system

Abstract

An object of the system according to the embodiment is to effectively utilize knowledge and experience of star human resources in a company to improve performance of the entire organization.SOLUTION: A system includes a knowledge learning part, a virtual participation part, a KPI analysis part, a feedback part, and a continuous learning part. The knowledge learning unit learns knowledge and experience of the star talent. The virtual participation unit participates in the conference or the KPI discussion based on the knowledge and experience learned by the knowledge learning unit. The KPI analysis unit analyzes an achievement status of the KPI. The feedback unit feeds back a result of the conference or the discussion. The continuous learning unit learns new knowledge and experience.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has made it difficult to effectively convey the knowledge and experience of star talent within a company to other employees, limiting its ability to improve the performance of the entire organization.

[0005] The system according to the embodiment aims to effectively utilize the knowledge and experience of star talent within a company to improve the performance of the entire organization. [Means for solving the problem]

[0006] The system according to the embodiment comprises a knowledge learning unit, a virtual participation unit, a KPI analysis unit, a feedback unit, and a continuous learning unit. The knowledge learning unit learns the knowledge and experience of star talent. The virtual participation unit participates in meetings and KPI discussions based on the knowledge and experience learned by the knowledge learning unit. The KPI analysis unit analyzes the achievement status of KPIs. The feedback unit provides feedback on the results of meetings and discussions. The continuous learning unit learns new knowledge and experience. [Effects of the Invention]

[0007] The system according to the embodiment can effectively utilize the knowledge and experience of star talent within a company to improve the performance of the entire organization. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The virtual employee solution system according to an embodiment of the present invention is a system that uses a generation AI to virtualize star talent within a company and allow them to participate in meetings and KPI discussions. As a result, the virtual employee solution system can virtualize star talent within a company and support efficient decision-making and problem-solving.

[0029] The virtual employee solution system according to the embodiment includes a knowledge learning unit, a virtual participation unit, a KPI analysis unit, a feedback unit, and a continuous learning unit. The knowledge learning unit learns the knowledge and experience of star talent. For example, the knowledge learning unit analyzes the star talent's past comments and work history to learn that knowledge. The knowledge learning unit can also analyze project deliverables to learn the star talent's experience. The knowledge learning unit can also analyze recordings of presentations given by the star talent and learn their content. The virtual participation unit participates in meetings and KPI discussions based on the knowledge and experience learned by the knowledge learning unit. For example, in a meeting, in response to an instruction such as "Please give your opinion on the progress of this project," the virtual participation unit can provide appropriate opinions based on the star talent's knowledge. In KPI discussions, the virtual participation unit can also evaluate the KPI achievement status and propose improvement measures. The virtual participation unit can also make comments and suggestions in meetings and discussions. The KPI analysis unit analyzes the KPI achievement status. For example, the KPI analysis unit analyzes past data and trends to evaluate the achievement status of KPIs. The KPI analysis unit can also propose optimal improvement measures based on the achievement status of KPIs. The KPI analysis unit can also monitor the achievement status of KPIs in real time and immediately propose improvement measures. The feedback unit provides feedback on the results of meetings and discussions. For example, the feedback unit automatically generates meeting minutes and shares them with relevant parties. The feedback unit can also summarize the results of KPI discussions and provide feedback to relevant parties. The feedback unit can also accurately understand the content of meetings and discussions and use them as a reference for moving forward to the next step. The continuous learning unit acquires new knowledge and experience. For example, the continuous learning unit analyzes recordings of meetings and discussions to learn new insights. The continuous learning unit can also analyze the content of meetings and discussions to incorporate new knowledge. The continuous learning unit can continuously learn and improve, and provide more accurate opinions and suggestions. As a result, the virtual employee solution system according to the embodiment can virtualize star talent within a company and support efficient decision-making and problem-solving.For example, even if a star talent is too busy to attend a meeting, the generative AI can participate in their place and provide important opinions and suggestions.In addition, in KPI discussions, the generative AI can suggest appropriate improvement measures, leading to improved business performance.

[0030] The knowledge learning unit can analyze the nonverbal communication of star talent and reflect this in the generation AI. For example, to analyze the nonverbal communication of star talent, the knowledge learning unit collects video data from past meetings and presentations and analyzes gesture and facial expression patterns. For example, it analyzes hand movements and facial expressions to identify nonverbal characteristics of specific statements. The knowledge learning unit can also collect and analyze posture and gaze data to analyze nonverbal communication. For example, it analyzes changes in posture and gaze movements to identify characteristics of nonverbal communication. The knowledge learning unit can also collect audio data and analyze voice tone and speed to analyze nonverbal communication. For example, it analyzes changes in voice tone and speaking speed to identify characteristics of nonverbal communication. This makes it possible to generate virtual employees that take nonverbal communication into account.

[0031] The knowledge learning unit can learn from past failure cases of star talent and generate preventive measures to avoid similar failures. For example, to learn from past failure cases of star talent, the knowledge learning unit collects data on failures and analyzes the causes and effects of the failures. For example, it analyzes project failure cases and identifies the factors behind the failures. The knowledge learning unit can also evaluate the impact of the failures and generate preventive measures to learn from the failure cases. For example, it evaluates the impact of the failures and identifies procedures to avoid similar failures. The knowledge learning unit can also analyze failure patterns to learn from the failure cases and generate preventive measures. For example, it identifies failure patterns and proposes risk management measures to avoid similar failures. In this way, it is possible to learn from past failures and provide preventive measures to avoid similar failures.

[0032] The knowledge learning department can integrate the knowledge and experience of star talent with the knowledge of experts from different industries to generate cross-domain insights. For example, the knowledge learning department collects data from experts from different industries and analyzes similarities and differences to integrate the knowledge and experience of star talent with the knowledge of experts from different industries. For example, it integrates knowledge from the technical field and the marketing field. The knowledge learning department can also collect and analyze best practices from different industries to integrate the knowledge of experts from different industries. For example, it can analyze success stories from different industries and identify common success factors. The knowledge learning department can also collect and analyze technologies and processes from different industries to integrate the knowledge of experts from different industries. For example, it can compare technologies and processes from different industries to generate cross-domain insights. This makes it possible to integrate knowledge from different industries and generate cross-domain insights.

[0033] The Knowledge Learning Department can apply the knowledge of star talent to the education and training programs of other employees, improving the overall skills of the organization. For example, the Knowledge Learning Department analyzes the work content and skill sets of star talent and designs education programs to apply their knowledge to the education and training programs of other employees. For example, specific technical or project management skills can be incorporated into training programs. The Knowledge Learning Department can also provide the star talent's knowledge as teaching materials to be applied to education and training programs. For example, the star talent's presentations and work procedures can be used as teaching materials. The Knowledge Learning Department can also share the star talent's knowledge in training sessions to be applied to education and training programs. For example, the star talent can conduct training sessions as instructors. This allows the star talent's knowledge to be applied to the education and training of other employees, improving the overall skills of the organization.

[0034] The virtual participation department can analyze the progress of the meeting in real time and make comments at the optimal timing. For example, the virtual participation department monitors the meeting agenda and comments made to understand the progress in order to analyze the progress of the meeting in real time. For example, it automatically generates minutes and visualizes the progress. The virtual participation department can also adjust the timing of comments according to the progress in order to make comments at the optimal timing. For example, if the discussion is stagnating, it will make comments that offer a new perspective. The virtual participation department can also adjust the content of comments according to the progress. For example, if the discussion is getting heated, it will offer a calm opinion. In this way, the effectiveness of the discussion can be maximized by making comments at the optimal timing according to the progress of the meeting.

[0035] The virtual participation section analyzes the background information of meeting participants and can make statements that are optimal for each individual participant. For example, to analyze the background information of meeting participants, the virtual participation section registers and analyzes the participants' work history and expertise in a database. For example, it adjusts the content of statements based on the participants' past projects and work content. The virtual participation section can also customize the content of statements based on the participants' background information. For example, it can make statements that include technical details for participants with technical expertise. The virtual participation section can also adjust the tone and style of statements based on the participants' background information. For example, it can make statements that emphasize a business perspective for participants in managerial positions. This makes it possible to improve the quality of discussions by making optimal statements based on the participants' background information.

[0036] The virtual participation unit can participate in meetings in different languages, making it possible to handle international conferences. For example, the virtual participation unit develops a multilingual translation system to participate in meetings in different languages. For example, it translates utterances in real time and provides them to participants of different languages. The virtual participation unit can also prepare utterance content in multiple languages ​​to generate utterances in different languages. For example, it prepares utterance content in multiple languages ​​in advance depending on the agenda of the meeting. The virtual participation unit can also provide an interpretation function to support participation in meetings in different languages. For example, an interpreter translates utterance content in real time during the meeting. This makes it possible to handle international conferences by participating in meetings in different languages.

[0037] The Virtual Participation Department can automatically generate meeting minutes and share them in real time. For example, the Virtual Participation Department develops a system that analyzes meeting content in real time and creates minutes to automatically generate meeting minutes. For example, speech recognition technology can be used to convert speech content into text. The Virtual Participation Department can also use cloud storage and real-time sharing tools to share minutes in real time. For example, minutes can be stored on the cloud and made accessible to participants in real time. The Virtual Participation Department can also monitor the progress of the meeting and automatically record important remarks and decisions to automatically generate minutes. For example, minutes can be organized by agenda item and key points can be highlighted. This allows meeting minutes to be automatically generated and shared in real time, allowing participants to quickly understand the content of the meeting.

[0038] The KPI analysis department can monitor KPI achievement status in real time and immediately propose improvement measures. For example, to monitor KPI achievement status in real time, the KPI analysis department develops a system that automatically collects KPI data and visualizes it on a dashboard. For example, it displays the progress of each KPI in graphs and charts. The KPI analysis department can also analyze real-time data and derive optimal improvement measures to immediately propose improvement measures based on KPI achievement status. For example, if KPI progress is lagging, it can propose resource reallocation or process review. The KPI analysis department can also provide an alert function to monitor KPI achievement status. For example, if KPI progress does not reach the target, it can issue an alert and take immediate countermeasures. This makes it possible to monitor KPI achievement status in real time and immediately propose improvement measures, thereby improving performance.

[0039] The KPI analysis department can analyze past KPI data and make predictions based on long-term trends. For example, to analyze past KPI data, the KPI analysis department collects past KPI data from a database and develops a system that performs trend analysis. For example, it identifies trends based on data from the past few years. The KPI analysis department can also use statistical models and machine learning algorithms to make predictions based on long-term trends. For example, it predicts future KPI achievement status based on past data. The KPI analysis department can also propose long-term strategies based on the results of trend analysis. For example, it determines resource allocation and project priorities based on trends. This allows future performance to be forecasted by analyzing past KPI data and making predictions based on long-term trends.

[0040] The KPI Analysis Department can integrate KPIs from different departments to improve company-wide performance. For example, to integrate KPIs from different departments, the KPI Analysis Department collects KPI data from each department and builds an integrated database. For example, it centrally manages KPIs from the sales and manufacturing departments. The KPI Analysis Department can also propose strategies to improve company-wide performance based on the integrated KPI data. For example, it can optimize resource allocation between departments. The KPI Analysis Department can also set common evaluation criteria to integrate KPIs from different departments. For example, it can evaluate KPIs from each department based on company-wide goals. This makes it possible to integrate KPIs from different departments and improve company-wide performance.

[0041] The KPI analysis department can visualize the results of KPI discussions to make them easier to understand intuitively. For example, the KPI analysis department develops a system that automatically generates graphs and charts to visualize the results of KPI discussions. For example, it can display KPI achievement status in bar graphs or pie charts. The KPI analysis department can also organize information based on visualized data to make it easier to understand intuitively. For example, it can emphasize important points to make them easier to understand visually. The KPI analysis department can also share visualized data in real time. For example, it can display visualized data on a screen during a meeting. This makes the results of KPI discussions more visible and easier to understand, thereby increasing the effectiveness of the discussions.

[0042] The feedback unit can optimize the content of the feedback for each individual participant and provide personalized feedback. For example, the feedback unit develops a system that analyzes the work content and skill set of each participant and provides personalized feedback in order to optimize the content of the feedback for each individual participant. For example, feedback for a specific skill is provided. The feedback unit can also analyze the participant's past performance and feedback history in order to provide optimized feedback for each individual participant. For example, feedback according to the current situation is provided based on the content of past feedback. The feedback unit can also generate feedback according to the participant's goals and needs in order to provide personalized feedback. For example, feedback based on individual goals is provided. In this way, the feedback content can be optimized for each individual participant and personalized feedback can be provided, thereby promoting the growth of the recipient.

[0043] The feedback department can analyze the feedback history and identify areas for long-term improvement. For example, the feedback department collects past feedback data to analyze the feedback history and develops a system to identify areas for long-term improvement. For example, it analyzes feedback trends and identifies common areas for improvement. The feedback department can also evaluate the effectiveness of feedback to identify areas for long-term improvement. For example, it analyzes the correlation between the content of feedback and business performance and identifies effective areas for improvement. The feedback department can also analyze changes in the frequency and content of feedback to identify areas for long-term improvement. For example, it identifies areas for improvement based on changes in the frequency and content of feedback. In this way, it is possible to support continuous growth by analyzing the feedback history and identifying areas for long-term improvement.

[0044] The feedback unit can provide feedback in different formats (audio, video, text) to make it easier to understand. For example, the feedback unit can develop a system that generates feedback in audio, video, and text formats to provide feedback in different formats. For example, audio feedback can be automatically generated and provided to participants. The feedback unit can also prepare feedback content in a multimedia format to provide feedback in different formats. For example, video feedback can be created to make it easier to understand visually. The feedback unit can also use interactive feedback tools to provide feedback in different formats. For example, an interactive feedback form can be provided to allow participants to give their reactions to the feedback. This makes it easier for the recipient to understand by providing feedback in different formats.

[0045] The feedback department can apply the feedback content to other projects and achieve overall improvement. For example, the feedback department develops a system for sharing feedback data in order to apply the feedback content to other projects. For example, common improvements can be applied to other projects. The feedback department can also organize the feedback content and propose general improvement measures in order to apply it to other projects. For example, improvement measures that were effective in a particular project can be applied to other projects. The feedback department can also analyze the feedback content and identify commonalities between projects in order to apply it to other projects. For example, common issues across multiple projects can be identified and improvement measures proposed. In this way, the feedback content can be applied to other projects in order to achieve overall improvement.

[0046] The continuous learning unit analyzes the relevance of new knowledge and experience to past learning content when acquiring new knowledge and experience, enabling efficient learning. For example, the continuous learning unit develops a system that collects learning history data and identifies the relevance in order to analyze the relevance to past learning content when acquiring new knowledge and experience. For example, it analyzes commonalities between past learning content and new knowledge. The continuous learning unit can also evaluate the importance of new knowledge based on the learning history data in order to analyze the relevance to past learning content. For example, it prioritizes learning knowledge that is highly relevant to past learning content. The continuous learning unit can also create a learning plan based on the learning history data in order to analyze the relevance to past learning content. For example, it determines the learning order of new knowledge based on past learning content. In this way, efficient learning can be achieved by analyzing the relevance to past learning content when acquiring new knowledge and experience.

[0047] The continuous learning department can monitor learning progress in real time and adjust learning content as necessary. For example, the continuous learning department develops a system that automatically collects learning data and visualizes progress in order to monitor learning progress in real time. For example, learning progress is displayed in graphs and charts. The continuous learning department can also analyze real-time data and change the learning plan in order to adjust learning content according to progress. For example, if progress is lagging, the learning content can be simplified. The continuous learning department can also change the learning schedule based on the learning data in order to adjust the learning pace according to progress. For example, if progress is fast, learning content can be added. In this way, the effectiveness of learning can be maximized by monitoring learning progress in real time and adjusting learning content as necessary.

[0048] The Continuing Learning Department can share the results of continuous learning with other employees and improve overall skills. For example, the Continuing Learning Department could build a platform for sharing learning data in order to share the results of continuous learning with other employees. For example, it could develop a system for sharing learning results online. The Continuing Learning Department could also organize learning data and provide it in a format that is easy for other employees to access in order to share learning results. For example, it could compile learning results in report format and post it on an internal portal. The Continuing Learning Department could also hold regular sharing sessions to share learning results. For example, it could provide a forum for presenting learning results and share knowledge with other employees. In this way, the results of continuous learning could be shared with other employees, thereby improving overall skills.

[0049] The continuous learning department can provide learning content in different formats (text, video, interactive) to make it easier to understand. For example, the continuous learning department develops a system that generates learning content in text, video, and interactive formats to provide learning content in different formats. For example, it can provide text materials and video materials simultaneously. The continuous learning department can also use interactive learning tools to provide learning content in different formats. For example, it can provide interactive quizzes and simulations. The continuous learning department can also create learning content in multimedia formats to provide learning content in different formats. For example, it can provide learning content that combines text, video, and audio. In this way, providing learning content in different formats makes it easier for recipients to understand.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The knowledge learning department can integrate the knowledge and experience of star talent with the knowledge of experts from different industries to generate cross-domain insights. For example, the knowledge learning department collects data from experts from different industries and analyzes similarities and differences to integrate the knowledge and experience of star talent with the knowledge of experts from different industries. For example, it integrates knowledge from the technical field and the marketing field. The knowledge learning department can also collect and analyze best practices from different industries to integrate the knowledge of experts from different industries. For example, it can analyze success stories from different industries and identify common success factors. The knowledge learning department can also collect and analyze technologies and processes from different industries to integrate the knowledge of experts from different industries. For example, it can compare technologies and processes from different industries to generate cross-domain insights. This makes it possible to integrate knowledge from different industries and generate cross-domain insights.

[0052] The knowledge learning unit can learn from past failure cases of star talent and generate preventive measures to avoid similar failures. For example, to learn from past failure cases of star talent, the knowledge learning unit collects data on failures and analyzes the causes and effects of the failures. For example, it analyzes project failure cases and identifies the factors behind the failures. The knowledge learning unit can also evaluate the impact of the failures and generate preventive measures to learn from the failure cases. For example, it evaluates the impact of the failures and identifies procedures to avoid similar failures. The knowledge learning unit can also analyze failure patterns to learn from the failure cases and generate preventive measures. For example, it identifies failure patterns and proposes risk management measures to avoid similar failures. In this way, it is possible to learn from past failures and provide preventive measures to avoid similar failures.

[0053] The knowledge learning unit can analyze the nonverbal communication of star talent and reflect this in the generation AI. For example, to analyze the nonverbal communication of star talent, the knowledge learning unit collects video data from past meetings and presentations and analyzes gesture and facial expression patterns. For example, it analyzes hand movements and facial expressions to identify nonverbal characteristics of specific statements. The knowledge learning unit can also collect and analyze posture and gaze data to analyze nonverbal communication. For example, it analyzes changes in posture and gaze movements to identify characteristics of nonverbal communication. The knowledge learning unit can also collect audio data and analyze voice tone and speed to analyze nonverbal communication. For example, it analyzes changes in voice tone and speaking speed to identify characteristics of nonverbal communication. This makes it possible to generate virtual employees that take nonverbal communication into account.

[0054] The Knowledge Learning Department can apply the knowledge of star talent to the education and training programs of other employees, improving the overall skills of the organization. For example, the Knowledge Learning Department analyzes the work content and skill sets of star talent and designs education programs to apply their knowledge to the education and training programs of other employees. For example, specific technical or project management skills can be incorporated into training programs. The Knowledge Learning Department can also provide the star talent's knowledge as teaching materials to be applied to education and training programs. For example, the star talent's presentations and work procedures can be used as teaching materials. The Knowledge Learning Department can also share the star talent's knowledge in training sessions to be applied to education and training programs. For example, the star talent can conduct training sessions as instructors. This allows the star talent's knowledge to be applied to the education and training of other employees, improving the overall skills of the organization.

[0055] The virtual participation department can analyze the progress of the meeting in real time and make comments at the optimal timing. For example, the virtual participation department monitors the meeting agenda and comments made to understand the progress in order to analyze the progress of the meeting in real time. For example, it automatically generates minutes and visualizes the progress. The virtual participation department can also adjust the timing of comments according to the progress in order to make comments at the optimal timing. For example, if the discussion is stagnating, it will make comments that offer a new perspective. The virtual participation department can also adjust the content of comments according to the progress. For example, if the discussion is getting heated, it will offer a calm opinion. In this way, the effectiveness of the discussion can be maximized by making comments at the optimal timing according to the progress of the meeting.

[0056] The virtual participation section analyzes the background information of meeting participants and can make statements that are optimal for each individual participant. For example, to analyze the background information of meeting participants, the virtual participation section registers and analyzes the participants' work history and expertise in a database. For example, it adjusts the content of statements based on the participants' past projects and work content. The virtual participation section can also customize the content of statements based on the participants' background information. For example, it can make statements that include technical details for participants with technical expertise. The virtual participation section can also adjust the tone and style of statements based on the participants' background information. For example, it can make statements that emphasize a business perspective for participants in managerial positions. This makes it possible to improve the quality of discussions by making optimal statements based on the participants' background information.

[0057] The virtual participation unit can participate in meetings in different languages, making it possible to handle international conferences. For example, the virtual participation unit develops a multilingual translation system to participate in meetings in different languages. For example, it translates utterances in real time and provides them to participants of different languages. The virtual participation unit can also prepare utterance content in multiple languages ​​to generate utterances in different languages. For example, it prepares utterance content in multiple languages ​​in advance depending on the agenda of the meeting. The virtual participation unit can also provide an interpretation function to support participation in meetings in different languages. For example, an interpreter translates utterance content in real time during the meeting. This makes it possible to handle international conferences by participating in meetings in different languages.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The knowledge learning department learns the star talent's knowledge and experience. For example, the knowledge learning department analyzes the star talent's past statements, work history, project deliverables, and presentation records to learn their knowledge and experience. Step 2: The virtual participants participate in meetings and KPI discussions based on the knowledge and experience gained by the knowledge learning team. For example, they provide appropriate feedback on instructions during meetings, evaluate progress in KPI discussions, and propose improvements. Step 3: The KPI analysis unit analyzes the KPI achievement status. For example, it analyzes past data and trends, evaluates the achievement status, and proposes optimal improvement measures. It can also monitor in real time and propose improvement measures immediately. Step 4: The feedback department provides feedback on the results of meetings and discussions. For example, it automatically generates meeting minutes and shares them with relevant parties, or summarizes the results of KPI discussions and provides feedback. Step 5: The continuous learning department acquires new knowledge and experiences. For example, they analyze recordings of meetings and discussions to learn new insights and continue to learn and improve.

[0060] (Example 2) The virtual employee solution system according to an embodiment of the present invention is a system that uses a generation AI to virtualize star talent within a company and allow them to participate in meetings and KPI discussions. As a result, the virtual employee solution system can virtualize star talent within a company and support efficient decision-making and problem-solving.

[0061] The virtual employee solution system according to the embodiment includes a knowledge learning unit, a virtual participation unit, a KPI analysis unit, a feedback unit, and a continuous learning unit. The knowledge learning unit learns the knowledge and experience of star talent. For example, the knowledge learning unit analyzes the star talent's past comments and work history to learn that knowledge. The knowledge learning unit can also analyze project deliverables to learn the star talent's experience. The knowledge learning unit can also analyze recordings of presentations given by the star talent and learn their content. The virtual participation unit participates in meetings and KPI discussions based on the knowledge and experience learned by the knowledge learning unit. For example, in a meeting, in response to an instruction such as "Please give your opinion on the progress of this project," the virtual participation unit can provide appropriate opinions based on the star talent's knowledge. In KPI discussions, the virtual participation unit can also evaluate the KPI achievement status and propose improvement measures. The virtual participation unit can also make comments and suggestions in meetings and discussions. The KPI analysis unit analyzes the KPI achievement status. For example, the KPI analysis unit analyzes past data and trends to evaluate the achievement status of KPIs. The KPI analysis unit can also propose optimal improvement measures based on the achievement status of KPIs. The KPI analysis unit can also monitor the achievement status of KPIs in real time and immediately propose improvement measures. The feedback unit provides feedback on the results of meetings and discussions. For example, the feedback unit automatically generates meeting minutes and shares them with relevant parties. The feedback unit can also summarize the results of KPI discussions and provide feedback to relevant parties. The feedback unit can also accurately understand the content of meetings and discussions and use them as a reference for moving forward to the next step. The continuous learning unit acquires new knowledge and experience. For example, the continuous learning unit analyzes recordings of meetings and discussions to learn new insights. The continuous learning unit can also analyze the content of meetings and discussions to incorporate new knowledge. The continuous learning unit can continuously learn and improve, and provide more accurate opinions and suggestions. As a result, the virtual employee solution system according to the embodiment can virtualize star talent within a company and support efficient decision-making and problem-solving.For example, even if a star talent is too busy to attend a meeting, the generative AI can participate in their place and provide important opinions and suggestions.In addition, in KPI discussions, the generative AI can suggest appropriate improvement measures, leading to improved business performance.

[0062] The knowledge learning unit can analyze the emotional state of star talent and learn the impact of emotional fluctuations on knowledge and experience. To analyze the emotional state of star talent, the knowledge learning unit, for example, collects video data from past meetings and presentations and analyzes emotional fluctuations using emotion recognition technology. For example, it analyzes facial expressions and tone of voice when speaking to identify patterns of emotional fluctuations. The knowledge learning unit also analyzes the relationship between emotional fluctuations and work results to learn the impact of emotional fluctuations on knowledge and experience. For example, it identifies the impact of emotional fluctuations on project progress. The knowledge learning unit also analyzes emotional fluctuations and decision-making results to learn the impact of emotional fluctuations on decision-making. For example, it identifies the impact of emotional fluctuations on the quality of decision-making. This makes it possible to learn by taking into account the emotional state of star talent.

[0063] The knowledge learning unit can analyze the nonverbal communication of star talent and reflect this in the generation AI. For example, to analyze the nonverbal communication of star talent, the knowledge learning unit collects video data from past meetings and presentations and analyzes gesture and facial expression patterns. For example, it analyzes hand movements and facial expressions to identify nonverbal characteristics of specific statements. The knowledge learning unit can also collect and analyze posture and gaze data to analyze nonverbal communication. For example, it analyzes changes in posture and gaze movements to identify characteristics of nonverbal communication. The knowledge learning unit can also collect audio data and analyze voice tone and speed to analyze nonverbal communication. For example, it analyzes changes in voice tone and speaking speed to identify characteristics of nonverbal communication. This makes it possible to generate virtual employees that take nonverbal communication into account.

[0064] The knowledge learning unit can learn from past failure cases of star talent and generate preventive measures to avoid similar failures. For example, to learn from past failure cases of star talent, the knowledge learning unit collects data on failures and analyzes the causes and effects of the failures. For example, it analyzes project failure cases and identifies the factors behind the failures. The knowledge learning unit can also evaluate the impact of the failures and generate preventive measures to learn from the failure cases. For example, it evaluates the impact of the failures and identifies procedures to avoid similar failures. The knowledge learning unit can also analyze failure patterns to learn from the failure cases and generate preventive measures. For example, it identifies failure patterns and proposes risk management measures to avoid similar failures. In this way, it is possible to learn from past failures and provide preventive measures to avoid similar failures.

[0065] The knowledge learning department can integrate the knowledge and experience of star talent with the knowledge of experts from different industries to generate cross-domain insights. For example, the knowledge learning department collects data from experts from different industries and analyzes similarities and differences to integrate the knowledge and experience of star talent with the knowledge of experts from different industries. For example, it integrates knowledge from the technical field and the marketing field. The knowledge learning department can also collect and analyze best practices from different industries to integrate the knowledge of experts from different industries. For example, it can analyze success stories from different industries and identify common success factors. The knowledge learning department can also collect and analyze technologies and processes from different industries to integrate the knowledge of experts from different industries. For example, it can compare technologies and processes from different industries to generate cross-domain insights. This makes it possible to integrate knowledge from different industries and generate cross-domain insights.

[0066] The Knowledge Learning Department can apply the knowledge of star talent to the education and training programs of other employees, improving the overall skills of the organization. For example, the Knowledge Learning Department analyzes the work content and skill sets of star talent and designs education programs to apply their knowledge to the education and training programs of other employees. For example, specific technical or project management skills can be incorporated into training programs. The Knowledge Learning Department can also provide the star talent's knowledge as teaching materials to be applied to education and training programs. For example, the star talent's presentations and work procedures can be used as teaching materials. The Knowledge Learning Department can also share the star talent's knowledge in training sessions to be applied to education and training programs. For example, the star talent can conduct training sessions as instructors. This allows the star talent's knowledge to be applied to the education and training of other employees, improving the overall skills of the organization.

[0067] The knowledge learning unit can use the emotion estimation function to determine the priority of learning content based on the emotions of the star talent. For example, the knowledge learning unit uses the emotion estimation function to analyze the emotional state of the star talent in real time and determine the priority of learning content based on emotions. For example, important knowledge is learned when positive emotions are strong. The knowledge learning unit can also use the emotion estimation function to adjust the priority of learning content according to emotional fluctuations. For example, the learning content can be changed according to emotional fluctuations to achieve efficient learning. The knowledge learning unit can also use the emotion estimation function to create a learning plan based on emotions. For example, the timing and content of learning can be adjusted according to the emotional state. In this way, learning efficiency can be improved by determining the priority of learning content based on emotions.

[0068] The virtual participation unit can perform real-time emotion analysis during a meeting and generate emotion-based utterances. For example, to perform real-time emotion analysis during a meeting, the virtual participation unit analyzes the facial expressions and tone of voice of participants to identify their emotional state. For example, emotion data is collected using a camera or microphone. The virtual participation unit can also adjust the content of utterances based on the results of the emotion analysis to generate emotion-based utterances. For example, if a participant is nervous, it can make utterances to relax them. The virtual participation unit can also change the content of utterances in accordance with emotional fluctuations in order to generate emotion-based utterances. For example, it can adjust the tone and content of utterances in accordance with emotional fluctuations. In this way, by generating utterances based on emotions during a meeting, it is possible to adjust the atmosphere of the meeting and promote effective discussions.

[0069] The virtual participation department can analyze the progress of the meeting in real time and make comments at the optimal timing. For example, the virtual participation department monitors the meeting agenda and comments made to understand the progress in order to analyze the progress of the meeting in real time. For example, it automatically generates minutes and visualizes the progress. The virtual participation department can also adjust the timing of comments according to the progress in order to make comments at the optimal timing. For example, if the discussion is stagnating, it will make comments that offer a new perspective. The virtual participation department can also adjust the content of comments according to the progress. For example, if the discussion is getting heated, it will offer a calm opinion. In this way, the effectiveness of the discussion can be maximized by making comments at the optimal timing according to the progress of the meeting.

[0070] The virtual participation section analyzes the background information of meeting participants and can make statements that are optimal for each individual participant. For example, to analyze the background information of meeting participants, the virtual participation section registers and analyzes the participants' work history and expertise in a database. For example, it adjusts the content of statements based on the participants' past projects and work content. The virtual participation section can also customize the content of statements based on the participants' background information. For example, it can make statements that include technical details for participants with technical expertise. The virtual participation section can also adjust the tone and style of statements based on the participants' background information. For example, it can make statements that emphasize a business perspective for participants in managerial positions. This makes it possible to improve the quality of discussions by making optimal statements based on the participants' background information.

[0071] The virtual participation unit can participate in meetings in different languages, making it possible to handle international conferences. For example, the virtual participation unit develops a multilingual translation system to participate in meetings in different languages. For example, it translates utterances in real time and provides them to participants of different languages. The virtual participation unit can also prepare utterance content in multiple languages ​​to generate utterances in different languages. For example, it prepares utterance content in multiple languages ​​in advance depending on the agenda of the meeting. The virtual participation unit can also provide an interpretation function to support participation in meetings in different languages. For example, an interpreter translates utterance content in real time during the meeting. This makes it possible to handle international conferences by participating in meetings in different languages.

[0072] The Virtual Participation Department can automatically generate meeting minutes and share them in real time. For example, the Virtual Participation Department develops a system that analyzes meeting content in real time and creates minutes to automatically generate meeting minutes. For example, speech recognition technology can be used to convert speech content into text. The Virtual Participation Department can also use cloud storage and real-time sharing tools to share minutes in real time. For example, minutes can be stored on the cloud and made accessible to participants in real time. The Virtual Participation Department can also monitor the progress of the meeting and automatically record important remarks and decisions to automatically generate minutes. For example, minutes can be organized by agenda item and key points can be highlighted. This allows meeting minutes to be automatically generated and shared in real time, allowing participants to quickly understand the content of the meeting.

[0073] The virtual participation unit can use the emotion estimation function to make statements according to the emotions of participants during a meeting and adjust the atmosphere of the meeting. For example, the virtual participation unit develops a system that uses the emotion estimation function to analyze the emotional state of participants during a meeting in real time and make statements according to their emotions. For example, if a participant is nervous, the virtual participation unit makes statements to relax them. The virtual participation unit can also use the emotion estimation function to adjust the content of statements according to emotional fluctuations. For example, if a participant is excited, the virtual participation unit makes calm statements. The virtual participation unit can also use the emotion estimation function to provide feedback based on emotions. For example, if a participant is feeling anxious, the virtual participation unit provides reassuring feedback. In this way, by making statements according to the emotions of participants during a meeting, the atmosphere of the meeting can be adjusted and effective discussions can be promoted.

[0074] The KPI analysis department can monitor KPI achievement status in real time and immediately propose improvement measures. For example, to monitor KPI achievement status in real time, the KPI analysis department develops a system that automatically collects KPI data and visualizes it on a dashboard. For example, it displays the progress of each KPI in graphs and charts. The KPI analysis department can also analyze real-time data and derive optimal improvement measures to immediately propose improvement measures based on KPI achievement status. For example, if KPI progress is lagging, it can propose resource reallocation or process review. The KPI analysis department can also provide an alert function to monitor KPI achievement status. For example, if KPI progress does not reach the target, it can issue an alert and take immediate countermeasures. This makes it possible to monitor KPI achievement status in real time and immediately propose improvement measures, thereby improving performance.

[0075] The KPI analysis department can analyze past KPI data and make predictions based on long-term trends. For example, to analyze past KPI data, the KPI analysis department collects past KPI data from a database and develops a system that performs trend analysis. For example, it identifies trends based on data from the past few years. The KPI analysis department can also use statistical models and machine learning algorithms to make predictions based on long-term trends. For example, it predicts future KPI achievement status based on past data. The KPI analysis department can also propose long-term strategies based on the results of trend analysis. For example, it determines resource allocation and project priorities based on trends. This allows future performance to be forecasted by analyzing past KPI data and making predictions based on long-term trends.

[0076] The KPI analysis department can analyze emotions during KPI discussions and propose improvement measures based on those emotions. For example, to perform emotion analysis during KPI discussions, the KPI analysis department develops a system that analyzes participants' facial expressions and tone of voice to identify their emotional state. For example, it collects emotional data using a camera or microphone. The KPI analysis department can also derive improvement measures based on the results of the emotion analysis in order to propose emotion-based improvement measures. For example, if a participant is feeling stressed, it can propose process improvement measures to reduce stress. The KPI analysis department can also adjust the progress of the discussion based on the results of the emotion analysis. For example, if a participant is feeling anxious, it can provide feedback to reassure them. In this way, by performing emotion analysis during KPI discussions and proposing improvement measures based on emotions, the quality of the discussion can be improved.

[0077] The KPI Analysis Department can integrate KPIs from different departments to improve company-wide performance. For example, to integrate KPIs from different departments, the KPI Analysis Department collects KPI data from each department and builds an integrated database. For example, it centrally manages KPIs from the sales and manufacturing departments. The KPI Analysis Department can also propose strategies to improve company-wide performance based on the integrated KPI data. For example, it can optimize resource allocation between departments. The KPI Analysis Department can also set common evaluation criteria to integrate KPIs from different departments. For example, it can evaluate KPIs from each department based on company-wide goals. This makes it possible to integrate KPIs from different departments and improve company-wide performance.

[0078] The KPI analysis department can visualize the results of KPI discussions to make them easier to understand intuitively. For example, the KPI analysis department develops a system that automatically generates graphs and charts to visualize the results of KPI discussions. For example, it can display KPI achievement status in bar graphs or pie charts. The KPI analysis department can also organize information based on visualized data to make it easier to understand intuitively. For example, it can emphasize important points to make them easier to understand visually. The KPI analysis department can also share visualized data in real time. For example, it can display visualized data on a screen during a meeting. This makes the results of KPI discussions more visible and easier to understand, thereby increasing the effectiveness of the discussions.

[0079] The KPI analysis unit can use the emotion estimation function to provide feedback based on the emotions of participants during KPI discussions. For example, the KPI analysis unit uses the emotion estimation function to develop a system that analyzes the emotional state of participants during KPI discussions in real time and provides feedback based on their emotions. For example, if a participant is feeling stressed, it can provide feedback to relax them. The KPI analysis unit can also use the emotion estimation function to adjust the content of the feedback according to emotional fluctuations. For example, if a participant is feeling anxious, it can provide feedback to reassure them. The KPI analysis unit can also use the emotion estimation function to suggest improvement measures based on emotions. For example, if a participant is feeling motivated, it can provide feedback to maintain that motivation. In this way, by providing feedback based on the emotions of participants during KPI discussions, the quality of discussions can be improved.

[0080] The feedback unit can perform sentiment analysis on the content of the feedback and emphasize positive feedback. For example, to sentiment analyze the content of the feedback, the feedback unit develops a system that analyzes text data and identifies feedback with positive sentiment. For example, an sentiment analysis algorithm is used to calculate a sentiment score of the feedback. The feedback unit can also preferentially display feedback with a high sentiment score to emphasize positive feedback. For example, the feedback unit can highlight positive feedback and communicate this to the recipient. The feedback unit can also visually emphasize the content of the feedback to emphasize positive feedback. For example, the feedback unit can highlight positive feedback with a different color or font. In this way, by sentiment analyzing the content of the feedback and emphasizing positive feedback, it is possible to improve the motivation of the recipient.

[0081] The feedback unit can optimize the content of the feedback for each individual participant and provide personalized feedback. For example, the feedback unit develops a system that analyzes the work content and skill set of each participant and provides personalized feedback in order to optimize the content of the feedback for each individual participant. For example, feedback for a specific skill is provided. The feedback unit can also analyze the participant's past performance and feedback history in order to provide optimized feedback for each individual participant. For example, feedback according to the current situation is provided based on the content of past feedback. The feedback unit can also generate feedback according to the participant's goals and needs in order to provide personalized feedback. For example, feedback based on individual goals is provided. In this way, the feedback content can be optimized for each individual participant and personalized feedback can be provided, thereby promoting the growth of the recipient.

[0082] The feedback department can analyze the feedback history and identify areas for long-term improvement. For example, the feedback department collects past feedback data to analyze the feedback history and develops a system to identify areas for long-term improvement. For example, it analyzes feedback trends and identifies common areas for improvement. The feedback department can also evaluate the effectiveness of feedback to identify areas for long-term improvement. For example, it analyzes the correlation between the content of feedback and business performance and identifies effective areas for improvement. The feedback department can also analyze changes in the frequency and content of feedback to identify areas for long-term improvement. For example, it identifies areas for improvement based on changes in the frequency and content of feedback. In this way, it is possible to support continuous growth by analyzing the feedback history and identifying areas for long-term improvement.

[0083] The feedback unit can provide feedback in different formats (audio, video, text) to make it easier to understand. For example, the feedback unit can develop a system that generates feedback in audio, video, and text formats to provide feedback in different formats. For example, audio feedback can be automatically generated and provided to participants. The feedback unit can also prepare feedback content in a multimedia format to provide feedback in different formats. For example, video feedback can be created to make it easier to understand visually. The feedback unit can also use interactive feedback tools to provide feedback in different formats. For example, an interactive feedback form can be provided to allow participants to give their reactions to the feedback. This makes it easier for the recipient to understand by providing feedback in different formats.

[0084] The feedback department can apply the feedback content to other projects and achieve overall improvement. For example, the feedback department develops a system for sharing feedback data in order to apply the feedback content to other projects. For example, common improvements can be applied to other projects. The feedback department can also organize the feedback content and propose general improvement measures in order to apply it to other projects. For example, improvement measures that were effective in a particular project can be applied to other projects. The feedback department can also analyze the feedback content and identify commonalities between projects in order to apply it to other projects. For example, common issues across multiple projects can be identified and improvement measures proposed. In this way, the feedback content can be applied to other projects in order to achieve overall improvement.

[0085] The feedback unit can use the emotion estimation function to provide content that corresponds to the emotions of the feedback recipient. For example, the feedback unit uses the emotion estimation function to develop a system that analyzes the emotional state of the feedback recipient in real time and provides feedback that corresponds to the emotions. For example, if the recipient is feeling stressed, the feedback unit provides feedback that relaxes the recipient. The feedback unit can also use the emotion estimation function to adjust the content of the feedback according to emotional fluctuations. For example, if the recipient is feeling anxious, the feedback unit provides feedback that reassures the recipient. The feedback unit can also use the emotion estimation function to adjust the tone and style of the feedback to provide feedback based on emotions. For example, the feedback unit provides feedback that elicits positive emotions. In this way, by providing content that corresponds to the emotions of the feedback recipient, the recipient's receptivity can be increased.

[0086] The continuous learning unit can use the emotion estimation function to determine the priority of learning content based on emotions during continuous learning. The continuous learning unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time during continuous learning and develop a system that determines the priority of learning content based on emotions. For example, important knowledge is learned when positive emotions are strong. The continuous learning unit can also use the emotion estimation function to adjust the priority of learning content according to emotional fluctuations. For example, the learning content can be changed according to emotional fluctuations to achieve efficient learning. The continuous learning unit can also use the emotion estimation function to create a learning plan based on emotions. For example, the timing and content of learning can be adjusted according to the emotional state. In this way, learning efficiency can be improved by determining the priority of learning content based on emotions.

[0087] The continuous learning unit analyzes the relevance of new knowledge and experience to past learning content when acquiring new knowledge and experience, enabling efficient learning. For example, the continuous learning unit develops a system that collects learning history data and identifies the relevance in order to analyze the relevance to past learning content when acquiring new knowledge and experience. For example, it analyzes commonalities between past learning content and new knowledge. The continuous learning unit can also evaluate the importance of new knowledge based on the learning history data in order to analyze the relevance to past learning content. For example, it prioritizes learning knowledge that is highly relevant to past learning content. The continuous learning unit can also create a learning plan based on the learning history data in order to analyze the relevance to past learning content. For example, it determines the learning order of new knowledge based on past learning content. In this way, efficient learning can be achieved by analyzing the relevance to past learning content when acquiring new knowledge and experience.

[0088] The continuous learning department can monitor learning progress in real time and adjust learning content as necessary. For example, the continuous learning department develops a system that automatically collects learning data and visualizes progress in order to monitor learning progress in real time. For example, learning progress is displayed in graphs and charts. The continuous learning department can also analyze real-time data and change the learning plan in order to adjust learning content according to progress. For example, if progress is lagging, the learning content can be simplified. The continuous learning department can also change the learning schedule based on the learning data in order to adjust the learning pace according to progress. For example, if progress is fast, learning content can be added. In this way, the effectiveness of learning can be maximized by monitoring learning progress in real time and adjusting learning content as necessary.

[0089] The Continuing Learning Department can share the results of continuous learning with other employees and improve overall skills. For example, the Continuing Learning Department could build a platform for sharing learning data in order to share the results of continuous learning with other employees. For example, it could develop a system for sharing learning results online. The Continuing Learning Department could also organize learning data and provide it in a format that is easy for other employees to access in order to share learning results. For example, it could compile learning results in report format and post it on an internal portal. The Continuing Learning Department could also hold regular sharing sessions to share learning results. For example, it could provide a forum for presenting learning results and share knowledge with other employees. In this way, the results of continuous learning could be shared with other employees, thereby improving overall skills.

[0090] The continuous learning department can provide learning content in different formats (text, video, interactive) to make it easier to understand. For example, the continuous learning department develops a system that generates learning content in text, video, and interactive formats to provide learning content in different formats. For example, it can provide text materials and video materials simultaneously. The continuous learning department can also use interactive learning tools to provide learning content in different formats. For example, it can provide interactive quizzes and simulations. The continuous learning department can also create learning content in multimedia formats to provide learning content in different formats. For example, it can provide learning content that combines text, video, and audio. In this way, providing learning content in different formats makes it easier for recipients to understand.

[0091] The continuous learning unit can use the emotion estimation function to provide feedback based on emotions during learning, thereby improving learning effectiveness. The continuous learning unit, for example, uses the emotion estimation function to develop a system that analyzes the emotional state during learning in real time and provides feedback based on emotions. For example, if the learner is feeling stressed, it provides feedback to relax the learner. The continuous learning unit can also use the emotion estimation function to adjust the content of the feedback according to emotional fluctuations. For example, if the learner is feeling anxious, it provides feedback to reassure the learner. The continuous learning unit can also use the emotion estimation function to create a learning plan based on emotions. For example, it adjusts the timing and content of learning according to the emotional state. In this way, by providing feedback based on emotions during learning, it is possible to improve learning effectiveness.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The knowledge learning department can integrate the knowledge and experience of star talent with the knowledge of experts from different industries to generate cross-domain insights. For example, the knowledge learning department collects data from experts from different industries and analyzes similarities and differences to integrate the knowledge and experience of star talent with the knowledge of experts from different industries. For example, it integrates knowledge from the technical field and the marketing field. The knowledge learning department can also collect and analyze best practices from different industries to integrate the knowledge of experts from different industries. For example, it can analyze success stories from different industries and identify common success factors. The knowledge learning department can also collect and analyze technologies and processes from different industries to integrate the knowledge of experts from different industries. For example, it can compare technologies and processes from different industries to generate cross-domain insights. This makes it possible to integrate knowledge from different industries and generate cross-domain insights.

[0094] The knowledge learning unit can learn from past failure cases of star talent and generate preventive measures to avoid similar failures. For example, to learn from past failure cases of star talent, the knowledge learning unit collects data on failures and analyzes the causes and effects of the failures. For example, it analyzes project failure cases and identifies the factors behind the failures. The knowledge learning unit can also evaluate the impact of the failures and generate preventive measures to learn from the failure cases. For example, it evaluates the impact of the failures and identifies procedures to avoid similar failures. The knowledge learning unit can also analyze failure patterns to learn from the failure cases and generate preventive measures. For example, it identifies failure patterns and proposes risk management measures to avoid similar failures. In this way, it is possible to learn from past failures and provide preventive measures to avoid similar failures.

[0095] The knowledge learning unit can analyze the nonverbal communication of star talent and reflect this in the generation AI. For example, to analyze the nonverbal communication of star talent, the knowledge learning unit collects video data from past meetings and presentations and analyzes gesture and facial expression patterns. For example, it analyzes hand movements and facial expressions to identify nonverbal characteristics of specific statements. The knowledge learning unit can also collect and analyze posture and gaze data to analyze nonverbal communication. For example, it analyzes changes in posture and gaze movements to identify characteristics of nonverbal communication. The knowledge learning unit can also collect audio data and analyze voice tone and speed to analyze nonverbal communication. For example, it analyzes changes in voice tone and speaking speed to identify characteristics of nonverbal communication. This makes it possible to generate virtual employees that take nonverbal communication into account.

[0096] The Knowledge Learning Department can apply the knowledge of star talent to the education and training programs of other employees, improving the overall skills of the organization. For example, the Knowledge Learning Department analyzes the work content and skill sets of star talent and designs education programs to apply their knowledge to the education and training programs of other employees. For example, specific technical or project management skills can be incorporated into training programs. The Knowledge Learning Department can also provide the star talent's knowledge as teaching materials to be applied to education and training programs. For example, the star talent's presentations and work procedures can be used as teaching materials. The Knowledge Learning Department can also share the star talent's knowledge in training sessions to be applied to education and training programs. For example, the star talent can conduct training sessions as instructors. This allows the star talent's knowledge to be applied to the education and training of other employees, improving the overall skills of the organization.

[0097] The knowledge learning unit can analyze the emotional state of star talent and learn the impact of emotional fluctuations on knowledge and experience. To analyze the emotional state of star talent, the knowledge learning unit, for example, collects video data from past meetings and presentations and analyzes emotional fluctuations using emotion recognition technology. For example, it analyzes facial expressions and tone of voice when speaking to identify patterns of emotional fluctuations. The knowledge learning unit also analyzes the relationship between emotional fluctuations and work results to learn the impact of emotional fluctuations on knowledge and experience. For example, it identifies the impact of emotional fluctuations on project progress. The knowledge learning unit also analyzes emotional fluctuations and decision-making results to learn the impact of emotional fluctuations on decision-making. For example, it identifies the impact of emotional fluctuations on the quality of decision-making. This makes it possible to learn by taking into account the emotional state of star talent.

[0098] The knowledge learning unit can use the emotion estimation function to determine the priority of learning content based on the emotions of the star talent. For example, the knowledge learning unit uses the emotion estimation function to analyze the emotional state of the star talent in real time and determine the priority of learning content based on emotions. For example, important knowledge is learned when positive emotions are strong. The knowledge learning unit can also use the emotion estimation function to adjust the priority of learning content according to emotional fluctuations. For example, the learning content can be changed according to emotional fluctuations to achieve efficient learning. The knowledge learning unit can also use the emotion estimation function to create a learning plan based on emotions. For example, the timing and content of learning can be adjusted according to the emotional state. In this way, learning efficiency can be improved by determining the priority of learning content based on emotions.

[0099] The virtual participation unit can perform real-time emotion analysis during a meeting and generate emotion-based utterances. For example, to perform real-time emotion analysis during a meeting, the virtual participation unit analyzes the facial expressions and tone of voice of participants to identify their emotional state. For example, emotion data is collected using a camera or microphone. The virtual participation unit can also adjust the content of utterances based on the results of the emotion analysis to generate emotion-based utterances. For example, if a participant is nervous, it can make utterances to relax them. The virtual participation unit can also change the content of utterances in accordance with emotional fluctuations in order to generate emotion-based utterances. For example, it can adjust the tone and content of utterances in accordance with emotional fluctuations. In this way, by generating utterances based on emotions during a meeting, it is possible to adjust the atmosphere of the meeting and promote effective discussions.

[0100] The virtual participation department can analyze the progress of the meeting in real time and make comments at the optimal timing. For example, the virtual participation department monitors the meeting agenda and comments made to understand the progress in order to analyze the progress of the meeting in real time. For example, it automatically generates minutes and visualizes the progress. The virtual participation department can also adjust the timing of comments according to the progress in order to make comments at the optimal timing. For example, if the discussion is stagnating, it will make comments that offer a new perspective. The virtual participation department can also adjust the content of comments according to the progress. For example, if the discussion is getting heated, it will offer a calm opinion. In this way, the effectiveness of the discussion can be maximized by making comments at the optimal timing according to the progress of the meeting.

[0101] The virtual participation section analyzes the background information of meeting participants and can make statements that are optimal for each individual participant. For example, to analyze the background information of meeting participants, the virtual participation section registers and analyzes the participants' work history and expertise in a database. For example, it adjusts the content of statements based on the participants' past projects and work content. The virtual participation section can also customize the content of statements based on the participants' background information. For example, it can make statements that include technical details for participants with technical expertise. The virtual participation section can also adjust the tone and style of statements based on the participants' background information. For example, it can make statements that emphasize a business perspective for participants in managerial positions. This makes it possible to improve the quality of discussions by making optimal statements based on the participants' background information.

[0102] The virtual participation unit can participate in meetings in different languages, making it possible to handle international conferences. For example, the virtual participation unit develops a multilingual translation system to participate in meetings in different languages. For example, it translates utterances in real time and provides them to participants of different languages. The virtual participation unit can also prepare utterance content in multiple languages ​​to generate utterances in different languages. For example, it prepares utterance content in multiple languages ​​in advance depending on the agenda of the meeting. The virtual participation unit can also provide an interpretation function to support participation in meetings in different languages. For example, an interpreter translates utterance content in real time during the meeting. This makes it possible to handle international conferences by participating in meetings in different languages.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: The knowledge learning department learns the star talent's knowledge and experience. For example, the knowledge learning department analyzes the star talent's past statements, work history, project deliverables, and presentation records to learn their knowledge and experience. Step 2: The virtual participants participate in meetings and KPI discussions based on the knowledge and experience gained by the knowledge learning team. For example, they provide appropriate feedback on instructions during meetings, evaluate progress in KPI discussions, and propose improvements. Step 3: The KPI analysis unit analyzes the KPI achievement status. For example, it analyzes past data and trends, evaluates the achievement status, and proposes optimal improvement measures. It can also monitor in real time and propose improvement measures immediately. Step 4: The feedback department provides feedback on the results of meetings and discussions. For example, it automatically generates meeting minutes and shares them with relevant parties, or summarizes the results of KPI discussions and provides feedback. Step 5: The continuous learning department acquires new knowledge and experiences. For example, they analyze recordings of meetings and discussions to learn new insights and continue to learn and improve.

[0105] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0106] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0107] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0108] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0109] 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.

[0110] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0111] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0112] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0113] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0114] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0115] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0116] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0117] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0118] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0119] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0120] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0121] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0122] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0125] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0126] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0131] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0132] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0133] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0134] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0137] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 7, a 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.

[0140] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0145] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0146] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0147] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0148] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0149] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0150] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0151] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0152] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0155] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0156] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0157] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0158] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0159] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0160] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0161] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0162] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0163] 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.

[0164] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0165] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0166] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0167] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0168] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0169] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0170] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0171] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0172] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. The Knowledge Learning Department studies the knowledge and experience of star talent, a virtual participation department that participates in meetings and KPI discussions based on the knowledge and experience learned by the knowledge learning department; A KPI analysis department that analyzes the achievement status of KPIs, A feedback department that provides feedback on the results of meetings and discussions; A continuing learning department where new knowledge and experience can be acquired. A system characterized by:

2. The knowledge learning unit Integrate the knowledge and experience of the star talent with the knowledge of experts in different industries to generate cross-domain insights 2. The system of claim 1.

3. The virtual participation unit: Perform real-time sentiment analysis during the meeting and generate sentiment-based statements 2. The system of claim 1.

4. The KPI analysis unit Monitor the achievement status of the KPIs in real time and propose immediate improvement measures 2. The system of claim 1.

5. The feedback unit Sentiment analysis of the feedback content and emphasis on positive feedback 2. The system of claim 1.

6. The continuous learning unit Prioritizing emotion-based learning content during ongoing learning 2. The system of claim 1.

Images