system

Abstract

The system according to the embodiment aims to identify only necessary meetings and realize efficient communication. [Solution] A system according to an embodiment includes a learning unit, an evaluation unit, and an analysis unit. The learning unit conducts collaborative learning between new employees and AI. The evaluation unit evaluates information obtained by the learning unit. The analysis unit identifies necessary meetings based on the information evaluated by the evaluation unit.

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 the problem of requiring a large number of meetings, making it difficult to communicate efficiently.

[0005] The system according to the embodiment aims to identify only necessary meetings and realize efficient communication. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning unit, an evaluation unit, and an analysis unit. The learning unit conducts collaborative learning between new employees and the AI. The evaluation unit evaluates the information obtained by the learning unit. The analysis unit identifies necessary meetings based on the information evaluated by the evaluation unit. [Effects of the Invention]

[0007] The system according to the embodiment can identify only necessary meetings and achieve efficient communication. [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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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) A communication efficiency system according to an embodiment of the present invention promotes organizational knowledge sharing and identifies only necessary meetings through collaborative learning between new employees and AI. The communication efficiency system improves communication within an organization by allowing new employees and AI to learn from each other. This system uses multifaceted evaluation by AI to identify only necessary meetings, contributing to improved employee performance. For example, in this communication efficiency system, new employees teach the AI ​​their work-related knowledge and skills while simultaneously receiving feedback from the AI. For example, the new employee explains the work process, and the AI ​​understands the content and provides appropriate advice. Next, the communication efficiency system uses AI to analyze emails and chats between employees, meeting minutes, and other information to identify which meetings are truly necessary. This reduces unnecessary meetings and enables only necessary meetings to be held. Furthermore, the communication efficiency system uses AI to evaluate the progress of work and the quality of deliverables and propose specific improvement measures. This allows employees to review their work and proceed more efficiently. This allows the communication efficiency system to achieve an efficient workflow and improve productivity throughout the organization. This reduces unnecessary meetings and improves employee performance. For example, by reducing unnecessary meetings, employees can focus on their core tasks. Also, receiving feedback from AI improves the quality of work, leading to improved performance across the organization.

[0029] A communication efficiency improvement system according to an embodiment includes a learning unit, an evaluation unit, and an analysis unit. The learning unit allows new employees and an AI to jointly learn. For example, the new employees teach the AI ​​knowledge and skills related to their work. For example, the learning unit allows the new employees to explain a work process, and the AI ​​can understand the content and provide appropriate advice. The learning unit also allows the AI ​​to provide feedback to the new employees. The evaluation unit evaluates information obtained by the learning unit. For example, the evaluation unit analyzes emails and chats between employees, meeting minutes, etc. The evaluation unit can analyze communication content and extract important information using natural language processing technology, for example. The evaluation unit can also evaluate the progress of work and the quality of deliverables using AI. For example, the evaluation unit monitors the progress of work in real time and evaluates the degree of progress. The analysis unit identifies necessary meetings based on the information evaluated by the evaluation unit. For example, the analysis unit can identify which meetings are truly necessary using AI. The analysis unit analyzes, for example, the purpose, participants, and agenda of a meeting to determine its necessity. As a result, the communication efficiency system according to the embodiment can promote knowledge sharing within an organization through collaborative learning between new employees and AI, and by identifying only necessary meetings, it can realize an efficient workflow and improve productivity throughout the organization.

[0030] The learning unit allows new employees to teach the AI ​​their work-related knowledge and skills. Examples of knowledge and skills include, but are not limited to, technical knowledge and business process skills. For example, the learning unit allows new employees to explain a business process, and the AI ​​can understand the content and provide appropriate advice. Furthermore, when new employees teach the AI ​​their work-related knowledge, the learning unit allows the AI ​​to learn that knowledge and provide similar knowledge to other employees in the future. For example, the learning unit allows new employees to explain work procedures, and the AI ​​can learn those procedures and explain those procedures to other employees. This allows new employees to teach the AI ​​their work-related knowledge and skills, and the AI ​​can learn that knowledge, promoting knowledge sharing within the organization. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit may input voice data in which a new employee explains a business process into the generation AI, which can then understand the content and provide appropriate advice.

[0031] The evaluation unit can analyze the content of emails and chats between employees and meeting minutes. For example, natural language processing technology can be used for the analysis. For example, the evaluation unit can analyze the content of emails between employees and extract important information. The evaluation unit can also analyze the content of chats and analyze communication patterns. Furthermore, the evaluation unit can analyze meeting minutes and extract key points of discussions. For example, the evaluation unit can use natural language processing technology to analyze the content of emails and chats and extract important keywords and phrases. The evaluation unit can also analyze meeting minutes and extract key points and conclusions of discussions. By analyzing the content of communication between employees, it is possible to identify necessary meetings and reduce unnecessary meetings. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without AI. For example, the evaluation unit can input the content of emails and chats between employees into a generation AI, which can extract important information.

[0032] The analysis unit can identify which meetings are necessary. The determination of whether a meeting is necessary includes, but is not limited to, the purpose, participants, and agenda of the meeting. For example, the analysis unit can analyze the purpose of the meeting and evaluate its importance. The analysis unit can also analyze the roles and involvement of participants to determine the necessity of the meeting. Furthermore, the analysis unit can analyze the content of the agenda and evaluate its urgency and importance. For example, the analysis unit can use AI to analyze the purpose, participants, and agenda of the meeting and determine its necessity. This allows for identifying only necessary meetings, thereby reducing unnecessary meetings and realizing an efficient workflow. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit can input information about the meeting agenda and participants into a generation AI, which then determines the necessity of the meeting.

[0033] The evaluation unit can evaluate the progress of work and the quality of deliverables. Examples of progress include, but are not limited to, the degree of task completion and deadline compliance. For example, the evaluation unit can monitor the progress of work in real time and evaluate the degree of progress. The evaluation unit can also use quality standards, error rates, user feedback, and the like to evaluate the quality of deliverables. For example, the evaluation unit can evaluate the degree of task completion and grasp the progress. The evaluation unit can also evaluate the quality of deliverables and perform evaluations based on the quality standards. This contributes to improving employee performance by evaluating the progress of work and the quality of deliverables. Some or all of the above-described processing in the evaluation unit can be performed using, for example, AI, or without AI. For example, the evaluation unit can input data on the progress of work and the quality of deliverables into a generation AI, which then performs evaluations.

[0034] The evaluation unit can propose specific improvement measures. Specific improvement measures include, but are not limited to, steps for improvement, required resources, and implementation timing. For example, the evaluation unit can evaluate the progress of work and the quality of deliverables and propose specific improvement measures. For example, the evaluation unit can suggest a review of task priorities based on the progress. The evaluation unit can also propose specific steps for improving quality based on the quality of the deliverables. Furthermore, the evaluation unit can also propose required resources and implementation timing. For example, the evaluation unit can use AI to evaluate the progress of work and the quality of deliverables and propose specific improvement measures. By proposing specific improvement measures, employees can review their own work and proceed more efficiently. Some or all of the above-described processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input data on the progress of work and the quality of deliverables into a generation AI, which then proposes specific improvement measures.

[0035] The learning unit can analyze the new employee's past learning history and select an appropriate learning method. Learning history includes, but is not limited to, past learning results, learning frequency, and learning format. For example, the learning unit can suggest a similar learning method based on a learning method that the new employee has used successfully in the past. The learning unit can also suggest an alternative method, avoiding learning methods that the new employee has struggled with in the past. Furthermore, the learning unit can suggest the most effective study time based on the new employee's past learning history. For example, the learning unit can use AI to analyze the new employee's past learning history and select an appropriate learning method. This can improve learning effectiveness by selecting the optimal learning method based on the new employee's past learning history. Some or all of the above-described processing in the learning unit can be performed using AI, for example, or without AI. For example, the learning unit can input the new employee's past learning history data into a generation AI, which can then select an appropriate learning method.

[0036] The learning unit can provide customized learning content based on the new employee's current work situation and areas of interest. Examples of work situation include, but are not limited to, current tasks, project progress, and work priorities. For example, the learning unit can provide learning content related to the project the new employee is currently working on. The learning unit can also prioritize providing learning content related to the new employee's areas of interest. Furthermore, the learning unit can provide learning content that strengthens necessary skills according to the new employee's work situation. For example, the learning unit can use AI to provide customized learning content based on the new employee's current work situation and areas of interest. This maximizes the learning effect by providing learning content tailored to the new employee's work situation and areas of interest. Some or all of the above-described processing in the learning unit can be performed using AI, for example, or without AI. For example, the learning unit can input data on the new employee's work situation and areas of interest into a generation AI, which then provides customized learning content.

[0037] The learning unit can select an appropriate learning means depending on the new employee's input method. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, if the new employee prefers voice input, the learning unit can provide audio learning content. Furthermore, if the new employee prefers text input, the learning unit can provide text-based learning content. Furthermore, if the new employee prefers images and visuals, the learning unit can provide learning means that make extensive use of visual content. For example, the learning unit can use AI to select an appropriate learning means depending on the new employee's input method. This maximizes the learning effect by providing learning means that correspond to the new employee's input method. Some or all of the above-described processing in the learning unit can be performed using AI, for example, or without AI. For example, the learning unit can input data on the new employee's input method into a generation AI, which can select an appropriate learning means.

[0038] The learning unit can prioritize providing relevant learning content based on the new employee's geographic location information. Examples of geographic location information include, but are not limited to, GPS data, IP addresses, and location information services. For example, if the new employee is in a specific region, the learning unit can provide business knowledge related to that region. Furthermore, if the new employee is on a business trip, the learning unit can provide learning content related to the business trip destination. Furthermore, if the new employee is working remotely, the learning unit can provide skills related to remote work. For example, the learning unit can use AI to prioritize providing relevant learning content based on the new employee's geographic location information. This maximizes the learning effect by providing learning content based on the new employee's geographic location information. Some or all of the above-described processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the new employee's geographic location data into a generation AI, which can then provide relevant learning content.

[0039] The learning unit can analyze the new employee's social media activity and provide relevant learning content. Social media activity includes, but is not limited to, the content of posts, follower responses, and activity frequency. For example, the learning unit can provide learning content related to topics the new employee has shown interest in on social media. The learning unit can also provide learning content that incorporates the opinions of experts the new employee follows on social media. Furthermore, the learning unit can suggest learning content that may be of interest to the new employee based on the new employee's social media activity. For example, the learning unit can use AI to analyze the new employee's social media activity and provide relevant learning content. This maximizes the learning effect by providing learning content based on the new employee's social media activity. Some or all of the above-described processing in the learning unit can be performed using AI, for example, or without AI. For example, the learning unit can input the new employee's social media activity data into a generation AI, which then provides relevant learning content.

[0040] The learning unit can customize the learning method by reflecting the new employee's past feedback. Examples of feedback include, but are not limited to, past evaluations, comments, and improvement suggestions. For example, the learning unit can provide a learning method that the new employee previously enjoyed. The learning unit can also avoid a learning method that the new employee previously dissatisfied with and provide an alternative method. Furthermore, the learning unit can improve and provide learning content based on the new employee's past feedback. For example, the learning unit can use AI to customize the learning method by reflecting the new employee's past feedback. This maximizes the learning effect by providing a learning method based on the new employee's past feedback. Some or all of the above-described processing in the learning unit can be performed using AI, for example, or without AI. For example, the learning unit can input the new employee's past feedback data into a generation AI, which can then customize the learning method.

[0041] The evaluation unit can improve the accuracy of the evaluation by referring to the employee's past work history. Work history includes, but is not limited to, past projects, task completion status, and work results. For example, the evaluation unit can set evaluation criteria based on the employee's past work history. The evaluation unit can also evaluate specific skills and knowledge from the employee's past work history. Furthermore, the evaluation unit can eliminate evaluation bias by referring to the employee's past work history. For example, the evaluation unit can use AI to improve the accuracy of the evaluation by referring to the employee's past work history. This allows the evaluation to be based on the employee's past work history, thereby improving the accuracy of the evaluation. Some or all of the above-described processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input the employee's past work history data into a generation AI, which can then improve the accuracy of the evaluation.

[0042] The evaluation unit can customize the evaluation content based on the employee's current work situation and areas of interest. Examples of work situation include, but are not limited to, current tasks, project progress, and work priorities. For example, the evaluation unit can provide evaluation content related to the project the employee is currently working on. The evaluation unit can also prioritize evaluation content related to the employee's areas of interest. Furthermore, the evaluation unit can provide content that evaluates the necessary skills based on the employee's work situation. For example, the evaluation unit can use AI to customize the evaluation content based on the employee's current work situation and areas of interest. This can improve the accuracy of the evaluation by providing evaluation content that is tailored to the employee's work situation and areas of interest. Some or all of the above-described processing in the evaluation unit can be performed using AI, for example, or without AI. For example, the evaluation unit can input data on the employee's work situation and areas of interest into the generation AI, which can then customize the evaluation content.

[0043] The evaluation unit can select an appropriate evaluation method depending on the employee's input method. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, if the employee prefers voice input, the evaluation unit can perform a voice evaluation. Furthermore, if the employee prefers text input, the evaluation unit can perform a text-based evaluation. Furthermore, if the employee prefers images or visuals, the evaluation unit can provide an evaluation method that makes extensive use of visual content. For example, the evaluation unit can use AI to select an appropriate evaluation method depending on the employee's input method. By providing an evaluation method that is appropriate for the employee's input method, the accuracy of the evaluation can be improved. Some or all of the above-described processing in the evaluation unit can be performed using AI, for example, or without AI. For example, the evaluation unit can input data on the employee's input method into a generation AI, which can then select an appropriate evaluation method.

[0044] The evaluation unit can prioritize providing highly relevant evaluation content based on the employee's geographic location information. Geographic location information includes, but is not limited to, GPS data, IP address, location information services, etc. For example, if an employee is in a specific area, the evaluation unit can evaluate the employee's work knowledge related to that area. Furthermore, if an employee is on a business trip, the evaluation unit can provide evaluation content related to the business trip destination. Furthermore, if an employee is working remotely, the evaluation unit can evaluate the employee's skills related to remote work. For example, the evaluation unit can use AI to prioritize providing highly relevant evaluation content based on the employee's geographic location information. This can improve the accuracy of the evaluation by providing evaluation content based on the employee's geographic location information. Some or all of the above-mentioned processing in the evaluation unit can be performed using AI, for example, or without AI. For example, the evaluation unit can input the employee's geographic location information data into a generation AI, which can then provide highly relevant evaluation content.

[0045] The evaluation unit can analyze the employee's social media activity and provide relevant evaluation content. Social media activity includes, but is not limited to, the content of posts, follower responses, and activity frequency. For example, the evaluation unit can provide evaluation content related to topics the employee is interested in on social media. The evaluation unit can also provide evaluation content that incorporates the opinions of experts the employee follows on social media. Furthermore, the evaluation unit can suggest evaluation content that may be of interest to the employee based on their social media activity. For example, the evaluation unit can use AI to analyze the employee's social media activity and provide relevant evaluation content. This can improve the accuracy of the evaluation by providing evaluation content based on the employee's social media activity. Some or all of the above-mentioned processing in the evaluation unit can be performed using AI, for example, or without AI. For example, the evaluation unit can input the employee's social media activity data into a generation AI, which can then provide relevant evaluation content.

[0046] The evaluation unit can customize the evaluation method by reflecting the employee's past feedback. Examples of feedback include, but are not limited to, past evaluations, comments, and improvement suggestions. For example, the evaluation unit can provide an evaluation method that the employee previously enjoyed. The evaluation unit can also provide an alternative evaluation method, avoiding an evaluation method that the employee previously dissatisfied with. Furthermore, the evaluation unit can improve and provide the evaluation content based on the employee's past feedback. For example, the evaluation unit can use AI to customize the evaluation method by reflecting the employee's past feedback. This can improve the accuracy of the evaluation by providing an evaluation method based on the employee's past feedback. Some or all of the above-described processing in the evaluation unit can be performed using AI, for example, or without AI. For example, the evaluation unit can input the employee's past feedback data into a generation AI, which can then customize the evaluation method.

[0047] The analysis unit can improve the accuracy of the analysis by referring to the employee's past work history. Work history includes, but is not limited to, past projects, task completion status, and work results. The analysis unit can, for example, set analysis criteria based on the employee's past work history. The analysis unit can also analyze specific skills and knowledge from the employee's past work history. Furthermore, the analysis unit can eliminate bias in the analysis by referring to the employee's past work history. For example, the analysis unit can use AI to improve the accuracy of the analysis by referring to the employee's past work history. This allows the analysis to be performed based on the employee's past work history, thereby improving the accuracy of the analysis. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input the employee's past work history data into a generation AI, which can then improve the accuracy of the analysis.

[0048] The analysis unit can customize the analysis content based on the employee's current work situation and areas of interest. Examples of work situation include, but are not limited to, current tasks, project progress, and work priorities. For example, the analysis unit can provide analysis content related to the project the employee is currently working on. The analysis unit can also prioritize analysis content related to the employee's areas of interest. Furthermore, the analysis unit can provide content analyzing the necessary skills according to the employee's work situation. For example, the analysis unit can customize the analysis content based on the employee's current work situation and areas of interest using AI. This can improve the accuracy of the analysis by providing analysis content tailored to the employee's work situation and areas of interest. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input data on the employee's work situation and areas of interest into the generation AI, which can then customize the analysis content.

[0049] The analysis unit can select an appropriate analysis method depending on the employee's input method. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, if the employee prefers voice input, the analysis unit can perform voice analysis. Furthermore, if the employee prefers text input, the analysis unit can perform text-based analysis. Furthermore, if the employee prefers images or visuals, the analysis unit can provide an analysis method that makes extensive use of visual content. For example, the analysis unit can use AI to select an appropriate analysis method depending on the employee's input method. By providing an analysis method that is appropriate for the employee's input method, the accuracy of the analysis can be improved. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input data on the employee's input method into a generation AI, which can then select an appropriate analysis method.

[0050] The analysis unit can prioritize providing highly relevant analysis content based on the employee's geographic location information. Examples of geographic location information include, but are not limited to, GPS data, IP addresses, and location information services. For example, if an employee is in a specific area, the analysis unit can analyze business knowledge related to that area. Furthermore, if an employee is on a business trip, the analysis unit can provide analysis content related to the business trip destination. Furthermore, if an employee is working remotely, the analysis unit can analyze skills related to remote work. For example, the analysis unit can use AI to prioritize providing highly relevant analysis content based on the employee's geographic location information. This can improve the accuracy of the analysis by providing analysis content based on the employee's geographic location information. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input the employee's geographic location information data into a generation AI, which can then provide highly relevant analysis content.

[0051] The analysis unit can analyze the employee's social media activity and provide related analysis content. Social media activity includes, but is not limited to, for example, the content of posts, follower reactions, and activity frequency. For example, the analysis unit can provide analysis content related to topics the employee is interested in on social media. The analysis unit can also provide analysis content that incorporates the opinions of experts the employee follows on social media. Furthermore, the analysis unit can suggest analysis content that may be of interest to the employee based on their social media activity. For example, the analysis unit can use AI to analyze the employee's social media activity and provide related analysis content. This can improve the accuracy of the analysis by providing analysis content based on the employee's social media activity. Some or all of the above-mentioned processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input the employee's social media activity data into a generation AI, which can then provide related analysis content.

[0052] The analysis unit can customize the analysis method by reflecting employees' past feedback. Examples of feedback include, but are not limited to, past evaluations, comments, and improvement suggestions. For example, the analysis unit can provide an analysis method that employees previously found popular. The analysis unit can also avoid an analysis method that employees previously disliked and provide an alternative method. Furthermore, the analysis unit can improve and provide the analysis content based on employees' past feedback. For example, the analysis unit can use AI to customize the analysis method by reflecting employees' past feedback. This can improve the accuracy of the analysis by providing an analysis method based on employees' past feedback. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input employees' past feedback data into a generation AI, which can then customize the analysis method.

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

[0054] The evaluation department can monitor employees' health status and adjust evaluation criteria based on their health condition. For example, if an employee is feeling unwell, the evaluation criteria can be relaxed to encourage them to perform their work within a reasonable range. Also, if an employee is healthy, the normal evaluation criteria can be applied to accurately evaluate their work performance. Furthermore, if an employee has specific health risks, evaluation criteria can be set that take those risks into consideration. This allows for the fairness and accuracy of evaluations to be improved by providing evaluation criteria that are tailored to the employee's health condition.

[0055] The analysis department can monitor employees' work performance in real time and issue an alert if it detects an abnormality. For example, if an employee's work performance suddenly drops, the analysis department can identify the cause and propose appropriate countermeasures. Also, if an employee's work performance exceeds a certain standard, the analysis department can evaluate the results and make the employee eligible for rewards or recognition. Furthermore, if an employee's work performance is unstable, the analysis department can analyze the pattern and provide advice for stabilizing the performance. In this way, by monitoring employee work performance in real time and taking appropriate measures, it is possible to improve the productivity of the entire organization.

[0056] The evaluation department can compare an employee's work performance with other employees and make a relative evaluation. For example, it can compare the performance of employees participating in the same project and identify employees who have shown excellent performance. It can also compare the performance of employees with the same position or job content to evaluate work efficiency and results. Furthermore, by comparing with past performance data, it can evaluate an employee's growth and areas for improvement. This allows for fair and accurate evaluation by evaluating employees' work performance relatively.

[0057] The learning department can suggest future career paths for new employees based on their learning history. For example, if a new employee has achieved outstanding results in a specific field, it can suggest a career path in that field. Also, if a new employee is studying in a balanced manner in multiple fields, it can suggest a comprehensive career path. Furthermore, if a new employee has a specific skill set, it can suggest a career path that makes use of that skill set. This makes it possible to support the career growth of new employees by providing them with the optimal career path based on their learning history.

[0058] The analysis unit can predict employee work performance and adjust work assignments based on the prediction results. For example, if a particular employee is predicted to perform well, important tasks can be assigned to that employee. Conversely, if a particular employee is predicted to perform poorly, tasks that require support can be assigned to that employee. Furthermore, it can predict the performance of the entire team and make optimal task assignments. This makes it possible to predict employee work performance and make optimal work assignments, thereby improving the productivity of the entire organization.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The Learning Department conducts collaborative learning between new employees and the AI. New employees teach the AI ​​their work-related knowledge and skills, and the AI ​​understands the content and provides appropriate advice and feedback. Step 2: The evaluation department evaluates the information obtained by the learning department. The evaluation department analyzes emails and chats between employees, meeting minutes, etc., and extracts important information using natural language processing technology. It also monitors and evaluates the progress of work and the quality of deliverables in real time. Step 3: The analysis unit identifies necessary meetings based on the information evaluated by the evaluation unit. The analysis unit uses AI to analyze the purpose, participants, and agenda of meetings to determine which meetings are truly necessary.

[0061] (Example 2) A communication efficiency system according to an embodiment of the present invention promotes organizational knowledge sharing and identifies only necessary meetings through collaborative learning between new employees and AI. The communication efficiency system improves communication within an organization by allowing new employees and AI to learn from each other. This system uses multifaceted evaluation by AI to identify only necessary meetings, contributing to improved employee performance. For example, in this communication efficiency system, new employees teach the AI ​​their work-related knowledge and skills while simultaneously receiving feedback from the AI. For example, the new employee explains the work process, and the AI ​​understands the content and provides appropriate advice. Next, the communication efficiency system uses AI to analyze emails and chats between employees, meeting minutes, and other information to identify which meetings are truly necessary. This reduces unnecessary meetings and enables only necessary meetings to be held. Furthermore, the communication efficiency system uses AI to evaluate the progress of work and the quality of deliverables and propose specific improvement measures. This allows employees to review their work and proceed more efficiently. This allows the communication efficiency system to achieve an efficient workflow and improve productivity throughout the organization. This reduces unnecessary meetings and improves employee performance. For example, by reducing unnecessary meetings, employees can focus on their core tasks. Also, receiving feedback from AI improves the quality of work, leading to improved performance across the organization.

[0062] A communication efficiency improvement system according to an embodiment includes a learning unit, an evaluation unit, and an analysis unit. The learning unit allows new employees and an AI to jointly learn. For example, the new employees teach the AI ​​knowledge and skills related to their work. For example, the learning unit allows the new employees to explain a work process, and the AI ​​can understand the content and provide appropriate advice. The learning unit also allows the AI ​​to provide feedback to the new employees. The evaluation unit evaluates information obtained by the learning unit. For example, the evaluation unit analyzes emails and chats between employees, meeting minutes, etc. The evaluation unit can analyze communication content and extract important information using natural language processing technology, for example. The evaluation unit can also evaluate the progress of work and the quality of deliverables using AI. For example, the evaluation unit monitors the progress of work in real time and evaluates the degree of progress. The analysis unit identifies necessary meetings based on the information evaluated by the evaluation unit. For example, the analysis unit can identify which meetings are truly necessary using AI. The analysis unit analyzes, for example, the purpose, participants, and agenda of a meeting to determine its necessity. As a result, the communication efficiency system according to the embodiment can promote knowledge sharing within an organization through collaborative learning between new employees and AI, and by identifying only necessary meetings, it can realize an efficient workflow and improve productivity throughout the organization.

[0063] The learning unit allows new employees to teach the AI ​​their work-related knowledge and skills. Examples of knowledge and skills include, but are not limited to, technical knowledge and business process skills. For example, the learning unit allows new employees to explain a business process, and the AI ​​can understand the content and provide appropriate advice. Furthermore, when new employees teach the AI ​​their work-related knowledge, the learning unit allows the AI ​​to learn that knowledge and provide similar knowledge to other employees in the future. For example, the learning unit allows new employees to explain work procedures, and the AI ​​can learn those procedures and explain those procedures to other employees. This allows new employees to teach the AI ​​their work-related knowledge and skills, and the AI ​​can learn that knowledge, promoting knowledge sharing within the organization. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit may input voice data in which a new employee explains a business process into the generation AI, which can then understand the content and provide appropriate advice.

[0064] The evaluation unit can analyze the content of emails and chats between employees and meeting minutes. For example, natural language processing technology can be used for the analysis. For example, the evaluation unit can analyze the content of emails between employees and extract important information. The evaluation unit can also analyze the content of chats and analyze communication patterns. Furthermore, the evaluation unit can analyze meeting minutes and extract key points of discussions. For example, the evaluation unit can use natural language processing technology to analyze the content of emails and chats and extract important keywords and phrases. The evaluation unit can also analyze meeting minutes and extract key points and conclusions of discussions. By analyzing the content of communication between employees, it is possible to identify necessary meetings and reduce unnecessary meetings. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without AI. For example, the evaluation unit can input the content of emails and chats between employees into a generation AI, which can extract important information.

[0065] The analysis unit can identify which meetings are necessary. The determination of whether a meeting is necessary includes, but is not limited to, the purpose, participants, and agenda of the meeting. For example, the analysis unit can analyze the purpose of the meeting and evaluate its importance. The analysis unit can also analyze the roles and involvement of participants to determine the necessity of the meeting. Furthermore, the analysis unit can analyze the content of the agenda and evaluate its urgency and importance. For example, the analysis unit can use AI to analyze the purpose, participants, and agenda of the meeting and determine its necessity. This allows for identifying only necessary meetings, thereby reducing unnecessary meetings and realizing an efficient workflow. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit can input information about the meeting agenda and participants into a generation AI, which then determines the necessity of the meeting.

[0066] The evaluation unit can evaluate the progress of work and the quality of deliverables. Examples of progress include, but are not limited to, the degree of task completion and deadline compliance. For example, the evaluation unit can monitor the progress of work in real time and evaluate the degree of progress. The evaluation unit can also use quality standards, error rates, user feedback, and the like to evaluate the quality of deliverables. For example, the evaluation unit can evaluate the degree of task completion and grasp the progress. The evaluation unit can also evaluate the quality of deliverables and perform evaluations based on the quality standards. This contributes to improving employee performance by evaluating the progress of work and the quality of deliverables. Some or all of the above-described processing in the evaluation unit can be performed using, for example, AI, or without AI. For example, the evaluation unit can input data on the progress of work and the quality of deliverables into a generation AI, which then performs evaluations.

[0067] The evaluation unit can propose specific improvement measures. Specific improvement measures include, but are not limited to, steps for improvement, required resources, and implementation timing. For example, the evaluation unit can evaluate the progress of work and the quality of deliverables and propose specific improvement measures. For example, the evaluation unit can suggest a review of task priorities based on the progress. The evaluation unit can also propose specific steps for improving quality based on the quality of the deliverables. Furthermore, the evaluation unit can also propose required resources and implementation timing. For example, the evaluation unit can use AI to evaluate the progress of work and the quality of deliverables and propose specific improvement measures. By proposing specific improvement measures, employees can review their own work and proceed more efficiently. Some or all of the above-described processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input data on the progress of work and the quality of deliverables into a generation AI, which then proposes specific improvement measures.

[0068] The learning unit can estimate the new employee's emotions and adjust the learning content and pace based on the estimated emotions. Emotion estimation includes, but is not limited to, facial expression recognition, voice analysis, and text analysis. For example, if the new employee is stressed, the learning unit can simplify the learning content and slow down the pace. Furthermore, if the new employee is relaxed, the learning unit can make the learning content more detailed and speed up the pace. Furthermore, if the new employee is excited, the learning unit can incorporate more practical tasks to increase motivation. For example, the learning unit can estimate the new employee's emotions using AI and adjust the learning content and pace based on the estimated emotions. This maximizes the learning effect by adjusting the learning content and pace according to the new employee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-mentioned processes in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit may input facial expression data of a new employee into a generation AI, which may infer the employee's emotions and adjust the learning content and pace accordingly.

[0069] The learning unit can analyze the new employee's past learning history and select an appropriate learning method. Learning history includes, but is not limited to, past learning results, learning frequency, and learning format. For example, the learning unit can suggest a similar learning method based on a learning method that the new employee has used successfully in the past. The learning unit can also suggest an alternative method, avoiding learning methods that the new employee has struggled with in the past. Furthermore, the learning unit can suggest the most effective study time based on the new employee's past learning history. For example, the learning unit can use AI to analyze the new employee's past learning history and select an appropriate learning method. This can improve learning effectiveness by selecting the optimal learning method based on the new employee's past learning history. Some or all of the above-described processing in the learning unit can be performed using AI, for example, or without AI. For example, the learning unit can input the new employee's past learning history data into a generation AI, which can then select an appropriate learning method.

[0070] The learning unit can provide customized learning content based on the new employee's current work situation and areas of interest. Examples of work situation include, but are not limited to, current tasks, project progress, and work priorities. For example, the learning unit can provide learning content related to the project the new employee is currently working on. The learning unit can also prioritize providing learning content related to the new employee's areas of interest. Furthermore, the learning unit can provide learning content that strengthens necessary skills according to the new employee's work situation. For example, the learning unit can use AI to provide customized learning content based on the new employee's current work situation and areas of interest. This maximizes the learning effect by providing learning content tailored to the new employee's work situation and areas of interest. Some or all of the above-described processing in the learning unit can be performed using AI, for example, or without AI. For example, the learning unit can input data on the new employee's work situation and areas of interest into a generation AI, which then provides customized learning content.

[0071] The learning unit can select an appropriate learning means depending on the new employee's input method. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, if the new employee prefers voice input, the learning unit can provide audio learning content. Furthermore, if the new employee prefers text input, the learning unit can provide text-based learning content. Furthermore, if the new employee prefers images and visuals, the learning unit can provide learning means that make extensive use of visual content. For example, the learning unit can use AI to select an appropriate learning means depending on the new employee's input method. This maximizes the learning effect by providing learning means that correspond to the new employee's input method. Some or all of the above-described processing in the learning unit can be performed using AI, for example, or without AI. For example, the learning unit can input data on the new employee's input method into a generation AI, which can select an appropriate learning means.

[0072] The learning unit can estimate the new employee's emotions and determine learning priorities based on the estimated emotions. Emotion estimation includes, but is not limited to, facial expression recognition, voice analysis, and text analysis. For example, if the new employee is feeling stressed, the learning unit can prioritize learning content that will help them relax. Furthermore, if the new employee is relaxed, the learning unit can prioritize learning content that is more difficult. Furthermore, if the new employee is excited, the learning unit can prioritize learning content that is more practical. For example, the learning unit can estimate the new employee's emotions using AI and determine learning priorities based on the estimated emotions. This maximizes the learning effect by determining learning priorities according to the new employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit can be performed using, for example, AI, or without AI. For example, the learning department can input facial expression data of new employees into the generation AI, which can then infer their emotions and determine learning priorities.

[0073] The learning unit can prioritize providing relevant learning content based on the new employee's geographic location information. Examples of geographic location information include, but are not limited to, GPS data, IP addresses, and location information services. For example, if the new employee is in a specific region, the learning unit can provide business knowledge related to that region. Furthermore, if the new employee is on a business trip, the learning unit can provide learning content related to the business trip destination. Furthermore, if the new employee is working remotely, the learning unit can provide skills related to remote work. For example, the learning unit can use AI to prioritize providing relevant learning content based on the new employee's geographic location information. This maximizes the learning effect by providing learning content based on the new employee's geographic location information. Some or all of the above-described processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the new employee's geographic location data into a generation AI, which can then provide relevant learning content.

[0074] The learning unit can analyze the new employee's social media activity and provide relevant learning content. Social media activity includes, but is not limited to, the content of posts, follower responses, and activity frequency. For example, the learning unit can provide learning content related to topics the new employee has shown interest in on social media. The learning unit can also provide learning content that incorporates the opinions of experts the new employee follows on social media. Furthermore, the learning unit can suggest learning content that may be of interest to the new employee based on the new employee's social media activity. For example, the learning unit can use AI to analyze the new employee's social media activity and provide relevant learning content. This maximizes the learning effect by providing learning content based on the new employee's social media activity. Some or all of the above-described processing in the learning unit can be performed using AI, for example, or without AI. For example, the learning unit can input the new employee's social media activity data into a generation AI, which then provides relevant learning content.

[0075] The learning unit can customize the learning method by reflecting the new employee's past feedback. Examples of feedback include, but are not limited to, past evaluations, comments, and improvement suggestions. For example, the learning unit can provide a learning method that the new employee previously enjoyed. The learning unit can also avoid a learning method that the new employee previously dissatisfied with and provide an alternative method. Furthermore, the learning unit can improve and provide learning content based on the new employee's past feedback. For example, the learning unit can use AI to customize the learning method by reflecting the new employee's past feedback. This maximizes the learning effect by providing a learning method based on the new employee's past feedback. Some or all of the above-described processing in the learning unit can be performed using AI, for example, or without AI. For example, the learning unit can input the new employee's past feedback data into a generation AI, which can then customize the learning method.

[0076] The evaluation unit can estimate the employee's emotions and adjust the evaluation criteria based on the estimated emotions. Emotion estimation includes, but is not limited to, facial expression recognition, voice analysis, and text analysis. For example, if an employee is feeling stressed, the evaluation unit can relax the evaluation criteria to reduce stress. Furthermore, if an employee is relaxed, the evaluation unit can tighten the evaluation criteria to encourage them to take on new challenges. Furthermore, if an employee is excited, the evaluation unit can adjust the evaluation criteria to maintain motivation. For example, the evaluation unit can use AI to estimate the employee's emotions and adjust the evaluation criteria based on the estimated emotions. This allows the evaluation accuracy to be improved by adjusting the evaluation criteria according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the evaluation unit can be performed using, for example, AI, or without AI. For example, the evaluation department can input facial expression data of employees into the generation AI, which can then infer their emotions and adjust the evaluation criteria.

[0077] The evaluation unit can improve the accuracy of the evaluation by referring to the employee's past work history. Work history includes, but is not limited to, past projects, task completion status, and work results. For example, the evaluation unit can set evaluation criteria based on the employee's past work history. The evaluation unit can also evaluate specific skills and knowledge from the employee's past work history. Furthermore, the evaluation unit can eliminate evaluation bias by referring to the employee's past work history. For example, the evaluation unit can use AI to improve the accuracy of the evaluation by referring to the employee's past work history. This allows the evaluation to be based on the employee's past work history, thereby improving the accuracy of the evaluation. Some or all of the above-described processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input the employee's past work history data into a generation AI, which can then improve the accuracy of the evaluation.

[0078] The evaluation unit can customize the evaluation content based on the employee's current work situation and areas of interest. Examples of work situation include, but are not limited to, current tasks, project progress, and work priorities. For example, the evaluation unit can provide evaluation content related to the project the employee is currently working on. The evaluation unit can also prioritize evaluation content related to the employee's areas of interest. Furthermore, the evaluation unit can provide content that evaluates the necessary skills based on the employee's work situation. For example, the evaluation unit can use AI to customize the evaluation content based on the employee's current work situation and areas of interest. This can improve the accuracy of the evaluation by providing evaluation content that is tailored to the employee's work situation and areas of interest. Some or all of the above-described processing in the evaluation unit can be performed using AI, for example, or without AI. For example, the evaluation unit can input data on the employee's work situation and areas of interest into the generation AI, which can then customize the evaluation content.

[0079] The evaluation unit can select an appropriate evaluation method depending on the employee's input method. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, if the employee prefers voice input, the evaluation unit can perform a voice evaluation. Furthermore, if the employee prefers text input, the evaluation unit can perform a text-based evaluation. Furthermore, if the employee prefers images or visuals, the evaluation unit can provide an evaluation method that makes extensive use of visual content. For example, the evaluation unit can use AI to select an appropriate evaluation method depending on the employee's input method. By providing an evaluation method that is appropriate for the employee's input method, the accuracy of the evaluation can be improved. Some or all of the above-described processing in the evaluation unit can be performed using AI, for example, or without AI. For example, the evaluation unit can input data on the employee's input method into a generation AI, which can then select an appropriate evaluation method.

[0080] The evaluation unit can estimate the employee's emotions and determine the priority of evaluations based on the estimated emotions. Emotion estimation includes, but is not limited to, facial expression recognition, voice analysis, and text analysis. For example, if the employee is feeling stressed, the evaluation unit can prioritize relaxing content in evaluations. Furthermore, if the employee is relaxed, the evaluation unit can prioritize difficult content in evaluations. Furthermore, if the employee is excited, the evaluation unit can prioritize practical content in evaluations. For example, the evaluation unit can estimate the employee's emotions using AI and determine the priority of evaluations based on the estimated emotions. This improves the accuracy of evaluations by prioritizing the evaluations according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the evaluation unit can be performed using, for example, AI, or without AI. For example, the evaluation department can input employee facial expression data into the generation AI, which can then infer emotions and determine evaluation priorities.

[0081] The evaluation unit can prioritize providing highly relevant evaluation content based on the employee's geographic location information. Geographic location information includes, but is not limited to, GPS data, IP address, location information services, etc. For example, if an employee is in a specific area, the evaluation unit can evaluate the employee's work knowledge related to that area. Furthermore, if an employee is on a business trip, the evaluation unit can provide evaluation content related to the business trip destination. Furthermore, if an employee is working remotely, the evaluation unit can evaluate the employee's skills related to remote work. For example, the evaluation unit can use AI to prioritize providing highly relevant evaluation content based on the employee's geographic location information. This can improve the accuracy of the evaluation by providing evaluation content based on the employee's geographic location information. Some or all of the above-mentioned processing in the evaluation unit can be performed using AI, for example, or without AI. For example, the evaluation unit can input the employee's geographic location information data into a generation AI, which can then provide highly relevant evaluation content.

[0082] The evaluation unit can analyze the employee's social media activity and provide relevant evaluation content. Social media activity includes, but is not limited to, the content of posts, follower responses, and activity frequency. For example, the evaluation unit can provide evaluation content related to topics the employee is interested in on social media. The evaluation unit can also provide evaluation content that incorporates the opinions of experts the employee follows on social media. Furthermore, the evaluation unit can suggest evaluation content that may be of interest to the employee based on their social media activity. For example, the evaluation unit can use AI to analyze the employee's social media activity and provide relevant evaluation content. This can improve the accuracy of the evaluation by providing evaluation content based on the employee's social media activity. Some or all of the above-mentioned processing in the evaluation unit can be performed using AI, for example, or without AI. For example, the evaluation unit can input the employee's social media activity data into a generation AI, which can then provide relevant evaluation content.

[0083] The evaluation unit can customize the evaluation method by reflecting the employee's past feedback. Examples of feedback include, but are not limited to, past evaluations, comments, and improvement suggestions. For example, the evaluation unit can provide an evaluation method that the employee previously enjoyed. The evaluation unit can also provide an alternative evaluation method, avoiding an evaluation method that the employee previously dissatisfied with. Furthermore, the evaluation unit can improve and provide the evaluation content based on the employee's past feedback. For example, the evaluation unit can use AI to customize the evaluation method by reflecting the employee's past feedback. This can improve the accuracy of the evaluation by providing an evaluation method based on the employee's past feedback. Some or all of the above-described processing in the evaluation unit can be performed using AI, for example, or without AI. For example, the evaluation unit can input the employee's past feedback data into a generation AI, which can then customize the evaluation method.

[0084] The analysis unit can estimate the employee's emotions and adjust the analysis criteria based on the estimated emotions. Emotion estimation includes, but is not limited to, facial expression recognition, voice analysis, and text analysis. For example, if an employee is feeling stressed, the analysis unit can relax the analysis criteria to reduce stress. Furthermore, if an employee is relaxed, the analysis unit can tighten the analysis criteria to encourage them to take on new challenges. Furthermore, if an employee is excited, the analysis unit can adjust the analysis criteria to maintain motivation. For example, the analysis unit can use AI to estimate the employee's emotions and adjust the analysis criteria based on the estimated emotions. By adjusting the analysis criteria according to the employee's emotions, the accuracy of the analysis can be improved. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input facial expression data of employees into the generation AI, which can then infer emotions and adjust the analysis criteria.

[0085] The analysis unit can improve the accuracy of the analysis by referring to the employee's past work history. Work history includes, but is not limited to, past projects, task completion status, and work results. The analysis unit can, for example, set analysis criteria based on the employee's past work history. The analysis unit can also analyze specific skills and knowledge from the employee's past work history. Furthermore, the analysis unit can eliminate bias in the analysis by referring to the employee's past work history. For example, the analysis unit can use AI to improve the accuracy of the analysis by referring to the employee's past work history. This allows the analysis to be performed based on the employee's past work history, thereby improving the accuracy of the analysis. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input the employee's past work history data into a generation AI, which can then improve the accuracy of the analysis.

[0086] The analysis unit can customize the analysis content based on the employee's current work situation and areas of interest. Examples of work situation include, but are not limited to, current tasks, project progress, and work priorities. For example, the analysis unit can provide analysis content related to the project the employee is currently working on. The analysis unit can also prioritize analysis content related to the employee's areas of interest. Furthermore, the analysis unit can provide content analyzing the necessary skills according to the employee's work situation. For example, the analysis unit can customize the analysis content based on the employee's current work situation and areas of interest using AI. This can improve the accuracy of the analysis by providing analysis content tailored to the employee's work situation and areas of interest. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input data on the employee's work situation and areas of interest into the generation AI, which can then customize the analysis content.

[0087] The analysis unit can select an appropriate analysis method depending on the employee's input method. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, if the employee prefers voice input, the analysis unit can perform voice analysis. Furthermore, if the employee prefers text input, the analysis unit can perform text-based analysis. Furthermore, if the employee prefers images or visuals, the analysis unit can provide an analysis method that makes extensive use of visual content. For example, the analysis unit can use AI to select an appropriate analysis method depending on the employee's input method. By providing an analysis method that is appropriate for the employee's input method, the accuracy of the analysis can be improved. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input data on the employee's input method into a generation AI, which can then select an appropriate analysis method.

[0088] The analysis unit can estimate the employee's emotions and determine analysis priorities based on the estimated emotions. Emotion estimation includes, but is not limited to, facial expression recognition, voice analysis, and text analysis. For example, if an employee is feeling stressed, the analysis unit can prioritize analyzing relaxing content. Furthermore, if an employee is relaxed, the analysis unit can prioritize analyzing difficult content. Furthermore, if an employee is excited, the analysis unit can prioritize analyzing practical content. For example, the analysis unit can use AI to estimate the employee's emotions and determine analysis priorities based on the estimated emotions. This improves the accuracy of analysis by prioritizing analysis based on the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input facial expression data of employees into the generation AI, which can then infer emotions and determine analysis priorities.

[0089] The analysis unit can prioritize providing highly relevant analysis content based on the employee's geographic location information. Examples of geographic location information include, but are not limited to, GPS data, IP addresses, and location information services. For example, if an employee is in a specific area, the analysis unit can analyze business knowledge related to that area. Furthermore, if an employee is on a business trip, the analysis unit can provide analysis content related to the business trip destination. Furthermore, if an employee is working remotely, the analysis unit can analyze skills related to remote work. For example, the analysis unit can use AI to prioritize providing highly relevant analysis content based on the employee's geographic location information. This can improve the accuracy of the analysis by providing analysis content based on the employee's geographic location information. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input the employee's geographic location information data into a generation AI, which can then provide highly relevant analysis content.

[0090] The analysis unit can analyze the employee's social media activity and provide related analysis content. Social media activity includes, but is not limited to, for example, the content of posts, follower reactions, and activity frequency. For example, the analysis unit can provide analysis content related to topics the employee is interested in on social media. The analysis unit can also provide analysis content that incorporates the opinions of experts the employee follows on social media. Furthermore, the analysis unit can suggest analysis content that may be of interest to the employee based on their social media activity. For example, the analysis unit can use AI to analyze the employee's social media activity and provide related analysis content. This can improve the accuracy of the analysis by providing analysis content based on the employee's social media activity. Some or all of the above-mentioned processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input the employee's social media activity data into a generation AI, which can then provide related analysis content.

[0091] The analysis unit can customize the analysis method by reflecting employees' past feedback. Examples of feedback include, but are not limited to, past evaluations, comments, and improvement suggestions. For example, the analysis unit can provide an analysis method that employees previously found popular. The analysis unit can also avoid an analysis method that employees previously disliked and provide an alternative method. Furthermore, the analysis unit can improve and provide the analysis content based on employees' past feedback. For example, the analysis unit can use AI to customize the analysis method by reflecting employees' past feedback. This can improve the accuracy of the analysis by providing an analysis method based on employees' past feedback. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input employees' past feedback data into a generation AI, which can then customize the analysis method. === Hard Collateral 1-1 === Each of the multiple elements including the learning unit, evaluation unit, and analysis unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the smart device 14, allowing new employees to teach the AI ​​their work-related knowledge and skills. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of emails and chats between employees, meeting minutes, etc., to extract important information. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and identifies necessary meetings. === Hard Collateral 1-2 === Each of the multiple elements, including the learning unit, evaluation unit, and analysis unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the smart glasses 214, allowing new employees to teach the AI ​​their work-related knowledge and skills. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of emails and chats between employees, meeting minutes, etc., to extract important information. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and identifies necessary meetings. === Hard Collateral 1-3 === Each of the multiple elements including the learning unit, evaluation unit, and analysis unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the headset-type terminal 314, allowing new employees to teach the AI ​​their work-related knowledge and skills. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of emails and chats between employees, meeting minutes, etc., to extract important information. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and identifies necessary meetings. === Hard Collateral 1-4 === Each of the multiple elements including the learning unit, evaluation unit, and analysis unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the robot 414, and a new employee can teach the AI ​​knowledge and skills related to the job. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of emails and chats between employees, meeting minutes, etc., to extract important information. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and identifies necessary meetings.

[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 learning department can estimate the learning style of new employees and customize the learning content based on the estimated learning style. For example, if a new employee prefers visual learning, it can provide learning materials that make heavy use of visual content. If a new employee prefers auditory learning, it can provide learning content in the form of audio guides or podcasts. Furthermore, if a new employee prefers practical learning, it can provide actual work simulations and hands-on training. This maximizes the learning effect by providing the optimal learning method according to the new employee's learning style.

[0094] The evaluation department can monitor employees' health status and adjust evaluation criteria based on their health condition. For example, if an employee is feeling unwell, the evaluation criteria can be relaxed to encourage them to perform their work within a reasonable range. Also, if an employee is healthy, the normal evaluation criteria can be applied to accurately evaluate their work performance. Furthermore, if an employee has specific health risks, evaluation criteria can be set that take those risks into consideration. This allows for the fairness and accuracy of evaluations to be improved by providing evaluation criteria that are tailored to the employee's health condition.

[0095] The analysis department can monitor employees' work performance in real time and issue an alert if it detects an abnormality. For example, if an employee's work performance suddenly drops, the analysis department can identify the cause and propose appropriate countermeasures. Also, if an employee's work performance exceeds a certain standard, the analysis department can evaluate the results and make the employee eligible for rewards or recognition. Furthermore, if an employee's work performance is unstable, the analysis department can analyze the pattern and provide advice for stabilizing the performance. In this way, by monitoring employee work performance in real time and taking appropriate measures, it is possible to improve the productivity of the entire organization.

[0096] The learning department can regularly evaluate new employees' learning progress and adjust their learning plans accordingly. For example, if a new employee is progressing faster than expected, the learning department can provide them with additional learning content to take the next step. If a new employee is falling behind in their studies, the learning department can also provide them with supplementary lessons or additional support. Furthermore, if a new employee is having difficulty in a particular area, the learning department can provide them with learning resources specialized for that area. This makes it possible to maximize the learning effect by providing a flexible learning plan that corresponds to the new employee's learning progress.

[0097] The evaluation department can compare an employee's work performance with other employees and make a relative evaluation. For example, it can compare the performance of employees participating in the same project and identify employees who have shown excellent performance. It can also compare the performance of employees with the same position or job content to evaluate work efficiency and results. Furthermore, by comparing with past performance data, it can evaluate an employee's growth and areas for improvement. This allows for fair and accurate evaluation by evaluating employees' work performance relatively.

[0098] The analysis unit can estimate an employee's emotions and adjust communication methods based on the estimated emotions. For example, if an employee is feeling stressed, the analysis unit can suggest a communication method that will help them relax. If the employee is relaxed, the analysis unit can also suggest a more proactive communication method. Furthermore, if the employee is excited, the analysis unit can suggest a communication method that will make use of that energy. In this way, the effectiveness of communication can be maximized by providing the optimal communication method according to the employee's emotions.

[0099] The learning department can suggest future career paths for new employees based on their learning history. For example, if a new employee has achieved outstanding results in a specific field, it can suggest a career path in that field. Also, if a new employee is studying in a balanced manner in multiple fields, it can suggest a comprehensive career path. Furthermore, if a new employee has a specific skill set, it can suggest a career path that makes use of that skill set. This makes it possible to support the career growth of new employees by providing them with the optimal career path based on their learning history.

[0100] The evaluation department can estimate an employee's emotions and adjust the content of the feedback based on the estimated emotions. For example, if an employee is feeling stressed, the evaluation department can prioritize providing positive feedback to reduce stress. If an employee is relaxed, the evaluation department can provide constructive feedback to encourage further growth. Furthermore, if an employee is excited, the department can provide feedback to utilize that energy. This makes it possible to maximize the effectiveness of feedback by providing optimal feedback according to the employee's emotions.

[0101] The analysis unit can predict employee work performance and adjust work assignments based on the prediction results. For example, if a particular employee is predicted to perform well, important tasks can be assigned to that employee. Conversely, if a particular employee is predicted to perform poorly, tasks that require support can be assigned to that employee. Furthermore, it can predict the performance of the entire team and make optimal task assignments. This makes it possible to predict employee work performance and make optimal work assignments, thereby improving the productivity of the entire organization.

[0102] The learning department can estimate the emotions of new employees and provide incentives to increase their motivation to learn based on the estimated emotions. For example, if a new employee is feeling stressed, it can provide a relaxing environment to increase their motivation to learn. If a new employee is relaxed, it can provide challenging tasks to maintain their motivation to learn. Furthermore, if a new employee is excited, it can provide rewards and recognition to utilize that energy. In this way, it is possible to maximize learning motivation by providing optimal incentives according to the emotions of the new employee.

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

[0104] Step 1: The Learning Department conducts collaborative learning between new employees and the AI. New employees teach the AI ​​their work-related knowledge and skills, and the AI ​​understands the content and provides appropriate advice and feedback. Step 2: The evaluation department evaluates the information obtained by the learning department. The evaluation department analyzes emails and chats between employees, meeting minutes, etc., and extracts important information using natural language processing technology. It also monitors and evaluates the progress of work and the quality of deliverables in real time. Step 3: The analysis unit identifies necessary meetings based on the information evaluated by the evaluation unit. The analysis unit uses AI to analyze the purpose, participants, and agenda of meetings to determine which meetings are truly necessary.

[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 (registered trademark) (Internet search engine).<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] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0109] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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).

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0119] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0120] 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.

[0121] 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.

[0122] 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 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.

[0123] 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.

[0124] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0125] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type 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.

[0133] 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.

[0134] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0135] 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0136] 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.

[0137] 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.

[0138] 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 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.

[0139] 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.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0152] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. 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 the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0153] 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.

[0154] 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.

[0155] 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 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.

[0156] 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.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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 area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0163] 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."

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] [Explanation of symbols]

[0177] 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. A learning department where new employees and AI learn together, an evaluation unit that evaluates the information obtained by the learning unit; and an analysis unit that identifies a necessary meeting based on the information evaluated by the evaluation unit. A system characterized by:

2. The learning unit New employees teach AI their work-related knowledge and skills 2. The system of claim 1.

3. The evaluation unit Analyzing emails and chat content between employees and meeting minutes 2. The system of claim 1.

4. The analysis unit Identify which meetings are necessary 2. The system of claim 1.

5. The evaluation unit Evaluate the progress of work and the quality of deliverables 2. The system of claim 1.

6. The evaluation unit Equipping an evaluation department that proposes specific improvement measures 2. The system of claim 1.

7. The learning unit Estimate new employees' emotions and adjust learning content and pace based on those emotions 2. The system of claim 1.

8. The learning unit Analyze new employees' past learning history and select appropriate learning methods 2. The system of claim 1.

9. The learning unit Offer new hires customized learning based on their current work situation and areas of interest 2. The system of claim 1.

10. The learning unit Select the appropriate learning method according to the input method of new employees 2. The system of claim 1.

Images