system

Abstract

The system according to this embodiment aims to save time on approval processes by utilizing an AI agent that simulates comments and judgments from a supervisor. [Solution] The system according to the embodiment comprises a reception unit, a judgment unit, a tracing unit, and a confirmation unit. The reception unit receives a simple questionnaire from the user in advance. The judgment unit determines the characteristics of the supervisor based on the information received by the reception unit. The tracing unit traces the feedback that the supervisor is likely to give based on the characteristics of the supervisor determined by the judgment unit. The confirmation unit submits meeting minutes and receives confirmation and additional comments from the supervisor.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there was a problem that productivity was low because superiors and officers in charge were busy and consultations and approvals took a long time.

[0005] The system according to the embodiment aims to save the time required for approval by utilizing an AI agent that assumes comments and judgments of superiors.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a judgment unit, a tracing unit, and a confirmation unit. The reception unit receives a short questionnaire from the user in advance. The judgment unit determines the characteristics of the supervisor based on the information received by the reception unit. The tracing unit traces the type of feedback the supervisor is likely to give based on the supervisor's characteristics determined by the judgment unit. The confirmation unit submits meeting minutes and receives confirmation and additional comments from the supervisor. [Effects of the Invention]

[0007] The system according to this embodiment can save time on approval processes by utilizing an AI agent that anticipates comments and judgments from supervisors. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The approval support system according to an embodiment of the present invention is a system for improving the low productivity related to approvals within a company, such as when supervisors or executives are too busy to find time for consultation meetings, or when time is finally available but a series of harsh criticisms lead to starting over. In this approval support system, the user answers a simple questionnaire in advance, and an AI agent determines the characteristics of the supervisor from a vast amount of statistical data and traces the type of feedback the supervisor is likely to give. Furthermore, by submitting meeting minutes and receiving confirmation and additional comments from the supervisor, the accuracy of the tracing can be improved. This mechanism can save time spent on approvals and improve productivity. For example, the user answers a simple questionnaire in advance. This questionnaire includes questions about the characteristics of the supervisor and past feedback. For example, questions such as "What kind of feedback does your supervisor usually give?" or "What kind of criticisms have you received in past meetings?" are included. This information is input into the AI ​​agent. Next, the AI ​​agent determines the characteristics of the supervisor from a vast amount of statistical data. The AI ​​agent analyzes past meeting minutes and feedback data and traces the type of feedback the supervisor is likely to give. For example, the AI ​​agent learns patterns of feedback given by a supervisor in the past and predicts what kind of feedback will be given in similar situations. Furthermore, it submits meeting minutes and receives confirmation and additional comments from the supervisor. After a user has a meeting with the AI ​​agent, they submit the minutes to their supervisor. The supervisor reviews the minutes and provides confirmation and additional comments. This improves the accuracy of the AI ​​agent's tracing, allowing it to provide more accurate feedback in subsequent meetings. This system saves time spent on approval and improves productivity. Users can reduce wasted time because they can receive feedback in advance through meetings with the AI ​​agent, even when their supervisor is busy. Supervisors also save time because they only need to confirm the minutes. For example, when a user proposes a new project, they can improve the proposal by having a meeting with the AI ​​agent beforehand and receiving feedback that their supervisor is likely to give.This reduces the time spent in meetings with supervisors and allows for more efficient approval. The approval support system enables users to anticipate supervisor feedback in advance, saving time on the approval process.

[0029] The approval support system according to this embodiment comprises a reception unit, a judgment unit, a tracing unit, and a confirmation unit. The reception unit receives a simple questionnaire from the user in advance. By having the user answer a simple questionnaire in advance, the reception unit collects information such as the characteristics of the user's supervisor and information about past feedback. For example, the reception unit provides a questionnaire that includes questions such as "What kind of feedback does your supervisor usually give?" and "What kind of feedback did you receive in past meetings?" The judgment unit determines the characteristics of the supervisor based on the information received by the reception unit. For example, the judgment unit determines the characteristics of the supervisor from a large amount of statistical data. For example, the judgment unit analyzes past meeting minutes and feedback data to predict the type of feedback the supervisor is likely to give. The tracing unit traces the type of feedback the supervisor is likely to give based on the characteristics of the supervisor determined by the judgment unit. For example, the tracing unit analyzes past meeting minutes and feedback data to trace the type of feedback the supervisor is likely to give. For example, the tracing unit learns the patterns of feedback the supervisor has given in the past and predicts what kind of feedback will be given in similar situations. The confirmation unit submits the meeting minutes and receives confirmation and additional comments from the supervisor. The confirmation unit, for example, submits meeting minutes to a supervisor after a user has a meeting with an AI agent. The supervisor reviews the minutes and provides confirmation or additional comments. This allows the confirmation unit to improve the accuracy of the AI ​​agent's tracing. As a result, the approval support system according to this embodiment allows the user to anticipate the supervisor's feedback in advance and save time on the approval process.

[0030] The reception department requires users to complete a short questionnaire beforehand. By having users complete this questionnaire, the reception department can collect information such as the characteristics of the user's supervisor and past feedback. Specifically, the questionnaire includes questions such as "What kind of feedback does your supervisor usually give?" and "What kind of feedback did you receive in past meetings?" This allows the reception department to understand the user's supervisor's feedback style and past behavioral patterns. Furthermore, the questionnaire responses are stored in a database within the system and used for subsequent processing. The questionnaire content includes a wide range of information, such as the user's job responsibilities, relationship with their supervisor, and specific details of past feedback. This allows the reception department to gain a detailed understanding of the user's situation and the characteristics of their supervisor, and provide accurate information to the decision-making and tracing departments. In addition, the questionnaire responses are updated regularly to reflect the latest information. For example, the questionnaire content can be updated in response to changes in circumstances, such as when a user joins a new project or their supervisor changes. This allows the reception department to always make decisions based on the latest information. Furthermore, the questionnaire responses are anonymized within the system, and the system is designed to protect privacy. This allows users to answer surveys with confidence.

[0031] The judgment unit determines the characteristics of the supervisor based on the information received by the reception unit. For example, the judgment unit determines the supervisor's characteristics from a vast amount of statistical data. Specifically, it analyzes past meeting minutes and feedback data to predict the type of feedback the supervisor is likely to give. The judgment unit uses AI to analyze this data and extract the supervisor's feedback patterns and behavioral characteristics. For example, it analyzes what kind of feedback the supervisor has given in the past and in what situations to predict feedback in similar situations. The AI ​​uses natural language processing technology to analyze meeting minutes and feedback data and extract the supervisor's statements, tone, and frequently occurring keywords. This allows the judgment unit to understand the supervisor's feedback style and behavioral patterns in detail. Furthermore, the judgment unit utilizes not only past data but also data collected in real time. For example, if a user receives new feedback, that information can be immediately reflected in the system and the supervisor's characteristics updated. This allows the judgment unit to always make decisions based on the latest information. In addition, the judgment unit can analyze the characteristics of multiple supervisors simultaneously and handle cases where a user receives feedback from multiple supervisors. This allows the judgment unit to respond flexibly according to the user's situation.

[0032] The tracing unit traces the type of feedback a supervisor is likely to give, based on the supervisor's characteristics identified by the judgment unit. Specifically, it analyzes past meeting minutes and feedback data to trace the type of feedback a supervisor is likely to give. The tracing unit uses AI to analyze this data and learn patterns of feedback the supervisor has given in the past. For example, it analyzes what kind of feedback a supervisor gave in a specific situation and predicts the type of feedback to give in a similar situation. The AI ​​uses machine learning algorithms to extract feedback patterns from past data and applies them to new situations. This allows the tracing unit to predict the type of feedback a supervisor is likely to give with high accuracy. Furthermore, the tracing unit continuously updates the feedback prediction results based on data collected in real time. For example, if a user receives new feedback, that information can be immediately reflected in the system and the feedback prediction results updated. This allows the tracing unit to always provide highly accurate feedback predictions based on the latest information. The tracing unit also analyzes the user's reactions and actions to feedback, and can predict how the supervisor's feedback will be received. This allows the tracing unit to provide optimal feedback to the user and facilitate smooth communication with their supervisor.

[0033] The confirmation unit submits meeting minutes and receives confirmation and additional comments from supervisors. Specifically, after a user has a meeting with an AI agent, they submit the minutes to their supervisor. The supervisor reviews the minutes and provides confirmation and additional comments. This allows the confirmation unit to improve the accuracy of the AI ​​agent's tracing. For example, if a supervisor provides specific feedback or corrections to the minutes, this information can be reflected in the system and used to predict future feedback. The confirmation unit automatically analyzes the content of the minutes and extracts the supervisor's feedback and comments. The AI ​​uses natural language processing technology to analyze the content of the minutes and extract the supervisor's statements, tone, and frequently occurring keywords. This allows the confirmation unit to understand the supervisor's feedback style and behavioral patterns in detail. Furthermore, the confirmation unit continuously improves the AI ​​agent's tracing algorithm based on the feedback and comments from supervisors. For example, it analyzes what kind of feedback a supervisor gave in a particular situation and adjusts the algorithm to predict feedback in similar situations. This allows the confirmation unit to improve the tracing accuracy of the AI ​​agent and provide users with more accurate feedback predictions. Furthermore, based on feedback and comments from supervisors, the confirmation unit can analyze user behavior and reactions and provide advice to facilitate smoother communication with supervisors. This enables the confirmation unit to improve communication between users and supervisors and streamline the approval process.

[0034] The judgment unit can determine the characteristics of a supervisor from a vast amount of statistical data. For example, the judgment unit accurately determines the characteristics of a supervisor using a vast amount of statistical data. For example, the judgment unit analyzes past meeting minutes and feedback data to predict the type of feedback a supervisor is likely to give. In this way, by using a vast amount of statistical data, the characteristics of a supervisor can be accurately determined. Statistical data includes, but is not limited to, past meeting minutes, feedback data, the supervisor's communication style, and the frequency of feedback. Some or all of the above processing in the judgment unit may be performed using AI, for example, or not using AI. For example, the judgment unit can input a vast amount of statistical data into a generating AI and have the generating AI perform the determination of the supervisor's characteristics.

[0035] The tracing unit can analyze past meeting minutes and feedback data to trace the type of feedback a supervisor is likely to give. For example, the tracing unit can learn patterns of feedback a supervisor has given in the past and predict what kind of feedback they will give in similar situations. This allows for accurate tracing of a supervisor's feedback by analyzing past data. Meeting minutes and feedback data include, but are not limited to, the content of past meetings, the content of the supervisor's feedback, and the supervisor's communication style. Some or all of the processing described above in the tracing unit may be performed using AI, for example, or not. For example, the tracing unit can input past meeting minutes and feedback data into a generating AI and have the generating AI perform the tracing of the type of feedback a supervisor is likely to give.

[0036] The confirmation unit can submit meeting minutes and receive confirmation and additional comments from supervisors. For example, after a user has a meeting with an AI agent, the confirmation unit submits the minutes to the supervisor. The supervisor reviews the minutes and provides confirmation and additional comments. This improves the accuracy of the AI ​​agent's tracing. By submitting meeting minutes and receiving feedback from supervisors, the accuracy of the tracing is improved. Confirmation and additional comments may include, but are not limited to, the content of the supervisor's feedback, the supervisor's communication style, and the supervisor's points of concern. Some or all of the above processes in the confirmation unit may be performed using AI, for example, or not using AI. For example, the confirmation unit can input the meeting minutes into a generating AI and have the generating AI perform tracing of the supervisor's feedback.

[0037] The reception desk can analyze a user's past survey response history and select the most appropriate questions. For example, the reception desk can automatically select relevant questions based on the user's past responses. For example, the reception desk can analyze a user's response patterns and suggest question formats that are easy to answer. The reception desk can also prioritize displaying questions related to specific topics from the user's past response history. This allows for the selection of the most appropriate questions by analyzing past response history. The most appropriate questions include, but are not limited to, the type of question, the selection method, and the relevance of the questions. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's past survey response history into a generating AI and have the generating AI select the most appropriate questions.

[0038] The reception desk can filter questions based on the user's current projects and areas of interest when they respond to a survey. For example, the reception desk may prioritize displaying questions related to the project the user is currently working on. For example, the reception desk may filter relevant questions based on the user's areas of interest. The reception desk may also select appropriate questions according to the progress of the user's project. This allows for the display of highly relevant questions by filtering questions based on the current project and areas of interest. Projects and areas of interest include, but are not limited to, the type of project, how the area of ​​interest was identified, and its progress. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk may input data on the user's current projects and areas of interest into a generating AI and have the generating AI perform the question filtering.

[0039] The reception desk can prioritize displaying questions that are highly relevant to the user's geographical location when they answer a survey. For example, if the user is in a specific region, the reception desk will prioritize displaying questions related to that region. For example, based on the user's location, the reception desk will display questions related to region-specific issues. If the user is on the move, the reception desk can also update questions related to their current location in real time. This allows for the display of highly relevant questions by considering geographical location. Geographical location information includes, but is not limited to, the method of obtaining location information, the criteria for selecting highly relevant questions, and region-specific issues. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's geographical location information into a generating AI and have the generating AI select highly relevant questions.

[0040] The reception desk can analyze a user's social media activity and present relevant questions when they respond to a survey. For example, the reception desk can analyze the content of a user's social media posts and present relevant questions. For example, the reception desk can display questions of interest based on the activity of the user's followers and friends. The reception desk can also analyze the user's social media trends and present questions on the latest topics. In this way, relevant questions can be presented by analyzing social media activity. Social media activity includes, but is not limited to, the type of activity, analysis algorithms, post content, the activity of followers and friends, and trends. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's social media activity data into a generating AI and have the generating AI perform the task of presenting relevant questions.

[0041] The decision-making unit can improve the accuracy of feature judgment by referring to the supervisor's past feedback history when making a decision. For example, the decision-making unit can analyze patterns of feedback the supervisor has given in the past and reflect them in the feature judgment. For example, the decision-making unit can adjust the feature judgment algorithm based on the supervisor's past feedback history. The decision-making unit can also prioritize the judgment of specific features from the supervisor's feedback history. This improves the accuracy of feature judgment by referring to past feedback history. Feedback history includes, but is not limited to, the content of past feedback, the frequency of feedback, and the pattern of feedback. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input the supervisor's past feedback history into a generating AI and have the generating AI perform the improvement of feature judgment accuracy.

[0042] The decision unit can apply different decision algorithms depending on the supervisor's position and job duties when making a decision. For example, the decision unit can select an appropriate feature judgment algorithm depending on the supervisor's position. For example, the decision unit can adjust the feature judgment algorithm based on the supervisor's job duties. The decision unit can also apply different feature judgment algorithms depending on the supervisor's position and job duties. This improves the accuracy of feature judgment by applying algorithms according to the position and job duties. Position and job duties include, but are not limited to, the type of position, the method of identifying job duties, and the scope of duties. Some or all of the above processing in the decision unit may be performed using AI, for example, or without using AI. For example, the decision unit can input data on the supervisor's position and job duties into a generating AI and have the generating AI execute the application of the decision algorithm.

[0043] The decision-making unit can perform feature determination while considering the geographical location of the supervisor's business. For example, the decision-making unit adjusts the feature determination algorithm based on the supervisor's business location. For example, the decision-making unit performs appropriate feature determination while considering the supervisor's geographical location of business. The decision-making unit can also apply different feature determination algorithms depending on the supervisor's business location. This improves the accuracy of feature determination by considering the geographical location of business. Geographical location of business includes, but is not limited to, the type of location, the method of consideration, and the scope of business. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input data on the supervisor's geographical location of business into a generating AI and have the generating AI perform feature determination.

[0044] The decision-making unit can improve the accuracy of its feature judgments by referring to the supervisor's relevant literature and work reports during the decision-making process. For example, the decision-making unit can refer to the supervisor's relevant literature and reflect it in its feature judgments. For example, the decision-making unit can adjust its feature judgment algorithm based on the supervisor's work reports. The decision-making unit can also prioritize the judgment of specific features from the supervisor's relevant literature and work reports. This improves the accuracy of feature judgments by referring to relevant literature and work reports. Relevant literature and work reports include, but are not limited to, the type of literature, the method of reference, the content of the work, and the content of the report. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or not using AI. For example, the decision-making unit can input data from the supervisor's relevant literature and work reports into a generating AI and have the generating AI perform the improvement of the accuracy of feature judgments.

[0045] The tracing unit can improve the accuracy of tracing by referring to the supervisor's past feedback patterns during the tracing process. For example, the tracing unit can analyze the patterns of feedback the supervisor has given in the past and reflect them in the tracing. For example, the tracing unit can adjust the tracing algorithm based on the supervisor's past feedback patterns. The tracing unit can also prioritize tracing specific feedback patterns from the supervisor's feedback patterns. This improves the accuracy of tracing by referring to past feedback patterns. Feedback patterns include, but are not limited to, the content of past feedback, the frequency of feedback, and the pattern of feedback. Some or all of the above processing in the tracing unit may be performed using AI, for example, or without AI. For example, the tracing unit can input the supervisor's past feedback patterns into a generating AI and have the generating AI perform the task of improving the accuracy of tracing.

[0046] The tracing unit can apply different tracing algorithms during tracing, depending on the supervisor's work content and project progress. For example, the tracing unit can select an appropriate tracing algorithm based on the supervisor's work content. For example, the tracing unit can adjust the tracing algorithm according to the supervisor's project progress. The tracing unit can also apply different tracing algorithms depending on the supervisor's work content and project progress. This allows for appropriate tracing according to the work content and project progress. Examples of work content and project progress include, but are not limited to, the type of work, the method of identifying progress, and the scope of the project. Some or all of the above processing in the tracing unit may be performed using AI, for example, or without AI. For example, the tracing unit can input data on the supervisor's work content and project progress into a generating AI and have the generating AI execute the application of the tracing algorithm.

[0047] The tracing unit can perform tracing while considering the geographical location of the supervisor's business. The tracing unit can adjust the tracing algorithm based on the supervisor's business location, for example. For example, the tracing unit can perform appropriate tracing by considering the supervisor's geographical location. The tracing unit can also apply different tracing algorithms depending on the supervisor's business location. This allows for appropriate tracing by considering the geographical location. Geographical location includes, but is not limited to, the type of location, the method of consideration, and the scope of work. Some or all of the above processing in the tracing unit may be performed using AI, for example, or without AI. For example, the tracing unit can input data on the supervisor's geographical location into a generating AI and have the generating AI perform the tracing.

[0048] The tracing unit can improve the accuracy of tracing by referring to the supervisor's relevant documents and work reports during the tracing process. For example, the tracing unit can refer to the supervisor's relevant documents and reflect them in the tracing. For example, the tracing unit can adjust the tracing algorithm based on the supervisor's work reports. The tracing unit can also prioritize tracing specific feedback from the supervisor's relevant documents and work reports. This improves the accuracy of tracing by referring to relevant documents and work reports. Relevant documents and work reports include, but are not limited to, the type of document, the method of reference, the work content, and the content of the report. Some or all of the above processing in the tracing unit may be performed using AI, for example, or not using AI. For example, the tracing unit can input data from the supervisor's relevant documents and work reports into a generating AI and have the generating AI perform the tracing accuracy improvement.

[0049] The confirmation unit can improve the accuracy of confirmation by referring to the supervisor's past confirmation history during confirmation. For example, the confirmation unit can analyze the patterns of confirmations made by the supervisor in the past and reflect them in the confirmation. For example, the confirmation unit can adjust the confirmation algorithm based on the supervisor's past confirmation history. The confirmation unit can also prioritize certain confirmations from the supervisor's confirmation history. This allows for improved confirmation accuracy by referring to past confirmation history. Confirmation history includes, but is not limited to, the content of past confirmations, the frequency of confirmations, and the patterns of confirmations. Some or all of the above processing in the confirmation unit may be performed using, for example, AI, or not using AI. For example, the confirmation unit can input the supervisor's past confirmation history into a generating AI and have the generating AI perform the correction of confirmation accuracy.

[0050] The ratification unit can apply different ratification algorithms depending on the supervisor's position and job duties during the ratification process. For example, the ratification unit can select an appropriate ratification algorithm based on the supervisor's position. For example, the ratification unit can adjust the ratification algorithm based on the supervisor's job duties. The ratification unit can also apply different ratification algorithms depending on the supervisor's position and job duties. This allows for improved ratification accuracy by applying algorithms according to the position and job duties. Position and job duties include, but are not limited to, the type of position, the method of identifying job duties, and the scope of duties. Some or all of the above-described processes in the ratification unit may be performed using AI, for example, or without AI. For example, the ratification unit can input data on the supervisor's position and job duties into a generating AI and have the generating AI execute the application of the ratification algorithm.

[0051] The ratification unit can perform ratification while considering the supervisor's geographical work location. The ratification unit can adjust the ratification algorithm based on the supervisor's work location, for example. For example, the ratification unit can perform appropriate ratification by considering the supervisor's geographical work location. The ratification unit can also apply different ratification algorithms depending on the supervisor's work location. This allows for appropriate ratification by considering the geographical work location. Geographical work location includes, but is not limited to, the type of location, the method of consideration, and the scope of work. Some or all of the above processing in the ratification unit may be performed using AI, for example, or without AI. For example, the ratification unit can input data on the supervisor's geographical work location into a generating AI and have the generating AI perform the ratification.

[0052] The confirmation unit can improve the accuracy of its confirmations by referring to the supervisor's relevant documents and work reports during the confirmation process. For example, the confirmation unit can refer to the supervisor's relevant documents and reflect them in the confirmation. For example, the confirmation unit can adjust the confirmation algorithm based on the supervisor's work reports. The confirmation unit can also prioritize certain confirmations based on the supervisor's relevant documents and work reports. This allows for improved accuracy of confirmations by referring to relevant documents and work reports. Relevant documents and work reports include, but are not limited to, the type of document, the method of reference, the work content, and the content of the report. Some or all of the above processing in the confirmation unit may be performed using AI, for example, or not using AI. For example, the confirmation unit can input data from the supervisor's relevant documents and work reports into a generating AI and have the generating AI perform the task of improving the accuracy of confirmations.

[0053] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0054] The reception desk can analyze a user's past survey response history and select the most appropriate questions. For example, it can automatically select relevant questions based on the user's past responses. It can also analyze the user's response patterns and suggest question formats that are easy to answer. It can also prioritize displaying questions related to specific topics based on the user's past response history. In this way, the most appropriate questions can be selected by analyzing past response history. The most appropriate questions include, but are not limited to, the type of question, the selection method, and the relevance of the questions. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the user's past survey response history into a generating AI and have the generating AI select the most appropriate questions.

[0055] The reception desk can filter questions based on the user's current projects and areas of interest when they respond to a survey. For example, it can prioritize displaying questions related to the project the user is currently working on. It can also filter relevant questions based on the user's areas of interest. It can even select appropriate questions according to the progress of the user's project. This allows for the display of highly relevant questions by filtering questions based on the user's current projects and areas of interest. Projects and areas of interest include, but are not limited to, the type of project, how the area of ​​interest was identified, and its progress. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input data on the user's current projects and areas of interest into a generating AI and have the generating AI perform the question filtering.

[0056] The decision-making unit can improve the accuracy of its feature judgments by referring to the supervisor's past feedback history when making a decision. For example, it can analyze patterns of feedback the supervisor has given in the past and reflect them in the feature judgments. It can adjust the feature judgment algorithm based on the supervisor's past feedback history. It can also prioritize the judgment of specific features from the supervisor's feedback history. In this way, the accuracy of feature judgments can be improved by referring to past feedback history. Feedback history includes, but is not limited to, the content of past feedback, the frequency of feedback, and the patterns of feedback. Some or all of the above processing in the decision-making unit may be performed using AI or not. For example, the decision-making unit can input the supervisor's past feedback history into a generating AI and have the generating AI perform the improvement of the feature judgment accuracy.

[0057] The tracing unit can improve the accuracy of tracing by referring to the supervisor's past feedback patterns during the tracing process. For example, it can analyze the patterns of feedback the supervisor has given in the past and reflect them in the tracing. The tracing algorithm can be adjusted based on the supervisor's past feedback patterns. It can also prioritize tracing specific feedback patterns from the supervisor's feedback patterns. This improves the accuracy of tracing by referring to past feedback patterns. Feedback patterns include, but are not limited to, the content of past feedback, the frequency of feedback, and the pattern of feedback. Some or all of the above processing in the tracing unit may be performed using AI or not. For example, the tracing unit can input the supervisor's past feedback patterns into a generating AI and have the generating AI perform the task of improving the accuracy of tracing.

[0058] The confirmation unit can improve the accuracy of confirmation by referring to the supervisor's past confirmation history. For example, it can analyze the patterns of confirmations the supervisor has made in the past and reflect them in the confirmation process. It can adjust the confirmation algorithm based on the supervisor's past confirmation history. It can also prioritize certain confirmations based on the supervisor's confirmation history. This allows for improved confirmation accuracy by referring to past confirmation history. Confirmation history includes, but is not limited to, the content of past confirmations, the frequency of confirmations, and the patterns of confirmations. Some or all of the above processing in the confirmation unit may be performed using AI or not. For example, the confirmation unit can input the supervisor's past confirmation history into a generating AI and have the generating AI perform the task of improving the accuracy of confirmations.

[0059] The ratification unit can apply different ratification algorithms depending on the supervisor's position and job duties during the ratification process. For example, it can select an appropriate ratification algorithm based on the supervisor's position. It can also adjust the ratification algorithm based on the supervisor's job duties. It can also apply different ratification algorithms depending on the supervisor's position and job duties. This allows for improved ratification accuracy by applying algorithms according to the supervisor's position and job duties. Position and job duties include, but are not limited to, the type of position, the method of identifying job duties, and the scope of duties. Some or all of the above-described processes in the ratification unit may be performed using AI or not. For example, the ratification unit can input data on the supervisor's position and job duties into a generating AI and have the generating AI execute the application of the ratification algorithm.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The reception desk has the user complete a short questionnaire in advance. By having the user complete a short questionnaire in advance, the reception desk can collect information such as the characteristics of the user's supervisor and past feedback. For example, the questionnaire may include questions such as "What kind of feedback does your supervisor usually give?" or "What kind of feedback have you received in past meetings?" Step 2: The judgment unit determines the characteristics of the supervisor based on the information received by the reception unit. For example, the judgment unit determines the characteristics of the supervisor from a vast amount of statistical data. It analyzes past meeting minutes and feedback data to predict the type of feedback the supervisor is likely to give. Step 3: The tracing unit traces the type of feedback the supervisor is likely to give, based on the supervisor's characteristics determined by the judgment unit. For example, the tracing unit analyzes past meeting minutes and feedback data to trace the type of feedback the supervisor is likely to give. It learns the patterns of feedback the supervisor has given in the past and predicts what kind of feedback they will give in similar situations. Step 4: The confirmation team submits the meeting minutes and receives confirmation and additional comments from their supervisor. After the user has a meeting with the AI ​​agent, they submit the meeting minutes to their supervisor. The supervisor reviews the minutes and provides confirmation and additional comments. This allows the confirmation team to improve the accuracy of the AI ​​agent's tracing.

[0062] (Example of form 2) The approval support system according to an embodiment of the present invention is a system for improving the low productivity related to approvals within a company, such as when supervisors or executives are too busy to find time for consultation meetings, or when time is finally available but a series of harsh criticisms lead to starting over. In this approval support system, the user answers a simple questionnaire in advance, and an AI agent determines the characteristics of the supervisor from a vast amount of statistical data and traces the type of feedback the supervisor is likely to give. Furthermore, by submitting meeting minutes and receiving confirmation and additional comments from the supervisor, the accuracy of the tracing can be improved. This mechanism can save time spent on approvals and improve productivity. For example, the user answers a simple questionnaire in advance. This questionnaire includes questions about the characteristics of the supervisor and past feedback. For example, questions such as "What kind of feedback does your supervisor usually give?" or "What kind of criticisms have you received in past meetings?" are included. This information is input into the AI ​​agent. Next, the AI ​​agent determines the characteristics of the supervisor from a vast amount of statistical data. The AI ​​agent analyzes past meeting minutes and feedback data and traces the type of feedback the supervisor is likely to give. For example, the AI ​​agent learns patterns of feedback given by a supervisor in the past and predicts what kind of feedback will be given in similar situations. Furthermore, it submits meeting minutes and receives confirmation and additional comments from the supervisor. After a user has a meeting with the AI ​​agent, they submit the minutes to their supervisor. The supervisor reviews the minutes and provides confirmation and additional comments. This improves the accuracy of the AI ​​agent's tracing, allowing it to provide more accurate feedback in subsequent meetings. This system saves time spent on approval and improves productivity. Users can reduce wasted time because they can receive feedback in advance through meetings with the AI ​​agent, even when their supervisor is busy. Supervisors also save time because they only need to confirm the minutes. For example, when a user proposes a new project, they can improve the proposal by having a meeting with the AI ​​agent beforehand and receiving feedback that their supervisor is likely to give.This reduces the time spent in meetings with supervisors and allows for more efficient approval. The approval support system enables users to anticipate supervisor feedback in advance, saving time on the approval process.

[0063] The approval support system according to this embodiment comprises a reception unit, a judgment unit, a tracing unit, and a confirmation unit. The reception unit receives a simple questionnaire from the user in advance. By having the user answer a simple questionnaire in advance, the reception unit collects information such as the characteristics of the user's supervisor and information about past feedback. For example, the reception unit provides a questionnaire that includes questions such as "What kind of feedback does your supervisor usually give?" and "What kind of feedback did you receive in past meetings?" The judgment unit determines the characteristics of the supervisor based on the information received by the reception unit. For example, the judgment unit determines the characteristics of the supervisor from a large amount of statistical data. For example, the judgment unit analyzes past meeting minutes and feedback data to predict the type of feedback the supervisor is likely to give. The tracing unit traces the type of feedback the supervisor is likely to give based on the characteristics of the supervisor determined by the judgment unit. For example, the tracing unit analyzes past meeting minutes and feedback data to trace the type of feedback the supervisor is likely to give. For example, the tracing unit learns the patterns of feedback the supervisor has given in the past and predicts what kind of feedback will be given in similar situations. The confirmation unit submits the meeting minutes and receives confirmation and additional comments from the supervisor. The confirmation unit, for example, submits meeting minutes to a supervisor after a user has a meeting with an AI agent. The supervisor reviews the minutes and provides confirmation or additional comments. This allows the confirmation unit to improve the accuracy of the AI ​​agent's tracing. As a result, the approval support system according to this embodiment allows the user to anticipate the supervisor's feedback in advance and save time on the approval process.

[0064] The reception department requires users to complete a short questionnaire beforehand. By having users complete this questionnaire, the reception department can collect information such as the characteristics of the user's supervisor and past feedback. Specifically, the questionnaire includes questions such as "What kind of feedback does your supervisor usually give?" and "What kind of feedback did you receive in past meetings?" This allows the reception department to understand the user's supervisor's feedback style and past behavioral patterns. Furthermore, the questionnaire responses are stored in a database within the system and used for subsequent processing. The questionnaire content includes a wide range of information, such as the user's job responsibilities, relationship with their supervisor, and specific details of past feedback. This allows the reception department to gain a detailed understanding of the user's situation and the characteristics of their supervisor, and provide accurate information to the decision-making and tracing departments. In addition, the questionnaire responses are updated regularly to reflect the latest information. For example, the questionnaire content can be updated in response to changes in circumstances, such as when a user joins a new project or their supervisor changes. This allows the reception department to always make decisions based on the latest information. Furthermore, the questionnaire responses are anonymized within the system, and the system is designed to protect privacy. This allows users to answer surveys with confidence.

[0065] The judgment unit determines the characteristics of the supervisor based on the information received by the reception unit. For example, the judgment unit determines the supervisor's characteristics from a vast amount of statistical data. Specifically, it analyzes past meeting minutes and feedback data to predict the type of feedback the supervisor is likely to give. The judgment unit uses AI to analyze this data and extract the supervisor's feedback patterns and behavioral characteristics. For example, it analyzes what kind of feedback the supervisor has given in the past and in what situations to predict feedback in similar situations. The AI ​​uses natural language processing technology to analyze meeting minutes and feedback data and extract the supervisor's statements, tone, and frequently occurring keywords. This allows the judgment unit to understand the supervisor's feedback style and behavioral patterns in detail. Furthermore, the judgment unit utilizes not only past data but also data collected in real time. For example, if a user receives new feedback, that information can be immediately reflected in the system and the supervisor's characteristics updated. This allows the judgment unit to always make decisions based on the latest information. In addition, the judgment unit can analyze the characteristics of multiple supervisors simultaneously and handle cases where a user receives feedback from multiple supervisors. This allows the judgment unit to respond flexibly according to the user's situation.

[0066] The tracing unit traces the type of feedback a supervisor is likely to give, based on the supervisor's characteristics identified by the judgment unit. Specifically, it analyzes past meeting minutes and feedback data to trace the type of feedback a supervisor is likely to give. The tracing unit uses AI to analyze this data and learn patterns of feedback the supervisor has given in the past. For example, it analyzes what kind of feedback a supervisor gave in a specific situation and predicts the type of feedback to give in a similar situation. The AI ​​uses machine learning algorithms to extract feedback patterns from past data and applies them to new situations. This allows the tracing unit to predict the type of feedback a supervisor is likely to give with high accuracy. Furthermore, the tracing unit continuously updates the feedback prediction results based on data collected in real time. For example, if a user receives new feedback, that information can be immediately reflected in the system and the feedback prediction results updated. This allows the tracing unit to always provide highly accurate feedback predictions based on the latest information. The tracing unit also analyzes the user's reactions and actions to feedback, and can predict how the supervisor's feedback will be received. This allows the tracing unit to provide optimal feedback to the user and facilitate smooth communication with their supervisor.

[0067] The confirmation unit submits meeting minutes and receives confirmation and additional comments from supervisors. Specifically, after a user has a meeting with an AI agent, they submit the minutes to their supervisor. The supervisor reviews the minutes and provides confirmation and additional comments. This allows the confirmation unit to improve the accuracy of the AI ​​agent's tracing. For example, if a supervisor provides specific feedback or corrections to the minutes, this information can be reflected in the system and used to predict future feedback. The confirmation unit automatically analyzes the content of the minutes and extracts the supervisor's feedback and comments. The AI ​​uses natural language processing technology to analyze the content of the minutes and extract the supervisor's statements, tone, and frequently occurring keywords. This allows the confirmation unit to understand the supervisor's feedback style and behavioral patterns in detail. Furthermore, the confirmation unit continuously improves the AI ​​agent's tracing algorithm based on the feedback and comments from supervisors. For example, it analyzes what kind of feedback a supervisor gave in a particular situation and adjusts the algorithm to predict feedback in similar situations. This allows the confirmation unit to improve the tracing accuracy of the AI ​​agent and provide users with more accurate feedback predictions. Furthermore, based on feedback and comments from supervisors, the confirmation unit can analyze user behavior and reactions and provide advice to facilitate smoother communication with supervisors. This enables the confirmation unit to improve communication between users and supervisors and streamline the approval process.

[0068] The judgment unit can determine the characteristics of a supervisor from a vast amount of statistical data. For example, the judgment unit accurately determines the characteristics of a supervisor using a vast amount of statistical data. For example, the judgment unit analyzes past meeting minutes and feedback data to predict the type of feedback a supervisor is likely to give. In this way, by using a vast amount of statistical data, the characteristics of a supervisor can be accurately determined. Statistical data includes, but is not limited to, past meeting minutes, feedback data, the supervisor's communication style, and the frequency of feedback. Some or all of the above processing in the judgment unit may be performed using AI, for example, or not using AI. For example, the judgment unit can input a vast amount of statistical data into a generating AI and have the generating AI perform the determination of the supervisor's characteristics.

[0069] The tracing unit can analyze past meeting minutes and feedback data to trace the type of feedback a supervisor is likely to give. For example, the tracing unit can learn patterns of feedback a supervisor has given in the past and predict what kind of feedback they will give in similar situations. This allows for accurate tracing of a supervisor's feedback by analyzing past data. Meeting minutes and feedback data include, but are not limited to, the content of past meetings, the content of the supervisor's feedback, and the supervisor's communication style. Some or all of the processing described above in the tracing unit may be performed using AI, for example, or not. For example, the tracing unit can input past meeting minutes and feedback data into a generating AI and have the generating AI perform the tracing of the type of feedback a supervisor is likely to give.

[0070] The confirmation unit can submit meeting minutes and receive confirmation and additional comments from supervisors. For example, after a user has a meeting with an AI agent, the confirmation unit submits the minutes to the supervisor. The supervisor reviews the minutes and provides confirmation and additional comments. This improves the accuracy of the AI ​​agent's tracing. By submitting meeting minutes and receiving feedback from supervisors, the accuracy of the tracing is improved. Confirmation and additional comments may include, but are not limited to, the content of the supervisor's feedback, the supervisor's communication style, and the supervisor's points of concern. Some or all of the above processes in the confirmation unit may be performed using AI, for example, or not using AI. For example, the confirmation unit can input the meeting minutes into a generating AI and have the generating AI perform tracing of the supervisor's feedback.

[0071] The reception desk can estimate the user's emotions and adjust the survey questions based on the estimated emotions. For example, if the user is stressed, the reception desk may simplify the questions and make them easier to answer. For example, if the user is relaxed, the reception desk may add more detailed questions to gather deeper information. If the user is in a hurry, the reception desk may also prioritize displaying important questions to allow for quick answers. This makes it easier to answer the survey by adjusting the questions according to the user's emotions. The estimation of the user's emotions 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 processing in the reception desk may be performed using AI or not. For example, the reception desk may input user emotion data into a generative AI and have the generative AI adjust the survey questions.

[0072] The reception desk can analyze a user's past survey response history and select the most appropriate questions. For example, the reception desk can automatically select relevant questions based on the user's past responses. For example, the reception desk can analyze a user's response patterns and suggest question formats that are easy to answer. The reception desk can also prioritize displaying questions related to specific topics from the user's past response history. This allows for the selection of the most appropriate questions by analyzing past response history. The most appropriate questions include, but are not limited to, the type of question, the selection method, and the relevance of the questions. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's past survey response history into a generating AI and have the generating AI select the most appropriate questions.

[0073] The reception desk can filter questions based on the user's current projects and areas of interest when they respond to a survey. For example, the reception desk may prioritize displaying questions related to the project the user is currently working on. For example, the reception desk may filter relevant questions based on the user's areas of interest. The reception desk may also select appropriate questions according to the progress of the user's project. This allows for the display of highly relevant questions by filtering questions based on the current project and areas of interest. Projects and areas of interest include, but are not limited to, the type of project, how the area of ​​interest was identified, and its progress. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk may input data on the user's current projects and areas of interest into a generating AI and have the generating AI perform the question filtering.

[0074] The reception desk can estimate the user's emotions and adjust the order in which they answer the questionnaire based on the estimated emotions. For example, if the user is stressed, the reception desk may start with easy questions and gradually increase the difficulty. For example, if the user is relaxed, the reception desk may display important questions first. If the user is in a hurry, the reception desk may also display important questions first to allow for quick answers. This makes it easier to answer the questionnaire by adjusting the order of answers according to the user's emotions. The estimation of the user's emotions 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 processing in the reception desk may be performed using AI or not. For example, the reception desk may input user emotion data into a generative AI and have the generative AI adjust the order in which the questionnaire answers are answered.

[0075] The reception desk can prioritize displaying questions that are highly relevant to the user's geographical location when they answer a survey. For example, if the user is in a specific region, the reception desk will prioritize displaying questions related to that region. For example, based on the user's location, the reception desk will display questions related to region-specific issues. If the user is on the move, the reception desk can also update questions related to their current location in real time. This allows for the display of highly relevant questions by considering geographical location. Geographical location information includes, but is not limited to, the method of obtaining location information, the criteria for selecting highly relevant questions, and region-specific issues. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's geographical location information into a generating AI and have the generating AI select highly relevant questions.

[0076] The reception desk can analyze a user's social media activity and present relevant questions when they respond to a survey. For example, the reception desk can analyze the content of a user's social media posts and present relevant questions. For example, the reception desk can display questions of interest based on the activity of the user's followers and friends. The reception desk can also analyze the user's social media trends and present questions on the latest topics. In this way, relevant questions can be presented by analyzing social media activity. Social media activity includes, but is not limited to, the type of activity, analysis algorithms, post content, the activity of followers and friends, and trends. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's social media activity data into a generating AI and have the generating AI perform the task of presenting relevant questions.

[0077] The decision unit can estimate the user's emotions and adjust the algorithm for judging the boss's characteristics based on the estimated user emotions. For example, if the user is stressed, the decision unit can simplify the boss's characteristic judgment and provide results quickly. For example, if the user is relaxed, the decision unit can perform a detailed characteristic judgment to improve accuracy. If the user is in a hurry, the decision unit can also prioritize important characteristics and provide results quickly. This improves the accuracy of characteristic judgment by adjusting the algorithm according to the user's emotions. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the decision unit may be performed using AI, for example, or not using AI. For example, the decision unit can input user emotion data into a generative AI and have the generative AI adjust the algorithm for judging the boss's characteristics.

[0078] The decision-making unit can improve the accuracy of feature judgment by referring to the supervisor's past feedback history when making a decision. For example, the decision-making unit can analyze patterns of feedback the supervisor has given in the past and reflect them in the feature judgment. For example, the decision-making unit can adjust the feature judgment algorithm based on the supervisor's past feedback history. The decision-making unit can also prioritize the judgment of specific features from the supervisor's feedback history. This improves the accuracy of feature judgment by referring to past feedback history. Feedback history includes, but is not limited to, the content of past feedback, the frequency of feedback, and the pattern of feedback. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input the supervisor's past feedback history into a generating AI and have the generating AI perform the improvement of feature judgment accuracy.

[0079] The decision unit can apply different decision algorithms depending on the supervisor's position and job duties when making a decision. For example, the decision unit can select an appropriate feature judgment algorithm depending on the supervisor's position. For example, the decision unit can adjust the feature judgment algorithm based on the supervisor's job duties. The decision unit can also apply different feature judgment algorithms depending on the supervisor's position and job duties. This improves the accuracy of feature judgment by applying algorithms according to the position and job duties. Position and job duties include, but are not limited to, the type of position, the method of identifying job duties, and the scope of duties. Some or all of the above processing in the decision unit may be performed using AI, for example, or without using AI. For example, the decision unit can input data on the supervisor's position and job duties into a generating AI and have the generating AI execute the application of the decision algorithm.

[0080] The decision unit can estimate the user's emotions and determine the priority of the characteristics of the supervisor based on the estimated user emotions. For example, if the user is stressed, the decision unit will prioritize important characteristics. For example, if the user is relaxed, the decision unit will perform detailed characteristic judgments to improve accuracy. If the user is in a hurry, the decision unit can also prioritize characteristics that can be judged quickly. This allows for rapid characteristic judgment by determining priorities according to the user's emotions. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the decision unit may be performed using AI, for example, or without AI. For example, the decision unit can input user emotion data into a generative AI and have the generative AI perform the determination of the priority of characteristic judgments.

[0081] The decision-making unit can perform feature determination while considering the geographical location of the supervisor's business. For example, the decision-making unit adjusts the feature determination algorithm based on the supervisor's business location. For example, the decision-making unit performs appropriate feature determination while considering the supervisor's geographical location of business. The decision-making unit can also apply different feature determination algorithms depending on the supervisor's business location. This improves the accuracy of feature determination by considering the geographical location of business. Geographical location of business includes, but is not limited to, the type of location, the method of consideration, and the scope of business. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input data on the supervisor's geographical location of business into a generating AI and have the generating AI perform feature determination.

[0082] The decision-making unit can improve the accuracy of its feature judgments by referring to the supervisor's relevant literature and work reports during the decision-making process. For example, the decision-making unit can refer to the supervisor's relevant literature and reflect it in its feature judgments. For example, the decision-making unit can adjust its feature judgment algorithm based on the supervisor's work reports. The decision-making unit can also prioritize the judgment of specific features from the supervisor's relevant literature and work reports. This improves the accuracy of feature judgments by referring to relevant literature and work reports. Relevant literature and work reports include, but are not limited to, the type of literature, the method of reference, the content of the work, and the content of the report. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or not using AI. For example, the decision-making unit can input data from the supervisor's relevant literature and work reports into a generating AI and have the generating AI perform the improvement of the accuracy of feature judgments.

[0083] The tracing unit can estimate the user's emotions and adjust the feedback tracing method based on the estimated user emotions. For example, if the user is stressed, the tracing unit provides simplified feedback. For example, if the user is relaxed, the tracing unit provides detailed feedback. If the user is in a hurry, the tracing unit can also prioritize providing important feedback. This allows for the provision of appropriate feedback by adjusting the tracing method according to the user's emotions. User emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the tracing unit may be performed using AI, or not using AI. For example, the tracing unit can input user emotion data into the generative AI and have the generative AI adjust the feedback tracing method.

[0084] The tracing unit can improve the accuracy of tracing by referring to the supervisor's past feedback patterns during the tracing process. For example, the tracing unit can analyze the patterns of feedback the supervisor has given in the past and reflect them in the tracing. For example, the tracing unit can adjust the tracing algorithm based on the supervisor's past feedback patterns. The tracing unit can also prioritize tracing specific feedback patterns from the supervisor's feedback patterns. This improves the accuracy of tracing by referring to past feedback patterns. Feedback patterns include, but are not limited to, the content of past feedback, the frequency of feedback, and the pattern of feedback. Some or all of the above processing in the tracing unit may be performed using AI, for example, or without AI. For example, the tracing unit can input the supervisor's past feedback patterns into a generating AI and have the generating AI perform the task of improving the accuracy of tracing.

[0085] The tracing unit can apply different tracing algorithms during tracing, depending on the supervisor's work content and project progress. For example, the tracing unit can select an appropriate tracing algorithm based on the supervisor's work content. For example, the tracing unit can adjust the tracing algorithm according to the supervisor's project progress. The tracing unit can also apply different tracing algorithms depending on the supervisor's work content and project progress. This allows for appropriate tracing according to the work content and project progress. Examples of work content and project progress include, but are not limited to, the type of work, the method of identifying progress, and the scope of the project. Some or all of the above processing in the tracing unit may be performed using AI, for example, or without AI. For example, the tracing unit can input data on the supervisor's work content and project progress into a generating AI and have the generating AI execute the application of the tracing algorithm.

[0086] The tracing unit can estimate the user's emotions and adjust the order in which the feedback trace results are displayed based on the estimated user emotions. For example, if the user is stressed, the tracing unit will display important feedback first. For example, if the user is relaxed, the tracing unit will display detailed feedback in a sequential manner. If the user is in a hurry, the tracing unit can also display feedback in a way that allows for quick review. This allows users to prioritize important feedback by adjusting the order in which feedback is displayed according to their emotions. The estimation of the user's emotions is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the tracing unit may be performed using AI, for example, or not using AI. For example, the tracing unit can input user emotion data into the generative AI and have the generative AI adjust the order in which feedback is displayed.

[0087] The tracing unit can perform tracing while considering the geographical location of the supervisor's business. The tracing unit can adjust the tracing algorithm based on the supervisor's business location, for example. For example, the tracing unit can perform appropriate tracing by considering the supervisor's geographical location. The tracing unit can also apply different tracing algorithms depending on the supervisor's business location. This allows for appropriate tracing by considering the geographical location. Geographical location includes, but is not limited to, the type of location, the method of consideration, and the scope of work. Some or all of the above processing in the tracing unit may be performed using AI, for example, or without AI. For example, the tracing unit can input data on the supervisor's geographical location into a generating AI and have the generating AI perform the tracing.

[0088] The tracing unit can improve the accuracy of tracing by referring to the supervisor's relevant documents and work reports during the tracing process. For example, the tracing unit can refer to the supervisor's relevant documents and reflect them in the tracing. For example, the tracing unit can adjust the tracing algorithm based on the supervisor's work reports. The tracing unit can also prioritize tracing specific feedback from the supervisor's relevant documents and work reports. This improves the accuracy of tracing by referring to relevant documents and work reports. Relevant documents and work reports include, but are not limited to, the type of document, the method of reference, the work content, and the content of the report. Some or all of the above processing in the tracing unit may be performed using AI, for example, or not using AI. For example, the tracing unit can input data from the supervisor's relevant documents and work reports into a generating AI and have the generating AI perform the tracing accuracy improvement.

[0089] The confirmation unit can estimate the user's emotions and adjust the way the meeting minutes are submitted based on the estimated emotions. For example, if the user is stressed, the confirmation unit may submit simplified minutes. For example, if the user is relaxed, the confirmation unit may submit detailed minutes. If the user is in a hurry, the confirmation unit may also submit minutes that prioritize and summarize the important points. This ensures that appropriate minutes are submitted by adjusting the submission method according to the user's emotions. The estimation of the user's emotions 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 processing in the confirmation unit may be performed using AI or not. For example, the confirmation unit can input user emotion data into a generative AI and have the generative AI adjust the way the meeting minutes are submitted.

[0090] The confirmation unit can improve the accuracy of confirmation by referring to the supervisor's past confirmation history during confirmation. For example, the confirmation unit can analyze the patterns of confirmations made by the supervisor in the past and reflect them in the confirmation. For example, the confirmation unit can adjust the confirmation algorithm based on the supervisor's past confirmation history. The confirmation unit can also prioritize certain confirmations from the supervisor's confirmation history. This allows for improved confirmation accuracy by referring to past confirmation history. Confirmation history includes, but is not limited to, the content of past confirmations, the frequency of confirmations, and the patterns of confirmations. Some or all of the above processing in the confirmation unit may be performed using, for example, AI, or not using AI. For example, the confirmation unit can input the supervisor's past confirmation history into a generating AI and have the generating AI perform the correction of confirmation accuracy.

[0091] The ratification unit can apply different ratification algorithms depending on the supervisor's position and job duties during the ratification process. For example, the ratification unit can select an appropriate ratification algorithm based on the supervisor's position. For example, the ratification unit can adjust the ratification algorithm based on the supervisor's job duties. The ratification unit can also apply different ratification algorithms depending on the supervisor's position and job duties. This allows for improved ratification accuracy by applying algorithms according to the position and job duties. Position and job duties include, but are not limited to, the type of position, the method of identifying job duties, and the scope of duties. Some or all of the above-described processes in the ratification unit may be performed using AI, for example, or without AI. For example, the ratification unit can input data on the supervisor's position and job duties into a generating AI and have the generating AI execute the application of the ratification algorithm.

[0092] The confirmation unit can estimate the user's emotions and adjust the order in which meeting minutes are submitted based on the estimated emotions. For example, if the user is stressed, the confirmation unit will submit important minutes first. For example, if the user is relaxed, the confirmation unit will submit detailed minutes in order. If the user is in a hurry, the confirmation unit can also submit minutes so that they can be quickly reviewed. This allows important minutes to be submitted preferentially by adjusting the order in which they are submitted according to the user's emotions. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the confirmation unit may be performed using AI, for example, or not using AI. For example, the confirmation unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the order in which meeting minutes are submitted.

[0093] The ratification unit can perform ratification while considering the supervisor's geographical work location. The ratification unit can adjust the ratification algorithm based on the supervisor's work location, for example. For example, the ratification unit can perform appropriate ratification by considering the supervisor's geographical work location. The ratification unit can also apply different ratification algorithms depending on the supervisor's work location. This allows for appropriate ratification by considering the geographical work location. Geographical work location includes, but is not limited to, the type of location, the method of consideration, and the scope of work. Some or all of the above processing in the ratification unit may be performed using AI, for example, or without AI. For example, the ratification unit can input data on the supervisor's geographical work location into a generating AI and have the generating AI perform the ratification.

[0094] The confirmation unit can improve the accuracy of its confirmations by referring to the supervisor's relevant documents and work reports during the confirmation process. For example, the confirmation unit can refer to the supervisor's relevant documents and reflect them in the confirmation. For example, the confirmation unit can adjust the confirmation algorithm based on the supervisor's work reports. The confirmation unit can also prioritize certain confirmations based on the supervisor's relevant documents and work reports. This allows for improved accuracy of confirmations by referring to relevant documents and work reports. Relevant documents and work reports include, but are not limited to, the type of document, the method of reference, the work content, and the content of the report. Some or all of the above processing in the confirmation unit may be performed using AI, for example, or not using AI. For example, the confirmation unit can input data from the supervisor's relevant documents and work reports into a generating AI and have the generating AI perform the task of improving the accuracy of confirmations.

[0095] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0096] The reception desk can estimate the user's emotions and adjust the survey questions based on those estimates. For example, if the user is stressed, the questions can be simplified and made easier to answer. If the user is relaxed, more detailed questions can be added to gather deeper information. If the user is in a hurry, important questions can be prioritized to allow for quicker responses. This makes it easier to answer the survey by adjusting the questions according to the user's emotions. The estimation of the user's emotions is achieved using 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 processing in the reception desk may be performed using AI or not. For example, the reception desk can input user emotion data into a generative AI and have the generative AI adjust the survey questions.

[0097] The decision unit can estimate the user's emotions and adjust the algorithm for judging the boss's characteristics based on the estimated user emotions. For example, if the user is stressed, the judgment of the boss's characteristics can be simplified and results can be provided quickly. If the user is relaxed, a detailed characteristic judgment can be performed to improve accuracy. If the user is in a hurry, important characteristics can be prioritized and results can be provided quickly. In this way, the accuracy of characteristic judgment can be improved by adjusting the algorithm according to the user's emotions. The estimation of the user's emotions is achieved using an emotion engine or generative AI, etc. 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 decision unit may be performed using AI or not using AI. For example, the decision unit can input user emotion data into a generative AI and have the generative AI adjust the algorithm for judging the boss's characteristics.

[0098] The tracing unit can estimate the user's emotions and adjust the feedback tracing method based on the estimated user emotions. For example, if the user is stressed, simplified feedback can be provided. If the user is relaxed, detailed feedback can be provided. If the user is in a hurry, important feedback can be prioritized. This allows for the provision of appropriate feedback by adjusting the tracing method according to the user's emotions. The estimation of the user's emotions is achieved using an emotion engine or generative AI, etc. 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 processing in the tracing unit may be performed using AI or not. For example, the tracing unit can input user emotion data into the generative AI and have the generative AI adjust the feedback tracing method.

[0099] The confirmation unit can estimate the user's emotions and adjust the way the meeting minutes are submitted based on the estimated emotions. For example, if the user is stressed, a simplified version of the minutes can be submitted. If the user is relaxed, a detailed version can be submitted. If the user is in a hurry, a version summarizing the key points can be submitted. This allows for the submission of appropriate minutes by adjusting the submission method according to the user's emotions. The estimation of the user's emotions is achieved using 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 processing in the confirmation unit may be performed using AI or not. For example, the confirmation unit can input user emotion data into a generative AI and have the generative AI adjust the way the meeting minutes are submitted.

[0100] The reception desk can analyze a user's past survey response history and select the most appropriate questions. For example, it can automatically select relevant questions based on the user's past responses. It can also analyze the user's response patterns and suggest question formats that are easy to answer. It can also prioritize displaying questions related to specific topics based on the user's past response history. In this way, the most appropriate questions can be selected by analyzing past response history. The most appropriate questions include, but are not limited to, the type of question, the selection method, and the relevance of the questions. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the user's past survey response history into a generating AI and have the generating AI select the most appropriate questions.

[0101] The reception desk can filter questions based on the user's current projects and areas of interest when they respond to a survey. For example, it can prioritize displaying questions related to the project the user is currently working on. It can also filter relevant questions based on the user's areas of interest. It can even select appropriate questions according to the progress of the user's project. This allows for the display of highly relevant questions by filtering questions based on the user's current projects and areas of interest. Projects and areas of interest include, but are not limited to, the type of project, how the area of ​​interest was identified, and its progress. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input data on the user's current projects and areas of interest into a generating AI and have the generating AI perform the question filtering.

[0102] The decision-making unit can improve the accuracy of its feature judgments by referring to the supervisor's past feedback history when making a decision. For example, it can analyze patterns of feedback the supervisor has given in the past and reflect them in the feature judgments. It can adjust the feature judgment algorithm based on the supervisor's past feedback history. It can also prioritize the judgment of specific features from the supervisor's feedback history. In this way, the accuracy of feature judgments can be improved by referring to past feedback history. Feedback history includes, but is not limited to, the content of past feedback, the frequency of feedback, and the patterns of feedback. Some or all of the above processing in the decision-making unit may be performed using AI or not. For example, the decision-making unit can input the supervisor's past feedback history into a generating AI and have the generating AI perform the improvement of the feature judgment accuracy.

[0103] The tracing unit can improve the accuracy of tracing by referring to the supervisor's past feedback patterns during the tracing process. For example, it can analyze the patterns of feedback the supervisor has given in the past and reflect them in the tracing. The tracing algorithm can be adjusted based on the supervisor's past feedback patterns. It can also prioritize tracing specific feedback patterns from the supervisor's feedback patterns. This improves the accuracy of tracing by referring to past feedback patterns. Feedback patterns include, but are not limited to, the content of past feedback, the frequency of feedback, and the pattern of feedback. Some or all of the above processing in the tracing unit may be performed using AI or not. For example, the tracing unit can input the supervisor's past feedback patterns into a generating AI and have the generating AI perform the task of improving the accuracy of tracing.

[0104] The confirmation unit can improve the accuracy of confirmation by referring to the supervisor's past confirmation history. For example, it can analyze the patterns of confirmations the supervisor has made in the past and reflect them in the confirmation process. It can adjust the confirmation algorithm based on the supervisor's past confirmation history. It can also prioritize certain confirmations based on the supervisor's confirmation history. This allows for improved confirmation accuracy by referring to past confirmation history. Confirmation history includes, but is not limited to, the content of past confirmations, the frequency of confirmations, and the patterns of confirmations. Some or all of the above processing in the confirmation unit may be performed using AI or not. For example, the confirmation unit can input the supervisor's past confirmation history into a generating AI and have the generating AI perform the task of improving the accuracy of confirmations.

[0105] The ratification unit can apply different ratification algorithms depending on the supervisor's position and job duties during the ratification process. For example, it can select an appropriate ratification algorithm based on the supervisor's position. It can also adjust the ratification algorithm based on the supervisor's job duties. It can also apply different ratification algorithms depending on the supervisor's position and job duties. This allows for improved ratification accuracy by applying algorithms according to the supervisor's position and job duties. Position and job duties include, but are not limited to, the type of position, the method of identifying job duties, and the scope of duties. Some or all of the above-described processes in the ratification unit may be performed using AI or not. For example, the ratification unit can input data on the supervisor's position and job duties into a generating AI and have the generating AI execute the application of the ratification algorithm.

[0106] The following briefly describes the processing flow for example form 2.

[0107] Step 1: The reception desk has the user complete a short questionnaire in advance. By having the user complete a short questionnaire in advance, the reception desk can collect information such as the characteristics of the user's supervisor and past feedback. For example, the questionnaire may include questions such as "What kind of feedback does your supervisor usually give?" or "What kind of feedback have you received in past meetings?" Step 2: The judgment unit determines the characteristics of the supervisor based on the information received by the reception unit. For example, the judgment unit determines the characteristics of the supervisor from a vast amount of statistical data. It analyzes past meeting minutes and feedback data to predict the type of feedback the supervisor is likely to give. Step 3: The tracing unit traces the type of feedback the supervisor is likely to give, based on the supervisor's characteristics determined by the judgment unit. For example, the tracing unit analyzes past meeting minutes and feedback data to trace the type of feedback the supervisor is likely to give. It learns the patterns of feedback the supervisor has given in the past and predicts what kind of feedback they will give in similar situations. Step 4: The confirmation team submits the meeting minutes and receives confirmation and additional comments from their supervisor. After the user has a meeting with the AI ​​agent, they submit the meeting minutes to their supervisor. The supervisor reviews the minutes and provides confirmation and additional comments. This allows the confirmation team to improve the accuracy of the AI ​​agent's tracing.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] Each of the multiple elements described above, including the reception unit, judgment unit, tracing unit, and confirmation unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14, and collects information on the supervisor's characteristics and past feedback by having the user answer a simple questionnaire in advance. The judgment unit is implemented by the identification processing unit 290 of the data processing device 12, and determines the supervisor's characteristics from a large amount of statistical data. The tracing unit is implemented by the identification processing unit 290 of the data processing device 12, and traces the feedback that the supervisor is likely to give. The confirmation unit is implemented by the control unit 46A of the smart device 14, and improves the accuracy of the tracing by submitting meeting minutes to the supervisor and receiving confirmation and additional comments. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0112] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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).

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] Each of the multiple elements described above, including the reception unit, judgment unit, tracing unit, and confirmation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214, which collects information on the supervisor's characteristics and past feedback by having the user answer a simple questionnaire in advance. The judgment unit is implemented by the identification processing unit 290 of the data processing unit 12, which determines the supervisor's characteristics from a large amount of statistical data. The tracing unit is implemented by the identification processing unit 290 of the data processing unit 12, which traces the feedback that the supervisor is likely to give. The confirmation unit is implemented by the control unit 46A of the smart glasses 214, which submits meeting minutes to the supervisor and improves the accuracy of the tracing by receiving confirmation and additional comments. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0128] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] Each of the multiple elements described above, including the reception unit, judgment unit, tracing unit, and confirmation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314, and collects information on the supervisor's characteristics and past feedback by having the user answer a simple questionnaire in advance. The judgment unit is implemented by the identification processing unit 290 of the data processing unit 12, and determines the supervisor's characteristics from a large amount of statistical data. The tracing unit is implemented by the identification processing unit 290 of the data processing unit 12, and traces the feedback that the supervisor is likely to give. The confirmation unit is implemented by the control unit 46A of the headset terminal 314, and improves the accuracy of the tracing by submitting meeting minutes to the supervisor and receiving confirmation and additional comments. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0144] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] Each of the multiple elements described above, including the reception unit, judgment unit, tracing unit, and confirmation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414, and collects information on the supervisor's characteristics and past feedback by having the user answer a simple questionnaire in advance. The judgment unit is implemented by the identification processing unit 290 of the data processing unit 12, and determines the supervisor's characteristics from a large amount of statistical data. The tracing unit is implemented by the identification processing unit 290 of the data processing unit 12, and traces the feedback that the supervisor is likely to give. The confirmation unit is implemented by the control unit 46A of the robot 414, and improves the accuracy of the tracing by submitting meeting minutes to the supervisor and receiving confirmation and additional comments. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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."

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] (Note 1) A reception area where users answer a short questionnaire in advance, A judgment unit that determines the characteristics of the supervisor based on the information received by the aforementioned reception unit, A tracing unit traces the type of feedback that a supervisor is likely to give, based on the characteristics of the supervisor determined by the aforementioned judgment unit. It includes a confirmation department where meeting minutes are submitted and confirmation and additional comments are received from superiors. A system characterized by the following features. (Note 2) The unit that makes the determination said, Judging a boss's characteristics from vast amounts of statistical data The system described in Appendix 1, characterized by the features described herein. (Note 3) The tracing unit is Analyze past meeting minutes and feedback data to trace the type of feedback your supervisor is likely to give. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned confirmation unit is, Submit meeting minutes and receive confirmation and additional comments from your supervisor. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reception unit is The system estimates the user's emotions and adjusts the survey questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is Analyze the user's past survey responses to select the most appropriate questions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is When users respond to a survey, the questions are filtered based on their current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is The system estimates user sentiment and adjusts the order of survey responses based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When users respond to surveys, the system prioritizes displaying questions that are more relevant to their geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When users respond to a survey, their social media activity is analyzed, and relevant questions are presented. The system described in Appendix 1, characterized by the features described herein. (Note 11) The unit that makes the determination said, The system estimates the user's emotions and adjusts the algorithm for identifying the manager's characteristics based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The unit that makes the determination said, When making decisions, refer to the supervisor's past feedback history to improve the accuracy of feature identification. The system described in Appendix 1, characterized by the features described herein. (Note 13) The unit that makes the determination said, When making a decision, different decision-making algorithms are applied depending on the supervisor's position and job responsibilities. The system described in Appendix 1, characterized by the features described herein. (Note 14) The unit that makes the determination said, The system estimates the user's emotions and prioritizes the characteristics of the supervisor based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The unit that makes the determination said, When making a decision, the geographical location of the supervisor's business base should be taken into consideration when making a characteristic assessment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The unit that makes the determination said, When making decisions, refer to relevant literature and work reports from your supervisor to improve the accuracy of your characteristic assessments. The system described in Appendix 1, characterized by the features described herein. (Note 17) The tracing unit is We estimate the user's emotions and adjust the feedback tracing method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The tracing unit is When tracing, refer to your supervisor's past feedback patterns to improve the accuracy of the tracing. The system described in Appendix 1, characterized by the features described herein. (Note 19) The tracing unit is During tracing, different tracing algorithms are applied depending on the supervisor's work content and the project's progress. The system described in Appendix 1, characterized by the features described herein. (Note 20) The tracing unit is It estimates the user's emotions and adjusts the order in which feedback trace results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The tracing unit is When tracing, take into account the geographical location of the supervisor's business. The system described in Appendix 1, characterized by the features described herein. (Note 22) The tracing unit is When tracing, refer to relevant documents and work reports from your supervisor to improve the accuracy of the tracing process. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned confirmation unit is, The system estimates user sentiment and adjusts the meeting minutes submission method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned confirmation unit is, When confirming a decision, refer to the supervisor's past confirmation history to improve the accuracy of the confirmation. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned confirmation unit is, When ratifying a decision, different ratification algorithms are applied depending on the supervisor's position and job responsibilities. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned confirmation unit is, The system estimates user sentiment and adjusts the order in which meeting minutes are submitted based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned confirmation unit is, When ratifying the decision, the supervisor's geographical work location should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned confirmation unit is, When confirming information, refer to relevant documents and work reports from your supervisor to improve the accuracy of the confirmation. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0180] 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 reception area where users answer a short questionnaire in advance, A judgment unit that determines the characteristics of the supervisor based on the information received by the aforementioned reception unit, A tracing unit traces the type of feedback that a supervisor is likely to give, based on the characteristics of the supervisor determined by the aforementioned judgment unit. It includes a confirmation department where meeting minutes are submitted and confirmation and additional comments are received from superiors. A system characterized by the following features.

2. The unit that makes the determination said, Judging a boss's characteristics from vast amounts of statistical data The system according to feature 1.

3. The tracing unit is Analyze past meeting minutes and feedback data to trace the type of feedback your supervisor is likely to give. The system according to feature 1.

4. The aforementioned confirmation unit is, Submit meeting minutes and receive confirmation and additional comments from your supervisor. The system according to feature 1.

5. The aforementioned reception unit is The system estimates the user's emotions and adjusts the survey questions based on those estimated emotions. The system according to feature 1.

6. The aforementioned reception unit is Analyze the user's past survey responses to select the most appropriate questions. The system according to feature 1.

7. The aforementioned reception unit is When users respond to a survey, the questions are filtered based on their current projects and areas of interest. The system according to feature 1.

8. The aforementioned reception unit is The system estimates user sentiment and adjusts the order of survey responses based on the estimated sentiment. The system according to feature 1.

Images