system

Abstract

The system according to this embodiment aims to conduct fair performance evaluations without being influenced by emotions. [Solution] The system according to the embodiment comprises a registration unit, a consultation unit, an analysis unit, and an answer provision unit. The registration unit registers the daily work and conduct of each member. The consultation unit allows evaluators to consult with the data registered by the registration unit at the time of evaluation. The analysis unit analyzes the data based on the content of the consultation by the consultation unit and provides an answer. The answer provision unit provides the analysis results obtained by the analysis unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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 is a problem that in personnel evaluation, the feelings and impressions of the evaluator affect the evaluation, making it difficult to conduct a fair evaluation.

[0005] The system according to the embodiment aims to conduct a fair evaluation without being influenced by emotions in personnel evaluation.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a registration unit, a consultation unit, an analysis unit, and an answer provision unit. The registration unit registers the daily work and conduct of each member. The consultation unit allows evaluators to consult with the data registered by the registration unit at the time of evaluation. The analysis unit analyzes the data based on the content of the consultation by the consultation unit and provides an answer. The answer provision unit provides the analysis results obtained by the analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can perform fair evaluations in personnel evaluations without being influenced by emotions. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

[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 personnel evaluation system according to an embodiment of the present invention is a system that improves the fairness of personnel evaluations using an AI agent. This system registers each member's daily work and conduct, and at the time of evaluation, evaluators consult with the AI ​​agent regarding the evaluation of members, thereby promoting fair judgments that are not influenced by emotions. First, each member's daily work and conduct are registered with the AI ​​agent. At this time, each member records their work content and conduct in detail every day and inputs it into the AI ​​agent. For example, they register the progress of a project and the content of communication with team members. This allows the AI ​​agent to understand the work status of each member. Next, at the time of evaluation, evaluators consult with the AI ​​agent regarding the evaluation of members. Evaluators ask the AI ​​agent questions regarding the evaluation of members, and the AI ​​agent provides answers based on the registered data. For example, if an evaluator asks, "What was this member's work performance like over the past six months?", the AI ​​agent analyzes the data from the past six months and provides information on the member's work performance. This allows evaluators to make fair evaluations that are not influenced by emotions. This mechanism makes it possible to make comprehensive evaluations that include past work performance, rather than just evaluating recent work at the time of evaluation. Furthermore, it enables fair evaluations that are not influenced by the evaluator's emotions or impressions. For example, even if an evaluator has favorable feelings towards a particular member, an evaluation based on objective data from the AI ​​agent promotes a fair judgment. In this way, using an AI agent can improve the fairness of performance evaluations. Evaluators can conduct fair evaluations that are not influenced by emotions, with the support of the AI ​​agent. This can improve the evaluation process throughout the organization, and is expected to lead to increased member motivation and improved work efficiency. As a result, the performance evaluation system can register each member's daily work and conduct, and evaluators can consult with the system at the time of evaluation to promote fair judgments that are not influenced by emotions.

[0029] The personnel evaluation system according to this embodiment comprises a registration unit, a consultation unit, an analysis unit, and an answer provision unit. The registration unit registers each member's daily work and conduct. The registration unit allows each member to record their work details and conduct in detail every day and input them into an AI agent. For example, they can register the progress of a project and the content of their communication with team members. This allows the registration unit to understand the work status of each member. The consultation unit allows evaluators to input questions regarding the evaluation of members at the time of evaluation. The consultation unit allows evaluators to ask questions such as, "What was this member's work performance like over the past six months?" This allows the consultation unit to allow evaluators to input questions regarding the evaluation of members. The analysis unit analyzes the members' work performance based on the registered data. The analysis unit can analyze data from the past six months and provide information about the members' work performance. This allows the analysis unit to analyze the members' work performance based on the registered data. The answer provision unit provides answers to evaluators based on the analysis results. The answer provision unit can provide evaluators with the analysis results obtained by the analysis unit. This allows the response provision unit to provide responses to evaluators based on the analysis results. As a result, the personnel evaluation system according to this embodiment can register each member's daily work and conduct, and evaluators can consult with the system at the time of evaluation to promote fair judgments that are not influenced by emotions.

[0030] The registration department registers each member's daily work and conduct. For example, each member can record their work and conduct in detail every day and input it into the AI ​​agent. Specifically, members input project progress, completed tasks, problems encountered, solutions, content of communication with team members, meeting summaries, and self-assessments through a dedicated application or web portal. This data is accumulated as a detailed record of daily work, and the AI ​​agent automatically organizes and categorizes the data. For example, project progress is recorded as task completion rate and on-time achievement, and communication content is evaluated as the degree of cooperation and problem-solving process. This allows the registration department to understand each member's work status in detail and accurately. In addition, the registration department regularly backs up the data entered by members to ensure data integrity and security. Furthermore, the registration department can provide feedback on the data entered by members to encourage improvement and refinement of the input content. This allows the registration department to accurately understand the members' work status and collect data that forms the basis of evaluation with high accuracy.

[0031] The consultation department allows evaluators to input questions about member evaluations during the evaluation period. For example, the consultation department allows evaluators to ask questions such as, "How has this member's work performance been over the past six months?" Specifically, evaluators can input specific evaluation questions through a dedicated interface. For example, they can input questions such as, "To what extent have this member's leadership skills improved?" or "How would this member's communication skills be evaluated?" The consultation department receives these questions and sends instructions to the analysis department for appropriate analysis. The consultation department also presents past evaluation data and relevant information in response to the questions entered by evaluators, helping evaluators to input more specific questions. In this way, the consultation department encourages evaluators to input detailed and specific questions about member evaluations, thereby improving the accuracy of evaluations. Furthermore, the consultation department organizes and categorizes the questions entered by evaluators, enabling the analysis department to perform analysis efficiently. In this way, the consultation department supports the process of evaluators inputting questions about member evaluations, thereby increasing the fairness and accuracy of evaluations.

[0032] The analysis department analyzes members' work performance based on registered data. For example, the analysis department can analyze data from the past six months and provide information about members' work performance. Specifically, it uses AI to comprehensively analyze registered data and evaluate members' work performance. For example, it comprehensively evaluates members' work performance based on indicators such as project progress, task completion rate, communication quality, problem-solving ability, and leadership skills. The AI ​​uses natural language processing technology to analyze text data entered by members and extract important keywords and phrases. It also uses machine learning algorithms to learn patterns from past data and predict members' work performance. This allows the analysis department to analyze members' work performance in detail and accurately based on registered data. Furthermore, the analysis department visualizes the analysis results so that evaluators can easily understand them. For example, it can use graphs and charts to visually show fluctuations in members' work performance. This allows the analysis department to provide evaluators with information to accurately grasp members' work performance and conduct fair evaluations.

[0033] The response provision unit provides answers to evaluators based on the analysis results. For example, the response provision unit can provide evaluators with the analysis results obtained by the analysis unit. Specifically, it presents the analysis results to evaluators in an easy-to-understand manner, supporting them in making appropriate judgments. For example, it can provide the analysis results in a report format, showing a detailed evaluation of the members' work performance. Also, if an evaluator requests an answer to a specific question, the response provision unit will provide a specific answer based on the analysis results. For example, in response to the question, "To what extent have this member's leadership skills improved?", it will show the degree of improvement in leadership skills compared to past data. Furthermore, the response provision unit supports evaluators in providing feedback to members based on the analysis results. For example, it provides information to help evaluators identify specific areas for improvement and points to strengthen for members. In this way, the response provision unit can provide answers to evaluators based on the analysis results, thereby increasing the fairness and accuracy of the evaluation. In addition, the response provision unit can collect feedback from evaluators and use it to improve the system. In this way, the response provision unit can support evaluators in making appropriate judgments, thereby improving the reliability and effectiveness of the overall system.

[0034] The registration unit can record each member's daily work and conduct in detail and input it into the AI ​​agent. For example, each member can record their daily work and conduct in detail and input it into the AI ​​agent. For example, they can register project progress and the content of their communication with team members. This allows the registration unit to understand the work status of each member. As a method of detailed recording, for example, each member can create a daily report and input it into the AI ​​agent. In addition, each member can record their work and conduct using voice input, which the AI ​​agent can convert into text data. Furthermore, each member can use a smartphone or tablet to record their work and conduct in real time. This allows the registration unit to record each member's daily work and conduct in detail and input it into the AI ​​agent. This allows the AI ​​agent to understand the work status of each member.

[0035] The consultation system allows evaluators to input questions about member evaluations during the evaluation period. For example, an evaluator could ask, "How was this member's work performance over the past six months?" This enables the consultation system to input questions about member evaluations. Specific questions can include, for example, questions about a member's work performance, teamwork, and communication skills. Evaluators can also ask about a member's strengths and areas for improvement. Furthermore, evaluators can ask about a member's goal achievement and project progress. This allows the consultation system to input questions about member evaluations during the evaluation period. This enables the AI ​​agent to provide appropriate answers to the evaluator's questions.

[0036] The analysis unit can analyze members' work performance based on registered data. For example, the analysis unit can analyze data from the past six months and provide information on members' work performance. This allows the analysis unit to analyze members' work performance based on registered data. Specific evaluation criteria and analysis methods for work performance include, for example, evaluating work results, efficiency, and quality. AI can also be used in the analysis of work performance. For example, AI can analyze members' work data and evaluate their work performance. Furthermore, natural language processing technology can be used in the analysis of work performance. For example, AI can analyze members' work reports and communication logs and evaluate their work performance. This allows the analysis unit to analyze members' work performance based on registered data. This enables evaluators to conduct fair evaluations without being influenced by emotions.

[0037] The response-providing unit can provide answers to evaluators based on the analysis results. For example, the response-providing unit can provide evaluators with the analysis results obtained by the analysis unit. This allows the response-providing unit to provide answers to evaluators based on the analysis results. As for the specific content and method of providing the analysis results, for example, the analysis results can be provided in report format. The analysis results can also be displayed visually as graphs or charts. Furthermore, the analysis results can be provided in real time. For example, when an evaluator inputs a question, the AI ​​agent can immediately provide the analysis results. This allows the response-providing unit to provide answers to evaluators based on the analysis results. This enables evaluators to conduct fair evaluations without being influenced by emotions.

[0038] The response system can provide evaluations based on objective data, even if the evaluator has a favorable feeling towards a particular member. For example, even if the evaluator has a favorable feeling towards a particular member, the AI ​​agent can provide an evaluation based on objective data. This allows the response system to provide evaluations based on objective data, even if the evaluator has a favorable feeling towards a particular member. Specific types of objective data and methods of collection include, for example, numerical data and log data. AI can also be used to collect objective data. For example, AI can collect member work data and perform an objective evaluation. Furthermore, sensors and cameras can be used to collect objective data. For example, AI can monitor member behavior and collect objective data. This allows the response system to provide evaluations based on objective data, even if the evaluator has a favorable feeling towards a particular member. This promotes fair judgment.

[0039] The registration unit can analyze a member's past work history and select the optimal recording method. For example, the registration unit can prioritize suggesting recording methods that members have frequently used in the past. Furthermore, the registration unit can suggest recording methods suitable for a specific project based on a member's past work history. In addition, the registration unit can analyze a member's past work history and suggest efficient recording methods. This allows the registration unit to select the optimal recording method by analyzing a member's past work history, enabling efficient recording. Specific criteria and selection methods for the optimal recording method may include, for example, recording efficiency and accuracy. This allows the registration unit to analyze a member's past work history and select the optimal recording method. Some or all of the above processing in the registration unit may be performed using AI, or not. For example, the registration unit can input a member's past work history data into a generating AI and have the generating AI select the optimal recording method.

[0040] The registration unit can filter the recording of work content and conduct based on the member's current projects and areas of interest. For example, the registration unit can prioritize recording information related to the project the member is currently working on. It can also filter and record relevant information based on the member's areas of interest. Furthermore, it can prioritize recording important information based on the progress of the member's current projects. This allows the registration unit to prioritize recording highly relevant information by filtering based on the member's current projects and areas of interest when recording work content and conduct. Specific criteria and methods for filtering can be considered, for example, filtering conditions and the algorithms used. This allows the registration unit to filter based on the member's current projects and areas of interest when recording work content and conduct. Some or all of the above processing in the registration unit may be performed using AI, or not. For example, the registration unit can input member project data and area of ​​interest data into a generating AI and have the generating AI perform the filtering.

[0041] The registration unit can prioritize recording highly relevant information by considering the geographical location of members when recording work content and conduct. For example, if a member is working in a specific location, the registration unit can prioritize recording information related to that location. Furthermore, the registration unit can filter and record relevant information based on the member's geographical location. Additionally, if a member is on the move, the registration unit can prioritize recording important information based on their current location. This enables efficient recording by prioritizing the recording of highly relevant information by considering the member's geographical location when recording work content and conduct. Specific types of geographical location information and collection methods can include, for example, GPS data and location services. This allows the registration unit to prioritize the recording of highly relevant information by considering the member's geographical location when recording work content and conduct. Some or all of the above processing in the registration unit may be performed using AI, or without AI. For example, the registration unit can input the member's geographical location data into a generating AI and have the generating AI record highly relevant information.

[0042] The registration unit can analyze members' social media activity and record relevant information when recording work content and conduct. For example, the registration unit can extract and record relevant information from members' social media activity. Furthermore, the registration unit can analyze members' social media activity and prioritize recording important information. In addition, the registration unit can filter and record highly relevant information based on members' social media activity. This enables efficient recording by analyzing members' social media activity and recording relevant information when recording work content and conduct. Specific types of social media activity and analysis methods can include, for example, post content and activity frequency. This allows the registration unit to analyze members' social media activity and record relevant information when recording work content and conduct. Some or all of the above processing in the registration unit may be performed using AI, or not. For example, the registration unit can input members' social media data into a generating AI and have the generating AI record relevant information.

[0043] The consultation department can select the optimal consultation method by referring to the evaluator's past evaluation history during a consultation. For example, the consultation department can prioritize suggesting consultation methods that the evaluator has used in the past. Furthermore, the consultation department can suggest consultation methods suitable for specific members based on the evaluator's past evaluation history. In addition, the consultation department can analyze the evaluator's past evaluation history and suggest efficient consultation methods. This enables efficient consultations by allowing the consultation department to select the optimal consultation method by referring to the evaluator's past evaluation history during a consultation. Specific content and methods of referencing the evaluation history may include, for example, past evaluation results and evaluation frequency. This allows the consultation department to select the optimal consultation method by referring to the evaluator's past evaluation history during a consultation. Some or all of the above processing in the consultation department may be performed using AI, or not. For example, the consultation department can input the evaluator's past evaluation history data into a generating AI and have the generating AI select the optimal consultation method.

[0044] The consultation department can customize the consultation content by considering the attribute information of the member being evaluated by the evaluator. For example, the consultation department can provide relevant information based on the attribute information of the member being evaluated. Furthermore, the consultation department can propose the most suitable consultation content by considering the attribute information of the member being evaluated. In addition, the consultation department can analyze the attribute information of the member being evaluated and provide customized consultation content. In this way, the consultation department can provide highly relevant information by customizing the consultation content by considering the attribute information of the member being evaluated by the evaluator during the consultation. Specific types of attribute information and methods of collection can include, for example, age, job title, and skills. In this way, the consultation department can customize the consultation content by considering the attribute information of the member being evaluated by the evaluator during the consultation. Some or all of the above processing in the consultation department may be performed using AI, for example, or without AI. For example, the consultation department can input the attribute information data of the member being evaluated into a generating AI and have the generating AI perform the customization of the consultation content.

[0045] The consultation department can prioritize processing highly relevant consultation content by considering the evaluator's geographical location information during consultations. For example, if the evaluator is consulting in a specific location, the consultation department can prioritize providing information related to that location. Furthermore, the consultation department can filter and provide relevant consultation content based on the evaluator's geographical location information. Additionally, if the evaluator is on the move, the consultation department can prioritize providing important consultation content based on their current location. This enables efficient consultations by prioritizing highly relevant consultation content by considering the evaluator's geographical location information during consultations. Specific types of geographical location information and methods of collection can include, for example, GPS data and location-based services. This allows the consultation department to prioritize processing highly relevant consultation content by considering the evaluator's geographical location information during consultations. Some or all of the above processing in the consultation department may be performed using AI, or without AI. For example, the consultation department can input the evaluator's geographical location data into a generating AI and have the generating AI process highly relevant consultation content.

[0046] The consultation department can analyze the evaluator's social media activity during a consultation and provide relevant consultation content. For example, the consultation department can extract and provide relevant information from the evaluator's social media activity. Furthermore, the consultation department can analyze the evaluator's social media activity and prioritize providing important consultation content. In addition, the consultation department can filter and provide highly relevant consultation content based on the evaluator's social media activity. This enables efficient consultations by allowing the consultation department to analyze the evaluator's social media activity and provide relevant consultation content during the consultation. Specific types of social media activity and analysis methods can include, for example, post content and activity frequency. This allows the consultation department to analyze the evaluator's social media activity and provide relevant consultation content during the consultation. Some or all of the above processing in the consultation department may be performed using AI, or not. For example, the consultation department can input the evaluator's social media data into a generating AI and have the generating AI provide relevant consultation content.

[0047] The analysis unit can optimize the analysis algorithm by referring to past analysis data during analysis. For example, the analysis unit can select the optimal analysis algorithm based on past analysis data. Furthermore, the analysis unit can propose an analysis method suitable for a specific member based on past analysis data. In addition, the analysis unit can analyze past analysis data and propose an efficient analysis algorithm. This enables efficient analysis by optimizing the analysis algorithm by referring to past analysis data during analysis. Specific examples of past analysis data and methods of reference include past analysis results and data storage methods. This allows the analysis unit to optimize the analysis algorithm by referring to past analysis data during analysis. Some or all of the above-described processes in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input past analysis data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0048] The analysis unit can improve the accuracy of its analysis by considering fluctuations in the work performance of the members being evaluated. For example, the analysis unit can improve the accuracy of its analysis based on fluctuations in the work performance of the members being evaluated. Furthermore, the analysis unit can propose the optimal analysis method by considering fluctuations in the work performance of the members being evaluated. In addition, the analysis unit can analyze fluctuations in the work performance of the members being evaluated and provide an efficient analysis method. As a result, the analysis unit improves the accuracy of its analysis by considering fluctuations in the work performance of the members being evaluated during the analysis. Specific evaluation criteria and analysis methods for fluctuations in work performance can include, for example, work results, efficiency, and quality. As a result, the analysis unit can improve the accuracy of its analysis by considering fluctuations in the work performance of the members being evaluated during the analysis. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the work performance data of the members being evaluated into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0049] The analysis unit can perform analysis while considering the geographical location information of the members being evaluated. For example, if the members being evaluated are working in a specific location, the analysis unit can perform analysis based on information related to that location. The analysis unit can also filter relevant information based on the geographical location information of the members being evaluated and perform analysis. Furthermore, if the members being evaluated are on the move, the analysis unit can prioritize the analysis of important information based on their current location. This allows the analysis unit to provide highly relevant information by considering the geographical location information of the members being evaluated during analysis. Specific types of geographical location information and methods of collection can include, for example, GPS data and location information services. This allows the analysis unit to perform analysis while considering the geographical location information of the members being evaluated. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the geographical location data of the members being evaluated into a generating AI and have the generating AI perform the analysis.

[0050] The analysis unit can improve the accuracy of its analysis by referring to relevant literature of the members being evaluated during the analysis process. For example, the analysis unit can select the optimal analysis method based on the relevant literature of the members being evaluated. Furthermore, the analysis unit can improve the accuracy of its analysis by referring to the relevant literature of the members being evaluated. In addition, the analysis unit can analyze the relevant literature of the members being evaluated and provide an efficient analysis method. As a result, the analysis unit improves the accuracy of its analysis by referring to the relevant literature of the members being evaluated during the analysis process. As specific types of relevant literature and methods of reference, for example, academic papers and technical reports can be considered. As a result, the analysis unit can improve the accuracy of its analysis by referring to the relevant literature of the members being evaluated during the analysis process. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the relevant literature data of the members being evaluated into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0051] The response provider can select the optimal response method by referring to the evaluator's past evaluation history when providing a response. For example, the response provider can prioritize suggesting response methods previously used by the evaluator. Furthermore, the response provider can suggest a response method suitable for a specific member based on the evaluator's past evaluation history. In addition, the response provider can analyze the evaluator's past evaluation history and suggest an efficient response method. This enables efficient responses by allowing the response provider to select the optimal response method by referring to the evaluator's past evaluation history when providing a response. Specific content and methods of referencing the evaluation history may include, for example, past evaluation results and evaluation frequency. This allows the response provider to select the optimal response method by referring to the evaluator's past evaluation history when providing a response. Some or all of the above processing in the response provider may be performed using AI, or without AI. For example, the response provider can input the evaluator's past evaluation history data into a generating AI and have the generating AI select the optimal response method.

[0052] The response-providing unit can improve the accuracy of its responses by considering fluctuations in the work performance of the members being evaluated. For example, the response-providing unit can improve the accuracy of its responses based on fluctuations in the work performance of the members being evaluated. Furthermore, the response-providing unit can propose the optimal response method by considering fluctuations in the work performance of the members being evaluated. In addition, the response-providing unit can analyze fluctuations in the work performance of the members being evaluated and provide an efficient response method. As a result, the response-providing unit improves the accuracy of its responses by considering fluctuations in the work performance of the members being evaluated when providing responses. Specific evaluation criteria and analysis methods for fluctuations in work performance can include, for example, work results, efficiency, and quality. As a result, the response-providing unit can improve the accuracy of its responses by considering fluctuations in the work performance of the members being evaluated when providing responses. Some or all of the above processing in the response-providing unit may be performed using AI, or not. For example, the response-providing unit can input the work performance data of the members being evaluated into a generating AI and have the generating AI perform the task of improving the accuracy of the responses.

[0053] The response provider can select the optimal response method when providing responses, taking into account the evaluator's geographical location information. For example, if the evaluator is requesting a response from a specific location, the response provider can prioritize providing information related to that location. Furthermore, the response provider can filter and provide relevant responses based on the evaluator's geographical location information. Additionally, if the evaluator is on the move, the response provider can prioritize providing important responses based on their current location. This allows the response provider to provide highly relevant information by selecting the optimal response method when providing responses, taking into account the evaluator's geographical location information. Specific types of geographical location information and methods of collection can include, for example, GPS data and location services. This allows the response provider to select the optimal response method when providing responses, taking into account the evaluator's geographical location information. Some or all of the above processing in the response provider may be performed using AI, or without AI. For example, the response provider can input the evaluator's geographical location data into a generating AI and have the generating AI select the optimal response method.

[0054] The response provider can improve the accuracy of its responses by referring to relevant literature of the member being evaluated when providing responses. For example, the response provider can select the optimal response method based on the relevant literature of the member being evaluated. Furthermore, the response provider can improve the accuracy of its responses by referring to relevant literature of the member being evaluated. In addition, the response provider can analyze the relevant literature of the member being evaluated and provide an efficient response method. As a result, the response provider improves the accuracy of its responses by referring to relevant literature of the member being evaluated when providing responses. Specific types of relevant literature and methods of reference can include, for example, academic papers and technical reports. As a result, the response provider can improve the accuracy of its responses by referring to relevant literature of the member being evaluated when providing responses. Some or all of the above processing in the response provider may be performed using AI, for example, or without AI. For example, the response provider can input the relevant literature data of the member being evaluated into a generating AI and have the generating AI perform the task of improving the accuracy of the responses.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The registration system can adjust the recording method when recording members' work content and conduct, taking into account their health condition. For example, if a member is unwell, a simplified recording method can be provided to reduce their burden. Conversely, if a member is healthy, a detailed recording method can be provided to collect more information. Furthermore, if a member is fatigued, voice input can be prioritized to allow for quick recording. In this way, by adjusting the recording method based on the member's health condition, the burden on members is reduced and recording becomes more efficient.

[0057] The consultation department can suggest the most suitable question format when evaluators input questions about member evaluations, by referring to the evaluator's past evaluation history. For example, it can prioritize suggesting question formats that the evaluator has used in the past. It can also suggest question formats suitable for specific members based on the evaluator's past evaluation history. Furthermore, it can analyze the evaluator's past evaluation history and suggest efficient question formats. As a result, the consultation department enables efficient questioning by suggesting the most suitable question format by referring to the evaluator's past evaluation history.

[0058] The analysis unit can adjust its analysis methods when analyzing members' work performance, taking into account each member's skill set. For example, if a member excels in a particular skill, the analysis can focus on analyzing work performance related to that skill. Furthermore, if a member is acquiring a new skill, the analysis can analyze their progress in acquiring that skill. Additionally, if a member possesses multiple skills, the analysis can analyze their work performance based on each skill. This allows the analysis unit to adjust its analysis methods based on each member's skill set, enabling a more accurate analysis of work performance.

[0059] The response provision unit can select the most suitable response format by referring to the evaluator's past evaluation results when providing responses to evaluators. For example, it can prioritize suggesting response formats previously used by the evaluator. It can also suggest response formats suitable for specific members based on the evaluator's past evaluation results. Furthermore, it can analyze the evaluator's past evaluation results and suggest efficient response formats. As a result, the response provision unit can provide efficient responses by selecting the most suitable response format by referring to the evaluator's past evaluation results.

[0060] The registration unit can prioritize recording highly relevant information when recording members' work content and conduct, taking into account the members' geographical location. For example, if a member is working in a specific location, it can prioritize recording information related to that location. It can also filter and record relevant information based on the member's geographical location. Furthermore, if a member is on the move, it can prioritize recording important information based on their current location. As a result, the registration unit can efficiently record information by prioritizing highly relevant information while considering the members' geographical location.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The registration section registers each member's daily tasks and conduct. For example, each member can record their daily tasks and conduct in detail and input them into the AI ​​agent. This allows for the registration of project progress and communication with team members, enabling a comprehensive understanding of each member's work status. Step 2: The consultation department allows evaluators to input questions regarding member evaluations during the evaluation period. For example, an evaluator can ask, "How was this member's work performance over the past six months?" This allows evaluators to input questions regarding member evaluations. Step 3: The analysis unit analyzes the members' work performance based on the registered data. For example, it can analyze data from the past six months and provide information about the members' work performance. This allows for the analysis of members' work performance based on the registered data. Step 4: The response provision unit provides the evaluator with a response based on the analysis results. For example, the analysis results obtained by the analysis unit can be provided to the evaluator. This allows the evaluator to receive a response based on the analysis results.

[0063] (Example of form 2) The personnel evaluation system according to an embodiment of the present invention is a system that improves the fairness of personnel evaluations using an AI agent. This system registers each member's daily work and conduct, and at the time of evaluation, evaluators consult with the AI ​​agent regarding the evaluation of members, thereby promoting fair judgments that are not influenced by emotions. First, each member's daily work and conduct are registered with the AI ​​agent. At this time, each member records their work content and conduct in detail every day and inputs it into the AI ​​agent. For example, they register the progress of a project and the content of communication with team members. This allows the AI ​​agent to understand the work status of each member. Next, at the time of evaluation, evaluators consult with the AI ​​agent regarding the evaluation of members. Evaluators ask the AI ​​agent questions regarding the evaluation of members, and the AI ​​agent provides answers based on the registered data. For example, if an evaluator asks, "What was this member's work performance like over the past six months?", the AI ​​agent analyzes the data from the past six months and provides information on the member's work performance. This allows evaluators to make fair evaluations that are not influenced by emotions. This mechanism makes it possible to make comprehensive evaluations that include past work performance, rather than just evaluating recent work at the time of evaluation. Furthermore, it enables fair evaluations that are not influenced by the evaluator's emotions or impressions. For example, even if an evaluator has favorable feelings towards a particular member, an evaluation based on objective data from the AI ​​agent promotes a fair judgment. In this way, using an AI agent can improve the fairness of performance evaluations. Evaluators can conduct fair evaluations that are not influenced by emotions, with the support of the AI ​​agent. This can improve the evaluation process throughout the organization, and is expected to lead to increased member motivation and improved work efficiency. As a result, the performance evaluation system can register each member's daily work and conduct, and evaluators can consult with the system at the time of evaluation to promote fair judgments that are not influenced by emotions.

[0064] The personnel evaluation system according to this embodiment comprises a registration unit, a consultation unit, an analysis unit, and an answer provision unit. The registration unit registers each member's daily work and conduct. The registration unit allows each member to record their work details and conduct in detail every day and input them into an AI agent. For example, they can register the progress of a project and the content of their communication with team members. This allows the registration unit to understand the work status of each member. The consultation unit allows evaluators to input questions regarding the evaluation of members at the time of evaluation. The consultation unit allows evaluators to ask questions such as, "What was this member's work performance like over the past six months?" This allows the consultation unit to allow evaluators to input questions regarding the evaluation of members. The analysis unit analyzes the members' work performance based on the registered data. The analysis unit can analyze data from the past six months and provide information about the members' work performance. This allows the analysis unit to analyze the members' work performance based on the registered data. The answer provision unit provides answers to evaluators based on the analysis results. The answer provision unit can provide evaluators with the analysis results obtained by the analysis unit. This allows the response provision unit to provide responses to evaluators based on the analysis results. As a result, the personnel evaluation system according to this embodiment can register each member's daily work and conduct, and evaluators can consult with the system at the time of evaluation to promote fair judgments that are not influenced by emotions.

[0065] The registration department registers each member's daily work and conduct. For example, each member can record their work and conduct in detail every day and input it into the AI ​​agent. Specifically, members input project progress, completed tasks, problems encountered, solutions, content of communication with team members, meeting summaries, and self-assessments through a dedicated application or web portal. This data is accumulated as a detailed record of daily work, and the AI ​​agent automatically organizes and categorizes the data. For example, project progress is recorded as task completion rate and on-time achievement, and communication content is evaluated as the degree of cooperation and problem-solving process. This allows the registration department to understand each member's work status in detail and accurately. In addition, the registration department regularly backs up the data entered by members to ensure data integrity and security. Furthermore, the registration department can provide feedback on the data entered by members to encourage improvement and refinement of the input content. This allows the registration department to accurately understand the members' work status and collect data that forms the basis of evaluation with high accuracy.

[0066] The consultation department allows evaluators to input questions about member evaluations during the evaluation period. For example, the consultation department allows evaluators to ask questions such as, "How has this member's work performance been over the past six months?" Specifically, evaluators can input specific evaluation questions through a dedicated interface. For example, they can input questions such as, "To what extent have this member's leadership skills improved?" or "How would this member's communication skills be evaluated?" The consultation department receives these questions and sends instructions to the analysis department for appropriate analysis. The consultation department also presents past evaluation data and relevant information in response to the questions entered by evaluators, helping evaluators to input more specific questions. In this way, the consultation department encourages evaluators to input detailed and specific questions about member evaluations, thereby improving the accuracy of evaluations. Furthermore, the consultation department organizes and categorizes the questions entered by evaluators, enabling the analysis department to perform analysis efficiently. In this way, the consultation department supports the process of evaluators inputting questions about member evaluations, thereby increasing the fairness and accuracy of evaluations.

[0067] The analysis department analyzes members' work performance based on registered data. For example, the analysis department can analyze data from the past six months and provide information about members' work performance. Specifically, it uses AI to comprehensively analyze registered data and evaluate members' work performance. For example, it comprehensively evaluates members' work performance based on indicators such as project progress, task completion rate, communication quality, problem-solving ability, and leadership skills. The AI ​​uses natural language processing technology to analyze text data entered by members and extract important keywords and phrases. It also uses machine learning algorithms to learn patterns from past data and predict members' work performance. This allows the analysis department to analyze members' work performance in detail and accurately based on registered data. Furthermore, the analysis department visualizes the analysis results so that evaluators can easily understand them. For example, it can use graphs and charts to visually show fluctuations in members' work performance. This allows the analysis department to provide evaluators with information to accurately grasp members' work performance and conduct fair evaluations.

[0068] The response provision unit provides answers to evaluators based on the analysis results. For example, the response provision unit can provide evaluators with the analysis results obtained by the analysis unit. Specifically, it presents the analysis results to evaluators in an easy-to-understand manner, supporting them in making appropriate judgments. For example, it can provide the analysis results in a report format, showing a detailed evaluation of the members' work performance. Also, if an evaluator requests an answer to a specific question, the response provision unit will provide a specific answer based on the analysis results. For example, in response to the question, "To what extent have this member's leadership skills improved?", it will show the degree of improvement in leadership skills compared to past data. Furthermore, the response provision unit supports evaluators in providing feedback to members based on the analysis results. For example, it provides information to help evaluators identify specific areas for improvement and points to strengthen for members. In this way, the response provision unit can provide answers to evaluators based on the analysis results, thereby increasing the fairness and accuracy of the evaluation. In addition, the response provision unit can collect feedback from evaluators and use it to improve the system. In this way, the response provision unit can support evaluators in making appropriate judgments, thereby improving the reliability and effectiveness of the overall system.

[0069] The registration unit can record each member's daily work and conduct in detail and input it into the AI ​​agent. For example, each member can record their daily work and conduct in detail and input it into the AI ​​agent. For example, they can register project progress and the content of their communication with team members. This allows the registration unit to understand the work status of each member. As a method of detailed recording, for example, each member can create a daily report and input it into the AI ​​agent. In addition, each member can record their work and conduct using voice input, which the AI ​​agent can convert into text data. Furthermore, each member can use a smartphone or tablet to record their work and conduct in real time. This allows the registration unit to record each member's daily work and conduct in detail and input it into the AI ​​agent. This allows the AI ​​agent to understand the work status of each member.

[0070] The consultation system allows evaluators to input questions about member evaluations during the evaluation period. For example, an evaluator could ask, "How was this member's work performance over the past six months?" This enables the consultation system to input questions about member evaluations. Specific questions can include, for example, questions about a member's work performance, teamwork, and communication skills. Evaluators can also ask about a member's strengths and areas for improvement. Furthermore, evaluators can ask about a member's goal achievement and project progress. This allows the consultation system to input questions about member evaluations during the evaluation period. This enables the AI ​​agent to provide appropriate answers to the evaluator's questions.

[0071] The analysis unit can analyze members' work performance based on registered data. For example, the analysis unit can analyze data from the past six months and provide information on members' work performance. This allows the analysis unit to analyze members' work performance based on registered data. Specific evaluation criteria and analysis methods for work performance include, for example, evaluating work results, efficiency, and quality. AI can also be used in the analysis of work performance. For example, AI can analyze members' work data and evaluate their work performance. Furthermore, natural language processing technology can be used in the analysis of work performance. For example, AI can analyze members' work reports and communication logs and evaluate their work performance. This allows the analysis unit to analyze members' work performance based on registered data. This enables evaluators to conduct fair evaluations without being influenced by emotions.

[0072] The response-providing unit can provide answers to evaluators based on the analysis results. For example, the response-providing unit can provide evaluators with the analysis results obtained by the analysis unit. This allows the response-providing unit to provide answers to evaluators based on the analysis results. As for the specific content and method of providing the analysis results, for example, the analysis results can be provided in report format. The analysis results can also be displayed visually as graphs or charts. Furthermore, the analysis results can be provided in real time. For example, when an evaluator inputs a question, the AI ​​agent can immediately provide the analysis results. This allows the response-providing unit to provide answers to evaluators based on the analysis results. This enables evaluators to conduct fair evaluations without being influenced by emotions.

[0073] The response system can provide evaluations based on objective data, even if the evaluator has a favorable feeling towards a particular member. For example, even if the evaluator has a favorable feeling towards a particular member, the AI ​​agent can provide an evaluation based on objective data. This allows the response system to provide evaluations based on objective data, even if the evaluator has a favorable feeling towards a particular member. Specific types of objective data and methods of collection include, for example, numerical data and log data. AI can also be used to collect objective data. For example, AI can collect member work data and perform an objective evaluation. Furthermore, sensors and cameras can be used to collect objective data. For example, AI can monitor member behavior and collect objective data. This allows the response system to provide evaluations based on objective data, even if the evaluator has a favorable feeling towards a particular member. This promotes fair judgment.

[0074] The registration unit can estimate the emotions of members and adjust the recording method of work content and conduct based on the estimated emotions of the members. For example, if a member is feeling stressed, the registration unit can provide a concise recording method to reduce their burden. Conversely, if a member is relaxed, the registration unit can provide a detailed recording method to collect more information. Furthermore, if a member is in a hurry, the registration unit can prioritize voice input to enable quick recording. This reduces the burden on members and enables efficient recording by adjusting the recording method based on their emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the registration unit may be performed using AI, for example, or not using AI. For example, the registration unit can input member emotion data into a generative AI and have the generative AI perform emotion estimation.

[0075] The registration unit can analyze a member's past work history and select the optimal recording method. For example, the registration unit can prioritize suggesting recording methods that members have frequently used in the past. Furthermore, the registration unit can suggest recording methods suitable for a specific project based on a member's past work history. In addition, the registration unit can analyze a member's past work history and suggest efficient recording methods. This allows the registration unit to select the optimal recording method by analyzing a member's past work history, enabling efficient recording. Specific criteria and selection methods for the optimal recording method may include, for example, recording efficiency and accuracy. This allows the registration unit to analyze a member's past work history and select the optimal recording method. Some or all of the above processing in the registration unit may be performed using AI, or not. For example, the registration unit can input a member's past work history data into a generating AI and have the generating AI select the optimal recording method.

[0076] The registration unit can filter the recording of work content and conduct based on the member's current projects and areas of interest. For example, the registration unit can prioritize recording information related to the project the member is currently working on. It can also filter and record relevant information based on the member's areas of interest. Furthermore, it can prioritize recording important information based on the progress of the member's current projects. This allows the registration unit to prioritize recording highly relevant information by filtering based on the member's current projects and areas of interest when recording work content and conduct. Specific criteria and methods for filtering can be considered, for example, filtering conditions and the algorithms used. This allows the registration unit to filter based on the member's current projects and areas of interest when recording work content and conduct. Some or all of the above processing in the registration unit may be performed using AI, or not. For example, the registration unit can input member project data and area of ​​interest data into a generating AI and have the generating AI perform the filtering.

[0077] The registration unit can estimate the emotions of members and determine the priority of what to record based on the estimated emotions. For example, if a member is stressed, the registration unit can prioritize recording important information to reduce their burden. If a member is relaxed, the registration unit can prioritize recording detailed information. Furthermore, if a member is in a hurry, the registration unit can prioritize recording information that can be recorded quickly. In this way, the registration unit can prioritize recording important information by determining the priority of what to record based on the emotions of members. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the registration unit may be performed using AI or not using AI. For example, the registration unit can input member emotion data into a generative AI and have the generative AI determine the priority of what to record.

[0078] The registration unit can prioritize recording highly relevant information by considering the geographical location of members when recording work content and conduct. For example, if a member is working in a specific location, the registration unit can prioritize recording information related to that location. Furthermore, the registration unit can filter and record relevant information based on the member's geographical location. Additionally, if a member is on the move, the registration unit can prioritize recording important information based on their current location. This enables efficient recording by prioritizing the recording of highly relevant information by considering the member's geographical location when recording work content and conduct. Specific types of geographical location information and collection methods can include, for example, GPS data and location services. This allows the registration unit to prioritize the recording of highly relevant information by considering the member's geographical location when recording work content and conduct. Some or all of the above processing in the registration unit may be performed using AI, or without AI. For example, the registration unit can input the member's geographical location data into a generating AI and have the generating AI record highly relevant information.

[0079] The registration unit can analyze members' social media activity and record relevant information when recording work content and conduct. For example, the registration unit can extract and record relevant information from members' social media activity. Furthermore, the registration unit can analyze members' social media activity and prioritize recording important information. In addition, the registration unit can filter and record highly relevant information based on members' social media activity. This enables efficient recording by analyzing members' social media activity and recording relevant information when recording work content and conduct. Specific types of social media activity and analysis methods can include, for example, post content and activity frequency. This allows the registration unit to analyze members' social media activity and record relevant information when recording work content and conduct. Some or all of the above processing in the registration unit may be performed using AI, or not. For example, the registration unit can input members' social media data into a generating AI and have the generating AI record relevant information.

[0080] The consultation unit can estimate the evaluator's emotions and adjust the way the consultation content is presented based on the estimated emotions. For example, if the evaluator is nervous, the consultation unit can provide a simple and easily understandable presentation. If the evaluator is relaxed, the consultation unit can provide a presentation that includes detailed information. Furthermore, if the evaluator is in a hurry, the consultation unit can provide a concise presentation. In this way, by adjusting the presentation of the consultation content based on the evaluator's emotions, the consultation unit can provide consultation content that is easy for the evaluator to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the consultation unit may be performed using AI, or not using AI. For example, the consultation unit can input the evaluator's emotion data into the generative AI and have the generative AI adjust the presentation of the consultation content.

[0081] The consultation department can select the optimal consultation method by referring to the evaluator's past evaluation history during a consultation. For example, the consultation department can prioritize suggesting consultation methods that the evaluator has used in the past. Furthermore, the consultation department can suggest consultation methods suitable for specific members based on the evaluator's past evaluation history. In addition, the consultation department can analyze the evaluator's past evaluation history and suggest efficient consultation methods. This enables efficient consultations by allowing the consultation department to select the optimal consultation method by referring to the evaluator's past evaluation history during a consultation. Specific content and methods of referencing the evaluation history may include, for example, past evaluation results and evaluation frequency. This allows the consultation department to select the optimal consultation method by referring to the evaluator's past evaluation history during a consultation. Some or all of the above processing in the consultation department may be performed using AI, or not. For example, the consultation department can input the evaluator's past evaluation history data into a generating AI and have the generating AI select the optimal consultation method.

[0082] The consultation department can customize the consultation content by considering the attribute information of the member being evaluated by the evaluator. For example, the consultation department can provide relevant information based on the attribute information of the member being evaluated. Furthermore, the consultation department can propose the most suitable consultation content by considering the attribute information of the member being evaluated. In addition, the consultation department can analyze the attribute information of the member being evaluated and provide customized consultation content. In this way, the consultation department can provide highly relevant information by customizing the consultation content by considering the attribute information of the member being evaluated by the evaluator during the consultation. Specific types of attribute information and methods of collection can include, for example, age, job title, and skills. In this way, the consultation department can customize the consultation content by considering the attribute information of the member being evaluated by the evaluator during the consultation. Some or all of the above processing in the consultation department may be performed using AI, for example, or without AI. For example, the consultation department can input the attribute information data of the member being evaluated into a generating AI and have the generating AI perform the customization of the consultation content.

[0083] The consultation unit can estimate the evaluator's emotions and prioritize consultation topics based on the estimated emotions. For example, if the evaluator is stressed, the consultation unit can prioritize important consultation topics. If the evaluator is relaxed, the consultation unit can prioritize detailed consultation topics. Furthermore, if the evaluator is in a hurry, the consultation unit can prioritize consultation topics that can be processed quickly. In this way, the consultation unit can prioritize important consultation topics by prioritizing them based on the evaluator's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the consultation unit may be performed using AI or not using AI. For example, the consultation unit can input evaluator emotion data into a generative AI and have the generative AI determine the priority of consultation topics.

[0084] The consultation department can prioritize processing highly relevant consultation content by considering the evaluator's geographical location information during consultations. For example, if the evaluator is consulting in a specific location, the consultation department can prioritize providing information related to that location. Furthermore, the consultation department can filter and provide relevant consultation content based on the evaluator's geographical location information. Additionally, if the evaluator is on the move, the consultation department can prioritize providing important consultation content based on their current location. This enables efficient consultations by prioritizing highly relevant consultation content by considering the evaluator's geographical location information during consultations. Specific types of geographical location information and methods of collection can include, for example, GPS data and location-based services. This allows the consultation department to prioritize processing highly relevant consultation content by considering the evaluator's geographical location information during consultations. Some or all of the above processing in the consultation department may be performed using AI, or without AI. For example, the consultation department can input the evaluator's geographical location data into a generating AI and have the generating AI process highly relevant consultation content.

[0085] The consultation department can analyze the evaluator's social media activity during a consultation and provide relevant consultation content. For example, the consultation department can extract and provide relevant information from the evaluator's social media activity. Furthermore, the consultation department can analyze the evaluator's social media activity and prioritize providing important consultation content. In addition, the consultation department can filter and provide highly relevant consultation content based on the evaluator's social media activity. This enables efficient consultations by allowing the consultation department to analyze the evaluator's social media activity and provide relevant consultation content during the consultation. Specific types of social media activity and analysis methods can include, for example, post content and activity frequency. This allows the consultation department to analyze the evaluator's social media activity and provide relevant consultation content during the consultation. Some or all of the above processing in the consultation department may be performed using AI, or not. For example, the consultation department can input the evaluator's social media data into a generating AI and have the generating AI provide relevant consultation content.

[0086] The analysis unit can estimate the emotions of the members being evaluated and adjust the analysis method based on the estimated emotions. For example, if the member being evaluated is stressed, the analysis unit can provide a simplified analysis method to reduce the burden. If the member being evaluated is relaxed, the analysis unit can provide a detailed analysis method to collect more information. Furthermore, if the member being evaluated is in a hurry, the analysis unit can provide a method that allows for rapid analysis. In this way, the analysis unit reduces the burden on members and enables efficient analysis by adjusting the analysis method based on the emotions of the members being evaluated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the emotional data of the members being evaluated into the generative AI and have the generative AI perform the adjustment of the analysis method.

[0087] The analysis unit can optimize the analysis algorithm by referring to past analysis data during analysis. For example, the analysis unit can select the optimal analysis algorithm based on past analysis data. Furthermore, the analysis unit can propose an analysis method suitable for a specific member based on past analysis data. In addition, the analysis unit can analyze past analysis data and propose an efficient analysis algorithm. This enables efficient analysis by optimizing the analysis algorithm by referring to past analysis data during analysis. Specific examples of past analysis data and methods of reference include past analysis results and data storage methods. This allows the analysis unit to optimize the analysis algorithm by referring to past analysis data during analysis. Some or all of the above-described processes in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input past analysis data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0088] The analysis unit can improve the accuracy of its analysis by considering fluctuations in the work performance of the members being evaluated. For example, the analysis unit can improve the accuracy of its analysis based on fluctuations in the work performance of the members being evaluated. Furthermore, the analysis unit can propose the optimal analysis method by considering fluctuations in the work performance of the members being evaluated. In addition, the analysis unit can analyze fluctuations in the work performance of the members being evaluated and provide an efficient analysis method. As a result, the analysis unit improves the accuracy of its analysis by considering fluctuations in the work performance of the members being evaluated during the analysis. Specific evaluation criteria and analysis methods for fluctuations in work performance can include, for example, work results, efficiency, and quality. As a result, the analysis unit can improve the accuracy of its analysis by considering fluctuations in the work performance of the members being evaluated during the analysis. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the work performance data of the members being evaluated into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0089] The analysis unit can estimate the emotions of the members being evaluated and adjust the display method of the analysis results based on the estimated emotions. For example, if the member being evaluated is tense, the analysis unit can provide a simple and highly visible display method. If the member being evaluated is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the member being evaluated is in a hurry, the analysis unit can provide a display method that gets straight to the point. In this way, by adjusting the display method of the analysis results based on the emotions of the members being evaluated, the analysis unit can provide a display that is easy for the members to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is 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 analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the emotion data of the members being evaluated into the generative AI and have the generative AI adjust the display method of the analysis results.

[0090] The analysis unit can perform analysis while considering the geographical location information of the members being evaluated. For example, if the members being evaluated are working in a specific location, the analysis unit can perform analysis based on information related to that location. The analysis unit can also filter relevant information based on the geographical location information of the members being evaluated and perform analysis. Furthermore, if the members being evaluated are on the move, the analysis unit can prioritize the analysis of important information based on their current location. This allows the analysis unit to provide highly relevant information by considering the geographical location information of the members being evaluated during analysis. Specific types of geographical location information and methods of collection can include, for example, GPS data and location information services. This allows the analysis unit to perform analysis while considering the geographical location information of the members being evaluated. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the geographical location data of the members being evaluated into a generating AI and have the generating AI perform the analysis.

[0091] The analysis unit can improve the accuracy of its analysis by referring to relevant literature of the members being evaluated during the analysis process. For example, the analysis unit can select the optimal analysis method based on the relevant literature of the members being evaluated. Furthermore, the analysis unit can improve the accuracy of its analysis by referring to the relevant literature of the members being evaluated. In addition, the analysis unit can analyze the relevant literature of the members being evaluated and provide an efficient analysis method. As a result, the analysis unit improves the accuracy of its analysis by referring to the relevant literature of the members being evaluated during the analysis process. As specific types of relevant literature and methods of reference, for example, academic papers and technical reports can be considered. As a result, the analysis unit can improve the accuracy of its analysis by referring to the relevant literature of the members being evaluated during the analysis process. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the relevant literature data of the members being evaluated into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0092] The response provider can estimate the evaluator's emotions and adjust the way the response is expressed based on the estimated emotions. For example, if the evaluator is nervous, the response provider can provide a simple and easily understandable expression. If the evaluator is relaxed, the response provider can provide an expression that includes detailed information. Furthermore, if the evaluator is in a hurry, the response provider can provide an expression that gets straight to the point. In this way, by adjusting the way the response is expressed based on the evaluator's emotions, the response provider can provide responses that are easy for the evaluator to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response provider may be performed using AI, for example, or not using AI. For example, the response provider can input the evaluator's emotion data into the generative AI and have the generative AI adjust the way the response is expressed.

[0093] The response provider can select the optimal response method by referring to the evaluator's past evaluation history when providing a response. For example, the response provider can prioritize suggesting response methods previously used by the evaluator. Furthermore, the response provider can suggest a response method suitable for a specific member based on the evaluator's past evaluation history. In addition, the response provider can analyze the evaluator's past evaluation history and suggest an efficient response method. This enables efficient responses by allowing the response provider to select the optimal response method by referring to the evaluator's past evaluation history when providing a response. Specific content and methods of referencing the evaluation history may include, for example, past evaluation results and evaluation frequency. This allows the response provider to select the optimal response method by referring to the evaluator's past evaluation history when providing a response. Some or all of the above processing in the response provider may be performed using AI, or without AI. For example, the response provider can input the evaluator's past evaluation history data into a generating AI and have the generating AI select the optimal response method.

[0094] The response-providing unit can improve the accuracy of its responses by considering fluctuations in the work performance of the members being evaluated. For example, the response-providing unit can improve the accuracy of its responses based on fluctuations in the work performance of the members being evaluated. Furthermore, the response-providing unit can propose the optimal response method by considering fluctuations in the work performance of the members being evaluated. In addition, the response-providing unit can analyze fluctuations in the work performance of the members being evaluated and provide an efficient response method. As a result, the response-providing unit improves the accuracy of its responses by considering fluctuations in the work performance of the members being evaluated when providing responses. Specific evaluation criteria and analysis methods for fluctuations in work performance can include, for example, work results, efficiency, and quality. As a result, the response-providing unit can improve the accuracy of its responses by considering fluctuations in the work performance of the members being evaluated when providing responses. Some or all of the above processing in the response-providing unit may be performed using AI, or not. For example, the response-providing unit can input the work performance data of the members being evaluated into a generating AI and have the generating AI perform the task of improving the accuracy of the responses.

[0095] The response provider can estimate the evaluator's emotions and prioritize responses based on the estimated emotions. For example, if the evaluator is stressed, the response provider can prioritize important responses. If the evaluator is relaxed, the response provider can prioritize detailed responses. Furthermore, if the evaluator is in a hurry, the response provider can prioritize responses that can be provided quickly. In this way, the response provider can prioritize important responses by prioritizing responses based on the evaluator's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response provider may be performed using AI or not using AI. For example, the response provider can input evaluator emotion data into a generative AI and have the generative AI determine the priority of responses.

[0096] The response provider can select the optimal response method when providing responses, taking into account the evaluator's geographical location information. For example, if the evaluator is requesting a response from a specific location, the response provider can prioritize providing information related to that location. Furthermore, the response provider can filter and provide relevant responses based on the evaluator's geographical location information. Additionally, if the evaluator is on the move, the response provider can prioritize providing important responses based on their current location. This allows the response provider to provide highly relevant information by selecting the optimal response method when providing responses, taking into account the evaluator's geographical location information. Specific types of geographical location information and methods of collection can include, for example, GPS data and location services. This allows the response provider to select the optimal response method when providing responses, taking into account the evaluator's geographical location information. Some or all of the above processing in the response provider may be performed using AI, or without AI. For example, the response provider can input the evaluator's geographical location data into a generating AI and have the generating AI select the optimal response method.

[0097] The response provider can improve the accuracy of its responses by referring to relevant literature of the member being evaluated when providing responses. For example, the response provider can select the optimal response method based on the relevant literature of the member being evaluated. Furthermore, the response provider can improve the accuracy of its responses by referring to relevant literature of the member being evaluated. In addition, the response provider can analyze the relevant literature of the member being evaluated and provide an efficient response method. As a result, the response provider improves the accuracy of its responses by referring to relevant literature of the member being evaluated when providing responses. Specific types of relevant literature and methods of reference can include, for example, academic papers and technical reports. As a result, the response provider can improve the accuracy of its responses by referring to relevant literature of the member being evaluated when providing responses. Some or all of the above processing in the response provider may be performed using AI, for example, or without AI. For example, the response provider can input the relevant literature data of the member being evaluated into a generating AI and have the generating AI perform the task of improving the accuracy of the responses.

[0098] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0099] The registration system can adjust the recording method when recording members' work content and conduct, taking into account their health condition. For example, if a member is unwell, a simplified recording method can be provided to reduce their burden. Conversely, if a member is healthy, a detailed recording method can be provided to collect more information. Furthermore, if a member is fatigued, voice input can be prioritized to allow for quick recording. In this way, by adjusting the recording method based on the member's health condition, the burden on members is reduced and recording becomes more efficient.

[0100] The consultation department can suggest the most suitable question format when evaluators input questions about member evaluations, by referring to the evaluator's past evaluation history. For example, it can prioritize suggesting question formats that the evaluator has used in the past. It can also suggest question formats suitable for specific members based on the evaluator's past evaluation history. Furthermore, it can analyze the evaluator's past evaluation history and suggest efficient question formats. As a result, the consultation department enables efficient questioning by suggesting the most suitable question format by referring to the evaluator's past evaluation history.

[0101] The analysis unit can adjust its analysis methods when analyzing members' work performance, taking into account each member's skill set. For example, if a member excels in a particular skill, the analysis can focus on analyzing work performance related to that skill. Furthermore, if a member is acquiring a new skill, the analysis can analyze their progress in acquiring that skill. Additionally, if a member possesses multiple skills, the analysis can analyze their work performance based on each skill. This allows the analysis unit to adjust its analysis methods based on each member's skill set, enabling a more accurate analysis of work performance.

[0102] The response provision unit can select the most suitable response format by referring to the evaluator's past evaluation results when providing responses to evaluators. For example, it can prioritize suggesting response formats previously used by the evaluator. It can also suggest response formats suitable for specific members based on the evaluator's past evaluation results. Furthermore, it can analyze the evaluator's past evaluation results and suggest efficient response formats. As a result, the response provision unit can provide efficient responses by selecting the most suitable response format by referring to the evaluator's past evaluation results.

[0103] The registration unit can prioritize recording highly relevant information when recording members' work content and conduct, taking into account the members' geographical location. For example, if a member is working in a specific location, it can prioritize recording information related to that location. It can also filter and record relevant information based on the member's geographical location. Furthermore, if a member is on the move, it can prioritize recording important information based on their current location. As a result, the registration unit can efficiently record information by prioritizing highly relevant information while considering the members' geographical location.

[0104] The registration unit can estimate the emotions of members and adjust the recording methods for work content and conduct based on the estimated emotions. For example, if a member is stressed, a concise recording method can be provided to reduce their burden. Conversely, if a member is relaxed, a detailed recording method can be provided to collect more information. Furthermore, if a member is in a hurry, voice input can be prioritized to allow for quick recording. In this way, by adjusting the recording method based on the emotions of members, the burden on members is reduced and recording becomes more efficient.

[0105] The consultation department can estimate the evaluator's emotions and adjust the way the consultation content is presented based on those emotions. For example, if the evaluator is nervous, a simple and easily understandable presentation can be provided. If the evaluator is relaxed, a presentation containing detailed information can be provided. Furthermore, if the evaluator is in a hurry, a concise presentation can be provided. In this way, by adjusting the presentation of the consultation content based on the evaluator's emotions, the consultation content can be made easier for the evaluator to understand.

[0106] The analysis unit can estimate the emotions of the members being evaluated and adjust the analysis method based on those estimated emotions. For example, if a member being evaluated is feeling stressed, a simplified analysis method can be provided to reduce their burden. If a member being evaluated is relaxed, a more detailed analysis method can be provided to collect more information. Furthermore, if a member being evaluated is in a hurry, a method that allows for rapid analysis can be provided. In this way, by adjusting the analysis method based on the emotions of the members being evaluated, the burden on the members is reduced and efficient analysis becomes possible.

[0107] The analysis unit can estimate the emotions of the members being evaluated and adjust the display method of the analysis results based on the estimated emotions. For example, if the member being evaluated is nervous, a simple and highly visible display method can be provided. If the member being evaluated is relaxed, a display method including detailed information can be provided. Furthermore, if the member being evaluated is in a hurry, a display method that focuses on the essential points can be provided. In this way, by adjusting the display method of the analysis results based on the emotions of the members being evaluated, it becomes possible to display the results in a way that is easy for the members to understand.

[0108] The response provider can estimate the evaluator's emotions and adjust the way the response is presented based on those emotions. For example, if the evaluator is nervous, it can provide a simple and easily understandable response. If the evaluator is relaxed, it can provide a response that includes detailed information. Furthermore, if the evaluator is in a hurry, it can provide a response that gets straight to the point. By adjusting the response's presentation based on the evaluator's emotions, the system can provide responses that are easy for the evaluator to understand.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The registration section registers each member's daily tasks and conduct. For example, each member can record their daily tasks and conduct in detail and input them into the AI ​​agent. This allows for the registration of project progress and communication with team members, enabling a comprehensive understanding of each member's work status. Step 2: The consultation department allows evaluators to input questions regarding member evaluations during the evaluation period. For example, an evaluator can ask, "How was this member's work performance over the past six months?" This allows evaluators to input questions regarding member evaluations. Step 3: The analysis unit analyzes the members' work performance based on the registered data. For example, it can analyze data from the past six months and provide information about the members' work performance. This allows for the analysis of members' work performance based on the registered data. Step 4: The response provision unit provides the evaluator with a response based on the analysis results. For example, the analysis results obtained by the analysis unit can be provided to the evaluator. This allows the evaluator to receive a response based on the analysis results.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] Each of the multiple elements described above, including the registration unit, consultation unit, analysis unit, and answer provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the registration unit is implemented by the control unit 46A of the smart device 14, which can record each member's daily work and conduct in detail and input it into the AI ​​agent. The consultation unit is implemented by the specific processing unit 290 of the data processing unit 12, which allows evaluators to input questions regarding the evaluation of members at the time of evaluation. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which can analyze the members' work performance based on the registered data. The answer provision unit is implemented by the specific processing unit 290 of the data processing unit 12, which can provide answers to evaluators based on the analysis results. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] 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.

[0117] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0118] The 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.

[0119] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0122] Figure 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.

[0123] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0125] In the 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.

[0126] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0127] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0128] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0129] The data processing system 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.

[0130] Each of the multiple elements described above, including the registration unit, consultation unit, analysis unit, and answer provision unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the registration unit is implemented by the control unit 46A of the smart glasses 214, which can record each member's daily work and conduct in detail and input it into the AI ​​agent. The consultation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which allows evaluators to input questions regarding the evaluation of members at the time of evaluation. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which can analyze the work performance of members based on the registered data. The answer provision unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which can provide answers to evaluators based on the analysis results. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0131] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0132] 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.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The 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.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (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).

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] Each of the multiple elements described above, including the registration unit, consultation unit, analysis unit, and answer provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the registration unit is implemented by the control unit 46A of the headset terminal 314, which can record each member's daily work and conduct in detail and input it into the AI ​​agent. The consultation unit is implemented by the specific processing unit 290 of the data processing unit 12, which allows evaluators to input questions regarding the evaluation of members at the time of evaluation. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which can analyze the work performance of members based on the registered data. The answer provision unit is implemented by the specific processing unit 290 of the data processing unit 12, which can provide answers to evaluators based on the analysis results. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0147] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.).

[0160] 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.

[0161] 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.

[0162] 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.

[0163] Each of the multiple elements described above, including the registration unit, consultation unit, analysis unit, and answer provision unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the registration unit is implemented by the control unit 46A of the robot 414, which can record in detail the daily work and conduct of each member and input it into the AI ​​agent. The consultation unit is implemented by the specific processing unit 290 of the data processing unit 12, which allows evaluators to input questions regarding the evaluation of members at the time of evaluation. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which can analyze the work performance of members based on the registered data. The answer provision unit is implemented by the specific processing unit 290 of the data processing unit 12, which can provide answers to evaluators based on the analysis results. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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."

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] (Note 1) The registration section registers each member's daily work and conduct, Based on the data registered by the aforementioned registration unit, there is a consultation unit that evaluators can consult with at the time of evaluation, An analysis unit analyzes data based on the content of the consultation by the aforementioned consultation unit and provides an answer, The system includes a response providing unit that provides the analysis results obtained by the analysis unit. A system characterized by the following features. (Note 2) The aforementioned registration unit is Detailed records of each member's daily work and conduct are entered into the AI ​​agent. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned consultation department, During the evaluation period, evaluators enter questions regarding the evaluation of the members. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned analysis unit, Analyze members' work performance based on registered data. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned response provision unit, Provide responses to evaluators based on the analysis results. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned response provision unit, Even if an evaluator has favorable feelings towards a particular member, provide an evaluation based on objective data. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned registration unit is The system estimates the emotions of the team members and adjusts the recording methods for their work and conduct based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned registration unit is Analyze the members' past work history and select the optimal recording method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned registration unit is When recording work content and conduct, filter the data based on the member's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned registration unit is Estimate the emotions of the members and determine the priority of what to record based on the estimated emotions of the members. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned registration unit is When recording work details and conduct, prioritize recording highly relevant information, taking into account the geographical location of team members. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned registration unit is When recording work content and conduct, analyze members' social media activity and record relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned consultation department, The system estimates the evaluator's emotions and adjusts the way the consultation content is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned consultation department, During the consultation, the evaluator's past evaluation history will be referenced to select the most appropriate consultation method. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned consultation department, During consultations, the content of the consultation will be customized by taking into account the attribute information of the member being evaluated by the evaluator. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned consultation department, The system estimates the evaluator's emotions and prioritizes the consultation topics based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned consultation department, During consultations, the system prioritizes processing consultations with high relevance, taking into account the evaluator's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned consultation department, During the consultation, we will analyze the evaluator's social media activity and provide relevant consultation content. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, The system estimates the emotions of the members being evaluated and adjusts the analysis method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, During analysis, the analysis algorithm is optimized by referring to past analysis data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit, During analysis, we improve the accuracy of the analysis by taking into account fluctuations in the work performance of the members being evaluated. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit, The system estimates the emotions of the members being evaluated and adjusts the display method of the analysis results based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit, During the analysis, the geographical location information of the members being evaluated will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit, During the analysis, we improve the accuracy of the analysis by referring to relevant literature for the members being evaluated. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned response provision unit, The system estimates the evaluator's emotions and adjusts the way responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned response provision unit, When providing a response, the evaluator's past evaluation history is referenced to select the most appropriate response method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned response provision unit, When providing responses, we will improve the accuracy of the responses by taking into account fluctuations in the work performance of the members being evaluated. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned response provision unit, The system estimates the evaluator's emotions and prioritizes responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned response provision unit, When providing responses, the most suitable response method will be selected, taking into account the evaluator's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned response provision unit, When providing responses, we will improve the accuracy of the responses by referring to relevant literature of the members being evaluated. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The registration section registers each member's daily work and conduct, Based on the data registered by the aforementioned registration unit, there is a consultation unit that evaluators can consult with at the time of evaluation, An analysis unit analyzes data based on the content of the consultation by the aforementioned consultation unit and provides an answer, The system includes a response providing unit that provides the analysis results obtained by the analysis unit. A system characterized by the following features.

2. The aforementioned registration unit is The daily work and conduct of each member are recorded in detail and entered into the AI ​​agent. The system according to feature 1.

3. The aforementioned consultation department, During the evaluation period, evaluators enter questions regarding the evaluation of the members. The system according to feature 1.

4. The aforementioned analysis unit, Analyze members' work performance based on registered data. The system according to feature 1.

5. The aforementioned response provision unit, Provide responses to evaluators based on the analysis results. The system according to feature 1.

6. The aforementioned response provision unit, Even if an evaluator has favorable feelings towards a particular member, provide an evaluation based on objective data. The system according to feature 1.

7. The aforementioned registration unit is The system estimates the emotions of the team members and adjusts the recording methods for their work and conduct based on those estimated emotions. The system according to feature 1.

8. The aforementioned registration unit is Analyze the members' past work history and select the optimal recording method. The system according to feature 1.

9. The aforementioned registration unit is When recording work content and conduct, filter the data based on the member's current projects and areas of interest. The system according to feature 1.

10. The aforementioned registration unit is Estimate the emotions of the members and determine the priority of what to record based on the estimated emotions of the members. The system according to feature 1.

Images