System

Abstract

An object of a system according to an embodiment is to allow a new employee to efficiently learn sales skills.SOLUTION: A system according to an embodiment includes a persona generator, a scenario generator, a test generator, a training generator, a correspondence generator, and a feedback generator. The persona generator creates a persona for the customer. The scenario generation unit generates a scenario corresponding to a difficult customer. The test generation unit generates a quiz or a question for testing the knowledge of the product. The training generation unit generates a training scenario when a new product is launched. The response generation unit generates a scenario for learning a response skill for a customer having a different language or cultural background. The feedback generator provides real-time feedback to the role play of the new employee.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques do not adequately train new employees to effectively acquire sales skills, and there is room for improvement.

[0005] The system according to the embodiment aims to enable new employees to efficiently acquire sales skills. [Means for solving the problem]

[0006] The system according to the embodiment includes a persona generation unit, a scenario generation unit, a test generation unit, a training generation unit, a response generation unit, and a feedback generation unit. The persona generation unit creates customer personas. The scenario generation unit generates scenarios for difficult customer interactions. The test generation unit generates quizzes and questions to test product knowledge. The training generation unit generates training scenarios for new product launches. The response generation unit generates scenarios for acquiring response skills for customers with different languages ​​and cultural backgrounds. The feedback generation unit provides real-time feedback to new employees' role-playing. [Effects of the Invention]

[0007] The system according to the embodiment can enable new employees to efficiently acquire sales skills. [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) The role-play training system according to an embodiment of the present invention is a system that uses a generation AI to efficiently teach sales skills to new employees. As a result, the role-play training system can shorten the training period for new employees and develop them into work-ready personnel.

[0029] A role-play training system according to an embodiment includes a persona generation unit, a scenario generation unit, a test generation unit, a training generation unit, a response generation unit, and a feedback generation unit. The persona generation unit creates customer personas. For example, the generation AI generates realistic customer images based on information such as age, gender, occupation, hobbies, and purchasing history. The generation AI also generates personas based on prompts containing customer characteristics and behavioral patterns. The scenario generation unit generates scenarios for difficult customer interactions. For example, the generation AI generates scenarios for handling complaints and returns. The generation AI also generates scenarios based on prompts containing difficult situations and customer reactions. The test generation unit generates quizzes and questions to test product knowledge. For example, the generation AI generates questions regarding the features and usage of a new product, differences from competing products, etc. The generation AI also generates test questions based on prompts containing detailed product information and test content. The training generation unit generates training scenarios for new product launches. For example, the generation AI creates training scenarios based on information regarding the new product's features, sales strategy, target customers, etc. The generation AI also generates scenarios based on prompts containing information about new products and training content. The response generation unit generates scenarios for acquiring skills for dealing with customers of different languages ​​and cultural backgrounds. For example, the generation AI simulates conversations in different languages ​​and response methods that take cultural differences into account. The generation AI also generates scenarios based on prompts containing information about languages ​​and cultural backgrounds. The feedback generation unit provides real-time feedback to new employees' role-playing. For example, the generation AI specifically points out good points and areas for improvement in customer response, which can be used in the next response. The generation AI also generates feedback based on prompts containing the new employee's response content and evaluation criteria. As a result, the role-play training system according to the embodiment allows new employees to efficiently acquire sales skills. For example, by creating customer personas, new employees can acquire skills for dealing with various customers, and by practicing difficult customer responses, they can improve their ability to respond in actual work.Product knowledge tests and new product launch training allow employees to deepen their product knowledge, and by acquiring skills to deal with language and cultural nuances, employees can serve global customers. Furthermore, real-time feedback allows employees to improve and reach higher levels of customer service skills.

[0030] The persona generation unit can reflect not only purchase history but also social media activity and the content of online reviews. For example, when creating a customer persona, the persona generation unit analyzes not only past purchase history but also social media postings and reflects them in the persona. For example, products and services mentioned by customers on social media are added to the persona. The persona generation unit also analyzes the content of online reviews and reflects them in the customer persona. For example, if a customer gives a high rating to a particular product, that information is added to the persona. The persona generation unit also reflects the customer's interests and concerns in the persona based on social media activity and the content of online reviews. For example, topics and keywords frequently mentioned by customers are added to the persona. This makes it possible to generate realistic personas based on more diverse information.

[0031] The persona generation unit can generate a more realistic customer image by using multimodal information including audio and video data. For example, when creating a customer persona, the persona generation unit analyzes audio data to reflect the customer's tone of voice and speaking style. For example, the persona generation unit estimates emotions and personality based on the customer's audio data. The persona generation unit also analyzes video data to reflect the customer's facial expressions and gestures in the persona. For example, the persona generation unit estimates emotions and behavior patterns based on the customer's video data. The persona generation unit also uses multimodal information including audio and video data to generate a more realistic customer image. For example, the persona generation unit creates a detailed persona based on the customer's audio and video data. This makes it possible to generate a more realistic customer image based on information including audio and video data.

[0032] The persona generation unit can generate customer personas for different industries and markets to perform cross-industry training. For example, the persona generation unit generates customer personas for different industries to perform cross-industry training. For example, customer personas for the IT industry and the medical industry are created, and training scenarios corresponding to each industry are provided. The persona generation unit can also generate customer personas for different markets to perform cross-industry training. For example, customer personas for emerging markets and mature markets are created, and training scenarios corresponding to each market are provided. The persona generation unit can also generate customer personas for different industries and markets to perform cross-industry training. For example, customer personas for the manufacturing industry and the service industry are created, and training scenarios corresponding to each industry are provided. This makes it possible to provide training based on customer personas for different industries and markets.

[0033] The scenario generation unit can incorporate scenarios based on actual past claim data. The scenario generation unit, for example, analyzes actual past claim data and creates difficult customer response scenarios based on that data. For example, it reflects the content of a specific claim in the scenario. The scenario generation unit also creates practice scenarios for customer responses based on actual claim data. For example, it incorporates past claim cases into the scenario. The scenario generation unit also creates practice scenarios for customer responses based on past claim data. For example, it reflects specific claim patterns in the scenario. This makes it possible to provide scenarios based on actual past claim data.

[0034] The scenario generation unit enables the acquisition of global response skills, including for dealing with customers of different languages ​​and cultural backgrounds. The scenario generation unit, for example, creates difficult customer response scenarios that include customers of different languages ​​and cultural backgrounds. For example, it provides a complaint handling scenario in a different language. The scenario generation unit also creates difficult customer response scenarios that include customers of different cultural backgrounds. For example, it reflects differences in complaint handling in different cultures in the scenario. The scenario generation unit also creates difficult customer response scenarios that include customers of different languages ​​and cultural backgrounds. For example, it reflects customer expectations and requests in different cultures in the scenario. This enables the acquisition of global response skills for dealing with customers of different languages ​​and cultural backgrounds.

[0035] The scenario generation unit can use voice recognition technology to respond according to the tone and speed of the customer's voice. The scenario generation unit, for example, uses voice recognition technology to analyze the tone and speed of the customer's voice and provides a response method based on the results. For example, if the customer's voice gets louder, a response method that corresponds to that emotion is provided. The scenario generation unit also analyzes the tone and speed of the customer's voice in real time and provides a response method based on the results. For example, if the customer's voice gets faster, a response method that corresponds to that emotion is provided. The scenario generation unit also uses voice recognition technology to analyze the tone and speed of the customer's voice and provides a response method based on the results. For example, if the customer's voice gets lower, a response method that corresponds to that emotion is provided. This makes it possible to respond according to the tone and speed of the customer's voice.

[0036] The test generation unit can incorporate questions based on actual sales data and customer reviews. The test generation unit, for example, creates product knowledge test questions based on actual sales data. For example, it provides questions that ask about how a particular product is being sold. The test generation unit also analyzes customer reviews and creates product knowledge test questions based on their content. For example, it provides questions that ask about key points that customers mentioned about a particular product. The test generation unit also creates product knowledge test questions based on actual sales data and customer reviews. For example, it provides questions that ask about the features of products that customers have given high ratings to. This makes it possible to provide questions based on actual sales data and customer reviews.

[0037] The test generation unit can assess global knowledge, including questions related to customers with different languages ​​and cultural backgrounds. The test generation unit, for example, includes questions related to customers with different languages ​​and cultural backgrounds in a product knowledge test. For example, it provides questions that ask about differences in product usage in specific cultures. The test generation unit also creates product knowledge tests in different languages ​​to assess global knowledge. For example, it provides test questions in English and Chinese. The test generation unit also includes questions related to customers with different cultural backgrounds in a product knowledge test. For example, it provides questions that ask about customer expectations and requirements in specific cultures. This makes it possible to assess global knowledge, including questions related to customers with different languages ​​and cultural backgrounds.

[0038] The test generation unit can incorporate multimedia questions using audio and video. For example, the test generation unit incorporates audio data into a product knowledge test and provides audio-based questions. For example, an audio description of a product is played and questions asking about the content are provided. The test generation unit also creates a product knowledge test using video data and provides video-based questions. For example, a video demonstration of a product is shown and questions asking about the content are provided. The test generation unit also incorporates multimedia questions using audio and video into a product knowledge test. For example, a video explanation of the product's features is used and questions asking about the content are provided. This makes it possible to provide multimedia questions using audio and video.

[0039] The training generation unit can reflect past sales data and market trends. For example, the training generation unit creates a training scenario for a new product launch based on past sales data. For example, it reflects how a particular product was sold in the scenario. The training generation unit also analyzes market trends and creates a training scenario for a new product launch based on that information. For example, it provides a scenario that reflects current market needs. The training generation unit also creates a training scenario for a new product launch based on past sales data and market trends. For example, it reflects a sales strategy for a particular market in the scenario. This makes it possible to provide training that reflects past sales data and market trends.

[0040] The training creation unit enables the acquisition of global response skills, including scenarios related to customers from different markets and cultural backgrounds. For example, the training creation unit includes scenarios related to customers from different markets and cultural backgrounds in training for launching a new product. For example, sales strategies in different markets are reflected in the scenarios. The training creation unit also includes scenarios related to customers from different cultural backgrounds in training for launching a new product. For example, customer expectations and demands in different cultures are reflected in the scenarios. The training creation unit also includes scenarios related to customers from different markets and cultural backgrounds in training for launching a new product. For example, differences in customer response in different markets are reflected in the scenarios. This enables the acquisition of global response skills, including scenarios related to customers from different markets and cultural backgrounds.

[0041] The training generation unit can incorporate multimedia scenarios using audio and video. For example, the training generation unit incorporates audio data into training when a new product is released and provides a scenario based on the audio. For example, an audio description of the product is played and the content is reflected in the scenario. The training generation unit also creates a training scenario when a new product is released using video data and provides a scenario based on the video. For example, a video of a product demonstration is shown and the content is reflected in the scenario. The training generation unit also incorporates multimedia scenarios using audio and video into training when a new product is released. For example, the features of the product are explained in a video and the content is reflected in the scenario. In this way, a multimedia scenario using audio and video can be provided.

[0042] The response generation unit can reflect actual customer data and cultural examples. The response generation unit, for example, creates a response scenario that addresses language and cultural nuances based on actual customer data. For example, the scenario reflects customer expectations and requests in a specific culture. The response generation unit also analyzes cultural examples and creates a response scenario that addresses language and cultural nuances based on that information. For example, the scenario reflects differences in customer responses in different cultures. The response generation unit also creates a response scenario that addresses language and cultural nuances based on actual customer data and cultural examples. For example, the scenario reflects customer expectations and requests in a specific culture. This makes it possible to provide a scenario that reflects actual customer data and cultural examples.

[0043] The response generation unit enables the acquisition of global response skills, including scenarios related to customers from different markets and cultural backgrounds. The response generation unit, for example, includes scenarios related to customers from different markets and cultural backgrounds in training on how to respond to language and cultural nuances. For example, differences in customer responses in different markets are reflected in the scenarios. The response generation unit also includes scenarios related to customers from different cultural backgrounds in training on how to respond to language and cultural nuances. For example, customer expectations and requests in different cultures are reflected in the scenarios. The response generation unit also includes scenarios related to customers from different markets and cultural backgrounds in training on how to respond to language and cultural nuances. For example, sales strategies in different markets are reflected in the scenarios. This enables the acquisition of global response skills, including scenarios related to customers from different markets and cultural backgrounds.

[0044] The response generation unit can incorporate a multimedia scenario using audio and video. For example, the response generation unit incorporates audio data into training on how to deal with language and cultural nuances and provides a scenario based on the audio. For example, conversations in different languages ​​are played back audio and the content is reflected in the scenario. The response generation unit also creates a training scenario on how to deal with language and cultural nuances using video data and provides a video-based scenario. For example, a video demonstration of how to deal with customers in different cultures is shown and the content is reflected in the scenario. The response generation unit also incorporates a multimedia scenario using audio and video into training on how to deal with language and cultural nuances. For example, customer expectations and requests in different cultures are explained in a video and the content is reflected in the scenario. In this way, a multimedia scenario using audio and video can be provided.

[0045] The feedback generation unit can reflect past training data and actual work data. The feedback generation unit, for example, provides real-time feedback based on past training data. For example, feedback on specific training content is provided. The feedback generation unit also analyzes actual work data and provides real-time feedback based on that information. For example, feedback according to the current work situation is provided. The feedback generation unit also provides real-time feedback based on past training data and actual work data. For example, feedback is provided based on performance in a specific work task. This makes it possible to provide feedback that reflects past training data and actual work data.

[0046] The feedback generation unit enables acquisition of global response skills, including feedback on customers with different languages ​​and cultural backgrounds. The feedback generation unit, for example, includes feedback on customers with different languages ​​and cultural backgrounds in the real-time feedback. For example, it provides feedback on customer responses in different languages. The feedback generation unit also includes feedback on customers with different cultural backgrounds in the real-time feedback. For example, it provides feedback on customer expectations and requirements in different cultures. The feedback generation unit also includes feedback on customers with different languages ​​and cultural backgrounds in the real-time feedback. For example, it provides feedback on customer responses in different markets. This enables acquisition of global response skills, including feedback on customers with different languages ​​and cultural backgrounds.

[0047] The feedback generation unit can incorporate multimedia feedback using audio and video. For example, the feedback generation unit incorporates audio data into real-time feedback and provides audio-based feedback. For example, the feedback generation unit analyzes audio of customer interactions and provides feedback based on the content of the audio. The feedback generation unit also creates real-time feedback using video data and provides video-based feedback. For example, the feedback generation unit analyzes video of customer interactions and provides feedback based on the content of the video. The feedback generation unit also incorporates multimedia feedback using audio and video into real-time feedback. For example, the feedback generation unit provides feedback based on audio and video of customer interactions. This makes it possible to provide multimedia feedback using audio and video.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The role-play training system can further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit, for example, collects and analyzes behavioral data from the user's past training sessions and actual work. For example, it records the user's responses and the results obtained, and identifies behavioral patterns based on that data. The behavior analysis unit can also customize training scenarios based on the user's behavioral data. For example, if the user has difficulty with a particular response, it can provide a scenario specialized for that response. The behavior analysis unit can also provide feedback based on the user's behavioral data. For example, it can specifically point out what was good about the user's past responses and what needs to be improved, and use that information in the next response. This makes it possible to provide more effective training based on the user's behavioral data.

[0050] The role-play training system may further include a learning style analysis unit that analyzes the user's learning style. The learning style analysis unit, for example, identifies which method of learning is most effective for the user. For example, it may provide a scenario that makes heavy use of videos and images to a user who prefers visual information, and a scenario that makes heavy use of audio to a user who prefers auditory information. The learning style analysis unit may also customize training scenarios based on the user's learning style. For example, if the user prefers practical learning, it may provide a scenario that is closer to actual work. The learning style analysis unit may also provide feedback based on the user's learning style. For example, if the user prefers theoretical explanations, it may provide feedback that includes those explanations. This may allow for more effective training based on the user's learning style.

[0051] The role-play training system may further include a data analysis unit that analyzes the user's past training data. The data analysis unit, for example, collects and analyzes the results of the user's past training. For example, it records the responses the user made and the results they obtained, and customizes training scenarios based on that data. The data analysis unit can also provide feedback based on the user's past training data. For example, it can specifically point out what was good about the user's past responses and what areas need improvement, and use this information in the next response. The data analysis unit can also adjust the progress of training based on the user's past training data. For example, if the user feels uncomfortable with a particular response, it can provide a scenario specialized for that response. This allows for more effective training based on the user's past training data.

[0052] The role-play training system may further include a skill analysis unit that analyzes the user's skill level. The skill analysis unit, for example, collects and analyzes the results of training the user has conducted in the past. For example, it identifies what skills the user has and what skills they are lacking. The skill analysis unit can also customize training scenarios based on the user's skill level. For example, if the user is lacking in a particular skill, it can provide a scenario that strengthens that skill. The skill analysis unit can also provide feedback based on the user's skill level. For example, if the user improves a particular skill, it can provide feedback on that skill. This makes it possible to provide more effective training based on the user's skill level.

[0053] The role-play training system may further include a performance analysis unit that analyzes the user's performance. The performance analysis unit, for example, collects and analyzes the results of training that the user has conducted in the past. For example, it identifies how the user performed and what areas need improvement. The performance analysis unit can also customize training scenarios based on the user's performance. For example, if the user is lacking in a particular performance, it provides a scenario that strengthens that performance. The performance analysis unit can also provide feedback based on the user's performance. For example, if the user improves a particular performance, it provides feedback on that performance. This makes it possible to provide more effective training based on the user's performance.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The persona generation unit creates a customer persona. For example, the generation AI generates a realistic customer profile based on information such as age, gender, occupation, hobbies, and purchasing history. The generation AI also generates a persona based on prompts that include customer characteristics and behavioral patterns. Step 2: The scenario generation unit generates scenarios for difficult customer interactions. For example, the generation AI generates scenarios for handling complaints and returns. The generation AI also generates scenarios based on prompts that include difficult situations and customer reactions. Step 3: The test generator generates quizzes and questions to test product knowledge. For example, the generator generates questions about the features and usage of a new product, how it differs from competing products, etc. The generator also generates test questions based on prompts containing detailed product information and test content. Step 4: The training generation unit generates training scenarios for the launch of a new product. For example, the generation AI creates training scenarios based on information about the new product's features, sales strategy, target customers, etc. The generation AI also generates scenarios based on prompts containing information about the new product and training content. Step 5: The response generation unit generates scenarios to acquire response skills for customers with different languages ​​and cultural backgrounds. For example, the generation AI simulates conversations in different languages ​​and response methods that take cultural differences into account. The generation AI also generates scenarios based on prompts that include information about language and cultural background. Step 6: The feedback generator provides real-time feedback to the new employee's role-play. For example, the generator can specifically point out what went well in the customer service and what needs improvement, which can be used for the next interaction. The generator also generates feedback based on prompts that include the new employee's response and evaluation criteria.

[0056] (Example 2) The role-play training system according to an embodiment of the present invention is a system that uses a generation AI to efficiently teach sales skills to new employees. As a result, the role-play training system can shorten the training period for new employees and develop them into work-ready personnel.

[0057] A role-play training system according to an embodiment includes a persona generation unit, a scenario generation unit, a test generation unit, a training generation unit, a response generation unit, and a feedback generation unit. The persona generation unit creates customer personas. For example, the generation AI generates realistic customer images based on information such as age, gender, occupation, hobbies, and purchasing history. The generation AI also generates personas based on prompts containing customer characteristics and behavioral patterns. The scenario generation unit generates scenarios for difficult customer interactions. For example, the generation AI generates scenarios for handling complaints and returns. The generation AI also generates scenarios based on prompts containing difficult situations and customer reactions. The test generation unit generates quizzes and questions to test product knowledge. For example, the generation AI generates questions regarding the features and usage of a new product, differences from competing products, etc. The generation AI also generates test questions based on prompts containing detailed product information and test content. The training generation unit generates training scenarios for new product launches. For example, the generation AI creates training scenarios based on information regarding the new product's features, sales strategy, target customers, etc. The generation AI also generates scenarios based on prompts containing information about new products and training content. The response generation unit generates scenarios for acquiring skills for dealing with customers of different languages ​​and cultural backgrounds. For example, the generation AI simulates conversations in different languages ​​and response methods that take cultural differences into account. The generation AI also generates scenarios based on prompts containing information about languages ​​and cultural backgrounds. The feedback generation unit provides real-time feedback to new employees' role-playing. For example, the generation AI specifically points out good points and areas for improvement in customer response, which can be used in the next response. The generation AI also generates feedback based on prompts containing the new employee's response content and evaluation criteria. As a result, the role-play training system according to the embodiment allows new employees to efficiently acquire sales skills. For example, by creating customer personas, new employees can acquire skills for dealing with various customers, and by practicing difficult customer responses, they can improve their ability to respond in actual work.Product knowledge tests and new product launch training allow employees to deepen their product knowledge, and by acquiring skills to deal with language and cultural nuances, employees can serve global customers. Furthermore, real-time feedback allows employees to improve and reach higher levels of customer service skills.

[0058] The persona generation unit can perform sentiment analysis using generative AI and dynamically update the persona in response to changes in sentiment. For example, the persona generation unit uses generative AI to create a customer persona and then performs sentiment analysis on that persona. For example, it analyzes the customer's purchase history and social media posts to detect changes in sentiment. The persona generation unit also periodically performs sentiment analysis on the customer persona and dynamically updates the persona in response to changes in sentiment. For example, if a customer's sentiment changes from positive to negative, the persona generation unit reflects that change. The persona generation unit also updates the persona's behavioral patterns and purchasing intent in real time based on the results of the sentiment analysis. For example, if a customer expresses positive sentiment toward a particular product, information related to that product is added to the persona. This makes it possible to generate realistic personas that respond to changes in customer sentiment.

[0059] The persona generation unit can reflect not only purchase history but also social media activity and the content of online reviews. For example, when creating a customer persona, the persona generation unit analyzes not only past purchase history but also social media postings and reflects them in the persona. For example, products and services mentioned by customers on social media are added to the persona. The persona generation unit also analyzes the content of online reviews and reflects them in the customer persona. For example, if a customer gives a high rating to a particular product, that information is added to the persona. The persona generation unit also reflects the customer's interests and concerns in the persona based on social media activity and the content of online reviews. For example, topics and keywords frequently mentioned by customers are added to the persona. This makes it possible to generate realistic personas based on more diverse information.

[0060] The persona generation unit can use the emotion estimation function to monitor the emotional state of the persona in real time and reflect it in the training scenario. The persona generation unit, for example, uses the emotion estimation function to monitor the emotional state of a customer persona in real time. For example, it analyzes the customer's online activities and purchase history and calculates an emotion score. The persona generation unit also monitors the emotional state of the persona in real time and reflects the results in the training scenario. For example, if a customer shows negative emotion, it generates a scenario corresponding to that emotion. The persona generation unit also uses the emotion estimation function to update the emotional state of the persona in real time and reflect it in the training scenario. For example, if a customer shows positive emotion, it generates a scenario corresponding to that emotion. This makes it possible to provide training scenarios based on the emotional state of the persona.

[0061] The persona generation unit can generate a more realistic customer image by using multimodal information including audio and video data. For example, when creating a customer persona, the persona generation unit analyzes audio data to reflect the customer's tone of voice and speaking style. For example, the persona generation unit estimates emotions and personality based on the customer's audio data. The persona generation unit also analyzes video data to reflect the customer's facial expressions and gestures in the persona. For example, the persona generation unit estimates emotions and behavior patterns based on the customer's video data. The persona generation unit also uses multimodal information including audio and video data to generate a more realistic customer image. For example, the persona generation unit creates a detailed persona based on the customer's audio and video data. This makes it possible to generate a more realistic customer image based on information including audio and video data.

[0062] The persona generation unit can generate customer personas for different industries and markets to perform cross-industry training. For example, the persona generation unit generates customer personas for different industries to perform cross-industry training. For example, customer personas for the IT industry and the medical industry are created, and training scenarios corresponding to each industry are provided. The persona generation unit can also generate customer personas for different markets to perform cross-industry training. For example, customer personas for emerging markets and mature markets are created, and training scenarios corresponding to each market are provided. The persona generation unit can also generate customer personas for different industries and markets to perform cross-industry training. For example, customer personas for the manufacturing industry and the service industry are created, and training scenarios corresponding to each industry are provided. This makes it possible to provide training based on customer personas for different industries and markets.

[0063] The persona generation unit can use the emotion estimation function to generate a customized training scenario based on the emotional state of the persona. For example, the persona generation unit uses the emotion estimation function to analyze the emotional state of the persona and generate a customized training scenario based on the results. For example, if a customer is feeling stressed, a scenario corresponding to that emotion is provided. The persona generation unit also monitors the emotional state of the persona in real time and generates a customized training scenario based on the results. For example, if a customer is excited, a scenario corresponding to that emotion is provided. The persona generation unit also uses the emotion estimation function to analyze the emotional state of the persona and generate a customized training scenario based on the results. For example, if a customer is feeling anxious, a scenario corresponding to that emotion is provided. This makes it possible to provide a customized training scenario based on the emotional state of the persona.

[0064] The scenario generation unit uses generation AI to perform emotion analysis and can update the scenario in real time according to changes in customer emotions. The scenario generation unit, for example, uses generation AI to create difficult customer response scenarios and perform emotion analysis. For example, it analyzes the content of a customer's complaint and updates the scenario according to changes in emotion. The scenario generation unit also monitors changes in customer emotions in real time and dynamically updates the scenario based on the results. For example, if a customer shows anger, it provides a scenario that corresponds to that emotion. The scenario generation unit also updates the scenario in real time according to changes in customer emotions based on the results of the emotion analysis. For example, if a customer shows dissatisfaction, it provides a scenario that corresponds to that emotion. This makes it possible to update the scenario in real time according to changes in customer emotions.

[0065] The scenario generation unit can incorporate scenarios based on actual past claim data. The scenario generation unit, for example, analyzes actual past claim data and creates difficult customer response scenarios based on that data. For example, it reflects the content of a specific claim in the scenario. The scenario generation unit also creates practice scenarios for customer responses based on actual claim data. For example, it incorporates past claim cases into the scenario. The scenario generation unit also creates practice scenarios for customer responses based on past claim data. For example, it reflects specific claim patterns in the scenario. This makes it possible to provide scenarios based on actual past claim data.

[0066] The scenario generation unit can use the emotion estimation function to monitor the emotional state of a customer in real time and dynamically change the response method. The scenario generation unit, for example, uses the emotion estimation function to monitor the emotional state of a customer in real time. For example, it analyzes the customer's facial expression and tone of voice and calculates an emotion score. The scenario generation unit also monitors the emotional state of a customer in real time and dynamically changes the response method based on the results. For example, if a customer shows anger, it provides a response method that corresponds to that emotion. The scenario generation unit also monitors the emotional state of a customer in real time using the emotion estimation function and dynamically changes the response method based on the results. For example, if a customer shows dissatisfaction, it provides a response method that corresponds to that emotion. This makes it possible to dynamically change the response method according to the emotional state of the customer.

[0067] The scenario generation unit enables the acquisition of global response skills, including for dealing with customers of different languages ​​and cultural backgrounds. The scenario generation unit, for example, creates difficult customer response scenarios that include customers of different languages ​​and cultural backgrounds. For example, it provides a complaint handling scenario in a different language. The scenario generation unit also creates difficult customer response scenarios that include customers of different cultural backgrounds. For example, it reflects differences in complaint handling in different cultures in the scenario. The scenario generation unit also creates difficult customer response scenarios that include customers of different languages ​​and cultural backgrounds. For example, it reflects customer expectations and requests in different cultures in the scenario. This enables the acquisition of global response skills for dealing with customers of different languages ​​and cultural backgrounds.

[0068] The scenario generation unit can use voice recognition technology to respond according to the tone and speed of the customer's voice. The scenario generation unit, for example, uses voice recognition technology to analyze the tone and speed of the customer's voice and provides a response method based on the results. For example, if the customer's voice gets louder, a response method that corresponds to that emotion is provided. The scenario generation unit also analyzes the tone and speed of the customer's voice in real time and provides a response method based on the results. For example, if the customer's voice gets faster, a response method that corresponds to that emotion is provided. The scenario generation unit also uses voice recognition technology to analyze the tone and speed of the customer's voice and provides a response method based on the results. For example, if the customer's voice gets lower, a response method that corresponds to that emotion is provided. This makes it possible to respond according to the tone and speed of the customer's voice.

[0069] The scenario generation unit can use the emotion estimation function to provide customized feedback based on the emotional state of the customer. For example, the scenario generation unit uses the emotion estimation function to analyze the emotional state of the customer and provide customized feedback based on the results. For example, if the customer expresses anger, feedback corresponding to that emotion is provided. The scenario generation unit also monitors the emotional state of the customer in real time and provides customized feedback based on the results. For example, if the customer expresses dissatisfaction, feedback corresponding to that emotion is provided. The scenario generation unit also uses the emotion estimation function to analyze the emotional state of the customer and provide customized feedback based on the results. For example, if the customer is feeling stressed, feedback corresponding to that emotion is provided. In this way, customized feedback based on the emotional state of the customer can be provided.

[0070] The test generation unit can perform emotion analysis using the generation AI and provide feedback according to the respondent's emotional state. For example, the test generation unit uses the generation AI to conduct a product knowledge test and analyze the respondent's emotional state. For example, if the respondent is feeling stressed, feedback corresponding to that emotion is provided. The test generation unit also provides feedback according to the respondent's emotional state based on the results of the emotion analysis. For example, if the respondent expresses positive emotion, feedback corresponding to that emotion is provided. The test generation unit also uses the generation AI to conduct a product knowledge test and monitor the respondent's emotional state in real time. For example, if the respondent is feeling anxious, feedback corresponding to that emotion is provided. This makes it possible to provide feedback according to the respondent's emotional state.

[0071] The test generation unit can incorporate questions based on actual sales data and customer reviews. The test generation unit, for example, creates product knowledge test questions based on actual sales data. For example, it provides questions that ask about how a particular product is being sold. The test generation unit also analyzes customer reviews and creates product knowledge test questions based on their content. For example, it provides questions that ask about key points that customers mentioned about a particular product. The test generation unit also creates product knowledge test questions based on actual sales data and customer reviews. For example, it provides questions that ask about the features of products that customers have given high ratings to. This makes it possible to provide questions based on actual sales data and customer reviews.

[0072] The test generation unit can use the emotion estimation function to monitor the respondent's emotional state in real time and dynamically adjust the difficulty of the test. The test generation unit, for example, uses the emotion estimation function to monitor the respondent's emotional state in real time. For example, if the respondent is feeling stressed, the difficulty of the test is lowered. The test generation unit also monitors the respondent's emotional state in real time and dynamically adjusts the difficulty of the test based on the results. For example, if the respondent is relaxed, the difficulty of the test is increased. The test generation unit also monitors the respondent's emotional state in real time using the emotion estimation function and dynamically adjusts the difficulty of the test based on the results. For example, if the respondent is feeling anxious, the difficulty of the test is lowered. This allows the difficulty of the test to be dynamically adjusted according to the respondent's emotional state.

[0073] The test generation unit can assess global knowledge, including questions related to customers with different languages ​​and cultural backgrounds. The test generation unit, for example, includes questions related to customers with different languages ​​and cultural backgrounds in a product knowledge test. For example, it provides questions that ask about differences in product usage in specific cultures. The test generation unit also creates product knowledge tests in different languages ​​to assess global knowledge. For example, it provides test questions in English and Chinese. The test generation unit also includes questions related to customers with different cultural backgrounds in a product knowledge test. For example, it provides questions that ask about customer expectations and requirements in specific cultures. This makes it possible to assess global knowledge, including questions related to customers with different languages ​​and cultural backgrounds.

[0074] The test generation unit can incorporate multimedia questions using audio and video. For example, the test generation unit incorporates audio data into a product knowledge test and provides audio-based questions. For example, an audio description of a product is played and questions asking about the content are provided. The test generation unit also creates a product knowledge test using video data and provides video-based questions. For example, a video demonstration of a product is shown and questions asking about the content are provided. The test generation unit also incorporates multimedia questions using audio and video into a product knowledge test. For example, a video explanation of the product's features is used and questions asking about the content are provided. This makes it possible to provide multimedia questions using audio and video.

[0075] The test generation unit can use the emotion estimation function to provide customized feedback based on the respondent's emotional state. For example, the test generation unit uses the emotion estimation function to analyze the respondent's emotional state and provide customized feedback based on the results. For example, if the respondent is feeling stressed, feedback corresponding to that emotion is provided. The test generation unit also monitors the respondent's emotional state in real time and provides customized feedback based on the results. For example, if the respondent expresses positive emotion, feedback corresponding to that emotion is provided. The test generation unit also uses the emotion estimation function to analyze the respondent's emotional state and provide customized feedback based on the results. For example, if the respondent is feeling anxious, feedback corresponding to that emotion is provided. This makes it possible to provide customized feedback based on the respondent's emotional state.

[0076] The training generation unit can use the generation AI to perform emotion analysis and provide real-time feedback according to the progress of the training. For example, the training generation unit uses the generation AI to conduct training when a new product is released and analyze the emotional state of the participants. For example, if a participant is feeling stressed, feedback corresponding to that emotion is provided. The training generation unit also provides real-time feedback according to the progress of the training based on the results of the emotion analysis. For example, if a participant expresses positive emotion, feedback corresponding to that emotion is provided. The training generation unit also uses the generation AI to conduct training when a new product is released and monitors the emotional state of the participants in real time. For example, if a participant is feeling anxious, feedback corresponding to that emotion is provided. This makes it possible to provide real-time feedback according to the progress of the training.

[0077] The training generation unit can reflect past sales data and market trends. For example, the training generation unit creates a training scenario for a new product launch based on past sales data. For example, it reflects how a particular product was sold in the scenario. The training generation unit also analyzes market trends and creates a training scenario for a new product launch based on that information. For example, it provides a scenario that reflects current market needs. The training generation unit also creates a training scenario for a new product launch based on past sales data and market trends. For example, it reflects a sales strategy for a particular market in the scenario. This makes it possible to provide training that reflects past sales data and market trends.

[0078] The training generation unit can use the emotion estimation function to monitor the emotional state of the training participant in real time and dynamically adjust the training content. The training generation unit, for example, uses the emotion estimation function to monitor the emotional state of the training participant in real time. For example, if the participant is feeling stressed, the training content is adjusted. The training generation unit also monitors the emotional state of the training participant in real time and dynamically adjusts the training content based on the results. For example, if the participant is relaxed, the difficulty of the training is increased. The training generation unit also monitors the emotional state of the training participant in real time using the emotion estimation function and dynamically adjusts the training content based on the results. For example, if the participant is feeling anxious, the training content is adjusted. In this way, the training content can be dynamically adjusted according to the emotional state of the training participant.

[0079] The training creation unit enables the acquisition of global response skills, including scenarios related to customers from different markets and cultural backgrounds. For example, the training creation unit includes scenarios related to customers from different markets and cultural backgrounds in training for launching a new product. For example, sales strategies in different markets are reflected in the scenarios. The training creation unit also includes scenarios related to customers from different cultural backgrounds in training for launching a new product. For example, customer expectations and demands in different cultures are reflected in the scenarios. The training creation unit also includes scenarios related to customers from different markets and cultural backgrounds in training for launching a new product. For example, differences in customer response in different markets are reflected in the scenarios. This enables the acquisition of global response skills, including scenarios related to customers from different markets and cultural backgrounds.

[0080] The training generation unit can incorporate multimedia scenarios using audio and video. For example, the training generation unit incorporates audio data into training when a new product is released and provides a scenario based on the audio. For example, an audio description of the product is played and the content is reflected in the scenario. The training generation unit also creates a training scenario when a new product is released using video data and provides a scenario based on the video. For example, a video of a product demonstration is shown and the content is reflected in the scenario. The training generation unit also incorporates multimedia scenarios using audio and video into training when a new product is released. For example, the features of the product are explained in a video and the content is reflected in the scenario. In this way, a multimedia scenario using audio and video can be provided.

[0081] The training generation unit can use the emotion estimation function to provide customized feedback based on the emotional state of the training participant. For example, the training generation unit uses the emotion estimation function to analyze the emotional state of the training participant and provide customized feedback based on the results. For example, if the participant is feeling stressed, feedback corresponding to that emotion is provided. The training generation unit also monitors the emotional state of the training participant in real time and provides customized feedback based on the results. For example, if the participant shows positive emotion, feedback corresponding to that emotion is provided. The training generation unit also uses the emotion estimation function to analyze the emotional state of the training participant and provide customized feedback based on the results. For example, if the participant is feeling anxious, feedback corresponding to that emotion is provided. In this way, customized feedback based on the emotional state of the training participant can be provided.

[0082] The response generation unit uses generative AI to perform sentiment analysis and can update scenarios in real time in response to changes in customer emotions. The response generation unit, for example, uses generative AI to create response scenarios that address language and cultural nuances and perform sentiment analysis. For example, it analyzes the customer's language and cultural background and updates the scenario in response to changes in emotion. The response generation unit also monitors changes in customer emotions in real time and dynamically updates the scenario based on the results. For example, if a customer expresses anger, it provides a scenario that corresponds to that emotion. The response generation unit also updates the scenario in real time in response to changes in customer emotions based on the results of the sentiment analysis. For example, if a customer expresses dissatisfaction, it provides a scenario that corresponds to that emotion. This makes it possible to update scenarios in real time in response to changes in customer emotions.

[0083] The response generation unit can reflect actual customer data and cultural examples. The response generation unit, for example, creates a response scenario that addresses language and cultural nuances based on actual customer data. For example, the scenario reflects customer expectations and requests in a specific culture. The response generation unit also analyzes cultural examples and creates a response scenario that addresses language and cultural nuances based on that information. For example, the scenario reflects differences in customer responses in different cultures. The response generation unit also creates a response scenario that addresses language and cultural nuances based on actual customer data and cultural examples. For example, the scenario reflects customer expectations and requests in a specific culture. This makes it possible to provide a scenario that reflects actual customer data and cultural examples.

[0084] The response generation unit can use the emotion estimation function to monitor the emotional state of the customer in real time and dynamically change the response method. The response generation unit, for example, uses the emotion estimation function to monitor the emotional state of the customer in real time. For example, it analyzes the customer's facial expression and tone of voice and calculates an emotion score. The response generation unit also monitors the customer's emotional state in real time and dynamically changes the response method based on the results. For example, if the customer shows anger, it provides a response method that corresponds to that emotion. The response generation unit also monitors the customer's emotional state in real time using the emotion estimation function and dynamically changes the response method based on the results. For example, if the customer shows dissatisfaction, it provides a response method that corresponds to that emotion. This makes it possible to dynamically change the response method according to the customer's emotional state.

[0085] The response generation unit enables the acquisition of global response skills, including scenarios related to customers from different markets and cultural backgrounds. The response generation unit, for example, includes scenarios related to customers from different markets and cultural backgrounds in training on how to respond to language and cultural nuances. For example, differences in customer responses in different markets are reflected in the scenarios. The response generation unit also includes scenarios related to customers from different cultural backgrounds in training on how to respond to language and cultural nuances. For example, customer expectations and requests in different cultures are reflected in the scenarios. The response generation unit also includes scenarios related to customers from different markets and cultural backgrounds in training on how to respond to language and cultural nuances. For example, sales strategies in different markets are reflected in the scenarios. This enables the acquisition of global response skills, including scenarios related to customers from different markets and cultural backgrounds.

[0086] The response generation unit can incorporate a multimedia scenario using audio and video. For example, the response generation unit incorporates audio data into training on how to deal with language and cultural nuances and provides a scenario based on the audio. For example, conversations in different languages ​​are played back audio and the content is reflected in the scenario. The response generation unit also creates a training scenario on how to deal with language and cultural nuances using video data and provides a video-based scenario. For example, a video demonstration of how to deal with customers in different cultures is shown and the content is reflected in the scenario. The response generation unit also incorporates a multimedia scenario using audio and video into training on how to deal with language and cultural nuances. For example, customer expectations and requests in different cultures are explained in a video and the content is reflected in the scenario. In this way, a multimedia scenario using audio and video can be provided.

[0087] The response generation unit can use the emotion estimation function to provide customized feedback based on the emotional state of the customer. The response generation unit, for example, uses the emotion estimation function to analyze the emotional state of the customer and provides customized feedback based on the results. For example, if the customer expresses anger, feedback corresponding to that emotion is provided. The response generation unit also monitors the emotional state of the customer in real time and provides customized feedback based on the results. For example, if the customer expresses dissatisfaction, feedback corresponding to that emotion is provided. The response generation unit also uses the emotion estimation function to analyze the emotional state of the customer and provides customized feedback based on the results. For example, if the customer is feeling stressed, feedback corresponding to that emotion is provided. In this way, customized feedback based on the emotional state of the customer can be provided.

[0088] The feedback generation unit uses the generation AI to perform emotion analysis and dynamically adjust the content of the feedback according to the emotional state. The feedback generation unit, for example, uses the generation AI to provide real-time feedback and analyze the emotional state of the participants. For example, if a participant is feeling stressed, feedback corresponding to that emotion is provided. The feedback generation unit also dynamically adjusts the content of the feedback according to the emotional state based on the results of the emotion analysis. For example, if a participant shows positive emotion, feedback corresponding to that emotion is provided. The feedback generation unit also uses the generation AI to provide real-time feedback and monitor the emotional state of the participants in real time. For example, if a participant is feeling anxious, feedback corresponding to that emotion is provided. This makes it possible to dynamically adjust the content of the feedback according to the emotional state.

[0089] The feedback generation unit can reflect past training data and actual work data. The feedback generation unit, for example, provides real-time feedback based on past training data. For example, feedback on specific training content is provided. The feedback generation unit also analyzes actual work data and provides real-time feedback based on that information. For example, feedback according to the current work situation is provided. The feedback generation unit also provides real-time feedback based on past training data and actual work data. For example, feedback is provided based on performance in a specific work task. This makes it possible to provide feedback that reflects past training data and actual work data.

[0090] The feedback generation unit can use the emotion estimation function to monitor the emotional state of the feedback recipient in real time and maximize the effect of the feedback. The feedback generation unit, for example, uses the emotion estimation function to monitor the emotional state of the feedback recipient in real time. For example, if the recipient is feeling stressed, feedback corresponding to that emotion is provided. The feedback generation unit also monitors the emotional state of the feedback recipient in real time and dynamically adjusts the content of the feedback based on the result. For example, if the recipient shows positive emotion, feedback corresponding to that emotion is provided. The feedback generation unit also uses the emotion estimation function to monitor the emotional state of the feedback recipient in real time and maximize the effect of the feedback based on the result. For example, if the recipient is feeling anxious, feedback corresponding to that emotion is provided. This makes it possible to maximize the effect of the feedback according to the emotional state of the feedback recipient.

[0091] The feedback generation unit enables acquisition of global response skills, including feedback on customers with different languages ​​and cultural backgrounds. The feedback generation unit, for example, includes feedback on customers with different languages ​​and cultural backgrounds in the real-time feedback. For example, it provides feedback on customer responses in different languages. The feedback generation unit also includes feedback on customers with different cultural backgrounds in the real-time feedback. For example, it provides feedback on customer expectations and requirements in different cultures. The feedback generation unit also includes feedback on customers with different languages ​​and cultural backgrounds in the real-time feedback. For example, it provides feedback on customer responses in different markets. This enables acquisition of global response skills, including feedback on customers with different languages ​​and cultural backgrounds.

[0092] The feedback generation unit can incorporate multimedia feedback using audio and video. For example, the feedback generation unit incorporates audio data into real-time feedback and provides audio-based feedback. For example, the feedback generation unit analyzes audio of customer interactions and provides feedback based on the content of the audio. The feedback generation unit also creates real-time feedback using video data and provides video-based feedback. For example, the feedback generation unit analyzes video of customer interactions and provides feedback based on the content of the video. The feedback generation unit also incorporates multimedia feedback using audio and video into real-time feedback. For example, the feedback generation unit provides feedback based on audio and video of customer interactions. This makes it possible to provide multimedia feedback using audio and video.

[0093] The feedback generation unit can use the emotion estimation function to provide customized feedback based on the emotional state of the feedback recipient. For example, the feedback generation unit uses the emotion estimation function to analyze the emotional state of the feedback recipient and provide customized feedback based on the results. For example, if the recipient is feeling stressed, feedback corresponding to that emotion is provided. The feedback generation unit also monitors the emotional state of the feedback recipient in real time and provides customized feedback based on the results. For example, if the recipient shows positive emotion, feedback corresponding to that emotion is provided. The feedback generation unit also uses the emotion estimation function to analyze the emotional state of the feedback recipient and provides customized feedback based on the results. For example, if the recipient is feeling anxious, feedback corresponding to that emotion is provided. In this way, customized feedback based on the emotional state of the feedback recipient can be provided.

[0094] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0095] The role-play training system can further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit, for example, collects and analyzes behavioral data from the user's past training sessions and actual work. For example, it records the user's responses and the results obtained, and identifies behavioral patterns based on that data. The behavior analysis unit can also customize training scenarios based on the user's behavioral data. For example, if the user has difficulty with a particular response, it can provide a scenario specialized for that response. The behavior analysis unit can also provide feedback based on the user's behavioral data. For example, it can specifically point out what was good about the user's past responses and what needs to be improved, and use that information in the next response. This makes it possible to provide more effective training based on the user's behavioral data.

[0096] The role-play training system may further include an emotion customization unit that estimates the user's emotions and customizes the training scenario based on the estimated emotions. The emotion customization unit, for example, analyzes the user's facial expressions and tone of voice to calculate an emotion score. The emotion customization unit also monitors the user's emotional state in real time and dynamically adjusts the training scenario based on the results. For example, if the user is feeling stressed, it provides a scenario that corresponds to that emotion. The emotion customization unit may also provide feedback based on the user's emotional state. For example, if the user shows a positive emotion, it provides feedback that corresponds to that emotion. This makes it possible to provide a customized training scenario based on the user's emotional state.

[0097] The role-play training system may further include a learning style analysis unit that analyzes the user's learning style. The learning style analysis unit, for example, identifies which method of learning is most effective for the user. For example, it may provide a scenario that makes heavy use of videos and images to a user who prefers visual information, and a scenario that makes heavy use of audio to a user who prefers auditory information. The learning style analysis unit may also customize training scenarios based on the user's learning style. For example, if the user prefers practical learning, it may provide a scenario that is closer to actual work. The learning style analysis unit may also provide feedback based on the user's learning style. For example, if the user prefers theoretical explanations, it may provide feedback that includes those explanations. This may allow for more effective training based on the user's learning style.

[0098] The role-play training system may further include an emotion adjustment unit that estimates the user's emotions and adjusts the progress of the training based on the estimated emotions. The emotion adjustment unit, for example, analyzes the user's facial expressions and tone of voice to calculate an emotion score. The emotion adjustment unit also monitors the user's emotional state in real time and dynamically adjusts the progress of the training based on the results. For example, if the user is feeling stressed, the emotion adjustment unit may slow down the progress of the training. The emotion adjustment unit may also adjust the content of the training based on the user's emotional state. For example, if the user expresses positive emotions, the emotion adjustment unit may provide content that corresponds to that emotion. This allows for customized training progress to be provided based on the user's emotional state.

[0099] The role-play training system may further include a data analysis unit that analyzes the user's past training data. The data analysis unit, for example, collects and analyzes the results of the user's past training. For example, it records the responses the user made and the results they obtained, and customizes training scenarios based on that data. The data analysis unit can also provide feedback based on the user's past training data. For example, it can specifically point out what was good about the user's past responses and what areas need improvement, and use this information in the next response. The data analysis unit can also adjust the progress of training based on the user's past training data. For example, if the user feels uncomfortable with a particular response, it can provide a scenario specialized for that response. This allows for more effective training based on the user's past training data.

[0100] The role-play training system may further include an emotion feedback unit that estimates the user's emotion and provides feedback based on the estimated emotion. The emotion feedback unit, for example, analyzes the user's facial expression and tone of voice to calculate an emotion score. The emotion feedback unit also monitors the user's emotional state in real time and provides feedback based on the results. For example, if the user is feeling stressed, feedback corresponding to that emotion is provided. The emotion feedback unit can also adjust the content of the feedback based on the user's emotional state. For example, if the user expresses a positive emotion, feedback corresponding to that emotion is provided. This makes it possible to provide customized feedback based on the user's emotional state.

[0101] The role-play training system may further include a skill analysis unit that analyzes the user's skill level. The skill analysis unit, for example, collects and analyzes the results of training the user has conducted in the past. For example, it identifies what skills the user has and what skills they are lacking. The skill analysis unit can also customize training scenarios based on the user's skill level. For example, if the user is lacking in a particular skill, it can provide a scenario that strengthens that skill. The skill analysis unit can also provide feedback based on the user's skill level. For example, if the user improves a particular skill, it can provide feedback on that skill. This makes it possible to provide more effective training based on the user's skill level.

[0102] The role-play training system may further include an emotional difficulty adjustment unit that estimates the user's emotions and adjusts the difficulty of the training based on the estimated emotions. The emotional difficulty adjustment unit, for example, analyzes the user's facial expressions and tone of voice to calculate an emotional score. The emotional difficulty adjustment unit also monitors the user's emotional state in real time and dynamically adjusts the difficulty of the training based on the results. For example, if the user is feeling stressed, the emotional difficulty adjustment unit can lower the difficulty of the training. The emotional difficulty adjustment unit can also adjust the content of the training based on the user's emotional state. For example, if the user expresses a positive emotion, content corresponding to that emotion is provided. This makes it possible to provide a customized training difficulty based on the user's emotional state.

[0103] The role-play training system may further include a performance analysis unit that analyzes the user's performance. The performance analysis unit, for example, collects and analyzes the results of training that the user has conducted in the past. For example, it identifies how the user performed and what areas need improvement. The performance analysis unit can also customize training scenarios based on the user's performance. For example, if the user is lacking in a particular performance, it provides a scenario that strengthens that performance. The performance analysis unit can also provide feedback based on the user's performance. For example, if the user improves a particular performance, it provides feedback on that performance. This makes it possible to provide more effective training based on the user's performance.

[0104] The role-play training system may further include an emotional content customization unit that estimates the user's emotions and customizes the training content based on the estimated emotions. The emotional content customization unit, for example, analyzes the user's facial expressions and tone of voice to calculate an emotional score. The emotional content customization unit also monitors the user's emotional state in real time and dynamically adjusts the training content based on the results. For example, if the user is feeling stressed, content corresponding to that emotion is provided. The emotional content customization unit can also adjust the training progress based on the user's emotional state. For example, if the user expresses positive emotions, progress corresponding to that emotion is provided. This makes it possible to provide customized training content based on the user's emotional state.

[0105] The processing flow of the second embodiment will be briefly explained below.

[0106] Step 1: The persona generation unit creates a customer persona. For example, the generation AI generates a realistic customer profile based on information such as age, gender, occupation, hobbies, and purchasing history. The generation AI also generates a persona based on prompts that include customer characteristics and behavioral patterns. Step 2: The scenario generation unit generates scenarios for difficult customer interactions. For example, the generation AI generates scenarios for handling complaints and returns. The generation AI also generates scenarios based on prompts that include difficult situations and customer reactions. Step 3: The test generator generates quizzes and questions to test product knowledge. For example, the generator generates questions about the features and usage of a new product, how it differs from competing products, etc. The generator also generates test questions based on prompts containing detailed product information and test content. Step 4: The training generation unit generates training scenarios for the launch of a new product. For example, the generation AI creates training scenarios based on information about the new product's features, sales strategy, target customers, etc. The generation AI also generates scenarios based on prompts containing information about the new product and training content. Step 5: The response generation unit generates scenarios to acquire response skills for customers with different languages ​​and cultural backgrounds. For example, the generation AI simulates conversations in different languages ​​and response methods that take cultural differences into account. The generation AI also generates scenarios based on prompts that include information about language and cultural background. Step 6: The feedback generator provides real-time feedback to the new employee's role-play. For example, the generator can specifically point out what went well in the customer service and what needs improvement, which can be used for the next interaction. The generator also generates feedback based on prompts that include the new employee's response and evaluation criteria.

[0107] 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.

[0108] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0109] 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.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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).

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0124] 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.

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

[0126] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0127] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0128] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0129] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0130] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0131] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0132] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0133] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0134] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0135] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the 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 specific processing unit 290 using these models.

[0136] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0137] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0138] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0139] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0140] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0141] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] In the robot 414, 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 robot 414 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.

[0152] 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.

[0153] 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.

[0154] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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."

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[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 role-play training system that uses generative AI to efficiently teach new employees sales skills, a persona generation unit that creates customer personas; a scenario generation unit that generates a scenario for dealing with difficult customers; a test generator that generates quizzes and questions to test product knowledge; a training generation unit that generates training scenarios for new product launches; a response generation unit that generates scenarios for acquiring response skills for dealing with customers with different languages ​​and cultural backgrounds; A feedback generation unit that provides real-time feedback to the role-playing of new employees. A system characterized by:

2. The persona generation unit The generative AI is used to perform emotion analysis and dynamically update the persona in response to changes in emotion.

2. The system of claim 1.

3. The persona generation unit Reflect not only purchase history but also social media activity and online reviews 2. The system of claim 1.

4. The persona generation unit The emotional state of the persona is monitored in real time and reflected in the training scenario.

2. The system of claim 1.

5. The persona generation unit Use multimodal information, including audio and video data, to create a more realistic customer profile 2. The system of claim 1.

6. The persona generation unit Generate customer personas for different industries and markets for cross-industry training 2. The system of claim 1.

7. The persona generation unit Generate customized training scenarios based on the persona's emotional state 2. The system of claim 1.

Images