system

Abstract

The system according to the embodiment aims to enable a person returning from leave to smoothly resume work by grasping changes in the organization and work when resuming work. 【Solution means】The system according to the embodiment includes a proxy response unit, a learning unit, and a procedure proxy unit. The proxy response unit participates in team chats and meetings on behalf of the person on leave and gives simple responses. The learning unit automatically learns changes in the organization, systems, work, etc. from meeting records, team chats, internal notification pages, and circular emails within the company. The procedure proxy unit substitutes for the applications required at the time of resuming work based on the information learned by the learning 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, the method 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, when a person on leave returns to work, it is difficult to grasp changes in the organization and business, and there is a problem that the return to work cannot be smoothly carried out.

[0005] The system according to the embodiment aims to enable a person on leave to grasp changes in the organization and business when returning to work and to be able to return to work smoothly.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a proxy response unit, a learning unit, and a procedural support unit. The proxy response unit participates in team chats and meetings on behalf of the employee on leave and provides simple acknowledgments. The learning unit automatically learns about changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails. The procedural support unit handles the necessary applications upon the employee's return to work based on the information learned by the learning unit. [Effects of the Invention]

[0007] The system according to this embodiment can help employees on leave to understand changes in the organization and operations when they return to work, enabling a smooth return to work. [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 a plurality of computers. Examples of communication standards applied 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) The AI ​​agent system according to an embodiment of the present invention is a system for facilitating information exchange and smooth return to work when an employee takes leave for maternity leave, childcare leave, caregiving, health reasons, etc. This AI agent system supports work-related communication on behalf of the employee on leave and provides necessary information upon their return to work, allowing the employee to focus on their leave with peace of mind and ensuring a smooth return to work. The AI ​​agent system has the following three main functions. First, the proxy response bot function participates in team chats and meetings on behalf of the employee on leave, making simple interjections to create a sense of presence. For example, by interjecting with "That's great!" during a meeting, it can make it appear as if the employee on leave is participating. Second, the business / system change learning function automatically learns changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails, and informs the employee upon their return to work. For example, if a new system is introduced during the employee's leave, the system can learn the details and explain them to the returning employee in a conversational format. Finally, the return-to-work procedure proxy function handles the procedures for regaining authority lost during leave upon returning to work. For example, the AI ​​can automatically handle the necessary applications when an employee returns to work, ensuring a smooth resumption of duties. This allows the AI ​​agent system to enable employees on leave to focus on their leave with peace of mind, facilitate a smooth return to work, and enable them to quickly become productive again. The AI ​​agent system supports work-related communication on behalf of employees on leave and provides necessary information upon their return, allowing them to focus on their leave with peace of mind and ensuring a smooth return to work.

[0029] The AI ​​agent system according to this embodiment comprises a proxy response unit, a learning unit, and a procedure proxy unit. The proxy response unit participates in team chats and meetings on behalf of the employee on leave and makes simple interjections. For example, the proxy response unit can make it appear as if the employee on leave is participating by making interjections such as "That's great!" during a meeting. The proxy response unit can also make interjections such as "Yes," "That's right," and "I understand" during a meeting. For example, the proxy response unit can also make interjections such as "I see," "That's right," and "Understood" during a meeting. The learning unit automatically learns changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails. For example, the learning unit can analyze meeting records and learn changes in the organization. For example, the learning unit can analyze the content of team chats and learn changes in operations. For example, the learning unit can analyze the content of internal announcement pages and notification emails and learn changes in systems. The procedural support unit handles the necessary applications for returning to work based on information learned by the learning unit. For example, the procedural support unit automatically creates and submits the return-to-work notification form required upon returning to work. The procedural support unit can also handle the submission of health check results required upon returning to work. For example, the procedural support unit can also handle the procedures for reacquiring necessary permissions upon returning to work. As a result, the AI ​​agent system according to this embodiment supports work-related communication on behalf of the employee on leave and provides the necessary information upon returning to work, allowing the employee on leave to focus on their leave with peace of mind and to return to work smoothly.

[0030] The proxy response unit participates in team chats and meetings on behalf of employees on leave, offering simple interjections. Specifically, the proxy response unit uses natural language processing technology to understand the context of the conversation and interject at the appropriate time. For example, by interjecting with "That's great!" during a meeting, it can make it appear as if the employee on leave is participating. The proxy response unit can also analyze the flow of the conversation in real time and interject with "Yes," "That's right," and "I understand." Furthermore, depending on the content of the conversation, the proxy response unit can interject with "I see," "That's right," and "Got it." In this way, the proxy response unit supports smooth team communication even when employees on leave are absent. The proxy response unit utilizes AI deep learning technology to learn from past conversation data and generate more natural responses. For example, it analyzes past meeting records and chat logs to learn appropriate interjection patterns in specific situations. This allows the proxy response unit to generate appropriate responses according to the context of the conversation, ensuring that team members do not feel uncomfortable. Furthermore, the proxy response unit uses speech recognition technology to analyze conversations in real time and can also provide verbal acknowledgments. This allows the proxy response unit to participate in audio and video conferences on behalf of the employee on leave, providing acknowledgments at appropriate times. In addition, the proxy response unit can customize the frequency and content of acknowledgments according to the user's settings. For example, by pre-setting the user's preferred acknowledgment patterns and frequencies, it can provide more personalized responses. As a result, the proxy response unit can effectively support communication on behalf of the employee on leave and maintain team cohesion.

[0031] The learning unit automatically learns about changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails. Specifically, the learning unit uses natural language processing technology to analyze meeting records and learn about organizational changes. For example, it extracts information such as the start of new projects or changes in team members and stores it in a database. The learning unit can also analyze the content of team chats and learn about changes in operations. For example, it extracts information about the introduction of new business processes or tools and updates the workflow. Furthermore, the learning unit can analyze the content of internal announcement pages and notification emails and learn about changes in systems. For example, it extracts information about new employee benefits or changes in internal regulations and notifies employees. The learning unit can also use AI machine learning technology to learn patterns of change based on past data and predict future changes. For example, it analyzes past meeting records and chat logs to understand trends in organizational and operational changes at specific times. This allows the learning unit to respond quickly to future changes. Furthermore, the learning unit can use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. For example, it can detect sudden organizational changes or abnormal changes in business processes and notify administrators. This allows the learning unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, improving the reliability and security of the entire system. In addition, the learning unit can continuously improve the accuracy and effectiveness of its learning algorithms based on user feedback. This enables the learning unit to always provide highly accurate learning based on the latest information, supporting quick and appropriate responses.

[0032] The Procedure Assistance Department handles the necessary applications for returning to work based on information learned by the Learning Department. Specifically, the Procedure Assistance Department automatically creates and submits the necessary return-to-work notification form. For example, it automatically updates the content of the return-to-work notification form based on organizational and operational changes learned by the Learning Department, ensuring that the latest information is reflected. The Procedure Assistance Department can also handle the submission of health check results required for returning to work. For example, it automatically obtains health check results, creates the necessary documents, and submits them. Furthermore, the Procedure Assistance Department can also handle the procedures for regaining necessary permissions upon returning to work. For example, it automatically regains access rights to systems and tools required by the returning employee, enabling them to smoothly resume work. The Procedure Assistance Department can perform these procedures quickly and accurately by utilizing AI automation technology. For example, it learns procedural patterns based on past procedural data and automatically generates the optimal procedural flow. This allows the Procedure Assistance Department to efficiently handle return-to-work procedures and reduce the burden on returning employees. In addition, the Procedure Assistance Department can customize the content and order of procedures according to user settings. For example, by pre-setting the priority and order of procedures desired by the user, a more personalized procedure can be provided. This allows the procedural support department to respond flexibly to the needs of those returning to work, creating an environment where they can focus on their return to work with peace of mind. Furthermore, the procedural support department can monitor the progress of the procedures in real time and notify the returning employee as needed. This allows the returning employee to understand the status of the procedures and proceed with their return to work preparations with confidence.

[0033] The proxy response unit can interject with phrases like "That's a good idea!" during a meeting. For example, the proxy response unit can interject with "That's a good idea!" during a meeting. The proxy response unit can also interject with phrases like "Exactly!" during a meeting. For example, the proxy response unit can interject with phrases like "I see, I understand." This makes it appear as if the person on leave is participating in the meeting by providing appropriate interjections. Some or all of the above processing in the proxy response unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proxy response unit can input the content of the meeting into a generative AI and have the generative AI execute appropriate interjections.

[0034] The learning unit can automatically learn about changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails. For example, the learning unit can analyze meeting records to learn about organizational changes. The learning unit can also analyze the content of team chats to learn about changes in operations. The learning unit can also analyze the content of internal announcement pages and notification emails to learn about changes in systems. This allows returning employees to stay informed of the latest information by automatically learning about changes in the organization, systems, and operations. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input meeting records and team chat content into a generative AI to allow the generative AI to learn about changes in the organization, systems, and operations.

[0035] The procedural assistance department can handle the necessary applications upon returning to work. For example, the procedural assistance department can automatically create and submit the return-to-work notification form required upon returning to work. The procedural assistance department can also handle the submission of the necessary health check results upon returning to work. The procedural assistance department can also handle the procedures for reacquiring necessary authority upon returning to work. By handling the necessary applications upon returning to work, the returning employee can smoothly resume their duties. Some or all of the above processes in the procedural assistance department may be performed using, for example, a generation AI, or without a generation AI. For example, the procedural assistance department can input the necessary application details into a generation AI and have the generation AI execute the application procedures.

[0036] The proxy response unit can analyze the progress of a meeting in real time and interject with appropriate responses at the right time. For example, when the meeting is lively, the AI ​​can interject with "That's right!". The proxy response unit can also interject with "Shall we move on to the next topic?" when the meeting is stalled. The proxy response unit can also interject with "Let's wrap things up" when the meeting is nearing its end. By interjecting at the appropriate time according to the progress of the meeting, the proxy response unit helps to keep the flow of the meeting smooth. Some or all of the above processing in the proxy response unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the proxy response unit can input meeting progress data into a generative AI and cause the generative AI to perform appropriate interjections at the right time.

[0037] The proxy response unit can analyze the content of team members' statements and apply different patterns of acknowledgments to each speaker. For example, if the speaker is a superior, the AI ​​might respond with a respectful acknowledgment such as "That's impressive!" If the speaker is a colleague, the AI ​​might respond with a friendly acknowledgment such as "That's a great idea!" If the speaker is a subordinate, the AI ​​might respond with an encouraging acknowledgment such as "Keep up the good work!" By applying different acknowledgment patterns to each speaker, more appropriate communication becomes possible. Some or all of the above processing in the proxy response unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proxy response unit can input the content of the statements into a generative AI and have the generative AI execute different acknowledgment patterns for each speaker.

[0038] The proxy response unit can customize the content of its responses according to the type and purpose of the meeting. For example, in a brainstorming meeting, the AI ​​might respond with "That's an interesting idea!" In a project progress meeting, the AI ​​might respond with "That's going well!" In a problem-solving meeting, the AI ​​might respond with "That solution sounds good!" By customizing the content of responses according to the type and purpose of the meeting, more appropriate communication becomes possible. Some or all of the above processing in the proxy response unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the proxy response unit can input data about the type and purpose of the meeting into the generative AI and have the generative AI customize the content of the responses.

[0039] The proxy response unit can handle not only team chat but also email and other communication tools. For example, in email exchanges, the proxy response unit's AI can respond with "Thank you for your confirmation." For example, in exchanges using project management tools, the proxy response unit's AI can respond with "I have checked the progress." For example, in exchanges using internal social networking services, the proxy response unit's AI can respond with "I agree with that opinion." This enables broader communication by supporting not only team chat but also email and other communication tools. Some or all of the above processing in the proxy response unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the proxy response unit can input data from emails or other communication tools into a generative AI and have the generative AI execute appropriate responses.

[0040] The learning unit can regularly update its learning content to maintain up-to-date information. For example, the learning unit can have its AI learn the latest meeting records through weekly updates. The learning unit can also have its AI learn the latest policy changes through monthly updates. The learning unit can also have its AI learn the latest team chat content through daily updates. This ensures that the learning content is always up-to-date by regularly updating it. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input regularly collected data into a generative AI to allow the generative AI to learn the latest information.

[0041] The learning unit can organize the learned information by category, making it easily accessible to returning employees. For example, the learning unit can categorize information related to organizational changes, making it easily accessible to returning employees. The learning unit can also categorize information related to system changes, making it easily accessible to returning employees. The learning unit can also categorize information related to changes in work processes, making it easily accessible to returning employees. By organizing the learned information by category, it becomes easily accessible to returning employees. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input the learned information into a generative AI and have the generative AI perform the process of organizing it by category.

[0042] The learning unit can make the learned content applicable to other departments and projects. For example, the learning unit can learn from meeting records of other departments and provide them to returning employees. The learning unit can also learn from the progress of other projects and provide them to returning employees. The learning unit can also learn from system changes in other departments and provide them to returning employees. This allows for broader information provision by making the learned content applicable to other departments and projects. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input data from other departments and projects into a generative AI and have the generative AI execute the application of the learned content.

[0043] The learning unit can also provide learning content in audio and video formats. For example, the learning unit can provide meeting records in audio format to make them easier for returning employees to understand. For example, the learning unit can provide information on system changes in video format to make it easier for returning employees to understand visually. For example, the learning unit can provide information on work changes in audio format so that returning employees can learn even while on the go. By providing learning content in audio and video formats, returning employees can acquire information in a wider variety of ways. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input learning content into a generative AI and have the generative AI provide it in audio and video formats.

[0044] The procedure management unit can track the progress of procedures in real time and provide notifications as needed. For example, the procedure management unit can track the progress of procedures in real time and notify the user. The procedure management unit can also notify the user when a procedure is completed. The procedure management unit can also notify the user when a problem occurs in a procedure. This allows the user to understand the progress of the procedure by tracking its progress in real time and providing notifications as needed. Some or all of the above processing in the procedure management unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the procedure management unit can input procedure progress data into a generating AI and have the generating AI execute notifications.

[0045] The procedural assistance unit can automatically collect and submit the necessary documents and information for the procedure. For example, the procedural assistance unit can automatically collect and submit the necessary documents. The procedural assistance unit can also automatically collect and submit the necessary information. The procedural assistance unit can also automatically collect and submit the necessary documents and information. This reduces the burden on the user by automatically collecting and submitting the necessary documents and information for the procedure. Some or all of the above processing in the procedural assistance unit may be performed using, for example, a generation AI, or without a generation AI. For example, the procedural assistance unit can input the necessary documents and information into a generation AI and have the generation AI perform the collection and submission.

[0046] The procedure outsourcing unit can provide not only the outsourcing of procedures but also the function of visualizing the progress of those procedures. For example, the procedure outsourcing unit can display the progress of procedures in a graph so that users can see it at a glance. For example, the procedure outsourcing unit can also display the progress of procedures in a list so that users can see it in detail. For example, the procedure outsourcing unit can display the progress of procedures in a calendar so that users can keep track of the schedule. In this way, by visualizing the progress of procedures, users can grasp the progress of the procedures at a glance. Some or all of the above processing in the procedure outsourcing unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the procedure outsourcing unit can input the progress of procedures data into a generation AI and have the generation AI perform the visualization.

[0047] The procedural outsourcing unit can apply its procedural outsourcing capabilities to other business processes. For example, the procedural outsourcing unit can perform procedures in other business processes, thereby reducing the user's burden. The procedural outsourcing unit can also track the progress of other business processes and notify the user. The procedural outsourcing unit can also automatically collect and submit documents and information from other business processes. This further reduces the user's burden by making procedural outsourcing applicable to other business processes. Some or all of the above-described processes in the procedural outsourcing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the procedural outsourcing unit can input data from other business processes into a generative AI and have the generative AI perform the procedural outsourcing.

[0048] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0049] The AI ​​agent system can also include a schedule management unit that manages the user's schedule and reminds them of important appointments. For example, the schedule management unit could send a reminder the day before a meeting. It could also send a reminder a week before an important deadline. Furthermore, it could send a reminder the day before a vacation. This ensures that users don't forget important appointments.

[0050] The AI ​​agent system can also include a learning management unit that manages the user's learning progress and customizes the learning content. For example, the learning management unit tracks the user's progress in acquiring specific skills. It can also provide additional learning resources for areas where the user struggles. Furthermore, it can offer rewards when the user achieves their goals. This can improve the user's learning efficiency and support skill acquisition.

[0051] The AI ​​agent system can also be equipped with a task management unit to further improve the user's work efficiency. For example, the task management unit can organize the user's tasks based on priority. It can also track the progress of the user's tasks and send reminders. Furthermore, it can report on the completion status of the user's tasks. This allows the user to manage tasks efficiently and proceed with their work smoothly.

[0052] The AI ​​agent system can also be equipped with a communication style learning unit that learns the user's communication style and provides appropriate communication methods. For example, the communication style learning unit learns the user's preferred communication method and sends messages in an appropriate way. If the user prefers email, the AI ​​can send messages via email. Similarly, if the user prefers chat, the AI ​​can send messages via chat. This enables communication in a way that is appropriate to the user's communication style.

[0053] The AI ​​agent system can also include a performance analysis unit that analyzes users' work performance and proposes improvements. For example, the performance analysis unit can periodically analyze users' work performance and suggest areas for improvement. It can also provide specific advice to improve users' work efficiency. Furthermore, it can compare users' work performance with other members and suggest best practices. This improves users' work performance and enables more effective work execution.

[0054] The following briefly describes the processing flow for example form 1.

[0055] Step 1: The proxy response team participates in team chats and meetings on behalf of the employee on leave, offering simple interjections. For example, during a meeting, they might say things like, "That's great!", "Yes," "Right," "I understand," "I see," "That's right," or "Got it," making it appear as if the employee on leave is participating. Step 2: The learning unit automatically learns about changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails. For example, it can analyze meeting records to learn about organizational changes. It can also analyze team chat content to learn about changes in operations. It can also analyze the content of internal announcement pages and notification emails to learn about changes in systems. Step 3: The procedural support department will handle the necessary applications for returning to work based on the information learned by the learning department. For example, it will automatically create and submit the return-to-work notification form required upon returning to work. It can also handle the submission of health examination results required upon returning to work. It can also handle the procedures for reacquiring necessary authority upon returning to work.

[0056] (Example of form 2) The AI ​​agent system according to an embodiment of the present invention is a system for facilitating information exchange and smooth return to work when an employee takes leave for maternity leave, childcare leave, caregiving, health reasons, etc. This AI agent system supports work-related communication on behalf of the employee on leave and provides necessary information upon their return to work, allowing the employee to focus on their leave with peace of mind and ensuring a smooth return to work. The AI ​​agent system has the following three main functions. First, the proxy response bot function participates in team chats and meetings on behalf of the employee on leave, making simple interjections to create a sense of presence. For example, by interjecting with "That's great!" during a meeting, it can make it appear as if the employee on leave is participating. Second, the business / system change learning function automatically learns changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails, and informs the employee upon their return to work. For example, if a new system is introduced during the employee's leave, the system can learn the details and explain them to the returning employee in a conversational format. Finally, the return-to-work procedure proxy function handles the procedures for regaining authority lost during leave upon returning to work. For example, the AI ​​can automatically handle the necessary applications when an employee returns to work, ensuring a smooth resumption of duties. This allows the AI ​​agent system to enable employees on leave to focus on their leave with peace of mind, facilitate a smooth return to work, and enable them to quickly become productive again. The AI ​​agent system supports work-related communication on behalf of employees on leave and provides necessary information upon their return, allowing them to focus on their leave with peace of mind and ensuring a smooth return to work.

[0057] The AI ​​agent system according to this embodiment comprises a proxy response unit, a learning unit, and a procedure proxy unit. The proxy response unit participates in team chats and meetings on behalf of the employee on leave and makes simple interjections. For example, the proxy response unit can make it appear as if the employee on leave is participating by making interjections such as "That's great!" during a meeting. The proxy response unit can also make interjections such as "Yes," "That's right," and "I understand" during a meeting. For example, the proxy response unit can also make interjections such as "I see," "That's right," and "Understood" during a meeting. The learning unit automatically learns changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails. For example, the learning unit can analyze meeting records and learn changes in the organization. For example, the learning unit can analyze the content of team chats and learn changes in operations. For example, the learning unit can analyze the content of internal announcement pages and notification emails and learn changes in systems. The procedural support unit handles the necessary applications for returning to work based on information learned by the learning unit. For example, the procedural support unit automatically creates and submits the return-to-work notification form required upon returning to work. The procedural support unit can also handle the submission of health check results required upon returning to work. For example, the procedural support unit can also handle the procedures for reacquiring necessary permissions upon returning to work. As a result, the AI ​​agent system according to this embodiment supports work-related communication on behalf of the employee on leave and provides the necessary information upon returning to work, allowing the employee on leave to focus on their leave with peace of mind and to return to work smoothly.

[0058] The proxy response unit participates in team chats and meetings on behalf of employees on leave, offering simple interjections. Specifically, the proxy response unit uses natural language processing technology to understand the context of the conversation and interject at the appropriate time. For example, by interjecting with "That's great!" during a meeting, it can make it appear as if the employee on leave is participating. The proxy response unit can also analyze the flow of the conversation in real time and interject with "Yes," "That's right," and "I understand." Furthermore, depending on the content of the conversation, the proxy response unit can interject with "I see," "That's right," and "Got it." In this way, the proxy response unit supports smooth team communication even when employees on leave are absent. The proxy response unit utilizes AI deep learning technology to learn from past conversation data and generate more natural responses. For example, it analyzes past meeting records and chat logs to learn appropriate interjection patterns in specific situations. This allows the proxy response unit to generate appropriate responses according to the context of the conversation, ensuring that team members do not feel uncomfortable. Furthermore, the proxy response unit uses speech recognition technology to analyze conversations in real time and can also provide verbal acknowledgments. This allows the proxy response unit to participate in audio and video conferences on behalf of the employee on leave, providing acknowledgments at appropriate times. In addition, the proxy response unit can customize the frequency and content of acknowledgments according to the user's settings. For example, by pre-setting the user's preferred acknowledgment patterns and frequencies, it can provide more personalized responses. As a result, the proxy response unit can effectively support communication on behalf of the employee on leave and maintain team cohesion.

[0059] The learning unit automatically learns about changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails. Specifically, the learning unit uses natural language processing technology to analyze meeting records and learn about organizational changes. For example, it extracts information such as the start of new projects or changes in team members and stores it in a database. The learning unit can also analyze the content of team chats and learn about changes in operations. For example, it extracts information about the introduction of new business processes or tools and updates the workflow. Furthermore, the learning unit can analyze the content of internal announcement pages and notification emails and learn about changes in systems. For example, it extracts information about new employee benefits or changes in internal regulations and notifies employees. The learning unit can also use AI machine learning technology to learn patterns of change based on past data and predict future changes. For example, it analyzes past meeting records and chat logs to understand trends in organizational and operational changes at specific times. This allows the learning unit to respond quickly to future changes. Furthermore, the learning unit can use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. For example, it can detect sudden organizational changes or abnormal changes in business processes and notify administrators. This allows the learning unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, improving the reliability and security of the entire system. In addition, the learning unit can continuously improve the accuracy and effectiveness of its learning algorithms based on user feedback. This enables the learning unit to always provide highly accurate learning based on the latest information, supporting quick and appropriate responses.

[0060] The Procedure Assistance Department handles the necessary applications for returning to work based on information learned by the Learning Department. Specifically, the Procedure Assistance Department automatically creates and submits the necessary return-to-work notification form. For example, it automatically updates the content of the return-to-work notification form based on organizational and operational changes learned by the Learning Department, ensuring that the latest information is reflected. The Procedure Assistance Department can also handle the submission of health check results required for returning to work. For example, it automatically obtains health check results, creates the necessary documents, and submits them. Furthermore, the Procedure Assistance Department can also handle the procedures for regaining necessary permissions upon returning to work. For example, it automatically regains access rights to systems and tools required by the returning employee, enabling them to smoothly resume work. The Procedure Assistance Department can perform these procedures quickly and accurately by utilizing AI automation technology. For example, it learns procedural patterns based on past procedural data and automatically generates the optimal procedural flow. This allows the Procedure Assistance Department to efficiently handle return-to-work procedures and reduce the burden on returning employees. In addition, the Procedure Assistance Department can customize the content and order of procedures according to user settings. For example, by pre-setting the priority and order of procedures desired by the user, a more personalized procedure can be provided. This allows the procedural support department to respond flexibly to the needs of those returning to work, creating an environment where they can focus on their return to work with peace of mind. Furthermore, the procedural support department can monitor the progress of the procedures in real time and notify the returning employee as needed. This allows the returning employee to understand the status of the procedures and proceed with their return to work preparations with confidence.

[0061] The proxy response unit can interject with phrases like "That's a good idea!" during a meeting. For example, the proxy response unit can interject with "That's a good idea!" during a meeting. The proxy response unit can also interject with phrases like "Exactly!" during a meeting. For example, the proxy response unit can interject with phrases like "I see, I understand." This makes it appear as if the person on leave is participating in the meeting by providing appropriate interjections. Some or all of the above processing in the proxy response unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proxy response unit can input the content of the meeting into a generative AI and have the generative AI execute appropriate interjections.

[0062] The learning unit can automatically learn about changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails. For example, the learning unit can analyze meeting records to learn about organizational changes. The learning unit can also analyze the content of team chats to learn about changes in operations. The learning unit can also analyze the content of internal announcement pages and notification emails to learn about changes in systems. This allows returning employees to stay informed of the latest information by automatically learning about changes in the organization, systems, and operations. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input meeting records and team chat content into a generative AI to allow the generative AI to learn about changes in the organization, systems, and operations.

[0063] The procedural assistance department can handle the necessary applications upon returning to work. For example, the procedural assistance department can automatically create and submit the return-to-work notification form required upon returning to work. The procedural assistance department can also handle the submission of the necessary health check results upon returning to work. The procedural assistance department can also handle the procedures for reacquiring necessary authority upon returning to work. By handling the necessary applications upon returning to work, the returning employee can smoothly resume their duties. Some or all of the above processes in the procedural assistance department may be performed using, for example, a generation AI, or without a generation AI. For example, the procedural assistance department can input the necessary application details into a generation AI and have the generation AI execute the application procedures.

[0064] The proxy response unit can estimate the user's emotions and adjust the content and timing of its responses based on the estimated emotions. For example, if the user is excited, the AI ​​might respond with a positive response such as, "That's wonderful!" If the user is depressed, the AI ​​might respond with a calm response such as, "I see, I understand." If the user is tired, the AI ​​might respond with a caring response such as, "Shall we take a short break?" By adjusting the content and timing of responses according to the user's emotions, more natural communication becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the proxy response unit may be performed using a generative AI, or not using a generative AI. For example, the proxy response unit can input user emotion data into a generating AI and have the generating AI adjust the content and timing of responses.

[0065] The proxy response unit can analyze the progress of a meeting in real time and interject with appropriate responses at the right time. For example, when the meeting is lively, the AI ​​can interject with "That's right!". The proxy response unit can also interject with "Shall we move on to the next topic?" when the meeting is stalled. The proxy response unit can also interject with "Let's wrap things up" when the meeting is nearing its end. By interjecting at the appropriate time according to the progress of the meeting, the proxy response unit helps to keep the flow of the meeting smooth. Some or all of the above processing in the proxy response unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the proxy response unit can input meeting progress data into a generative AI and cause the generative AI to perform appropriate interjections at the right time.

[0066] The proxy response unit can analyze the content of team members' statements and apply different patterns of acknowledgments to each speaker. For example, if the speaker is a superior, the AI ​​might respond with a respectful acknowledgment such as "That's impressive!" If the speaker is a colleague, the AI ​​might respond with a friendly acknowledgment such as "That's a great idea!" If the speaker is a subordinate, the AI ​​might respond with an encouraging acknowledgment such as "Keep up the good work!" By applying different acknowledgment patterns to each speaker, more appropriate communication becomes possible. Some or all of the above processing in the proxy response unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proxy response unit can input the content of the statements into a generative AI and have the generative AI execute different acknowledgment patterns for each speaker.

[0067] The proxy response unit can estimate the user's emotions and adjust the tone and expression of its responses based on the estimated emotions. For example, if the user is happy, the AI ​​might respond with a cheerful tone saying, "That's wonderful!" If the user is sad, the AI ​​might respond with a calm tone saying, "That must have been tough." If the user is angry, the AI ​​might respond with a calm tone saying, "I understand." By adjusting the tone and expression of responses according to the user's emotions, more natural communication becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the proxy response unit may be performed using a generative AI, for example, or without a generative AI. For example, the proxy response unit can input user emotion data into the generating AI and have the generating AI adjust the tone and expression of the responses.

[0068] The proxy response unit can customize the content of its responses according to the type and purpose of the meeting. For example, in a brainstorming meeting, the AI ​​might respond with "That's an interesting idea!" In a project progress meeting, the AI ​​might respond with "That's going well!" In a problem-solving meeting, the AI ​​might respond with "That solution sounds good!" By customizing the content of responses according to the type and purpose of the meeting, more appropriate communication becomes possible. Some or all of the above processing in the proxy response unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the proxy response unit can input data about the type and purpose of the meeting into the generative AI and have the generative AI customize the content of the responses.

[0069] The proxy response unit can handle not only team chat but also email and other communication tools. For example, in email exchanges, the proxy response unit's AI can respond with "Thank you for your confirmation." For example, in exchanges using project management tools, the proxy response unit's AI can respond with "I have checked the progress." For example, in exchanges using internal social networking services, the proxy response unit's AI can respond with "I agree with that opinion." This enables broader communication by supporting not only team chat but also email and other communication tools. Some or all of the above processing in the proxy response unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the proxy response unit can input data from emails or other communication tools into a generative AI and have the generative AI execute appropriate responses.

[0070] The learning unit can estimate the user's emotions and determine the priority of learning content based on the estimated user emotions. For example, if the user is feeling anxious, the learning unit may prioritize learning about important institutional changes. If the user is excited, the learning unit may also prioritize learning about information on new projects. If the user is relaxed, the learning unit may also learn about overall business changes in a balanced way. This allows for prioritizing learning content according to the user's emotions, enabling the learning of more important information. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the learning unit may be performed using or without a generative AI. For example, the learning unit can input user emotion data into a generative AI and have the generative AI determine the priority of learning content.

[0071] The learning unit can regularly update its learning content to maintain up-to-date information. For example, the learning unit can have its AI learn the latest meeting records through weekly updates. The learning unit can also have its AI learn the latest policy changes through monthly updates. The learning unit can also have its AI learn the latest team chat content through daily updates. This ensures that the learning content is always up-to-date by regularly updating it. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input regularly collected data into a generative AI to allow the generative AI to learn the latest information.

[0072] The learning unit can organize the learned information by category, making it easily accessible to returning employees. For example, the learning unit can categorize information related to organizational changes, making it easily accessible to returning employees. The learning unit can also categorize information related to system changes, making it easily accessible to returning employees. The learning unit can also categorize information related to changes in work processes, making it easily accessible to returning employees. By organizing the learned information by category, it becomes easily accessible to returning employees. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input the learned information into a generative AI and have the generative AI perform the process of organizing it by category.

[0073] The learning unit can estimate the user's emotions and adjust the display method of the learning content based on the estimated user emotions. For example, if the user is nervous, the learning unit can provide a simple and highly visible display method using AI. If the user is relaxed, the learning unit can also provide a display method that includes detailed information. If the user is in a hurry, the learning unit can also provide a display method that gets straight to the point. By adjusting the display method of the learning content according to the user's emotions, it becomes possible to provide more appropriate information. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the learning unit may be performed using a generative AI, or not using a generative AI. For example, the learning unit can input user emotion data into a generative AI and have the generative AI adjust the display method of the learning content.

[0074] The learning unit can make the learned content applicable to other departments and projects. For example, the learning unit can learn from meeting records of other departments and provide them to returning employees. The learning unit can also learn from the progress of other projects and provide them to returning employees. The learning unit can also learn from system changes in other departments and provide them to returning employees. This allows for broader information provision by making the learned content applicable to other departments and projects. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input data from other departments and projects into a generative AI and have the generative AI execute the application of the learned content.

[0075] The learning unit can also provide learning content in audio and video formats. For example, the learning unit can provide meeting records in audio format to make them easier for returning employees to understand. For example, the learning unit can provide information on system changes in video format to make it easier for returning employees to understand visually. For example, the learning unit can provide information on work changes in audio format so that returning employees can learn even while on the go. By providing learning content in audio and video formats, returning employees can acquire information in a wider variety of ways. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input learning content into a generative AI and have the generative AI provide it in audio and video formats.

[0076] The procedural assistance unit can estimate the user's emotions and determine the priority of procedures based on the estimated emotions. For example, if the user is feeling anxious, the AI ​​in the procedural assistance unit will prioritize important procedures. If the user is relaxed, the AI ​​in the procedural assistance unit can perform procedures in a balanced manner. If the user is in a hurry, the AI ​​in the procedural assistance unit can perform procedures quickly. This allows for prioritizing more important procedures by determining the priority of procedures according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the procedural assistance unit may be performed using a generative AI, or not. For example, the procedural assistance unit can input user emotion data into a generative AI and have the generative AI determine the priority of procedures.

[0077] The procedure management unit can track the progress of procedures in real time and provide notifications as needed. For example, the procedure management unit can track the progress of procedures in real time and notify the user. The procedure management unit can also notify the user when a procedure is completed. The procedure management unit can also notify the user when a problem occurs in a procedure. This allows the user to understand the progress of the procedure by tracking its progress in real time and providing notifications as needed. Some or all of the above processing in the procedure management unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the procedure management unit can input procedure progress data into a generating AI and have the generating AI execute notifications.

[0078] The procedural assistance unit can automatically collect and submit the necessary documents and information for the procedure. For example, the procedural assistance unit can automatically collect and submit the necessary documents. The procedural assistance unit can also automatically collect and submit the necessary information. The procedural assistance unit can also automatically collect and submit the necessary documents and information. This reduces the burden on the user by automatically collecting and submitting the necessary documents and information for the procedure. Some or all of the above processing in the procedural assistance unit may be performed using, for example, a generation AI, or without a generation AI. For example, the procedural assistance unit can input the necessary documents and information into a generation AI and have the generation AI perform the collection and submission.

[0079] The procedure assistance unit can estimate the user's emotions and adjust the procedure based on the estimated emotions. For example, if the user is feeling anxious, the procedure assistance unit's AI can carefully explain the procedure. If the user is relaxed, the procedure assistance unit's AI can also explain the procedure concisely. If the user is in a hurry, the procedure assistance unit's AI can also explain the procedure quickly. This allows for more appropriate procedures by adjusting the procedure according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the procedure assistance unit may be performed using a generative AI, or not. For example, the procedure assistance unit can input user emotion data into a generative AI and have the generative AI adjust the procedure.

[0080] The procedure outsourcing unit can provide not only the outsourcing of procedures but also the function of visualizing the progress of those procedures. For example, the procedure outsourcing unit can display the progress of procedures in a graph so that users can see it at a glance. For example, the procedure outsourcing unit can also display the progress of procedures in a list so that users can see it in detail. For example, the procedure outsourcing unit can display the progress of procedures in a calendar so that users can keep track of the schedule. In this way, by visualizing the progress of procedures, users can grasp the progress of the procedures at a glance. Some or all of the above processing in the procedure outsourcing unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the procedure outsourcing unit can input the progress of procedures data into a generation AI and have the generation AI perform the visualization.

[0081] The procedural outsourcing unit can apply its procedural outsourcing capabilities to other business processes. For example, the procedural outsourcing unit can perform procedures in other business processes, thereby reducing the user's burden. The procedural outsourcing unit can also track the progress of other business processes and notify the user. The procedural outsourcing unit can also automatically collect and submit documents and information from other business processes. This further reduces the user's burden by making procedural outsourcing applicable to other business processes. Some or all of the above-described processes in the procedural outsourcing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the procedural outsourcing unit can input data from other business processes into a generative AI and have the generative AI perform the procedural outsourcing.

[0082] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0083] The AI ​​agent system can also include an emotion adjustment unit that estimates the user's emotions and adjusts the content of communication based on those estimated emotions. For example, if the user is feeling stressed, the emotion adjustment unit can send an encouraging message to help the AI ​​relax. For example, if the user is happy, the emotion adjustment unit can send a message that shares that happiness. For example, if the user is feeling anxious, the emotion adjustment unit can send a reassuring message. This enables communication that is tailored to the user's emotions, providing more natural and effective support.

[0084] The AI ​​agent system can also include a schedule management unit that manages the user's schedule and reminds them of important appointments. For example, the schedule management unit could send a reminder the day before a meeting. It could also send a reminder a week before an important deadline. Furthermore, it could send a reminder the day before a vacation. This ensures that users don't forget important appointments.

[0085] The AI ​​agent system can also include a health management unit that monitors the user's health status and provides health advice as needed. For example, if the user's stress level is high, the health management unit can provide advice on how to relax. For example, if the user is not getting enough sleep, the health management unit can provide advice on how to improve sleep. For example, if the health management unit detects that the user is not getting enough exercise, it can provide advice to encourage exercise. This helps maintain the user's health status and improve work efficiency.

[0086] The AI ​​agent system can also include a learning management unit that manages the user's learning progress and customizes the learning content. For example, the learning management unit tracks the user's progress in acquiring specific skills. It can also provide additional learning resources for areas where the user struggles. Furthermore, it can offer rewards when the user achieves their goals. This can improve the user's learning efficiency and support skill acquisition.

[0087] The AI ​​agent system can further estimate the user's emotions and adjust the difficulty level of the learning content based on those emotions. For example, if the user is tired, the AI ​​will provide easy content. If the user is focused, the AI ​​can provide more difficult content. If the user is relaxed, the AI ​​can provide balanced content. This allows for adjustment of learning content according to the user's emotions, resulting in more effective learning.

[0088] The AI ​​agent system can also be equipped with a task management unit to further improve the user's work efficiency. For example, the task management unit can organize the user's tasks based on priority. It can also track the progress of the user's tasks and send reminders. Furthermore, it can report on the completion status of the user's tasks. This allows the user to manage tasks efficiently and proceed with their work smoothly.

[0089] The AI ​​agent system can further estimate the user's emotions and adjust task priorities based on those emotions. For example, if the user is stressed, the task management unit will prioritize important tasks. If the user is relaxed, the task management unit can also distribute tasks evenly. If the user is in a hurry, the task management unit can process tasks quickly. This allows for task prioritization based on the user's emotions, resulting in efficient task management.

[0090] The AI ​​agent system can also be equipped with a communication style learning unit that learns the user's communication style and provides appropriate communication methods. For example, the communication style learning unit learns the user's preferred communication method and sends messages in an appropriate way. If the user prefers email, the AI ​​can send messages via email. Similarly, if the user prefers chat, the AI ​​can send messages via chat. This enables communication in a way that is appropriate to the user's communication style.

[0091] The AI ​​agent system can further estimate the user's emotions and adjust the frequency of communication based on those emotions. For example, if the user is stressed, the AI ​​will reduce the frequency of communication. Conversely, if the user is relaxed, the AI ​​can increase the frequency of communication. If the user is busy, the AI ​​can send only important messages. This allows for adjustment of communication frequency according to the user's emotions, resulting in more effective communication.

[0092] The AI ​​agent system can also include a performance analysis unit that analyzes users' work performance and proposes improvements. For example, the performance analysis unit can periodically analyze users' work performance and suggest areas for improvement. It can also provide specific advice to improve users' work efficiency. Furthermore, it can compare users' work performance with other members and suggest best practices. This improves users' work performance and enables more effective work execution.

[0093] The following briefly describes the processing flow for example form 2.

[0094] Step 1: The proxy response team participates in team chats and meetings on behalf of the employee on leave, offering simple interjections. For example, during a meeting, they might say things like, "That's great!", "Yes," "Right," "I understand," "I see," "That's right," or "Got it," making it appear as if the employee on leave is participating. Step 2: The learning unit automatically learns about changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails. For example, it can analyze meeting records to learn about organizational changes. It can also analyze team chat content to learn about changes in operations. It can also analyze the content of internal announcement pages and notification emails to learn about changes in systems. Step 3: The procedural support department will handle the necessary applications for returning to work based on the information learned by the learning department. For example, it will automatically create and submit the return-to-work notification form required upon returning to work. It can also handle the submission of health examination results required upon returning to work. It can also handle the procedures for reacquiring necessary authority upon returning to work.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] Each of the multiple elements described above, including the proxy response unit, learning unit, and procedural proxy unit, is implemented, for example, in at least one of the smart device 14 and the data processing device 12. For example, the proxy response unit is implemented by the control unit 46A of the smart device 14, and can make it appear as if an employee on leave is participating in a meeting by interjecting with comments such as "That's great!" during the meeting. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes meeting records and team chat content to learn about changes in the organization and operations. The procedural proxy unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and automatically creates and submits the application required when returning to work. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0099] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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).

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] Each of the multiple elements described above, including the proxy response unit, learning unit, and procedural proxy unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the proxy response unit is implemented by the control unit 46A of the smart glasses 214, and can make it appear as if an employee on leave is participating in a meeting by interjecting with phrases like "That's great!" during the meeting. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, and analyzes meeting records and team chat content to learn about changes in the organization and operations. The procedural proxy unit is implemented by the specific processing unit 290 of the data processing unit 12, and automatically creates and submits the application required upon returning to work. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0115] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] Each of the multiple elements described above, including the proxy response unit, learning unit, and procedural proxy unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing unit 12. For example, the proxy response unit is implemented by the control unit 46A of the headset terminal 314, and can make it appear as if an employee on leave is participating in a meeting by interjecting with phrases like "That's great!" during the meeting. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and analyzes meeting records and team chat content to learn about changes in the organization and operations. The procedural proxy unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and automatically creates and submits the application required upon returning to work. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0131] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] Each of the multiple elements described above, including the proxy response unit, learning unit, and procedural proxy unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the proxy response unit is implemented by the control unit 46A of the robot 414, and can make it appear as if an employee on leave is participating in a meeting by interjecting with phrases like "That's great!" The learning unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and analyzes meeting records and team chat content to learn about changes in the organization and operations. The procedural proxy unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and automatically creates and submits the application required upon returning to work. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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."

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] (Note 1) A proxy response unit that participates in team chats and meetings on behalf of employees on leave, and provides simple responses, The learning unit automatically learns about changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails. The system includes a procedural assistance unit that handles the necessary applications upon returning to work based on the information learned by the aforementioned learning unit. A system characterized by the following features. (Note 2) The aforementioned proxy response unit is During a meeting, interject with phrases like, "That's a great idea!" The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned learning unit, It automatically learns about changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned procedural agency department, We will handle the necessary applications for returning to work. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned proxy response unit is It estimates the user's emotions and adjusts the content and timing of responses based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned proxy response unit is Analyze the progress of the meeting in real time and interject with appropriate responses at the right moments. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned proxy response unit is Analyze what team members say and apply different patterns of responses to each speaker. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned proxy response unit is It estimates the user's emotions and adjusts the tone and expression of responses based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned proxy response unit is Customize the content of your responses according to the type and purpose of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned proxy response unit is It supports not only team chat but also email and other communication tools. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning unit, It estimates the user's emotions and determines the priority of learning content based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned learning unit, We regularly update the learning materials to keep the information up-to-date. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned learning unit, The learned information is organized by category, making it easily accessible to those returning to work. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned learning unit, It estimates the user's emotions and adjusts how the learning content is displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned learning unit, To enable the application of learned content to other departments and projects. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned learning unit, Learning content is also provided in audio and video formats. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned procedural agency department, The system estimates the user's emotions and determines the priority of procedures based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned procedural agency department, Track the progress of the procedure in real time and notify as needed. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned procedural agency department, Automatically collects and submits the necessary documents and information for the procedure. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned procedural agency department, It estimates the user's emotions and adjusts the procedure based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned procedural agency department, In addition to handling the procedures on your behalf, we also provide a function to visualize the progress of those procedures. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned procedural agency department, To enable the application of procedural outsourcing to other business processes. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0167] 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 proxy response unit that participates in team chats and meetings on behalf of employees on leave, and provides simple responses, The learning unit automatically learns about changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails. The system includes a procedural assistance unit that handles the necessary applications upon returning to work based on the information learned by the aforementioned learning unit. A system characterized by the following features.

2. The aforementioned proxy response unit is Nodding in agreement during a meeting The system according to feature 1.

3. The aforementioned learning unit, It automatically learns about changes in the organization, systems, and operations from meeting records, team chats, internal announcement pages, and notification emails. The system according to feature 1.

4. The aforementioned procedural agency department, We will handle the necessary applications for returning to work. The system according to feature 1.

5. The aforementioned proxy response unit is It estimates the user's emotions and adjusts the content and timing of responses based on the estimated emotions. The system according to feature 1.

6. The aforementioned proxy response unit is Analyze the progress of the meeting in real time and interject with appropriate responses at the right moments. The system according to feature 1.

7. The aforementioned proxy response unit is Analyze what team members say and apply different patterns of responses to each speaker. The system according to feature 1.

8. The aforementioned proxy response unit is It estimates the user's emotions and adjusts the tone and expression of responses based on the estimated emotions. The system according to feature 1.

9. The aforementioned proxy response unit is Customize the content of your responses according to the type and purpose of the meeting. The system according to feature 1.

10. The aforementioned proxy response unit is It supports not only team chat but also email and other communication tools. The system according to feature 1.

Images