit proposes which parts of the business process should be optimized based on optimization evaluation criteria. Specifically, the optimization unit analyzes each step of the business process in detail and identifies bottlenecks. This allows it to make concrete improvement proposals to improve the overall efficiency of the business process. The optimization unit can estimate employee emotions and adjust the business process optimization method based on the estimated emotions. For example, if an employee is stressed, the optimization unit applies a simpler optimization method. This reduces the burden on employees and maintains work efficiency. When optimizing business processes, the optimization unit can apply different optimization algorithms depending on the employee's work content. For example, in the case of data entry tasks, the optimization unit applies optimization algorithms that improve input speed and accuracy. This allows for optimal optimization according to the work content. When optimizing business processes, the optimization unit can improve the accuracy of optimization by referring to the employee's past work patterns. For example, based on past work patterns, the optimization unit prioritizes optimizing frequently occurring tasks. This improves the accuracy of optimization and enables more efficient work execution. The optimization unit can estimate employee emotions and determine the priority of workflow optimization based on the estimated emotions. For example, if an employee is stressed, the optimization unit will postpone the optimization of less important tasks. This reduces the burden on employees and maintains work efficiency. The optimization unit can also consider employees' geographical location when optimizing workflows. For example, if an employee is in the office, the optimization unit will prioritize optimizing work-related tasks. This enables optimal optimization that takes geographical factors into account. The optimization unit can also analyze employees' social media activity when optimizing workflows and optimize the relevant workflows. For example, if an employee is using social media during work hours, the optimization unit will optimize that workflow.This allows the optimization unit to comprehensively consider employees' work content, emotional state, geographical location information, social media activity, and other factors to perform optimal optimization. As a result, the optimization unit can improve employee work efficiency and make concrete suggestions to eliminate inefficiencies and wasted time.

[0079] The support department provides personalized support based on the workflow optimized by the optimization department. The support department can learn employees' work styles and preferences to provide personalized support. For example, the support department provides appropriate support based on the employee's work content and preferences. Specifically, the support department analyzes the employee's work content and automatically provides the necessary tools and resources. It also provides advice on how to proceed with tasks and how to use tools, according to the employee's preferences. The support department can estimate the employee's emotions and adjust the personalized support method based on the estimated emotions. For example, if an employee is stressed, the support department applies a simpler support method. This reduces the employee's burden and maintains work efficiency. When providing personalized support, the support department can apply different support algorithms depending on the employee's work content. For example, in the case of data entry tasks, the support department applies a support algorithm that improves input speed and accuracy. This allows for optimal support tailored to the work content. When providing personalized support, the support department can improve the accuracy of support by referring to the employee's past work patterns. For example, the support department can prioritize frequently occurring support requests based on past work patterns. This improves the accuracy and effectiveness of support. The support department can estimate employee emotions and determine personalized support priorities based on those emotions. For example, if an employee is stressed, the support department will postpone providing less important support. This reduces the burden on employees and maintains work efficiency. When providing personalized support, the support department can take into account the employee's geographical location. For example, if an employee is in the office, the support department will prioritize work-related support. This allows for optimal support that takes geographical factors into account. When providing personalized support, the support department can analyze employees' social media activity and provide relevant support.For example, the support department can provide support if an employee uses social media during work hours. This allows the support department to provide optimal support by comprehensively considering factors such as the employee's work content, emotional state, geographical location, and social media activity. As a result, the support department can improve employee work efficiency and make concrete suggestions to eliminate inefficiencies and wasted time.

[0080] The data collection unit can comprehensively record the operation status of work PCs. For example, the data collection unit can record the operation status of work PCs in real time and store it in a database. When recording operation status, the data collection unit can select the type of data to record according to the employee's work content. For example, in the case of data entry work, the data collection unit will focus on recording data related to input speed and accuracy. When recording operation status, the data collection unit can improve the accuracy of the recording by referring to the employee's past operation history. For example, based on past operation history, the data collection unit will prioritize recording frequently used operations. The data collection unit can estimate the employee's emotions and adjust the frequency of recording operation status based on the estimated emotions of the employee. For example, if the data collection unit is feeling stressed, it will reduce the frequency of recording operation status to alleviate the workload. When recording operation status, the data collection unit can prioritize recording highly relevant operations by considering the employee's geographical location information. For example, if the data collection unit is in the office, it will prioritize recording work-related operations. When recording operation status, the data collection unit can analyze the employee's social media activity and record relevant operations. For example, the data collection unit records when employees use social media during work hours. This allows for the collection of detailed data by comprehensively recording the usage status of work PCs.

[0081] The analysis department can analyze recorded operational data and learn work patterns. For example, it can analyze operational data using data aggregation methods and pattern recognition algorithms. The analysis department can estimate employee emotions and adjust the analysis method based on the estimated emotions. For example, if an employee is stressed, the analysis department can apply a simplified analysis method. When analyzing recorded operational data, the analysis department can apply different analysis algorithms depending on the employee's work content. For example, in the case of data entry, the analysis department can apply algorithms that analyze input speed and accuracy. When analyzing recorded operational data, the analysis department can improve the accuracy of the analysis by referring to the employee's past work patterns. For example, based on past work patterns, the analysis department can focus on analyzing frequently occurring operations. When analyzing recorded operational data, the analysis department can consider the employee's geographical location. For example, if an employee is in the office, the analysis department can focus on analyzing work-related operations. When analyzing recorded operational data, the analysis department can improve the accuracy of the analysis by referring to the employee's relevant literature. For example, the analysis department refers to literature related to the work and uses it to analyze operational status. By learning work patterns, they can improve the efficiency of their work.

[0082] The automation unit can automate tasks such as creating and prioritizing to-do lists, drafting and proposing emails, data entry, processing, and analysis. For example, the automation unit can analyze employee work content and organize tasks based on importance and urgency. It can estimate employee emotions and adjust automation methods based on these estimations. For instance, if an employee is stressed, the automation unit applies a simpler automation method. During automation, the automation unit can apply different automation algorithms depending on the employee's work content. For example, for data entry tasks, the automation unit applies an algorithm that improves input speed and accuracy. During automation, the automation unit can improve the accuracy of automation by referring to the employee's past work patterns. For example, based on past work patterns, the automation unit prioritizes automating frequently occurring tasks. The automation unit can estimate employee emotions and determine automation priorities based on these estimations. For example, if an employee is stressed, the automation unit postpones the automation of less important tasks. The automation unit can also consider employee geographical location information during automation. For example, the automation department prioritizes automating work-related tasks when employees are in the office. During automation, the automation department can analyze employees' social media activity and automate related tasks. For instance, if an employee uses social media during work hours, the automation department will automate that task. This process of automating tasks can improve work efficiency.

[0083] The system can schedule meetings, notify participants, and automatically create and summarize meeting minutes. For example, it can check employee schedules and suggest optimal meeting times. It can estimate employee emotions and adjust how results are displayed based on the estimated emotions. For example, if an employee is stressed, it provides a simple and highly visible display. When displaying results, the system can apply different display algorithms depending on the employee's work content. For example, for data entry tasks, it visually displays results related to entry speed and accuracy. When displaying results, the system can improve display accuracy by referring to the employee's past work patterns. For example, based on past work patterns, it prioritizes frequently occurring results. The system can estimate employee emotions and prioritize results based on the estimated emotions. For example, if an employee is stressed, it postpones displaying less important results. When displaying results, the system can consider the employee's geographical location. For example, the service provider can prioritize displaying work-related results when an employee is in the office. When displaying results, the service provider can analyze employee social media activity and provide relevant results. For instance, if an employee is using social media during work hours, the service provider can display the results. This can improve work efficiency by automating meeting scheduling and minute creation.

[0084] The optimization unit can propose optimizations for business processes. For example, the optimization unit proposes which parts of the business process should be optimized based on optimization evaluation criteria. The optimization unit can estimate employee emotions and adjust the business process optimization method based on the estimated emotions. For example, if an employee is feeling stressed, the optimization unit will apply a simpler optimization method. When optimizing business processes, the optimization unit can apply different optimization algorithms depending on the employee's work content. For example, in the case of data entry tasks, the optimization unit will apply an optimization algorithm that improves input speed and accuracy. When optimizing business processes, the optimization unit can improve the accuracy of optimization by referring to the employee's past work patterns. For example, based on past work patterns, the optimization unit prioritizes optimizing frequently occurring tasks. The optimization unit can estimate employee emotions and determine the priority of business process optimization based on the estimated emotions. For example, if an employee is feeling stressed, the optimization unit will postpone the optimization of less important tasks. When optimizing business processes, the optimization unit can consider the employee's geographical location information. For example, the optimization unit prioritizes optimizing work-related tasks when employees are in the office. When optimizing workflows, the optimization unit can analyze employees' social media activity and optimize related workflows. For instance, if an employee uses social media during work hours, the optimization unit will optimize that workflow. This allows for improved work efficiency by suggesting workflow optimizations.

[0085] The support department can learn employees' work styles and preferences and provide personalized support. For example, the support department can provide appropriate support based on the employee's work content and preferences. The support department can estimate the employee's emotions and adjust the personalized support method based on the estimated emotions. For example, if the support department is stressed, it will apply a simpler support method. When providing personalized support, the support department can apply different support algorithms depending on the employee's work content. For example, for data entry tasks, the support department will apply a support algorithm that improves input speed and accuracy. When providing personalized support, the support department can improve the accuracy of support by referring to the employee's past work patterns. For example, based on past work patterns, the support department will prioritize providing support that occurs frequently. The support department can estimate the employee's emotions and determine the priority of personalized support based on the estimated emotions. For example, if the support department is stressed, it will postpone providing support of lower importance. When providing personalized support, the support department can take the employee's geographical location into consideration. For example, the support department prioritizes providing work-related support to employees when they are in the office. When providing personalized support, the support department can analyze employees' social media activity and provide relevant support. For instance, if an employee uses social media during work hours, the support department can provide support for that. This allows for increased work efficiency by providing support tailored to employees' work styles and preferences.

[0086] The data collection unit can estimate an employee's emotions and adjust the frequency of recording their work activity based on the estimated emotions. For example, if an employee is stressed, the data collection unit can reduce the frequency of recording their work activity to alleviate their workload. If an employee is relaxed, the data collection unit can increase the frequency of recording their work activity to collect more detailed data. If an employee is focused, the data collection unit can appropriately adjust the frequency of recording their work activity to avoid disrupting their work. In this way, the workload can be reduced by adjusting the frequency of recording their work activity according to their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0087] The data collection unit can select the type of data to record according to the employee's work content when recording operational status. For example, in the case of data entry, the data collection unit can focus on recording data related to input speed and accuracy. In the case of email correspondence, the data collection unit can record data related to the time and content of emails sent and received. In the case of meeting participation, the data collection unit can record data related to meeting participation time and content of comments. By recording data according to the content of the work, it is possible to improve work efficiency.

[0088] The data collection unit can improve the accuracy of recordings by referring to the employee's past operation history when recording operation status. For example, the data collection unit can prioritize recording frequently used operations based on past operation history. The data collection unit can analyze past operation errors and record them in detail if similar errors occur. The data collection unit can refer to past operation patterns and issue alerts if abnormal operations occur. In this way, the accuracy of recordings can be improved by referring to past operation history.

[0089] The data collection unit can estimate an employee's emotions and determine the priority of operations to record based on the estimated emotions. For example, if an employee is stressed, the data collection unit will postpone recording low-priority operations. If an employee is relaxed, the data collection unit can record all operations equally. If an employee is focused, the data collection unit can prioritize recording high-priority operations. This allows for increased work efficiency by prioritizing operations according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0090] The data collection unit can prioritize recording highly relevant operations by considering the employee's geographical location when recording operation status. For example, if an employee is in the office, the data collection unit will prioritize recording work-related operations. If an employee is on a business trip, the data collection unit can focus on recording operations performed at the business trip location. If an employee is working remotely, the data collection unit can record operations performed at home in detail. By recording operations while considering geographical location, the system can improve work efficiency.

[0091] The data collection unit can analyze employees' social media activity and record relevant actions when recording operational status. For example, if an employee uses social media during work hours, the data collection unit can record that activity. The data collection unit can analyze work-related posts on social media and record relevant actions. The data collection unit can record work-related feedback obtained from social media activity. This allows for improved work efficiency by analyzing social media activity and recording actions.

[0092] The analysis department can estimate employees' emotions and adjust the analysis method based on the estimated emotions. For example, if an employee is stressed, the analysis department can apply a simple analysis method. If an employee is relaxed, the analysis department can apply a detailed analysis method. If an employee is focused, the analysis department can apply a complex analysis method. This allows for increased work efficiency by adjusting the analysis method according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0093] The analysis department can apply different analysis algorithms to the recorded operational status depending on the employee's work content. For example, in the case of data entry, the analysis department can apply an algorithm that analyzes input speed and accuracy. In the case of email correspondence, the analysis department can apply an algorithm that analyzes the time it takes to send and receive emails and their content. In the case of meeting participation, the analysis department can apply an algorithm that analyzes the time spent at meetings and the content of what was said. By applying an analysis algorithm tailored to the work content, the department can improve the efficiency of operations.

[0094] The analysis department can improve the accuracy of its analysis by referring to employees' past work patterns when analyzing recorded operational status. For example, the analysis department can focus its analysis on frequently occurring operations based on past work patterns. The analysis department can analyze past work errors and conduct a detailed analysis if similar errors occur. The analysis department can refer to past work patterns and issue alerts if abnormal operations occur. This improves the accuracy of the analysis by referring to past work patterns.

[0095] The analysis department can estimate employees' emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if an employee is stressed, the analysis department can provide a simple and highly visible display. If an employee is relaxed, the analysis department can provide a display that includes detailed information. If an employee is focused, the analysis department can provide a display that focuses on the key points. This allows for improved work efficiency by adjusting the display of analysis results according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0096] The analysis department can take into account the geographical location of employees when analyzing recorded operational data. For example, if an employee is in the office, the analysis department will focus on analyzing work-related operations. If an employee is on a business trip, the analysis department can analyze operations performed at the business trip location. If an employee is working remotely, the analysis department can conduct a detailed analysis of operations performed at home. By considering geographical location during the analysis, the department can improve the efficiency of operations.

[0097] The analysis department can improve the accuracy of its analysis by referring to relevant employee literature when analyzing recorded operational status. For example, the analysis department can refer to work-related literature to aid in the analysis of operational status. Based on the knowledge gained from relevant literature, the analysis department can adjust its analysis algorithms. By referring to relevant literature, the analysis department can gain insights that lead to increased work efficiency. Thus, by referring to relevant literature, the accuracy of the analysis can be improved.

[0098] The automation unit can estimate an employee's emotions and adjust the automation method based on the estimated emotions. For example, if an employee is stressed, the automation unit can apply a simple automation method. If an employee is relaxed, the automation unit can apply a more detailed automation method. If an employee is focused, the automation unit can apply a more complex automation method. This allows for increased work efficiency by adjusting the automation method according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0099] The automation unit can apply different automation algorithms depending on the employee's work content during automation. For example, in the case of data entry, the automation unit can apply an automation algorithm that improves input speed and accuracy. In the case of email correspondence, the automation unit can apply an algorithm that automates the sending and receiving time and content of emails. In the case of meeting participation, the automation unit can apply an algorithm that automates meeting scheduling and minute-taking. In this way, by applying automation algorithms tailored to the work content, the efficiency of work can be improved.

[0100] The automation unit can improve the accuracy of automation by referring to employees' past work patterns during the automation process. For example, the automation unit can prioritize the automation of frequently occurring tasks based on past work patterns. The automation unit can analyze past work errors and automate similar errors if they occur again. The automation unit can refer to past work patterns and issue alerts if an unusual task occurs. This allows the accuracy of automation to be improved by referring to past work patterns.

[0101] The automation unit can estimate employees' emotions and determine automation priorities based on those estimated emotions. For example, if an employee is stressed, the automation unit will postpone the automation of low-priority tasks. If an employee is relaxed, the automation unit can automate all tasks equally. If an employee is focused, the automation unit can prioritize the automation of high-priority tasks. This allows for increased work efficiency by determining automation priorities according to employee 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.

[0102] The automation unit can perform automation while taking into account the geographical location of employees. For example, if an employee is in the office, the automation unit will prioritize automating work-related tasks. If an employee is on a business trip, the automation unit can focus on automating tasks at the business trip location. If an employee is working remotely, the automation unit can automate tasks at home in detail. By considering geographical location when performing automation, the efficiency of operations can be improved.

[0103] The automation department can analyze employees' social media activity and automate related tasks during the automation process. For example, if an employee uses social media during work hours, the automation department can automate that task. The automation department can analyze work-related posts on social media and automate related tasks. The automation department can automate the process of obtaining work-related feedback from social media activity. This allows for increased work efficiency by analyzing social media activity and automating tasks.

[0104] The system can estimate an employee's emotions and adjust how the results are displayed based on that estimation. For example, if an employee is stressed, the system can provide a simple and highly visible display. If an employee is relaxed, the system can provide a display that includes detailed information. If an employee is focused, the system can provide a concise display. By adjusting the display of results according to an employee's emotions, the system can improve work efficiency. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0105] The data delivery system can apply different display algorithms depending on the employee's work content when displaying the results it provides. For example, in the case of data entry, the system can visually display results related to input speed and accuracy. In the case of email correspondence, the system can display results related to email sending and receiving time and content. In the case of meeting participation, the system can display results related to meeting participation time and content of comments. By applying a display algorithm tailored to the work content, the system can improve work efficiency.

[0106] The data delivery unit can improve the accuracy of the displayed results by referring to employees' past work patterns. For example, the unit can focus on displaying frequently occurring results based on past work patterns. The unit can analyze past work errors and display them in detail when similar errors occur. The unit can refer to past work patterns and issue alerts when abnormal results occur. This improves the accuracy of the displayed results by referring to past work patterns.

[0107] The delivery system can estimate an employee's emotions and prioritize the results it delivers based on those emotions. For example, if an employee is stressed, the system will delay displaying less important results. If an employee is relaxed, the system can display all results equally. If an employee is focused, the system can prioritize displaying more important results. This allows for increased work efficiency by prioritizing results according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0108] The data delivery system can display results while taking into account the employee's geographical location. For example, if an employee is in the office, the system can prioritize displaying work-related results. If an employee is on a business trip, the system can focus on displaying results from their business trip location. If an employee is working remotely, the system can display detailed results from their home. By displaying results while considering geographical location, the system can improve work efficiency.

[0109] The service provider can analyze employees' social media activity and provide relevant results when displaying the results. For example, it can display results if an employee uses social media during work hours. The service provider can analyze work-related posts on social media and display relevant results. The service provider can display work-related feedback derived from social media activity. This allows for improved work efficiency by analyzing social media activity and providing results.

[0110] The optimization unit can estimate employees' emotions and adjust the optimization method of the workflow based on the estimated emotions. For example, if an employee is stressed, the optimization unit can apply a simple optimization method. If an employee is relaxed, the optimization unit can apply a detailed optimization method. If an employee is focused, the optimization unit can apply a complex optimization method. This allows for improved work efficiency by adjusting the workflow optimization method according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0111] The optimization unit can apply different optimization algorithms depending on the employee's work content when optimizing business workflows. For example, in the case of data entry, the optimization unit can apply an optimization algorithm that improves input speed and accuracy. In the case of email correspondence, the optimization unit can apply an algorithm that optimizes the sending and receiving time and content of emails. In the case of meeting participation, the optimization unit can apply an algorithm that optimizes meeting scheduling and minute-taking. In this way, by applying an optimization algorithm tailored to the work content, business efficiency can be improved.

[0112] The optimization unit can improve the accuracy of optimization by referring to employees' past work patterns when optimizing business workflows. For example, the optimization unit can prioritize the optimization of frequently occurring tasks based on past work patterns. The optimization unit can analyze past work errors and optimize when similar errors occur. The optimization unit can refer to past work patterns and issue alerts when abnormal tasks occur. In this way, the accuracy of optimization can be improved by referring to past work patterns.

[0113] The optimization unit can estimate employees' emotions and determine the priority of workflow optimization based on those estimated emotions. For example, if an employee is stressed, the optimization unit will postpone the optimization of low-priority tasks. If an employee is relaxed, the optimization unit can optimize all tasks equally. If an employee is focused, the optimization unit can prioritize the optimization of high-priority tasks. This allows for increased work efficiency by determining the priority of workflow optimization according to employees' emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0114] The optimization unit can optimize business workflows while considering employees' geographical location information. For example, if an employee is in the office, the optimization unit will prioritize optimizing work-related tasks. If an employee is on a business trip, the optimization unit can focus on optimizing tasks performed at the business trip location. If an employee is working remotely, the optimization unit can optimize tasks performed at home in detail. By considering geographical location information during optimization, business efficiency can be improved.

[0115] The optimization unit can analyze employees' social media activity and optimize related workflows when optimizing business processes. For example, if an employee uses social media during work hours, the optimization unit can optimize that workflow. The optimization unit can analyze work-related posts on social media and optimize related workflows. The optimization unit can optimize work-related feedback obtained from social media activity. In this way, by analyzing social media activity and optimizing workflows, business efficiency can be improved.

[0116] The support department can estimate employees' emotions and adjust personalized support methods based on the estimated emotions. For example, if an employee is stressed, the support department can apply a simple support method. If an employee is relaxed, the support department can apply a more detailed support method. If an employee is focused, the support department can apply a more complex support method. This allows for increased work efficiency by adjusting support methods according to employees' 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.

[0117] The support department can apply different support algorithms depending on the employee's work content when providing personalized support. For example, for data entry tasks, the support department can apply support algorithms that improve input speed and accuracy. For email correspondence tasks, the support department can apply algorithms that support email sending and receiving times and content. For meeting participation tasks, the support department can apply algorithms that support meeting scheduling and minute-taking. In this way, by applying support algorithms tailored to the work content, the efficiency of operations can be improved.

[0118] The support department can improve the accuracy of personalized support by referring to employees' past work patterns. For example, the support department can prioritize support for frequently occurring issues based on past work patterns. The support department can analyze past work errors and provide support when similar errors occur. The support department can refer to past work patterns and issue alerts when unusual work occurs. In this way, the accuracy of support can be improved by referring to past work patterns.

[0119] The support department can estimate employees' emotions and determine personalized support priorities based on those estimated emotions. For example, if an employee is stressed, the support department can postpone providing less important support. If an employee is relaxed, the support department can provide all support equally. If an employee is focused, the support department can prioritize providing high-priority support. This allows for increased operational efficiency by prioritizing support according to employee 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.

[0120] The support department can provide personalized support while taking into account the employee's geographical location. For example, if an employee is in the office, the support department can prioritize work-related support. If an employee is on a business trip, the support department can focus on providing support at their destination. If an employee is working remotely, the support department can provide detailed support at their home. By considering geographical location when providing support, the support department can improve operational efficiency.

[0121] The support department can analyze employees' social media activity and provide relevant support when providing personalized support. For example, if an employee uses social media during work hours, the support department can provide support. The support department can analyze work-related posts on social media and provide relevant support. The support department can provide support based on work-related feedback obtained from social media activity. This allows for increased work efficiency by analyzing social media activity and providing support accordingly.

[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 AI ​​agent system can also monitor employee health and make suggestions to improve work efficiency. For example, the data collection unit monitors employees' heart rate and stress levels and adjusts their workload based on their health status. The analysis unit analyzes health data and learns work patterns that correspond to employees' health status. The automation unit adjusts task priorities based on health status to reduce the burden on employees. This results in improved work efficiency that takes employee health into consideration.

[0124] The AI ​​agent system can also assess employees' skill levels and suggest appropriate training programs. For example, the data collection unit records employee work performance data and assesses skill levels. The analysis unit analyzes the skill data to identify employees' strengths and weaknesses. The automation unit automatically generates training programs based on skill levels and provides them to employees. This leads to improved employee skills and increased work efficiency.

[0125] AI agent systems can also include feedback functions to improve employee motivation. For example, a data collection unit records employee work performance data and estimates their motivation level. An analysis unit analyzes the motivation data and generates feedback that helps improve employee motivation. A delivery unit provides the feedback to employees to improve their motivation. This leads to increased employee motivation and improved work efficiency.

[0126] AI agent systems can also include support functions to improve employees' communication skills. For example, the data collection unit records employee communication data and evaluates skill levels. The analysis unit analyzes the communication data to identify employees' strengths and weaknesses. The automation unit automatically generates training programs based on skill levels and provides them to employees. This leads to improved employee communication skills and increased work efficiency.

[0127] The AI ​​agent system can also estimate employees' emotions and adjust the work environment based on those emotions. For example, the data collection unit records employee emotional data and estimates stress levels. The analysis unit analyzes the emotional data and proposes ways to adjust the work environment according to the employee's emotions. The delivery unit provides the employee with the results of the work environment adjustments, thereby reducing stress. This ensures that the work environment is adjusted in accordance with the employees' emotions.

[0128] The AI ​​agent system can also monitor employee work performance in real time and provide immediate feedback. For example, the data collection unit records employee work data in real time and evaluates performance. The analysis unit analyzes the real-time data and generates immediate feedback. The delivery unit immediately provides the feedback to employees to improve their work performance. This enables real-time improvement of work performance.

[0129] The AI ​​agent system can also estimate employees' emotions and adjust task assignments based on those emotions. For example, the data collection unit records employee emotional data and estimates stress levels. The analysis unit analyzes the emotional data and suggests task assignment methods that are appropriate to the employee's emotions. The automation unit adjusts task assignments based on emotions to reduce workload. This ensures that tasks are assigned in a way that is appropriate to the employees' emotions.

[0130] The AI ​​agent system can also evaluate employee work performance and propose rewards and incentives. For example, the data collection unit records employee work data and evaluates performance. The analysis unit analyzes the performance data and generates reward and incentive proposals. The delivery unit provides these proposals to employees to improve their motivation. This ensures that rewards and incentives are proposed based on work performance.

[0131] The AI ​​agent system can also estimate employees' emotions and adjust their work schedules based on those emotions. For example, the data collection unit records employee emotional data and estimates their stress levels. The analysis unit analyzes the emotional data and proposes scheduling adjustments that are appropriate for the employee's emotions. The delivery unit provides the scheduling adjustment results to the employee, reducing stress. This ensures that work schedules are adjusted in accordance with the employee's emotions.

[0132] The AI ​​agent system can also evaluate employee work performance and suggest career paths. For example, the data collection unit records employee work data and evaluates performance. The analysis unit analyzes the performance data and suggests career paths for employees. The delivery unit provides these career path suggestions to employees and supports their career growth. This ensures that career paths are suggested based on work performance.

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

[0134] Step 1: The data collection unit records the operation status of work PCs. For example, it records mouse movements, keyboard input, application usage, etc., and saves them to a database in real time. The data collection unit selects the type of data to record according to the employee's work content and improves the accuracy of the recording by considering past operation history, employee sentiment, geographical location information, and social media activity. Step 2: The analysis unit analyzes the operational status recorded by the data collection unit. The analysis unit learns operational patterns and analyzes operational status using data aggregation methods and pattern recognition algorithms. The accuracy of the analysis is improved by considering employee sentiment, work content, past operational patterns, geographical location information, and relevant literature. Step 3: The automation department automates tasks based on the analysis results obtained by the analysis department. The automation department automates tasks such as creating and prioritizing to-do lists, drafting and proposing emails, data entry, processing, and analysis. The accuracy of automation is improved by considering employee sentiment, job content, past work patterns, geographical location information, and social media activity. Step 4: The delivery department provides the results of tasks automated by the automation department. The delivery department schedules meetings and notifies participants, and automatically creates and summarizes meeting minutes. It adjusts how the results are displayed, taking into account employee sentiment, job content, past work patterns, geographical location, and social media activity. Step 5: The Optimization Department optimizes the workflow based on the results provided by the Delivery Department. The Optimization Department proposes workflow optimizations and improves the accuracy of the optimization by considering employee sentiment, work content, past work patterns, geographical location information, and social media activity. Step 6: The support department provides personalized support based on the workflow optimized by the optimization department. The support department learns employees' work styles and preferences and provides personalized support that takes into account employees' emotions, work content, past work patterns, geographical location, and social media activity.

[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 data collection unit, analysis unit, automation unit, provision unit, optimization unit, and support unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data collection unit is implemented by the computer 36 of the smart device 14 and records the operation status of the business PC. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the recorded operation status. The automation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automates tasks. The provision unit is implemented by the control unit 46A of the smart device 14 and provides the results of the automated tasks. The optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and optimizes the business flow. The support unit is implemented by the control unit 46A of the smart device 14 and provides individualized support. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[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 data collection unit, analysis unit, automation unit, provision unit, optimization unit, and support unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit is implemented by the computer 36 of the smart glasses 214 and records the operation status of the business PC. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the recorded operation status. The automation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automates tasks. The provision unit is implemented by the control unit 46A of the smart glasses 214 and provides the results of the automated tasks. The optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and optimizes the business flow. The support unit is implemented by the control unit 46A of the smart glasses 214 and provides individualized support. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[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 collection unit, analysis unit, automation unit, provision unit, optimization unit, and support unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the computer 36 of the headset terminal 314 and records the operation status of the business PC. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the recorded operation status. The automation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automates tasks. The provision unit is implemented by the control unit 46A of the headset terminal 314 and provides the results of the automated tasks. The optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and optimizes the business flow. The support unit is implemented by the control unit 46A of the headset terminal 314 and provides individualized support. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[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 data collection unit, analysis unit, automation unit, provision unit, optimization unit, and support unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the data collection unit is implemented by the computer 36 of the robot 414 and records the operation status of the business PC. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the recorded operation status. The automation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automates tasks. The provision unit is implemented by the control unit 46A of the robot 414 and provides the results of the automated tasks. The optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and optimizes the business flow. The support unit is implemented by the control unit 46A of the robot 414 and provides individualized support. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[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) A data collection unit that records the operation status of the work PC, An analysis unit analyzes the operating status recorded by the aforementioned collection unit, An automation unit that automates tasks based on the analysis results obtained by the aforementioned analysis unit, A providing unit that provides the results of the task automated by the automation unit, An optimization unit that optimizes the business flow based on the results provided by the aforementioned provisioning unit, The system includes a support unit that provides personalized support based on the business flow optimized by the optimization unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is Comprehensively record the usage status of work PCs. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit is Analyze recorded operation data to learn work patterns. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned automation unit, Automate tasks such as creating and prioritizing to-do lists, drafting and proposing emails, and automating data entry, processing, and analysis. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, It schedules meetings, notifies participants, and automatically generates and summarizes meeting minutes. The system described in Appendix 1, characterized by the features described herein. (Note 6) The optimization unit, We propose optimizations to business processes. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned support unit is Learn employees' work styles and preferences to provide personalized support. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is The system estimates employee emotions and adjusts the frequency of recording operational status based on the estimated employee emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When recording operational status, select the type of data to record according to the employee's work content. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is When recording operational status, the accuracy of the recording is improved by referring to the employee's past operational history. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is The system estimates employee emotions and determines the priority of operational situations to record based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When recording operational status, the system prioritizes recording operations that are highly relevant, taking into account the employee's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is When recording operational status, analyze employee social media activity and record related operations. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit is We estimate employee sentiment and adjust the analysis method based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit is When analyzing recorded operational data, different analysis algorithms are applied depending on the employee's job duties. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit is When analyzing recorded operational data, referencing employees' past work patterns improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit is The system estimates employee sentiment and adjusts how the analysis results are displayed based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit is When analyzing recorded operational data, the analysis should take into account the geographical location of employees. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit is When analyzing recorded operational data, we improve the accuracy of the analysis by referring to relevant employee literature. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned automation unit, It estimates employee emotions and adjusts the automation method based on the estimated employee emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned automation unit, When automating tasks, different automation algorithms are applied depending on the employee's work content. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned automation unit, When automating processes, referencing employees' past work patterns improves the accuracy of the automation. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned automation unit, It estimates employee sentiment and determines automation priorities based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned automation unit, When automating processes, the system should take into account the geographical location of employees. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned automation unit, During automation, analyze employees' social media activity and automate related tasks. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, We estimate employee sentiment and adjust how the results are displayed based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When displaying the results provided, different display algorithms are applied depending on the employee's job duties. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, When displaying the results provided, the system improves the accuracy of the display by referencing the employee's past work patterns. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, The system estimates employee sentiment and prioritizes the results provided based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When displaying the results provided, the display will take into account the geographical location information of the employees. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned supply unit is, When displaying the results provided, we analyze employees' social media activity and provide relevant results. The system described in Appendix 1, characterized by the features described herein. (Note 32) The optimization unit, The system estimates employee sentiment and adjusts the optimization of workflows based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 33) The optimization unit, When optimizing business processes, different optimization algorithms are applied depending on the employee's specific tasks. The system described in Appendix 1, characterized by the features described herein. (Note 34) The optimization unit, When optimizing business processes, referencing employees' past work patterns improves the accuracy of the optimization. The system described in Appendix 1, characterized by the features described herein. (Note 35) The optimization unit, The system estimates employee sentiment and determines the priority of business process optimization based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 36) The optimization unit, When optimizing business processes, consider the geographical location of employees. The system described in Appendix 1, characterized by the features described herein. (Note 37) The optimization unit, When optimizing business processes, analyze employees' social media activity and optimize the relevant business processes. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned support unit is Estimate employees' emotions and tailor individualized support methods based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned support unit is When providing personalized support, different support algorithms are applied depending on the employee's job responsibilities. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned support unit is When providing personalized support, referencing employees' past work patterns improves the accuracy of the support. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned support unit is Estimate employee emotions and determine personalized support priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned support unit is When providing personalized support, consider the geographical location of the employee. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned support unit is When providing personalized support, analyze employees' social media activity and provide relevant support. The system described in Appendix 1, 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. A data collection unit that records the operation status of the work PC, An analysis unit analyzes the operating status recorded by the aforementioned collection unit, An automation unit that automates tasks based on the analysis results obtained by the aforementioned analysis unit, A providing unit that provides the results of the task automated by the automation unit, An optimization unit that optimizes the business flow based on the results provided by the aforementioned provisioning unit, The system includes a support unit that provides personalized support based on the business flow optimized by the optimization unit. A system characterized by the following features.

2. The aforementioned collection unit is Comprehensively record the usage status of work PCs. The system according to feature 1.

3. The aforementioned analysis unit is Analyze recorded operation data to learn work patterns. The system according to feature 1.

4. The aforementioned automation unit, Automate tasks such as creating and prioritizing to-do lists, drafting and proposing emails, and automating data entry, processing, and analysis. The system according to feature 1.

5. The aforementioned supply unit is, It schedules meetings, notifies participants, and automatically generates and summarizes meeting minutes. The system according to feature 1.

6. The optimization unit, We propose optimizations to business processes. The system according to feature 1.

7. The aforementioned support unit is Learn employees' work styles and preferences to provide personalized support. The system according to feature 1.

8. The aforementioned collection unit is The system estimates employee emotions and adjusts the frequency of recording operational status based on the estimated employee emotions. The system according to feature 1.

9. The aforementioned collection unit is When recording operational status, select the type of data to record according to the employee's work content. The system according to feature 1.

10. The aforementioned collection unit is When recording operational status, the accuracy of the recording is improved by referring to the employee's past operational history. The system according to feature 1.

Images