system

Abstract

The system according to the embodiment aims to provide effective feedback in real time in training for sales and customer service. [Solution] A system according to an embodiment includes a scenario presenting unit, a script generating unit, a feedback providing unit, and a conversation analyzing unit. The scenario presenting unit presents a scenario. The script generating unit generates a script based on the scenario presented by the scenario presenting unit. The feedback providing unit provides feedback based on the script generated by the script generating unit. The conversation analyzing unit analyzes employee conversations in real time based on the feedback provided by the feedback providing 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] With conventional technology, it was difficult to provide effective feedback in real time when training employees in sales and customer service.

[0005] The system according to the embodiment aims to provide effective feedback in real time in training for sales and customer service. [Means for solving the problem]

[0006] The system according to the embodiment includes a scenario presenting unit, a script generating unit, a feedback providing unit, and a conversation analyzing unit. The scenario presenting unit presents a scenario. The script generating unit generates a script based on the scenario presented by the scenario presenting unit. The feedback providing unit provides feedback based on the script generated by the script generating unit. The conversation analyzing unit analyzes employee conversations in real time based on the feedback provided by the feedback providing unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide effective feedback in real time in training for sales and customer service. [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 role-playing training system according to an embodiment of the present invention uses a generative AI to conduct role-playing training for sales, customer service, and customer service. This role-playing training system presents scenarios to employees, automatically generates role-playing scripts based on the training content, and provides immediate feedback to new employees and existing employees. Furthermore, it analyzes the conversations employees have in actual sales and customer service situations in real time and provides immediate feedback. For example, the generative AI presents employees with scenarios such as handling customer complaints or introducing new products. Employees perform role-playing based on these scenarios. The generative AI then analyzes the content of the role-play and automatically generates a script. This script includes specific advice on how employees should respond. For example, it may include how to apologize in response to a customer complaint and how to present a solution. Furthermore, the generative AI analyzes the conversations employees have in actual sales and customer service situations in real time. For example, it analyzes the content of conversations employees have with customers and provides appropriate feedback immediately. This allows employees to immediately identify areas for improvement and apply them to their next interactions. This system is expected to improve employee skills and contribute to increased customer satisfaction. For example, even when a new employee handles a complaint for the first time, the support of the generative AI will enable them to respond appropriately. Veteran employees can also reflect on their own responses and further improve their skills. In this way, the role-playing training system can help improve employee skills.

[0029] A role-playing training system according to an embodiment includes a scenario presentation unit, a script generation unit, a feedback provision unit, and a conversation analysis unit. The scenario presentation unit uses a generation AI to present scenarios to employees. The scenario presentation unit uses the generation AI to present various scenarios, such as handling customer complaints or introducing new products. The generation AI can generate scenarios using a natural language processing model such as GPT-4 (registered trademark) or Gemini. The script generation unit automatically generates a script using the generation AI. The script generation unit generates a script that includes specific advice on how an employee should respond. The generation AI can generate a script using a Transformer model, for example. The feedback provision unit analyzes conversations in real time using the generation AI and provides feedback. The feedback provision unit analyzes, for example, the content of conversations between employees and customers and provides appropriate feedback immediately. The generation AI can analyze conversations and generate feedback using, for example, speech recognition technology or natural language processing technology. The conversation analysis unit analyzes employee conversations in real time using the generation AI. The conversation analysis unit, for example, analyzes the content of an employee's conversation with a customer and provides appropriate feedback immediately. The generation AI, for example, can estimate the employee's emotions using emotion analysis technology and reflect the estimated emotions in the feedback. This allows the role-playing training system according to the embodiment to improve employee skills. Some or all of the above-described processing in the feedback providing unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the feedback providing unit may input employee conversation data into the generation AI and cause the generation AI to generate feedback from the conversation data. Furthermore, the feedback providing unit may analyze the employee's emotional data in real time and immediately grasp changes in emotion. For example, the feedback providing unit may monitor the employee's facial expressions in real time and immediately detect changes in emotion. The feedback providing unit may also accumulate employee emotional data and analyze long-term emotional trends. For example, the feedback providing unit may analyze the employee's emotional data over time to identify patterns of emotional change.This allows you to get a detailed understanding of employee sentiment and reflect it in your feedback.

[0030] The scenario presentation unit can present scenarios to employees using a generation AI. The scenario presentation unit presents scenarios to employees using, for example, a generation AI. The generation AI can generate scenarios using a natural language processing model such as GPT-4 or Gemini. For example, the generation AI presents scenarios to employees, such as handling customer complaints or introducing new products. Employees then role-play based on these scenarios. Using the generation AI, appropriate scenarios can be presented to employees. Some or all of the above-described processing in the scenario presentation unit may be performed using, for example, a generation AI. For example, the scenario presentation unit can input customized scenarios based on the employee's job duties and position into the generation AI and have the generation AI generate the scenario. Furthermore, the scenario presentation unit can analyze employee emotional data in real time and instantly grasp changes in emotion. For example, the scenario presentation unit can monitor employee facial expressions in real time and instantly detect changes in emotion. The scenario presentation unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the scenario presentation unit analyzes employee emotion data over time to identify patterns of change in emotion, thereby gaining a detailed understanding of employee emotions and reflecting this in the presentation of scenarios.

[0031] The script generation unit can automatically generate a script using a generative AI. The script generation unit automatically generates a script using, for example, a generative AI. The generative AI can generate a script using, for example, a Transformer model. For example, the script generates a script that includes specific advice on how an employee should respond. The generative AI generates a script that describes, for example, how an employee should apologize in response to a customer complaint and how they should present a solution. This enables automatic script generation using the generative AI. Some or all of the above-mentioned processing in the script generation unit may be performed using, for example, a generative AI. For example, the script generation unit can input a script customized based on the employee's job description and position into the generative AI and have the generative AI generate the script. Furthermore, the script generation unit can analyze employee emotional data in real time and immediately grasp changes in emotion. For example, the script generation unit can monitor employee facial expressions in real time and immediately detect changes in emotion. The script generation unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the script generation unit analyzes employee emotion data over time to identify patterns of change in emotion, thereby gaining a detailed understanding of employee emotions and reflecting this in the generation of scripts.

[0032] The feedback providing unit can analyze conversations in real time using a generation AI and provide feedback. The feedback providing unit can, for example, analyze conversations in real time using a generation AI and provide feedback. The generation AI can, for example, analyze conversations and generate feedback using speech recognition technology or natural language processing technology. For example, the generation AI can analyze the content of an employee's conversation with a customer and immediately provide appropriate feedback. This enables real-time conversation analysis and feedback provision using the generation AI. Some or all of the above-described processing in the feedback providing unit can be performed using, for example, a generation AI. For example, the feedback providing unit can input employee conversation data into the generation AI and cause the generation AI to generate feedback from the conversation data. Furthermore, the feedback providing unit can analyze employee emotional data in real time and immediately grasp emotional changes. For example, the feedback providing unit can monitor employee facial expressions in real time and immediately detect emotional changes. The feedback providing unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the feedback providing unit can analyze employee emotional data over time to identify patterns of emotional changes. This allows you to get a detailed understanding of employee sentiment and reflect it in your feedback.

[0033] The conversation analysis unit can analyze employee conversations in real time using a generative AI. The conversation analysis unit, for example, uses a generative AI to analyze employee conversations in real time. The generative AI can analyze conversations and generate feedback using, for example, speech recognition technology or natural language processing technology. For example, the generative AI can analyze the content of an employee's conversation with a customer and provide appropriate feedback immediately. In this way, the generative AI can analyze employee conversations in real time. Some or all of the above-mentioned processing in the conversation analysis unit can be performed using, for example, a generative AI. For example, the conversation analysis unit can input employee conversation data into a generative AI and have the generative AI generate feedback from the conversation data. Furthermore, the conversation analysis unit can analyze employee emotional data in real time and immediately grasp changes in emotion. For example, the conversation analysis unit can monitor employee facial expressions in real time and immediately detect changes in emotion. The conversation analysis unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the conversation analysis unit can analyze employee emotional data over time to identify patterns of emotional change. This allows for a detailed understanding of employee sentiment and allows for analysis of conversations.

[0034] The scenario presentation unit can analyze past training data and present a scenario according to the employee's skill level. For example, the scenario presentation unit analyzes past training data and presents a scenario according to the employee's skill level. The generation AI can select an appropriate scenario based on the employee's past training data. For example, the generation AI selects an appropriate scenario based on the employee's past training data. The generation AI can also adjust the difficulty of the scenario according to the employee's skill level. Furthermore, the generation AI can analyze the employee's past performance and present an optimal scenario. This allows for the employee's skills to be improved by presenting an appropriate scenario based on the past training data. Some or all of the above-described processing in the scenario presentation unit can be performed using, or without, the generation AI. For example, the scenario presentation unit can input the employee's past training data into the generation AI and select a scenario based on the training data. Furthermore, the scenario presentation unit can analyze the employee's skill level in real time and immediately grasp changes in skills. For example, the scenario presentation unit monitors the employee's performance in real time and immediately detects changes in skills. The scenario presentation unit can also accumulate employee skill data and analyze long-term skill trends. For example, the scenario presentation unit can analyze employee skill data over time to identify skill change patterns. This allows for a detailed understanding of employee skills and reflects this in the presentation of scenarios.

[0035] The scenario presentation unit can provide a customized scenario based on the employee's job content and job title. The scenario presentation unit provides a customized scenario based on, for example, the employee's job content and job title. The generation AI can, for example, present a sales representative with a business negotiation scenario and a customer service representative with a complaint handling scenario. For example, the generation AI presents a sales representative with a business negotiation scenario. The generation AI can also present a customer service representative with a complaint handling scenario. The generation AI can also present a manager with a training scenario for a subordinate. This enables more practical training by providing scenarios tailored to the employee's job content and job title. Some or all of the above-described processing in the scenario presentation unit may be performed using, or without, the generation AI. For example, the scenario presentation unit can input employee job content and job title data into the generation AI and have the generation AI generate a scenario. Furthermore, the scenario presentation unit can analyze employee job content and job title data in real time to immediately grasp changes in job content and job title. For example, the scenario presentation unit monitors employees' job content and job titles in real time and immediately detects changes. The scenario presentation unit can also accumulate data on employees' job content and job titles and analyze long-term trends. For example, the scenario presentation unit can analyze employee job content and job title data over time to identify change patterns. This allows for a detailed understanding of employees' job content and job titles and reflect this in the scenarios provided.

[0036] The scenario presentation unit can present an optimal scenario based on the employee's past feedback history. The scenario presentation unit, for example, presents an optimal scenario based on the employee's past feedback history. The generation AI can, for example, select an appropriate scenario based on the employee's past feedback. For example, the generation AI selects an appropriate scenario based on the employee's past feedback. The generation AI can also analyze the employee's past feedback history and adjust the difficulty of the scenario. Furthermore, the generation AI can present an optimal scenario based on the employee's feedback history. This allows for the employee's skills to be improved by presenting an appropriate scenario based on the past feedback history. Some or all of the above-described processing in the scenario presentation unit may be performed using, or without, the generation AI. For example, the scenario presentation unit can input the employee's past feedback history into the generation AI and select a scenario based on the feedback history. Furthermore, the scenario presentation unit can analyze the employee's feedback history in real time and immediately grasp changes in feedback. For example, the scenario presentation unit monitors the employee's feedback in real time and immediately detects changes. The scenario presentation unit can also accumulate employee feedback history and analyze long-term trends. For example, the scenario presentation unit can analyze employee feedback history over time to identify change patterns. This allows for a detailed understanding of employee feedback and reflects it in the presentation of scenarios.

[0037] The scenario presentation unit can customize a scenario taking into account the employee's geographical and cultural background. The scenario presentation unit customizes the scenario taking into account, for example, the employee's geographical and cultural background. The generation AI can present a region-specific scenario taking into account the employee's geographical background. For example, the generation AI can present a region-specific scenario taking into account the employee's geographical background. The generation AI can also present a culturally appropriate scenario taking into account the employee's cultural background. Furthermore, the generation AI can present an optimal scenario by comprehensively considering the employee's geographical and cultural background. This enables more appropriate training by providing a scenario that takes into account the geographical and cultural background. Some or all of the above-described processing in the scenario presentation unit may be performed using, or without, the generation AI. For example, the scenario presentation unit can input the employee's geographical and cultural background data into the generation AI and cause the generation AI to generate a scenario. Furthermore, the scenario presentation unit can analyze the employee's geographical and cultural background data in real time and immediately grasp changes in the background. For example, the scenario presentation unit can monitor the employee's geographical and cultural background in real time and immediately detect changes. The scenario presentation unit can also accumulate data on employees' geographical and cultural backgrounds and analyze trends of long-term changes. For example, the scenario presentation unit can analyze data on employees' geographical and cultural backgrounds over time to identify patterns of change. This allows for a detailed understanding of employees' geographical and cultural backgrounds and reflects this in the presentation of scenarios.

[0038] The script generation unit can adjust the level of detail of the script based on the importance of the scenario. The script generation unit adjusts the level of detail of the script based on, for example, the importance of the scenario. The generation AI can, for example, evaluate the importance of the scenario and generate a detailed script for an important scenario and a concise script for a low-importance scenario. For example, the generation AI can evaluate the importance of the scenario and generate a detailed script for an important scenario. Furthermore, the generation AI can adjust the level of detail of the script based on the importance of the scenario. As a result, an appropriate script can be provided by adjusting the level of detail of the script based on the importance of the scenario. Some or all of the above-described processing in the script generation unit can be performed using, for example, the generation AI. For example, the script generation unit can input scenario importance data to the generation AI and adjust the level of detail of the script based on the importance data. Furthermore, the script generation unit can analyze the scenario importance data in real time and immediately grasp changes in importance. For example, the script generation unit monitors the importance of scenarios in real time and immediately detects any changes. The script generation unit can also accumulate scenario importance data and analyze long-term trends in importance. For example, the script generation unit can analyze scenario importance data over time to identify patterns of change in importance. This allows the script generation unit to grasp the importance of scenarios in detail and reflect this in the level of detail in the script.

[0039] The script generation unit can apply different generation algorithms depending on the scenario category. For example, the script generation unit can apply different generation algorithms depending on the scenario category. For example, the generation AI can apply a specific algorithm to a complaint handling scenario and a different algorithm to a new product introduction scenario. For example, the generation AI can apply a specific algorithm to generate a script for a complaint handling scenario. Furthermore, the generation AI can apply a different algorithm to generate a script for a new product introduction scenario. Furthermore, the generation AI can select the optimal generation algorithm depending on the scenario category and generate a script. This allows an appropriate script to be provided by applying the optimal generation algorithm depending on the scenario category. Some or all of the above-described processing in the script generation unit can be performed using, for example, the generation AI. For example, the script generation unit can input scenario category data to the generation AI and select a generation algorithm based on the category data. Furthermore, the script generation unit can analyze the scenario category data in real time and immediately grasp changes in the category. For example, the script generation unit can monitor scenario categories in real time and immediately detect changes. The script generation unit can also accumulate scenario category data and analyze long-term category trends. For example, the script generation unit can analyze scenario category data over time to identify patterns of category change. This allows a detailed understanding of scenario categories to be reflected in the selection of a generation algorithm.

[0040] The script generation unit can determine the priority of scripts based on the submission time of the scenario. The script generation unit can determine the priority of scripts based on, for example, the submission time of the scenario. The generation AI can, for example, prioritize generating scripts for urgent scenarios and prioritize generating scripts for scenarios with an approaching submission deadline. For example, the generation AI can prioritize generating scripts for urgent scenarios. Furthermore, the generation AI can prioritize generating scripts for scenarios with an approaching submission deadline. Furthermore, the generation AI can determine the priority of scripts based on the submission time of the scenario. As a result, by determining the priority of scripts based on the submission time of the scenario, an appropriate script can be provided. Some or all of the above-described processing in the script generation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the script generation unit can input scenario submission time data into the generation AI and determine the priority of scripts based on the submission time data. Furthermore, the script generation unit can analyze the scenario submission time data in real time and immediately grasp changes in the submission time. For example, the script generation unit monitors the timing of scenario submissions in real time and immediately detects any changes. The script generation unit can also accumulate data on the timing of scenario submissions and analyze long-term trends in the timing of submissions. For example, the script generation unit can analyze the data on the timing of scenario submissions over time to identify patterns of change in the timing of submissions. This allows for a detailed understanding of the timing of scenario submissions and reflects this in the prioritization of scripts.

[0041] The script generation unit can adjust the order of the script based on the relevance of the scenarios. The script generation unit adjusts the order of the script based on, for example, the relevance of the scenarios. The generation AI can, for example, prioritize generating a script for a highly relevant scenario and postpone generating a script for a less relevant scenario. For example, the generation AI can prioritize generating a script for a highly relevant scenario. Also, the generation AI can postpone generating a script for a less relevant scenario. Furthermore, the generation AI can adjust the order of the script based on the relevance of the scenarios. As a result, an appropriate script can be provided by adjusting the order of the script based on the relevance of the scenarios. Some or all of the above-described processing in the script generation unit may be performed using, for example, the generation AI. For example, the script generation unit can input scenario relevance data to the generation AI and adjust the order of the script based on the relevance data. Furthermore, the script generation unit can analyze the scenario relevance data in real time and immediately grasp changes in relevance. For example, the script generation unit monitors the relevance of scenarios in real time and immediately detects changes. The script generation unit can also accumulate scenario relevance data and analyze long-term trends in relevance. For example, the script generation unit can analyze scenario relevance data over time to identify patterns of change in relevance. This allows the script generation unit to grasp the relevance of scenarios in detail and reflect this in the order of the script.

[0042] The feedback providing unit can provide optimal feedback based on the employee's past performance data. For example, the feedback providing unit provides optimal feedback based on the employee's past performance data. The generation AI can provide appropriate feedback based on the employee's past performance data. For example, the generation AI can provide appropriate feedback based on the employee's past performance data. The generation AI can also analyze the employee's past performance and point out areas for improvement. Furthermore, the generation AI can refer to the employee's past performance data to provide optimal feedback. This allows for the employee's skills to be improved by providing appropriate feedback based on past performance data. Some or all of the above-described processing in the feedback providing unit can be performed using, or without, the generation AI. For example, the feedback providing unit can input the employee's past performance data into the generation AI and provide feedback based on the performance data. Furthermore, the feedback providing unit can analyze the employee's performance data in real time and immediately grasp changes in performance. For example, the feedback providing unit can monitor the employee's performance in real time and immediately detect changes. The feedback providing unit can also accumulate employee performance data and analyze long-term performance trends. For example, the feedback providing unit analyzes employee performance data over time to identify patterns of change in performance, thereby enabling detailed understanding of employee performance and reflecting this in feedback.

[0043] The feedback providing unit can provide customized feedback based on the employee's job title and job content. The feedback providing unit provides customized feedback based on, for example, the employee's job title and job content. The generation AI can, for example, provide feedback on sales skills to a sales representative and feedback on customer service representatives regarding customer service. For example, the generation AI can provide feedback on sales skills to a sales representative. The generation AI can also provide feedback on customer service representatives regarding customer service. Furthermore, the generation AI can provide feedback to a manager regarding the guidance of their subordinates. This enables more practical feedback by providing feedback tailored to the employee's job title and job content. Some or all of the above-described processing in the feedback providing unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the feedback providing unit can input employee job title and job content data into the generation AI and cause the generation AI to generate feedback. Furthermore, the feedback providing unit can analyze employee job title and job content data in real time to immediately grasp changes in job titles and job content. For example, the feedback providing unit monitors employee job titles and job content in real time and immediately detects changes. The feedback providing unit can also accumulate data on employee job titles and job content and analyze long-term trends. For example, the feedback providing unit can analyze data on employee job titles and job content over time to identify change patterns. This allows for a detailed understanding of employee job titles and job content and reflects this in the provision of feedback.

[0044] The feedback providing unit can customize the feedback by taking into account the employee's geographical and cultural background. The feedback providing unit customizes the feedback by taking into account, for example, the employee's geographical and cultural background. The generation AI can provide region-specific feedback by taking into account the employee's geographical background. For example, the generation AI can provide region-specific feedback by taking into account the employee's geographical background. The generation AI can also provide culturally appropriate feedback by taking into account the employee's cultural background. Furthermore, the generation AI can provide optimal feedback by comprehensively taking into account the employee's geographical and cultural background. This enables more appropriate feedback by providing feedback that takes into account the geographical and cultural background. Some or all of the above-described processing in the feedback providing unit can be performed using, for example, the generation AI. For example, the feedback providing unit can input the employee's geographical and cultural background data into the generation AI and cause the generation AI to generate feedback. Furthermore, the feedback providing unit can analyze the employee's geographical and cultural background data in real time and immediately grasp changes in the background. For example, the feedback providing unit can monitor the employee's geographical and cultural background in real time and immediately detect changes. The feedback providing unit can also accumulate data on employees' geographical and cultural backgrounds and analyze trends of long-term changes. For example, the feedback providing unit can analyze data on employees' geographical and cultural backgrounds over time to identify patterns of change. This allows for a detailed understanding of employees' geographical and cultural backgrounds and reflects this in the provision of feedback.

[0045] The feedback providing unit can analyze the employee's social media activity and provide relevant feedback. For example, the feedback providing unit can analyze the employee's social media activity and provide relevant feedback. The generation AI can provide appropriate feedback based on the employee's social media activity. For example, the generation AI can analyze the employee's social media activity and provide appropriate feedback. The generation AI can also point out areas for improvement based on the employee's social media activity. Furthermore, the generation AI can refer to the employee's social media activity and provide optimal feedback. This allows for the employee's skills to be improved by providing appropriate feedback based on the social media activity. Some or all of the above-described processing in the feedback providing unit can be performed using, for example, the generation AI. For example, the feedback providing unit can input the employee's social media activity data into the generation AI and provide feedback based on the activity data. Furthermore, the feedback providing unit can analyze the employee's social media activity data in real time and immediately grasp changes in activity. For example, the feedback providing unit can monitor the employee's social media activity in real time and immediately detect changes. The feedback providing unit can also accumulate the employee's social media activity data and analyze long-term activity trends. For example, the feedback providing unit analyzes employee social media activity data over time to identify patterns of change in activity, thereby enabling a detailed understanding of employee social media activity and the provision of feedback based on that information.

[0046] The conversation analysis unit can improve the accuracy of analysis based on past conversation data of employees. The conversation analysis unit improves the accuracy of analysis based on, for example, past conversation data of employees. The generation AI can perform appropriate conversation analysis based on, for example, past conversation data of employees. For example, the generation AI improves the accuracy of analysis based on past conversation data of employees. Furthermore, the generation AI can analyze past conversation patterns of employees and select the optimal analysis method. Furthermore, the generation AI can refer to past conversation data of employees to perform highly accurate analysis. As a result, appropriate conversation analysis is possible by improving the accuracy of analysis based on past conversation data. Some or all of the above-described processing in the conversation analysis unit may be performed using, for example, the generation AI. For example, the conversation analysis unit can input past conversation data of employees into the generation AI and improve the accuracy of analysis based on the conversation data. Furthermore, the conversation analysis unit can analyze employee conversation data in real time and immediately grasp changes in the conversation. For example, the conversation analysis unit monitors employee conversations in real time and immediately detects changes. The conversation analysis unit can also accumulate employee conversation data and analyze long-term conversation trends. For example, the conversation analysis unit can analyze employee conversation data over time to identify patterns of change in conversation. This allows for a detailed understanding of employee conversations and reflects this in the accuracy of the analysis.

[0047] The conversation analysis unit can perform customized analysis based on the employee's job content and job title. The conversation analysis unit can perform customized analysis based on, for example, the employee's job content and job title. The generation AI can, for example, analyze the conversation of a sales representative and provide feedback on their sales skills. For example, the generation AI can analyze the conversation of a sales representative and provide feedback on their sales skills. The generation AI can also analyze the conversation of a customer service representative and provide feedback on customer service. Furthermore, the generation AI can analyze the conversation of a manager and provide feedback on coaching their subordinates. This enables appropriate feedback by performing conversation analysis based on job content and job title. Some or all of the above-described processing in the conversation analysis unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the conversation analysis unit can input employee job content and job title data into the generation AI and have the generation AI perform conversation analysis. Furthermore, the conversation analysis unit can analyze employee job content and job title data in real time, thereby immediately identifying changes in job content and job title. For example, the conversation analysis unit monitors employees' job content and job titles in real time and immediately detects changes. The conversation analysis unit can also accumulate data on employee job content and job titles and analyze long-term trends. For example, the conversation analysis unit analyzes employee job content and job title data over time to identify change patterns. This allows for a detailed understanding of employee job content and job titles and reflects this in conversation analysis.

[0048] The conversation analysis unit can perform conversation analysis taking into account the geographical and cultural backgrounds of employees. The conversation analysis unit, for example, performs conversation analysis taking into account the geographical and cultural backgrounds of employees. The generation AI can, for example, analyze region-specific conversation patterns taking into account the geographical backgrounds of employees. For example, the generation AI can analyze region-specific conversation patterns taking into account the geographical backgrounds of employees. The generation AI can also perform culturally appropriate conversation analysis taking into account the cultural backgrounds of employees. Furthermore, the generation AI can comprehensively consider the geographical and cultural backgrounds of employees to perform optimal conversation analysis. This enables appropriate feedback by performing conversation analysis taking into account geographical and cultural backgrounds. Some or all of the above-described processing in the conversation analysis unit may be performed using, or without, the generation AI. For example, the conversation analysis unit can input the geographical and cultural background data of employees into the generation AI and have the generation AI perform conversation analysis. Furthermore, the conversation analysis unit can analyze the geographical and cultural background data of employees in real time, thereby immediately identifying changes in background. For example, the conversation analysis unit monitors employees' geographical and cultural backgrounds in real time and immediately detects any changes. The conversation analysis unit can also accumulate data on employees' geographical and cultural backgrounds and analyze trends in long-term changes. For example, the conversation analysis unit analyzes employees' geographical and cultural background data over time to identify patterns of change. This allows for a detailed understanding of employees' geographical and cultural backgrounds and reflects them in conversation analysis.

[0049] The conversation analysis unit can analyze employees' social media activities and refer to related conversation data. For example, the conversation analysis unit can analyze employees' social media activities and refer to related conversation data. The generation AI can perform appropriate conversation analysis based on employees' social media activities. For example, the generation AI can analyze employees' social media activities and refer to related conversation data. The generation AI can also identify conversation trends from employees' social media activities. Furthermore, the generation AI can refer to employees' social media activities and perform optimal conversation analysis. This enables appropriate conversation analysis based on social media activities, enabling appropriate feedback. Some or all of the above-described processing in the conversation analysis unit can be performed using, for example, the generation AI. For example, the conversation analysis unit can input employees' social media activity data into the generation AI and have the generation AI perform conversation analysis based on the activity data. Furthermore, the conversation analysis unit can analyze employees' social media activity data in real time and immediately identify changes in activity. For example, the conversation analysis unit can monitor employees' social media activity in real time and immediately detect changes. The conversation analysis unit can also accumulate employee social media activity data and analyze long-term activity trends. For example, the conversation analysis unit can analyze employee social media activity data over time to identify patterns of change in activity. This allows for a detailed understanding of employee social media activity and the analysis to be reflected in the conversation analysis.

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

[0051] The scenario presentation unit can customize scenarios based on an employee's past performance data. For example, it can present scenarios that an employee struggled with in the past to identify areas for improvement. It can also present scenarios to strengthen scenarios that an employee excels at. Furthermore, it can analyze an employee's performance data and generate scenarios to improve specific skills. This enables more effective training based on an employee's past performance.

[0052] The script generator can customize scripts based on each employee's individual learning style. For example, it can generate a script that makes extensive use of diagrams and charts for visual learners, and one that includes audio guides for auditory learners. It can also generate a script that includes many concrete examples for practical learners. Furthermore, it can analyze each employee's learning style and provide the optimal script format. This enables effective training tailored to each employee's learning style.

[0053] The conversation analysis unit can analyze the tone and pace of an employee's conversation and provide appropriate feedback. For example, if an employee is speaking quickly, it can advise them to slow down. If an employee is speaking in a monotonous tone, it can instruct them to add emotion. Furthermore, it can analyze the rhythm of an employee's conversation and suggest more effective communication methods. This allows for specific feedback to be given to improve employees' conversation skills.

[0054] The script generation unit can adjust the content of the script based on the employee's past feedback history. For example, it can generate a script that reflects feedback the employee has received in the past and highlights areas for improvement. It can also generate a script to further strengthen the skills in which the employee excels. Furthermore, it can analyze the employee's feedback history and provide a script to improve specific skills. This enables more effective training based on the employee's past feedback.

[0055] The conversation analysis unit can analyze the content of employee conversations and provide feedback based on specific keywords and phrases. For example, if an employee frequently uses the phrase "I'm sorry" when dealing with customers, it can advise on the appropriate way to apologize. Also, if an employee frequently uses the phrase "Thank you," it can provide feedback to strengthen the expression of gratitude. Furthermore, it can analyze specific keywords in employee conversations and provide appropriate feedback. This makes it possible to provide specific feedback based on the content of an employee's conversations.

[0056] The script generation unit can customize scripts taking into account the geographical and cultural backgrounds of employees. For example, it can generate scripts based on the culture and customs specific to a region, allowing employees to learn responses appropriate to that region. It can also provide scripts to improve intercultural communication skills. Furthermore, it can analyze the geographical and cultural backgrounds of employees and provide the most appropriate scripts. This enables effective training tailored to the geographical and cultural backgrounds of employees.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The scenario presentation unit uses the generation AI to present scenarios to employees. For example, the generation AI presents various scenarios, such as handling customer complaints or introducing new products. The generation AI can generate scenarios using natural language processing models such as GPT-4 and Gemini. Step 2: The script generation unit automatically generates a script using generative AI. For example, it generates a script that includes specific advice on how employees should respond. The generative AI can generate a script using a Transformer model. Step 3: The feedback provision unit uses generation AI to analyze the conversation in real time and provide feedback. For example, it can analyze what an employee is talking about with a customer and provide appropriate feedback immediately. The generation AI can analyze the conversation and generate feedback using voice recognition technology and natural language processing technology. It can also analyze employee emotional data in real time and immediately grasp changes in emotion. It can also accumulate employee emotional data and analyze long-term emotional trends. Step 4: The conversation analysis unit uses generative AI to analyze employee conversations in real time. For example, it can analyze what an employee is saying to a customer and provide appropriate feedback immediately. Generative AI can use sentiment analysis technology to estimate the employee's emotions and reflect them in the feedback.

[0059] (Example 2) A role-playing training system according to an embodiment of the present invention uses a generative AI to conduct role-playing training for sales, customer service, and customer service. This role-playing training system presents scenarios to employees, automatically generates role-playing scripts based on the training content, and provides immediate feedback to new employees and existing employees. Furthermore, it analyzes the conversations employees have in actual sales and customer service situations in real time and provides immediate feedback. For example, the generative AI presents employees with scenarios such as handling customer complaints or introducing new products. Employees perform role-playing based on these scenarios. The generative AI then analyzes the content of the role-play and automatically generates a script. This script includes specific advice on how employees should respond. For example, it may include how to apologize in response to a customer complaint and how to present a solution. Furthermore, the generative AI analyzes the conversations employees have in actual sales and customer service situations in real time. For example, it analyzes the content of conversations employees have with customers and provides appropriate feedback immediately. This allows employees to immediately identify areas for improvement and apply them to their next interactions. This system is expected to improve employee skills and contribute to increased customer satisfaction. For example, even when a new employee handles a complaint for the first time, the support of the generative AI will enable them to respond appropriately. Veteran employees can also reflect on their own responses and further improve their skills. In this way, the role-playing training system can help improve employee skills.

[0060] A role-playing training system according to an embodiment includes a scenario presentation unit, a script generation unit, a feedback provision unit, and a conversation analysis unit. The scenario presentation unit uses a generation AI to present scenarios to employees. The scenario presentation unit uses the generation AI to present various scenarios, such as handling customer complaints or introducing new products. The generation AI can generate scenarios using a natural language processing model such as GPT-4 or Gemini. The script generation unit automatically generates a script using the generation AI. The script generation unit generates a script that includes specific advice on how an employee should respond. The generation AI can generate a script using a Transformer model, for example. The feedback provision unit analyzes conversations in real time using the generation AI and provides feedback. The feedback provision unit analyzes, for example, the content of conversations between employees and customers and provides appropriate feedback immediately. The generation AI can analyze conversations and generate feedback using, for example, speech recognition technology or natural language processing technology. The conversation analysis unit analyzes employee conversations in real time using the generation AI. The conversation analysis unit, for example, analyzes the content of an employee's conversation with a customer and provides appropriate feedback immediately. The generation AI, for example, can estimate the employee's emotions using emotion analysis technology and reflect the estimated emotions in the feedback. This allows the role-playing training system according to the embodiment to improve employee skills. Some or all of the above-described processing in the feedback providing unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the feedback providing unit may input employee conversation data into the generation AI and cause the generation AI to generate feedback from the conversation data. Furthermore, the feedback providing unit may analyze the employee's emotional data in real time and immediately grasp changes in emotion. For example, the feedback providing unit may monitor the employee's facial expressions in real time and immediately detect changes in emotion. The feedback providing unit may also accumulate employee emotional data and analyze long-term emotional trends. For example, the feedback providing unit may analyze the employee's emotional data over time to identify patterns of emotional change.This allows you to get a detailed understanding of employee sentiment and reflect it in your feedback.

[0061] The scenario presentation unit can present scenarios to employees using a generation AI. The scenario presentation unit presents scenarios to employees using, for example, a generation AI. The generation AI can generate scenarios using a natural language processing model such as GPT-4 or Gemini. For example, the generation AI presents scenarios to employees, such as handling customer complaints or introducing new products. Employees then role-play based on these scenarios. Using the generation AI, appropriate scenarios can be presented to employees. Some or all of the above-described processing in the scenario presentation unit may be performed using, for example, a generation AI. For example, the scenario presentation unit can input customized scenarios based on the employee's job duties and position into the generation AI and have the generation AI generate the scenario. Furthermore, the scenario presentation unit can analyze employee emotional data in real time and instantly grasp changes in emotion. For example, the scenario presentation unit can monitor employee facial expressions in real time and instantly detect changes in emotion. The scenario presentation unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the scenario presentation unit analyzes employee emotion data over time to identify patterns of change in emotion, thereby gaining a detailed understanding of employee emotions and reflecting this in the presentation of scenarios.

[0062] The script generation unit can automatically generate a script using a generative AI. The script generation unit automatically generates a script using, for example, a generative AI. The generative AI can generate a script using, for example, a Transformer model. For example, the script generates a script that includes specific advice on how an employee should respond. The generative AI generates a script that describes, for example, how an employee should apologize in response to a customer complaint and how they should present a solution. This enables automatic script generation using the generative AI. Some or all of the above-mentioned processing in the script generation unit may be performed using, for example, a generative AI. For example, the script generation unit can input a script customized based on the employee's job description and position into the generative AI and have the generative AI generate the script. Furthermore, the script generation unit can analyze employee emotional data in real time and immediately grasp changes in emotion. For example, the script generation unit can monitor employee facial expressions in real time and immediately detect changes in emotion. The script generation unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the script generation unit analyzes employee emotion data over time to identify patterns of change in emotion, thereby gaining a detailed understanding of employee emotions and reflecting this in the generation of scripts.

[0063] The feedback providing unit can analyze conversations in real time using a generation AI and provide feedback. The feedback providing unit can, for example, analyze conversations in real time using a generation AI and provide feedback. The generation AI can, for example, analyze conversations and generate feedback using speech recognition technology or natural language processing technology. For example, the generation AI can analyze the content of an employee's conversation with a customer and immediately provide appropriate feedback. This enables real-time conversation analysis and feedback provision using the generation AI. Some or all of the above-described processing in the feedback providing unit can be performed using, for example, a generation AI. For example, the feedback providing unit can input employee conversation data into the generation AI and cause the generation AI to generate feedback from the conversation data. Furthermore, the feedback providing unit can analyze employee emotional data in real time and immediately grasp emotional changes. For example, the feedback providing unit can monitor employee facial expressions in real time and immediately detect emotional changes. The feedback providing unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the feedback providing unit can analyze employee emotional data over time to identify patterns of emotional changes. This allows you to get a detailed understanding of employee sentiment and reflect it in your feedback.

[0064] The conversation analysis unit can analyze employee conversations in real time using a generative AI. The conversation analysis unit, for example, uses a generative AI to analyze employee conversations in real time. The generative AI can analyze conversations and generate feedback using, for example, speech recognition technology or natural language processing technology. For example, the generative AI can analyze the content of an employee's conversation with a customer and provide appropriate feedback immediately. In this way, the generative AI can analyze employee conversations in real time. Some or all of the above-mentioned processing in the conversation analysis unit can be performed using, for example, a generative AI. For example, the conversation analysis unit can input employee conversation data into a generative AI and have the generative AI generate feedback from the conversation data. Furthermore, the conversation analysis unit can analyze employee emotional data in real time and immediately grasp changes in emotion. For example, the conversation analysis unit can monitor employee facial expressions in real time and immediately detect changes in emotion. The conversation analysis unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the conversation analysis unit can analyze employee emotional data over time to identify patterns of emotional change. This allows for a detailed understanding of employee sentiment and allows for analysis of conversations.

[0065] The scenario presentation unit can estimate the employee's emotions and adjust the difficulty of the scenario based on the estimated employee's emotions. The scenario presentation unit, for example, can estimate the employee's emotions and adjust the difficulty of the scenario based on the estimated employee's emotions. The generation AI can estimate the employee's emotions using, for example, facial expression recognition technology or voice tone analysis technology. For example, if the employee is nervous, the generation AI can present an easy scenario and gradually increase the difficulty. Alternatively, if the employee is relaxed, the generation AI can present a more difficult scenario to help improve the employee's skills. Furthermore, if the employee is stressed, the generation AI can present a relaxing scenario to help reduce stress. This allows appropriate training by adjusting the difficulty of the scenario based on the employee's emotions. Some or all of the above-described processing in the scenario presentation unit may be performed using, or without, the generation AI. For example, the scenario presentation unit can input the employee's emotional data into the generation AI and adjust the difficulty of the scenario based on the emotional data. Furthermore, the scenario presentation unit can analyze the employee's emotional data in real time to instantly grasp changes in emotions. For example, the scenario presentation unit can monitor employees' facial expressions in real time and instantly detect changes in their emotions. The scenario presentation unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the scenario presentation unit can analyze employee emotional data over time to identify patterns of emotional change. This allows for a detailed understanding of employee emotions and reflects this in adjusting the difficulty of the scenario.

[0066] The scenario presentation unit can analyze past training data and present a scenario according to the employee's skill level. For example, the scenario presentation unit analyzes past training data and presents a scenario according to the employee's skill level. The generation AI can select an appropriate scenario based on the employee's past training data. For example, the generation AI selects an appropriate scenario based on the employee's past training data. The generation AI can also adjust the difficulty of the scenario according to the employee's skill level. Furthermore, the generation AI can analyze the employee's past performance and present an optimal scenario. This allows for the employee's skills to be improved by presenting an appropriate scenario based on the past training data. Some or all of the above-described processing in the scenario presentation unit can be performed using, or without, the generation AI. For example, the scenario presentation unit can input the employee's past training data into the generation AI and select a scenario based on the training data. Furthermore, the scenario presentation unit can analyze the employee's skill level in real time and immediately grasp changes in skills. For example, the scenario presentation unit monitors the employee's performance in real time and immediately detects changes in skills. The scenario presentation unit can also accumulate employee skill data and analyze long-term skill trends. For example, the scenario presentation unit can analyze employee skill data over time to identify skill change patterns. This allows for a detailed understanding of employee skills and reflects this in the presentation of scenarios.

[0067] The scenario presentation unit can provide a customized scenario based on the employee's job content and job title. The scenario presentation unit provides a customized scenario based on, for example, the employee's job content and job title. The generation AI can, for example, present a sales representative with a business negotiation scenario and a customer service representative with a complaint handling scenario. For example, the generation AI presents a sales representative with a business negotiation scenario. The generation AI can also present a customer service representative with a complaint handling scenario. The generation AI can also present a manager with a training scenario for a subordinate. This enables more practical training by providing scenarios tailored to the employee's job content and job title. Some or all of the above-described processing in the scenario presentation unit may be performed using, or without, the generation AI. For example, the scenario presentation unit can input employee job content and job title data into the generation AI and have the generation AI generate a scenario. Furthermore, the scenario presentation unit can analyze employee job content and job title data in real time to immediately grasp changes in job content and job title. For example, the scenario presentation unit monitors employees' job content and job titles in real time and immediately detects changes. The scenario presentation unit can also accumulate data on employees' job content and job titles and analyze long-term trends. For example, the scenario presentation unit can analyze employee job content and job title data over time to identify change patterns. This allows for a detailed understanding of employees' job content and job titles and reflect this in the scenarios provided.

[0068] The scenario presentation unit can estimate an employee's emotions and select a scenario theme based on the estimated employee emotions. The scenario presentation unit, for example, estimates an employee's emotions and selects a scenario theme based on the estimated employee emotions. The generation AI can estimate an employee's emotions using, for example, facial expression recognition technology or voice tone analysis technology. For example, if an employee is excited, the generation AI can select a scenario with a challenging theme. Also, if an employee is calm, the generation AI can select a scenario with a relaxing theme. Furthermore, if an employee is tired, the generation AI can select a scenario with an easy theme. This enables appropriate training by selecting a scenario theme based on the employee's emotions. Some or all of the above-described processing in the scenario presentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the scenario presentation unit can input employee emotion data into the generation AI and select a scenario theme based on the emotion data. Furthermore, the scenario presentation unit can analyze employee emotion data in real time to instantly grasp changes in emotion. For example, the scenario presentation unit can monitor employees' facial expressions in real time and instantly detect changes in their emotions. The scenario presentation unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the scenario presentation unit can analyze employee emotional data over time and identify patterns of emotional change. This allows for a detailed understanding of employee emotions and reflects this in the selection of scenario themes.

[0069] The scenario presentation unit can present an optimal scenario based on the employee's past feedback history. The scenario presentation unit, for example, presents an optimal scenario based on the employee's past feedback history. The generation AI can, for example, select an appropriate scenario based on the employee's past feedback. For example, the generation AI selects an appropriate scenario based on the employee's past feedback. The generation AI can also analyze the employee's past feedback history and adjust the difficulty of the scenario. Furthermore, the generation AI can present an optimal scenario based on the employee's feedback history. This allows for the employee's skills to be improved by presenting an appropriate scenario based on the past feedback history. Some or all of the above-described processing in the scenario presentation unit may be performed using, or without, the generation AI. For example, the scenario presentation unit can input the employee's past feedback history into the generation AI and select a scenario based on the feedback history. Furthermore, the scenario presentation unit can analyze the employee's feedback history in real time and immediately grasp changes in feedback. For example, the scenario presentation unit monitors the employee's feedback in real time and immediately detects changes. The scenario presentation unit can also accumulate employee feedback history and analyze long-term trends. For example, the scenario presentation unit can analyze employee feedback history over time to identify change patterns. This allows for a detailed understanding of employee feedback and reflects it in the presentation of scenarios.

[0070] The scenario presentation unit can customize a scenario taking into account the employee's geographical and cultural background. The scenario presentation unit customizes the scenario taking into account, for example, the employee's geographical and cultural background. The generation AI can present a region-specific scenario taking into account the employee's geographical background. For example, the generation AI can present a region-specific scenario taking into account the employee's geographical background. The generation AI can also present a culturally appropriate scenario taking into account the employee's cultural background. Furthermore, the generation AI can present an optimal scenario by comprehensively considering the employee's geographical and cultural background. This enables more appropriate training by providing a scenario that takes into account the geographical and cultural background. Some or all of the above-described processing in the scenario presentation unit may be performed using, or without, the generation AI. For example, the scenario presentation unit can input the employee's geographical and cultural background data into the generation AI and cause the generation AI to generate a scenario. Furthermore, the scenario presentation unit can analyze the employee's geographical and cultural background data in real time and immediately grasp changes in the background. For example, the scenario presentation unit can monitor the employee's geographical and cultural background in real time and immediately detect changes. The scenario presentation unit can also accumulate data on employees' geographical and cultural backgrounds and analyze trends of long-term changes. For example, the scenario presentation unit can analyze data on employees' geographical and cultural backgrounds over time to identify patterns of change. This allows for a detailed understanding of employees' geographical and cultural backgrounds and reflects this in the presentation of scenarios.

[0071] The script generation unit can estimate the employee's emotions and adjust the script's presentation style based on the estimated employee's emotions. The script generation unit, for example, can estimate the employee's emotions and adjust the script's presentation style based on the estimated employee's emotions. The generation AI can estimate the employee's emotions using, for example, facial expression recognition technology or voice tone analysis technology. For example, if the employee is nervous, the generation AI can generate a script with simple and easy-to-understand presentation styles. If the employee is relaxed, the generation AI can generate a script with detailed presentation styles. Furthermore, if the employee is stressed, the generation AI can generate a script with relaxing presentation styles. This allows the script's presentation style to be adjusted according to the employee's emotions, thereby providing an appropriate script. Some or all of the above-described processing in the script generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the script generation unit can input the employee's emotional data into the generation AI and adjust the script's presentation style based on the emotional data. Furthermore, the script generation unit can analyze the employee's emotional data in real time and immediately grasp changes in emotions. For example, the script generation unit can monitor employees' facial expressions in real time and instantly detect changes in their emotions. The script generation unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the script generation unit can analyze employee emotional data over time to identify patterns of emotional change. This allows for a detailed understanding of employee emotions and reflects this in the way the script is written.

[0072] The script generation unit can adjust the level of detail of the script based on the importance of the scenario. The script generation unit adjusts the level of detail of the script based on, for example, the importance of the scenario. The generation AI can, for example, evaluate the importance of the scenario and generate a detailed script for an important scenario and a concise script for a low-importance scenario. For example, the generation AI can evaluate the importance of the scenario and generate a detailed script for an important scenario. Furthermore, the generation AI can adjust the level of detail of the script based on the importance of the scenario. As a result, an appropriate script can be provided by adjusting the level of detail of the script based on the importance of the scenario. Some or all of the above-described processing in the script generation unit can be performed using, for example, the generation AI. For example, the script generation unit can input scenario importance data to the generation AI and adjust the level of detail of the script based on the importance data. Furthermore, the script generation unit can analyze the scenario importance data in real time and immediately grasp changes in importance. For example, the script generation unit monitors the importance of scenarios in real time and immediately detects any changes. The script generation unit can also accumulate scenario importance data and analyze long-term trends in importance. For example, the script generation unit can analyze scenario importance data over time to identify patterns of change in importance. This allows the script generation unit to grasp the importance of scenarios in detail and reflect this in the level of detail in the script.

[0073] The script generation unit can apply different generation algorithms depending on the scenario category. For example, the script generation unit can apply different generation algorithms depending on the scenario category. For example, the generation AI can apply a specific algorithm to a complaint handling scenario and a different algorithm to a new product introduction scenario. For example, the generation AI can apply a specific algorithm to generate a script for a complaint handling scenario. Furthermore, the generation AI can apply a different algorithm to generate a script for a new product introduction scenario. Furthermore, the generation AI can select the optimal generation algorithm depending on the scenario category and generate a script. This allows an appropriate script to be provided by applying the optimal generation algorithm depending on the scenario category. Some or all of the above-described processing in the script generation unit can be performed using, for example, the generation AI. For example, the script generation unit can input scenario category data to the generation AI and select a generation algorithm based on the category data. Furthermore, the script generation unit can analyze the scenario category data in real time and immediately grasp changes in the category. For example, the script generation unit can monitor scenario categories in real time and immediately detect changes. The script generation unit can also accumulate scenario category data and analyze long-term category trends. For example, the script generation unit can analyze scenario category data over time to identify patterns of category change. This allows a detailed understanding of scenario categories to be reflected in the selection of a generation algorithm.

[0074] The script generation unit can estimate the employee's emotions and adjust the length of the script based on the estimated employee emotions. The script generation unit, for example, can estimate the employee's emotions and adjust the length of the script based on the estimated employee emotions. The generation AI can estimate the employee's emotions using, for example, facial expression recognition technology or voice tone analysis technology. For example, if the employee is nervous, the generation AI can generate a short, concise script. If the employee is relaxed, the generation AI can generate a longer script with detailed explanations. Furthermore, if the employee is stressed, the generation AI can generate a short, relaxing script. This allows the length of the script to be adjusted according to the employee's emotions, thereby providing an appropriate script. Some or all of the above-described processing in the script generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the script generation unit can input employee emotion data into the generation AI and adjust the length of the script based on the emotion data. Furthermore, the script generation unit can analyze employee emotion data in real time and immediately grasp changes in emotion. For example, the script generation unit can monitor employees' facial expressions in real time and instantly detect changes in their emotions. The script generation unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the script generation unit can analyze employee emotional data over time to identify patterns of emotional change. This allows for a detailed understanding of employee emotions and the length of the script to be reflected.

[0075] The script generation unit can determine the priority of scripts based on the submission time of the scenario. The script generation unit can determine the priority of scripts based on, for example, the submission time of the scenario. The generation AI can, for example, prioritize generating scripts for urgent scenarios and prioritize generating scripts for scenarios with an approaching submission deadline. For example, the generation AI can prioritize generating scripts for urgent scenarios. Furthermore, the generation AI can prioritize generating scripts for scenarios with an approaching submission deadline. Furthermore, the generation AI can determine the priority of scripts based on the submission time of the scenario. As a result, by determining the priority of scripts based on the submission time of the scenario, an appropriate script can be provided. Some or all of the above-described processing in the script generation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the script generation unit can input scenario submission time data into the generation AI and determine the priority of scripts based on the submission time data. Furthermore, the script generation unit can analyze the scenario submission time data in real time and immediately grasp changes in the submission time. For example, the script generation unit monitors the timing of scenario submissions in real time and immediately detects any changes. The script generation unit can also accumulate data on the timing of scenario submissions and analyze long-term trends in the timing of submissions. For example, the script generation unit can analyze the data on the timing of scenario submissions over time to identify patterns of change in the timing of submissions. This allows for a detailed understanding of the timing of scenario submissions and reflects this in the prioritization of scripts.

[0076] The script generation unit can adjust the order of the script based on the relevance of the scenarios. The script generation unit adjusts the order of the script based on, for example, the relevance of the scenarios. The generation AI can, for example, prioritize generating a script for a highly relevant scenario and postpone generating a script for a less relevant scenario. For example, the generation AI can prioritize generating a script for a highly relevant scenario. Also, the generation AI can postpone generating a script for a less relevant scenario. Furthermore, the generation AI can adjust the order of the script based on the relevance of the scenarios. As a result, an appropriate script can be provided by adjusting the order of the script based on the relevance of the scenarios. Some or all of the above-described processing in the script generation unit may be performed using, for example, the generation AI. For example, the script generation unit can input scenario relevance data to the generation AI and adjust the order of the script based on the relevance data. Furthermore, the script generation unit can analyze the scenario relevance data in real time and immediately grasp changes in relevance. For example, the script generation unit monitors the relevance of scenarios in real time and immediately detects changes. The script generation unit can also accumulate scenario relevance data and analyze long-term trends in relevance. For example, the script generation unit can analyze scenario relevance data over time to identify patterns of change in relevance. This allows the script generation unit to grasp the relevance of scenarios in detail and reflect this in the order of the script.

[0077] The feedback providing unit can estimate the employee's emotions and adjust the feedback expression method based on the estimated employee's emotions. For example, the feedback providing unit can estimate the employee's emotions and adjust the feedback expression method based on the estimated employee's emotions. The generation AI can estimate the employee's emotions using, for example, facial expression recognition technology or voice tone analysis technology. For example, if the employee is nervous, the generation AI can provide feedback using gentle expressions. Furthermore, if the employee is relaxed, the generation AI can provide detailed feedback. Furthermore, if the employee is stressed, the generation AI can provide feedback using relaxing expressions. This allows appropriate feedback to be provided by adjusting the feedback expression method according to the employee's emotions. Some or all of the above-described processing in the feedback providing unit may be performed using, for example, the generation AI. For example, the feedback providing unit can input the employee's emotional data into the generation AI and adjust the feedback expression method based on the emotional data. Furthermore, the feedback providing unit can analyze the employee's emotional data in real time and immediately grasp changes in emotions. For example, the feedback providing unit can monitor the employee's facial expressions in real time and immediately detect changes in emotions. The feedback providing unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the feedback providing unit can analyze employee emotional data over time to identify patterns of emotional change. This allows for a detailed understanding of employee emotions and reflects this in the way feedback is expressed.

[0078] The feedback providing unit can provide optimal feedback based on the employee's past performance data. For example, the feedback providing unit provides optimal feedback based on the employee's past performance data. The generation AI can provide appropriate feedback based on the employee's past performance data. For example, the generation AI can provide appropriate feedback based on the employee's past performance data. The generation AI can also analyze the employee's past performance and point out areas for improvement. Furthermore, the generation AI can refer to the employee's past performance data to provide optimal feedback. This allows for the employee's skills to be improved by providing appropriate feedback based on past performance data. Some or all of the above-described processing in the feedback providing unit can be performed using, or without, the generation AI. For example, the feedback providing unit can input the employee's past performance data into the generation AI and provide feedback based on the performance data. Furthermore, the feedback providing unit can analyze the employee's performance data in real time and immediately grasp changes in performance. For example, the feedback providing unit can monitor the employee's performance in real time and immediately detect changes. The feedback providing unit can also accumulate employee performance data and analyze long-term performance trends. For example, the feedback providing unit analyzes employee performance data over time to identify patterns of change in performance, thereby enabling detailed understanding of employee performance and reflecting this in feedback.

[0079] The feedback providing unit can provide customized feedback based on the employee's job title and job content. The feedback providing unit provides customized feedback based on, for example, the employee's job title and job content. The generation AI can, for example, provide feedback on sales skills to a sales representative and feedback on customer service representatives regarding customer service. For example, the generation AI can provide feedback on sales skills to a sales representative. The generation AI can also provide feedback on customer service representatives regarding customer service. Furthermore, the generation AI can provide feedback to a manager regarding the guidance of their subordinates. This enables more practical feedback by providing feedback tailored to the employee's job title and job content. Some or all of the above-described processing in the feedback providing unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the feedback providing unit can input employee job title and job content data into the generation AI and cause the generation AI to generate feedback. Furthermore, the feedback providing unit can analyze employee job title and job content data in real time to immediately grasp changes in job titles and job content. For example, the feedback providing unit monitors employee job titles and job content in real time and immediately detects changes. The feedback providing unit can also accumulate data on employee job titles and job content and analyze long-term trends. For example, the feedback providing unit can analyze data on employee job titles and job content over time to identify change patterns. This allows for a detailed understanding of employee job titles and job content and reflects this in the provision of feedback.

[0080] The feedback providing unit can estimate the employee's emotions and determine the priority of feedback based on the estimated employee's emotions. The feedback providing unit can, for example, estimate the employee's emotions and determine the priority of feedback based on the estimated employee's emotions. The generation AI can estimate the employee's emotions using, for example, facial expression recognition technology or voice tone analysis technology. For example, if the employee is nervous, the generation AI can prioritize providing feedback. Also, if the employee is relaxed, the generation AI can provide detailed feedback. Furthermore, if the employee is stressed, the generation AI can prioritize providing relaxing feedback. This allows appropriate feedback to be provided by determining the priority of feedback based on the employee's emotions. Some or all of the above-described processing in the feedback providing unit can be performed using, for example, the generation AI. For example, the feedback providing unit can input employee emotion data into the generation AI and determine the priority of feedback based on the emotion data. Furthermore, the feedback providing unit can analyze the employee's emotion data in real time and immediately grasp changes in emotion. For example, the feedback providing unit can monitor the employee's facial expressions in real time and immediately detect changes in emotion. The feedback providing unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the feedback providing unit can analyze employee emotional data over time to identify patterns of emotional change. This allows for a detailed understanding of employee emotions and reflects this in feedback priorities.

[0081] The feedback providing unit can customize the feedback by taking into account the employee's geographical and cultural background. The feedback providing unit customizes the feedback by taking into account, for example, the employee's geographical and cultural background. The generation AI can provide region-specific feedback by taking into account the employee's geographical background. For example, the generation AI can provide region-specific feedback by taking into account the employee's geographical background. The generation AI can also provide culturally appropriate feedback by taking into account the employee's cultural background. Furthermore, the generation AI can provide optimal feedback by comprehensively taking into account the employee's geographical and cultural background. This enables more appropriate feedback by providing feedback that takes into account the geographical and cultural background. Some or all of the above-described processing in the feedback providing unit can be performed using, for example, the generation AI. For example, the feedback providing unit can input the employee's geographical and cultural background data into the generation AI and cause the generation AI to generate feedback. Furthermore, the feedback providing unit can analyze the employee's geographical and cultural background data in real time and immediately grasp changes in the background. For example, the feedback providing unit can monitor the employee's geographical and cultural background in real time and immediately detect changes. The feedback providing unit can also accumulate data on employees' geographical and cultural backgrounds and analyze trends of long-term changes. For example, the feedback providing unit can analyze data on employees' geographical and cultural backgrounds over time to identify patterns of change. This allows for a detailed understanding of employees' geographical and cultural backgrounds and reflects this in the provision of feedback.

[0082] The feedback providing unit can analyze the employee's social media activity and provide relevant feedback. For example, the feedback providing unit can analyze the employee's social media activity and provide relevant feedback. The generation AI can provide appropriate feedback based on the employee's social media activity. For example, the generation AI can analyze the employee's social media activity and provide appropriate feedback. The generation AI can also point out areas for improvement based on the employee's social media activity. Furthermore, the generation AI can refer to the employee's social media activity and provide optimal feedback. This allows for the employee's skills to be improved by providing appropriate feedback based on the social media activity. Some or all of the above-described processing in the feedback providing unit can be performed using, for example, the generation AI. For example, the feedback providing unit can input the employee's social media activity data into the generation AI and provide feedback based on the activity data. Furthermore, the feedback providing unit can analyze the employee's social media activity data in real time and immediately grasp changes in activity. For example, the feedback providing unit can monitor the employee's social media activity in real time and immediately detect changes. The feedback providing unit can also accumulate the employee's social media activity data and analyze long-term activity trends. For example, the feedback providing unit analyzes employee social media activity data over time to identify patterns of change in activity, thereby enabling a detailed understanding of employee social media activity and the provision of feedback based on that information.

[0083] The conversation analysis unit can estimate the employee's emotions and adjust the conversation analysis criteria based on the estimated employee emotions. The conversation analysis unit can, for example, estimate the employee's emotions and adjust the conversation analysis criteria based on the estimated employee emotions. The generation AI can estimate the employee's emotions using, for example, facial expression recognition technology or voice tone analysis technology. For example, if the employee is nervous, the generation AI can analyze the conversation using relaxed criteria. Furthermore, if the employee is relaxed, the generation AI can analyze the conversation using strict criteria. Furthermore, if the employee is stressed, the generation AI can analyze the conversation using criteria that emphasize stress reduction. This allows for appropriate conversation analysis by adjusting the conversation analysis criteria according to the employee's emotions. Some or all of the above-described processing in the conversation analysis unit can be performed using, for example, the generation AI, or without the generation AI. For example, the conversation analysis unit can input employee emotion data into the generation AI and adjust the conversation analysis criteria based on the emotion data. Furthermore, the conversation analysis unit can analyze employee emotion data in real time and immediately grasp changes in emotion. For example, the conversation analysis unit monitors employees' facial expressions in real time and immediately detects changes in their emotions. The conversation analysis unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the conversation analysis unit analyzes employee emotional data over time to identify patterns of emotional change. This allows for a detailed understanding of employee emotions and reflects them in the conversation analysis criteria.

[0084] The conversation analysis unit can improve the accuracy of analysis based on past conversation data of employees. The conversation analysis unit improves the accuracy of analysis based on, for example, past conversation data of employees. The generation AI can perform appropriate conversation analysis based on, for example, past conversation data of employees. For example, the generation AI improves the accuracy of analysis based on past conversation data of employees. Furthermore, the generation AI can analyze past conversation patterns of employees and select the optimal analysis method. Furthermore, the generation AI can refer to past conversation data of employees to perform highly accurate analysis. As a result, appropriate conversation analysis is possible by improving the accuracy of analysis based on past conversation data. Some or all of the above-described processing in the conversation analysis unit may be performed using, for example, the generation AI. For example, the conversation analysis unit can input past conversation data of employees into the generation AI and improve the accuracy of analysis based on the conversation data. Furthermore, the conversation analysis unit can analyze employee conversation data in real time and immediately grasp changes in the conversation. For example, the conversation analysis unit monitors employee conversations in real time and immediately detects changes. The conversation analysis unit can also accumulate employee conversation data and analyze long-term conversation trends. For example, the conversation analysis unit can analyze employee conversation data over time to identify patterns of change in conversation. This allows for a detailed understanding of employee conversations and reflects this in the accuracy of the analysis.

[0085] The conversation analysis unit can perform customized analysis based on the employee's job content and job title. The conversation analysis unit can perform customized analysis based on, for example, the employee's job content and job title. The generation AI can, for example, analyze the conversation of a sales representative and provide feedback on their sales skills. For example, the generation AI can analyze the conversation of a sales representative and provide feedback on their sales skills. The generation AI can also analyze the conversation of a customer service representative and provide feedback on customer service. Furthermore, the generation AI can analyze the conversation of a manager and provide feedback on coaching their subordinates. This enables appropriate feedback by performing conversation analysis based on job content and job title. Some or all of the above-described processing in the conversation analysis unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the conversation analysis unit can input employee job content and job title data into the generation AI and have the generation AI perform conversation analysis. Furthermore, the conversation analysis unit can analyze employee job content and job title data in real time, thereby immediately identifying changes in job content and job title. For example, the conversation analysis unit monitors employees' job content and job titles in real time and immediately detects changes. The conversation analysis unit can also accumulate data on employee job content and job titles and analyze long-term trends. For example, the conversation analysis unit analyzes employee job content and job title data over time to identify change patterns. This allows for a detailed understanding of employee job content and job titles and reflects this in conversation analysis.

[0086] The conversation analysis unit can estimate an employee's emotions and adjust the order in which the conversation analysis results are displayed based on the estimated employee emotions. For example, the conversation analysis unit can estimate an employee's emotions and adjust the order in which the conversation analysis results are displayed based on the estimated employee emotions. The generation AI can estimate an employee's emotions using, for example, facial expression recognition technology or voice tone analysis technology. For example, if an employee is nervous, the generation AI can prioritize displaying important results. Also, if an employee is relaxed, the generation AI can prioritize displaying detailed results in an orderly manner. Furthermore, if an employee is stressed, the generation AI can prioritize displaying results that are useful for stress reduction. This allows for appropriate feedback by adjusting the order in which the conversation analysis results are displayed based on the employee's emotions. Some or all of the above-described processing in the conversation analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the conversation analysis unit can input employee emotion data into the generation AI and adjust the order in which the conversation analysis results are displayed based on the emotion data. Furthermore, the conversation analysis unit can analyze employee emotion data in real time and immediately grasp changes in emotion. For example, the conversation analysis unit monitors employees' facial expressions in real time and instantly detects changes in their emotions. The conversation analysis unit can also accumulate employee emotional data and analyze long-term emotional trends. For example, the conversation analysis unit analyzes employee emotional data over time to identify patterns of emotional change. This allows for a detailed understanding of employee emotions and reflects this in the display of conversation analysis results.

[0087] The conversation analysis unit can perform conversation analysis taking into account the geographical and cultural backgrounds of employees. The conversation analysis unit, for example, performs conversation analysis taking into account the geographical and cultural backgrounds of employees. The generation AI can, for example, analyze region-specific conversation patterns taking into account the geographical backgrounds of employees. For example, the generation AI can analyze region-specific conversation patterns taking into account the geographical backgrounds of employees. The generation AI can also perform culturally appropriate conversation analysis taking into account the cultural backgrounds of employees. Furthermore, the generation AI can comprehensively consider the geographical and cultural backgrounds of employees to perform optimal conversation analysis. This enables appropriate feedback by performing conversation analysis taking into account geographical and cultural backgrounds. Some or all of the above-described processing in the conversation analysis unit may be performed using, or without, the generation AI. For example, the conversation analysis unit can input the geographical and cultural background data of employees into the generation AI and have the generation AI perform conversation analysis. Furthermore, the conversation analysis unit can analyze the geographical and cultural background data of employees in real time, thereby immediately identifying changes in background. For example, the conversation analysis unit monitors employees' geographical and cultural backgrounds in real time and immediately detects any changes. The conversation analysis unit can also accumulate data on employees' geographical and cultural backgrounds and analyze trends in long-term changes. For example, the conversation analysis unit analyzes employees' geographical and cultural background data over time to identify patterns of change. This allows for a detailed understanding of employees' geographical and cultural backgrounds and reflects them in conversation analysis.

[0088] The conversation analysis unit can analyze employees' social media activities and refer to related conversation data. For example, the conversation analysis unit can analyze employees' social media activities and refer to related conversation data. The generation AI can perform appropriate conversation analysis based on employees' social media activities. For example, the generation AI can analyze employees' social media activities and refer to related conversation data. The generation AI can also identify conversation trends from employees' social media activities. Furthermore, the generation AI can refer to employees' social media activities and perform optimal conversation analysis. This enables appropriate conversation analysis based on social media activities, enabling appropriate feedback. Some or all of the above-described processing in the conversation analysis unit can be performed using, for example, the generation AI. For example, the conversation analysis unit can input employees' social media activity data into the generation AI and have the generation AI perform conversation analysis based on the activity data. Furthermore, the conversation analysis unit can analyze employees' social media activity data in real time and immediately identify changes in activity. For example, the conversation analysis unit can monitor employees' social media activity in real time and immediately detect changes. The conversation analysis unit can also accumulate employee social media activity data and analyze long-term activity trends. For example, the conversation analysis unit can analyze employee social media activity data over time to identify patterns of change in activity. This allows for a detailed understanding of employee social media activity and the analysis to be reflected in the conversation analysis. === Hard Collateral 1-1 === Each of the multiple elements including the scenario presenting unit, script generating unit, feedback providing unit, and conversation analyzing 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 scenario presenting unit is realized by the control unit 46A of the smart device 14 and presents a scenario to the employee. The script generating unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of the employee's role-playing and automatically generates a script. The feedback providing unit is realized by the control unit 46A of the smart device 14 and analyzes the employee's conversation in real time and provides immediate feedback. The conversation analyzing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the employee's conversation in real time. === Hard Collateral 1-2 === Each of the multiple elements including the scenario presenting unit, script generating unit, feedback providing unit, and conversation analyzing 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 scenario presenting unit is realized by the control unit 46A of the smart glasses 214 and presents a scenario to the employee. The script generating unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of the employee's role-playing and automatically generates a script. The feedback providing unit is realized by the control unit 46A of the smart glasses 214 and analyzes the employee's conversation in real time and provides immediate feedback. The conversation analyzing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the employee's conversation in real time. === Hard Collateral 1-3 === Each of the multiple elements including the scenario presenting unit, script generating unit, feedback providing unit, and conversation analyzing 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 scenario presenting unit is realized by the control unit 46A of the headset type terminal 314 and presents a scenario to the employee. The script generating unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of the employee's role-playing and automatically generates a script. The feedback providing unit is realized by the control unit 46A of the headset type terminal 314 and analyzes the employee's conversation in real time and provides immediate feedback. The conversation analyzing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the employee's conversation in real time. === Hard Collateral 1-4 === Each of the multiple elements including the scenario presenting unit, script generating unit, feedback providing unit, and conversation analyzing unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the scenario presenting unit is realized by the control unit 46A of the robot 414 and presents a scenario to the employee. The script generating unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of the employee's role-playing and automatically generates a script. The feedback providing unit is realized by the control unit 46A of the robot 414 and analyzes the employee's conversation in real time and provides immediate feedback. The conversation analyzing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the employee's conversation in real time.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The scenario presentation unit can customize scenarios based on an employee's past performance data. For example, it can present scenarios that an employee struggled with in the past to identify areas for improvement. It can also present scenarios to strengthen scenarios that an employee excels at. Furthermore, it can analyze an employee's performance data and generate scenarios to improve specific skills. This enables more effective training based on an employee's past performance.

[0091] The script generator can customize scripts based on each employee's individual learning style. For example, it can generate a script that makes extensive use of diagrams and charts for visual learners, and one that includes audio guides for auditory learners. It can also generate a script that includes many concrete examples for practical learners. Furthermore, it can analyze each employee's learning style and provide the optimal script format. This enables effective training tailored to each employee's learning style.

[0092] The feedback providing unit can estimate the employee's emotions and adjust the timing of feedback based on the estimated employee emotions. For example, if the employee is tense, the feedback can be delayed to give the employee time to relax. If the employee is relaxed, the feedback can be provided immediately. Furthermore, if the employee is feeling stressed, the feedback can be provided in stages. This makes it possible to provide feedback at appropriate times according to the employee's emotions.

[0093] The conversation analysis unit can analyze the tone and pace of an employee's conversation and provide appropriate feedback. For example, if an employee is speaking quickly, it can advise them to slow down. If an employee is speaking in a monotonous tone, it can instruct them to add emotion. Furthermore, it can analyze the rhythm of an employee's conversation and suggest more effective communication methods. This allows for specific feedback to be given to improve employees' conversation skills.

[0094] The scenario presentation unit can estimate the employee's emotions and adjust the speed at which the scenario progresses based on the estimated employee emotions. For example, if the employee is nervous, the scenario progress can be slowed down to give them time to deepen their understanding. If the employee is relaxed, the scenario progress can be sped up to efficiently conduct training. Furthermore, if the employee is feeling stressed, the scenario progress can be gradually adjusted. This makes it possible to progress the scenario appropriately according to the employee's emotions.

[0095] The script generation unit can adjust the content of the script based on the employee's past feedback history. For example, it can generate a script that reflects feedback the employee has received in the past and highlights areas for improvement. It can also generate a script to further strengthen the skills in which the employee excels. Furthermore, it can analyze the employee's feedback history and provide a script to improve specific skills. This enables more effective training based on the employee's past feedback.

[0096] The feedback providing unit can estimate the employee's emotions and adjust the content of the feedback based on the estimated employee's emotions. For example, if the employee is tense, positive feedback can be given first. If the employee is relaxed, feedback including detailed points for improvement can be given. Furthermore, if the employee is feeling stressed, feedback including advice on how to relax can be given. In this way, appropriate feedback can be given according to the employee's emotions.

[0097] The conversation analysis unit can analyze the content of employee conversations and provide feedback based on specific keywords and phrases. For example, if an employee frequently uses the phrase "I'm sorry" when dealing with customers, it can advise on the appropriate way to apologize. Also, if an employee frequently uses the phrase "Thank you," it can provide feedback to strengthen the expression of gratitude. Furthermore, it can analyze specific keywords in employee conversations and provide appropriate feedback. This makes it possible to provide specific feedback based on the content of an employee's conversations.

[0098] The scenario presentation unit can estimate the employee's emotions and adjust the feedback method of the scenario based on the estimated employee's emotions. For example, if the employee is nervous, feedback can be provided in stages, allowing time for the employee to deepen their understanding. If the employee is relaxed, detailed feedback can be provided immediately. Furthermore, if the employee is feeling stressed, a feedback method that helps the employee relax can be adopted. This makes it possible to provide an appropriate feedback method according to the employee's emotions.

[0099] The script generation unit can customize scripts taking into account the geographical and cultural backgrounds of employees. For example, it can generate scripts based on the culture and customs specific to a region, allowing employees to learn responses appropriate to that region. It can also provide scripts to improve intercultural communication skills. Furthermore, it can analyze the geographical and cultural backgrounds of employees and provide the most appropriate scripts. This enables effective training tailored to the geographical and cultural backgrounds of employees.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The scenario presentation unit uses the generation AI to present scenarios to employees. For example, the generation AI presents various scenarios, such as handling customer complaints or introducing new products. The generation AI can generate scenarios using natural language processing models such as GPT-4 and Gemini. Step 2: The script generation unit automatically generates a script using generative AI. For example, it generates a script that includes specific advice on how employees should respond. The generative AI can generate a script using a Transformer model. Step 3: The feedback provision unit uses generation AI to analyze the conversation in real time and provide feedback. For example, it can analyze what an employee is talking about with a customer and provide appropriate feedback immediately. The generation AI can analyze the conversation and generate feedback using voice recognition technology and natural language processing technology. It can also analyze employee emotional data in real time and immediately grasp changes in emotion. It can also accumulate employee emotional data and analyze long-term emotional trends. Step 4: The conversation analysis unit uses generative AI to analyze employee conversations in real time. For example, it can analyze what an employee is saying to a customer and provide appropriate feedback immediately. Generative AI can use sentiment analysis technology to estimate the employee's emotions and reflect them in the feedback.

[0102] 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.

[0103] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0104] 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.

[0105] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0120] 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.

[0121] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0136] 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.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

[0139] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

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

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

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

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

[0145] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

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

[0147] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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.

[0149] 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.

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

[0151] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0153] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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."

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] [Explanation of symbols]

[0174] 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 scenario presentation unit that presents a scenario; a script generation unit that generates a script based on the scenario presented by the scenario presentation unit; a feedback providing unit that provides feedback based on the script generated by the script generating unit; a conversation analysis unit that analyzes employee conversations in real time based on the feedback provided by the feedback providing unit. A system characterized by:

2. The scenario presentation unit Use generative AI to present scenarios to employees 2. The system of claim 1.

3. The script generation unit Automatically generate scripts using generative AI 2. The system of claim 1.

4. The feedback providing unit: Uses generative AI to analyze conversations and provide feedback in real time 2. The system of claim 1.

5. The conversation analysis unit Analyzing employee conversations in real time with generative AI 2. The system of claim 1.

6. The scenario presentation unit Estimate employee emotions and adjust the difficulty of the scenario based on the estimated employee emotions 2. The system of claim 1.

7. The scenario presentation unit Analyze past training data and present scenarios tailored to employees' skill levels 2. The system of claim 1.

8. The scenario presentation unit Offering customized scenarios based on employee job duties and job titles 2. The system of claim 1.

Images