System

Abstract

An object of a system according to an embodiment is to perform sufficient training without being subjected to temporal and physical constraints.SOLUTION: In one embodiment, a system includes a role playing implementer, a training customizer, a feedback provider, a record analyzer, and a schedule manager. The role-playing implementer uses the generated AI. The training customizing unit performs training based on the scenario provided by the role playing implementing unit. The feedback providing unit analyzes the result of the training performed by the training customizing unit and provides feedback. The record analysis unit records and analyzes the feedback provided by the feedback providing unit. The schedule management unit manages a training schedule based on the data obtained by the record analysis unit.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 have the problem that training is limited in time and physical strength, making it difficult to train sufficiently.

[0005] The system according to the embodiment aims to provide sufficient training without being restricted by time or physical strength. [Means for solving the problem]

[0006] The system according to the embodiment includes a role-playing implementation unit, a training customization unit, a feedback providing unit, a record analysis unit, and a schedule management unit. The role-playing implementation unit uses a generation AI. The training customization unit conducts training based on a scenario provided by the role-playing implementation unit. The feedback providing unit analyzes the results of the training conducted by the training customization unit and provides feedback. The record analysis unit records and analyzes the feedback provided by the feedback providing unit. The schedule management unit manages the training schedule based on the data obtained by the record analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment allows sufficient training without being restricted by time or physical strength. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The training system according to an embodiment of the present invention utilizes generative AI to streamline training for customer service contests aimed at improving the sales skills of shop crews, allowing the shop crews to train to their heart's content.

[0029] A training system according to an embodiment includes a role-playing implementation unit, a training customization unit, a feedback provision unit, a record analysis unit, and a schedule management unit. The role-playing implementation unit uses a generation AI to act as the partner in a customer service role-play conducted by a shop crew member. For example, the generation AI provides various scenarios for the customer role, and the shop crew member serves customers based on the scenarios. The generation AI generates responses for the customer role using a text generation AI such as GPT-3 or BERT. The training customization unit conducts training based on the scenarios provided by the role-playing implementation unit. For example, the generation AI customizes the training content according to the skill level of the shop crew member and the purpose of the training. For beginners, the training content may include practice on basic customer service skills, while for advanced employees, the training content may include practice on advanced complaint handling and closing techniques. The feedback provision unit analyzes the results of the training conducted by the training customization unit and provides feedback. For example, the generation AI analyzes audio and text data during training to evaluate the flow of customer service, the use of language, and the appropriateness of responses to customer requests, and points out areas for improvement. The record analysis unit records and analyzes the feedback provided by the feedback provision unit. For example, the generation AI can save records of training conducted by shop crew members and analyze them later. The schedule management unit manages training schedules based on the data obtained by the record analysis unit. For example, the generation AI can suggest optimal training times based on the shop crew members' schedules, supporting efficient schedule management. As a result, the training system according to the embodiment can efficiently support the improvement of the sales skills of shop crew members.

[0030] The role-playing implementation unit can provide scenarios tailored to specific customer demographics. For example, the generation AI could play the role of an elderly customer, incorporating age-specific needs and questions into the scenario so that the shop staff can practice their skills in dealing with the elderly. For example, questions about health products and ease of use could be included. Alternatively, the generation AI could play the role of a young customer, providing a scenario based on the latest trends and topics on social media so that the shop staff can improve their customer service skills for young people. For example, questions about popular fashion items and new technologies could be included. Alternatively, the generation AI could play the role of a foreign tourist, providing a scenario based on different cultures and languages ​​so that the shop staff can practice their multicultural skills. For example, questions about tourist destinations and local customs could be included. This allows the shop staff to improve their skills in dealing with a variety of customers.

[0031] The training customization unit can analyze the shop crew's past training data, identify individual weaknesses, and provide focused training. In the training customization unit, for example, the generation AI analyzes the shop crew's past training data and identifies areas where specific skills are lacking. For example, if closing techniques are weak, training will be focused on that area. The generation AI can also identify individual weaknesses based on the shop crew's past training data and propose a customized training plan. For example, if a shop crew is not good at handling complaints, that area will be strengthened. The generation AI can also analyze the shop crew's past training data and identify areas where specific skills have not improved. For example, if product knowledge is lacking, training will be focused on that area. In this way, skills can be improved by identifying individual weaknesses and providing focused training.

[0032] The training customization unit can customize the training content according to the learning style of the shop crew. For example, the generation AI in the training customization unit analyzes the learning style of the shop crew and provides visual learning materials to crew members who prefer visual learning. For example, training using videos and diagrams is carried out. The generation AI also analyzes the learning style of the shop crew and provides audio learning materials to crew members who prefer auditory learning. For example, training in the form of audio guides or podcasts is carried out. The generation AI also analyzes the learning style of the shop crew and provides practical scenarios to crew members who prefer experiential learning. For example, training using role-playing or simulations is carried out. This makes it possible to provide training according to the learning style of the shop crew.

[0033] The feedback providing unit can analyze the audio data and specifically point out areas for improvement in pronunciation or intonation. For example, the feedback providing unit analyzes the audio data during training by the generation AI to identify pronunciation errors or unnatural intonation. For example, if the pronunciation of a particular word is unclear, the feedback providing unit points out areas for improvement. The generation AI also specifically points out areas for improvement in intonation based on the audio data. For example, it points out areas where the intonation should rise when asking a question, and encourages practice of appropriate intonation. The generation AI also analyzes the audio data and provides feedback on areas for improvement in pronunciation or intonation. For example, if the pronunciation of a particular phrase is unnatural, the feedback providing unit instructs the shop crew to practice that part repeatedly. In this way, by specifically pointing out areas for improvement in pronunciation and intonation, the communication skills of the shop crew can be improved.

[0034] The feedback providing unit can analyze non-verbal communication and provide feedback on areas for improvement in gestures or facial expressions. For example, the feedback providing unit analyzes video data during training by the generation AI and specifically points out areas for improvement in gestures and facial expressions. For example, if hand movements are unnatural, the feedback providing unit points out areas for improvement. The generation AI also specifically points out areas for improvement in facial expressions based on non-verbal communication data. For example, if there are not enough smiles, the feedback providing unit instructs the employee to smile more. The generation AI also analyzes non-verbal communication during training and provides feedback on areas for improvement in gestures and facial expressions. For example, if there is a lack of eye contact, the feedback providing unit instructs the employee to strengthen that area. In this way, by providing feedback on areas for improvement in non-verbal communication, the customer service skills of the shop crew can be improved.

[0035] The record analysis unit can store audio data and text data from training over a long period of time and analyze skill improvement over time. For example, the generation AI stores audio data from training over a long period of time and analyzes improvement in pronunciation and intonation over time. For example, it compares past data with current data to identify areas for improvement. The generation AI also stores text data from training and analyzes skill improvement over time. For example, it compares past training content with current training content to understand progress. The generation AI also stores training data over a long period of time and displays skill improvement over time in a graph. For example, it shows the improvement of each skill in a line graph. This makes it possible to understand the growth of shop crew members by analyzing skill improvement based on long-term data.

[0036] The record analysis unit can identify skill improvement patterns for individual shop crew members based on training records and propose optimal training plans. In the record analysis unit, for example, the generation AI identifies skill improvement patterns for individual shop crew members based on training records. For example, it analyzes the period until a specific skill improves and proposes an optimal training plan. The generation AI also analyzes training records and identifies skill improvement trends for individual shop crew members. For example, it analyzes whether a specific training method is effective and proposes an optimal plan. The generation AI also identifies skill improvement patterns for individual shop crew members based on training records and proposes a customized training plan. For example, it proposes the training content necessary to improve a specific skill. In this way, effective skill improvement can be achieved by identifying individual skill improvement patterns and proposing an optimal training plan.

[0037] The schedule management unit can suggest optimal training times based on the shop crew's schedules and support efficient schedule management. In the schedule management unit, for example, the generation AI analyzes the shop crew's work schedules and suggests optimal training times. For example, training can be conducted during breaks between shifts or break times. The generation AI also sets training priorities based on the shop crew's schedules and supports efficient schedule management. For example, important training can be prioritized in the schedule. The generation AI also analyzes the shop crew's schedules and suggests the optimal timing for training. For example, training can be conducted during times when there is less work. This makes it possible to suggest optimal training times based on the shop crew's schedules and support efficient schedule management.

[0038] The schedule management unit can monitor the training progress in real time and adjust the schedule as necessary. For example, the generation AI monitors the training progress in real time and adjusts the schedule as necessary. For example, it reschedules the schedule if the training is behind schedule. The generation AI also analyzes the training progress data and issues an alert if the schedule needs to be adjusted. For example, it notifies the user if a specific skill is not improving as planned. The generation AI also grasps the training progress in real time and automatically adjusts the schedule. For example, it sets the timing of the next training session according to the training progress. This makes it possible to monitor the training progress in real time and adjust the schedule as necessary, thereby achieving efficient training.

[0039] The schedule management unit supports training at different time periods and locations, allowing shop crew members to train flexibly. The schedule management unit, for example, allows the generation AI to support training at different time periods, allowing shop crew members to train according to their own convenience. For example, it provides training in the early morning or late night. The generation AI also supports training at different locations, allowing shop crew members to train anywhere. For example, it provides training at home or in a cafe. The generation AI also supports training regardless of time period or location, allowing shop crew members to train flexibly. For example, it provides online training. In this way, it is possible to support training at different time periods and locations, allowing shop crew members to train flexibly.

[0040] The schedule management unit can integrate training schedules with other work schedules to improve overall work efficiency. In the schedule management unit, for example, the generation AI integrates training schedules with other work schedules to improve overall work efficiency. For example, by incorporating training between work. The generation AI also analyzes work schedules and suggests the optimal timing for training. For example, training could be conducted during times when there is less work. The generation AI also integrates training and work schedules to support efficient schedule management. For example, training could be conducted outside of peak work hours. In this way, by integrating the training schedule with other work schedules, overall work efficiency can be improved.

[0041] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0042] The training system can also be equipped with a virtual reality (VR) unit. The VR unit allows shop crew members to train in a virtual space that closely resembles the actual store environment. For example, the VR unit can recreate the store's layout and product placement, simulating the crew's movements and customer service in an actual store. The VR unit can also provide scenarios tailored to different store environments and customer demographics, allowing crew members to practice skills for responding to a variety of situations. Furthermore, the VR unit can provide a relaxation mode to reduce the stress and tension that crew members feel during training. This allows for more realistic and effective training.

[0043] The training system can further include a gamification section. The gamification section incorporates game elements into the training to increase crew motivation. For example, crew members can earn points each time they complete a training task and compete with other crew members in a ranking format. They can also earn badges and titles each time they master a specific skill. Furthermore, the gamification section can provide missions and challenges that allow crew members to feel a sense of accomplishment during training. This increases crew members' motivation to participate in training and enables effective skill improvement.

[0044] The training system may further include a social interaction section. The social interaction section provides a function for promoting communication and cooperation among crew members. For example, crew members may chat or video call with other crew members in real time during training. The social interaction section may also provide a platform for crew members to share their training progress and results and provide feedback to each other. Furthermore, the social interaction section may provide scenarios and missions for crew members to train together as a team. This may deepen bonds among crew members and improve teamwork.

[0045] The training system can further include a voice recognition unit. The voice recognition unit analyzes the crew's speech in real time and provides appropriate feedback. For example, when the crew performs role-playing of customer service, the voice recognition unit analyzes the speech and points out appropriate wording and expressions. The voice recognition unit can also analyze the crew's speaking speed and tone of voice and provide feedback on areas for improvement. Furthermore, the voice recognition unit can convert the crew's speech into text so that it can be reviewed later. This makes it possible to provide specific feedback to improve the crew's communication skills.

[0046] The training system can further include an automatic translation unit. The automatic translation unit supports training of crew members to deal with customers who speak different languages. For example, when a crew member practices customer service in a foreign language, the automatic translation unit provides real-time translations and teaches appropriate expressions. The automatic translation unit can also provide translated scenarios when the crew member performs training scenarios in different languages. Furthermore, the automatic translation unit can provide feedback on areas for improvement in pronunciation and grammar when the crew member is training in a foreign language. This makes it possible to provide specific training to improve the crew member's multilingual skills.

[0047] The training system can further include a data visualization section. The data visualization section visually displays the crew's training data, allowing them to understand their progress and areas for improvement at a glance. For example, training results can be displayed in graphs and charts, allowing crew members to check their own growth. The data visualization section can also visually show the crew's skill improvement trends and clarify which areas are being strengthened. Furthermore, the data visualization section can provide a function that allows crew members to compare their training progress with other crew members. This allows crew members to visually understand their training results and increase their motivation.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The role-playing implementation unit uses the generation AI to act as the partner in a customer service role-play conducted by the shop staff. For example, the generation AI provides various scenarios for the customer role, and the shop staff acts as the customer based on those scenarios. The generation AI uses text generation AI such as GPT-3 or BERT to generate responses for the customer role. Step 2: The training customization department conducts training based on scenarios provided by the role-playing implementation department. For example, the generation AI customizes the training content according to the skill level of the shop crew and the training objectives. For beginners, the AI ​​provides practice in basic customer service skills, while for advanced staff, it provides practice in advanced complaint handling and closing techniques. Step 3: The feedback provision unit analyzes the results of the training conducted by the training customization unit and provides feedback. For example, the generation AI analyzes the audio and text data during training, evaluates the flow of customer service, the use of language, and the appropriateness of responding to customer requests, and points out areas for improvement. Step 4: The recording and analysis unit records and analyzes the feedback provided by the feedback providing unit. For example, the generation AI can save a record of the training conducted by the shop crew and analyze it later. Step 5: The schedule management unit manages the training schedule based on the data obtained by the record analysis unit. For example, the generative AI can suggest optimal training times based on the shop crew schedule, supporting efficient schedule management.

[0050] (Example 2) The training system according to an embodiment of the present invention utilizes generative AI to streamline training for customer service contests aimed at improving the sales skills of shop crews, allowing the shop crews to train to their heart's content.

[0051] A training system according to an embodiment includes a role-playing implementation unit, a training customization unit, a feedback provision unit, a record analysis unit, and a schedule management unit. The role-playing implementation unit uses a generation AI to act as the partner in a customer service role-play conducted by a shop crew member. For example, the generation AI provides various scenarios for the customer role, and the shop crew member serves customers based on the scenarios. The generation AI generates responses for the customer role using a text generation AI such as GPT-3 or BERT. The training customization unit conducts training based on the scenarios provided by the role-playing implementation unit. For example, the generation AI customizes the training content according to the skill level of the shop crew member and the purpose of the training. For beginners, the training content may include practice on basic customer service skills, while for advanced employees, the training content may include practice on advanced complaint handling and closing techniques. The feedback provision unit analyzes the results of the training conducted by the training customization unit and provides feedback. For example, the generation AI analyzes audio and text data during training to evaluate the flow of customer service, the use of language, and the appropriateness of responses to customer requests, and points out areas for improvement. The record analysis unit records and analyzes the feedback provided by the feedback provision unit. For example, the generation AI can save records of training conducted by shop crew members and analyze them later. The schedule management unit manages training schedules based on the data obtained by the record analysis unit. For example, the generation AI can suggest optimal training times based on the shop crew members' schedules, supporting efficient schedule management. As a result, the training system according to the embodiment can efficiently support the improvement of the sales skills of shop crew members.

[0052] The role-playing implementation unit can provide scenarios tailored to specific customer demographics. For example, the generation AI could play the role of an elderly customer, incorporating age-specific needs and questions into the scenario so that the shop staff can practice their skills in dealing with the elderly. For example, questions about health products and ease of use could be included. Alternatively, the generation AI could play the role of a young customer, providing a scenario based on the latest trends and topics on social media so that the shop staff can improve their customer service skills for young people. For example, questions about popular fashion items and new technologies could be included. Alternatively, the generation AI could play the role of a foreign tourist, providing a scenario based on different cultures and languages ​​so that the shop staff can practice their multicultural skills. For example, questions about tourist destinations and local customs could be included. This allows the shop staff to improve their skills in dealing with a variety of customers.

[0053] The role-playing implementation unit can change a customer's emotions or attitude in real time. For example, the role-playing implementation unit provides scenarios in which the generation AI plays the role of a customer and changes emotions over the course of a conversation. For example, a scenario is set in which a customer who is initially calm suddenly becomes angry, and the shop staff practices responding to that change. The generation AI also provides scenarios in which the generation AI plays the role of a customer and changes attitude. For example, a scenario is set in which a customer who is initially indifferent gradually becomes interested, and the shop staff practices responding to that change. The generation AI also provides scenarios in which the generation AI plays the role of a customer and reflects changes in emotions in real time. For example, a scenario is set in which a customer expresses joy or surprise after hearing an explanation of a product, and the shop staff practices responding to that reaction. This allows the user to experience more realistic customer service scenarios.

[0054] The role-playing implementation unit can use the emotion estimation function to show the emotional reaction of the customer to the shop crew's response. In the role-playing implementation unit, for example, the generation AI plays the customer and shows the emotional reaction to the shop crew's response in real time. For example, it expresses joy or dissatisfaction in response to the shop crew's explanation, and the shop crew adjusts its response based on that reaction. In addition, using the emotion estimation function, the generation AI plays the customer and provides emotional feedback to the shop crew's response. For example, it shows a smile if the shop crew's response is appropriate and shows confusion if it is inappropriate. In addition, the generation AI plays the customer and incorporates the emotional reaction to the shop crew's response into the scenario, allowing the shop crew to practice adjusting their response based on that reaction. For example, it reflects in real time whether the customer is interested in the product explanation. This allows practice adjusting their response based on their emotional reaction.

[0055] The training customization unit can analyze the shop crew's past training data, identify individual weaknesses, and provide focused training. In the training customization unit, for example, the generation AI analyzes the shop crew's past training data and identifies areas where specific skills are lacking. For example, if closing techniques are weak, training will be focused on that area. The generation AI can also identify individual weaknesses based on the shop crew's past training data and propose a customized training plan. For example, if a shop crew is not good at handling complaints, that area will be strengthened. The generation AI can also analyze the shop crew's past training data and identify areas where specific skills have not improved. For example, if product knowledge is lacking, training will be focused on that area. In this way, skills can be improved by identifying individual weaknesses and providing focused training.

[0056] The training customization unit can customize the training content according to the learning style of the shop crew. For example, the generation AI in the training customization unit analyzes the learning style of the shop crew and provides visual learning materials to crew members who prefer visual learning. For example, training using videos and diagrams is carried out. The generation AI also analyzes the learning style of the shop crew and provides audio learning materials to crew members who prefer auditory learning. For example, training in the form of audio guides or podcasts is carried out. The generation AI also analyzes the learning style of the shop crew and provides practical scenarios to crew members who prefer experiential learning. For example, training using role-playing or simulations is carried out. This makes it possible to provide training according to the learning style of the shop crew.

[0057] The training customization unit can use the emotion estimation function to grasp the emotional state of the shop crew and suggest training content to reduce stress. For example, the training customization unit uses the emotion estimation function to have the generation AI grasp the emotional state of the shop crew in real time and suggest training content to reduce stress. For example, training including breathing techniques and stretching for relaxation is performed. The generation AI also analyzes the emotional state of the shop crew and suggests training content to help them relax if they are under high stress. For example, training is provided while listening to relaxation music. The generation AI also uses the emotion estimation function to grasp the emotional state of the shop crew and customize training content to reduce stress. For example, training including mindfulness and meditation for stress relief is performed. This reduces the stress of the shop crew and enables effective training.

[0058] The feedback providing unit can analyze the audio data and specifically point out areas for improvement in pronunciation or intonation. For example, the feedback providing unit analyzes the audio data during training by the generation AI to identify pronunciation errors or unnatural intonation. For example, if the pronunciation of a particular word is unclear, the feedback providing unit points out areas for improvement. The generation AI also specifically points out areas for improvement in intonation based on the audio data. For example, it points out areas where the intonation should rise when asking a question, and encourages practice of appropriate intonation. The generation AI also analyzes the audio data and provides feedback on areas for improvement in pronunciation or intonation. For example, if the pronunciation of a particular phrase is unnatural, the feedback providing unit instructs the shop crew to practice that part repeatedly. In this way, by specifically pointing out areas for improvement in pronunciation and intonation, the communication skills of the shop crew can be improved.

[0059] The feedback providing unit can analyze non-verbal communication and provide feedback on areas for improvement in gestures or facial expressions. For example, the feedback providing unit analyzes video data during training by the generation AI and specifically points out areas for improvement in gestures and facial expressions. For example, if hand movements are unnatural, the feedback providing unit points out areas for improvement. The generation AI also specifically points out areas for improvement in facial expressions based on non-verbal communication data. For example, if there are not enough smiles, the feedback providing unit instructs the employee to smile more. The generation AI also analyzes non-verbal communication during training and provides feedback on areas for improvement in gestures and facial expressions. For example, if there is a lack of eye contact, the feedback providing unit instructs the employee to strengthen that area. In this way, by providing feedback on areas for improvement in non-verbal communication, the customer service skills of the shop crew can be improved.

[0060] The feedback providing unit can use the emotion estimation function to analyze the emotional reactions of the shop crew and point out areas for improvement in their emotional response. For example, the feedback providing unit uses the emotion estimation function to have the generation AI analyze the emotional reactions of the shop crew in real time and point out areas for improvement in their emotional response. For example, if the shop crew does not respond calmly to a customer's dissatisfaction, the generation AI points out areas for improvement. The generation AI also analyzes the emotional reactions of the shop crew and specifically points out areas for improvement in their emotional response. For example, if the reaction to a customer's joy is weak, the generation AI instructs the shop crew to express joy more actively. The generation AI also uses the emotion estimation function to analyze the emotional reactions of the shop crew and provides feedback on areas for improvement in their emotional response. For example, if the response to a customer's anger is inappropriate, the generation AI instructs the shop crew to strengthen that aspect. In this way, by pointing out areas for improvement in their emotional response, the emotional response skills of the shop crew can be improved.

[0061] The record analysis unit can store audio data and text data from training over a long period of time and analyze skill improvement over time. For example, the generation AI stores audio data from training over a long period of time and analyzes improvement in pronunciation and intonation over time. For example, it compares past data with current data to identify areas for improvement. The generation AI also stores text data from training and analyzes skill improvement over time. For example, it compares past training content with current training content to understand progress. The generation AI also stores training data over a long period of time and displays skill improvement over time in a graph. For example, it shows the improvement of each skill in a line graph. This makes it possible to understand the growth of shop crew members by analyzing skill improvement based on long-term data.

[0062] The record analysis unit can identify skill improvement patterns for individual shop crew members based on training records and propose optimal training plans. In the record analysis unit, for example, the generation AI identifies skill improvement patterns for individual shop crew members based on training records. For example, it analyzes the period until a specific skill improves and proposes an optimal training plan. The generation AI also analyzes training records and identifies skill improvement trends for individual shop crew members. For example, it analyzes whether a specific training method is effective and proposes an optimal plan. The generation AI also identifies skill improvement patterns for individual shop crew members based on training records and proposes a customized training plan. For example, it proposes the training content necessary to improve a specific skill. In this way, effective skill improvement can be achieved by identifying individual skill improvement patterns and proposing an optimal training plan.

[0063] The record analysis unit can use the emotion estimation function to record changes in the shop crew's emotions and analyze their emotional growth. For example, the record analysis unit uses the emotion estimation function to have the generation AI record the shop crew's emotional changes in real time and analyze their emotional growth. For example, the emotional state at the start and end of training is compared. The generation AI also records the shop crew's emotional changes and displays their emotional growth in a graph. For example, a line graph shows the progress of the emotion score during the training period. The generation AI also uses the emotion estimation function to record the shop crew's emotional changes and provide feedback on their emotional growth. For example, an increase in positive emotions can be highlighted. In this way, by recording emotional changes and analyzing their emotional growth, the shop crew's emotional response skills can be improved.

[0064] The schedule management unit can suggest optimal training times based on the shop crew's schedules and support efficient schedule management. In the schedule management unit, for example, the generation AI analyzes the shop crew's work schedules and suggests optimal training times. For example, training can be conducted during breaks between shifts or break times. The generation AI also sets training priorities based on the shop crew's schedules and supports efficient schedule management. For example, important training can be prioritized in the schedule. The generation AI also analyzes the shop crew's schedules and suggests the optimal timing for training. For example, training can be conducted during times when there is less work. This makes it possible to suggest optimal training times based on the shop crew's schedules and support efficient schedule management.

[0065] The schedule management unit can monitor the training progress in real time and adjust the schedule as necessary. For example, the generation AI monitors the training progress in real time and adjusts the schedule as necessary. For example, it reschedules the schedule if the training is behind schedule. The generation AI also analyzes the training progress data and issues an alert if the schedule needs to be adjusted. For example, it notifies the user if a specific skill is not improving as planned. The generation AI also grasps the training progress in real time and automatically adjusts the schedule. For example, it sets the timing of the next training session according to the training progress. This makes it possible to monitor the training progress in real time and adjust the schedule as necessary, thereby achieving efficient training.

[0066] The schedule management unit can use the emotion estimation function to consider the emotional state of the shop crew and propose a schedule to reduce stress. For example, the schedule management unit uses the emotion estimation function to have the generation AI grasp the emotional state of the shop crew in real time and propose a schedule to reduce stress. For example, if stress is high, the generation AI may suggest taking more breaks. The generation AI may also analyze the emotional state of the shop crew and adjust the schedule so that training occurs during times when stress is low. For example, training may occur during times when the shop crew is relaxed. The generation AI may also use the emotion estimation function to consider the emotional state of the shop crew and customize a schedule to reduce stress. For example, activities for relieving stress may be incorporated into the schedule. In this way, effective training can be achieved by considering the emotional state of the shop crew and proposing a schedule to reduce stress.

[0067] The schedule management unit supports training at different time periods and locations, allowing shop crew members to train flexibly. The schedule management unit, for example, allows the generation AI to support training at different time periods, allowing shop crew members to train according to their own convenience. For example, it provides training in the early morning or late night. The generation AI also supports training at different locations, allowing shop crew members to train anywhere. For example, it provides training at home or in a cafe. The generation AI also supports training regardless of time period or location, allowing shop crew members to train flexibly. For example, it provides online training. In this way, it is possible to support training at different time periods and locations, allowing shop crew members to train flexibly.

[0068] The schedule management unit can integrate training schedules with other work schedules to improve overall work efficiency. In the schedule management unit, for example, the generation AI integrates training schedules with other work schedules to improve overall work efficiency. For example, by incorporating training between work. The generation AI also analyzes work schedules and suggests the optimal timing for training. For example, training could be conducted during times when there is less work. The generation AI also integrates training and work schedules to support efficient schedule management. For example, training could be conducted outside of peak work hours. In this way, by integrating the training schedule with other work schedules, overall work efficiency can be improved.

[0069] The schedule management unit uses the emotion estimation function to adjust the timing of training based on the emotions of the shop crew, thereby deriving optimal training effects. For example, the schedule management unit uses the emotion estimation function to have the generation AI grasp the emotional state of the shop crew in real time and adjust the timing of training. For example, training is conducted when emotions are stable. The generation AI also analyzes the emotional state of the shop crew and suggests the optimal training timing. For example, training is conducted when positive emotions are strong. The generation AI also uses the emotion estimation function to customize the timing of training based on the emotions of the shop crew. For example, training is conducted during times when stress is low. In this way, by adjusting the timing of training based on the emotions of the shop crew, optimal training effects can be derive.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The training system can also be equipped with a virtual reality (VR) unit. The VR unit allows shop crew members to train in a virtual space that closely resembles the actual store environment. For example, the VR unit can recreate the store's layout and product placement, simulating the crew's movements and customer service in an actual store. The VR unit can also provide scenarios tailored to different store environments and customer demographics, allowing crew members to practice skills for responding to a variety of situations. Furthermore, the VR unit can provide a relaxation mode to reduce the stress and tension that crew members feel during training. This allows for more realistic and effective training.

[0072] The training system can further include a gamification section. The gamification section incorporates game elements into the training to increase crew motivation. For example, crew members can earn points each time they complete a training task and compete with other crew members in a ranking format. They can also earn badges and titles each time they master a specific skill. Furthermore, the gamification section can provide missions and challenges that allow crew members to feel a sense of accomplishment during training. This increases crew members' motivation to participate in training and enables effective skill improvement.

[0073] The training system can also be equipped with a biometrics unit. The biometrics unit monitors the crew's biological information in real time and provides data to maximize the effectiveness of training. For example, it measures heart rate and electrodermal activity to understand the crew's stress level and concentration. The biometrics unit can also adjust the training content based on the crew's biological information. For example, if stress levels are high, it can suggest relaxation training. Furthermore, the biometrics unit can monitor the crew's health status and issue alerts to prevent excessive stress and fatigue. This makes it possible to achieve effective training while maintaining the crew's health.

[0074] The training system may further include a social interaction section. The social interaction section provides a function for promoting communication and cooperation among crew members. For example, crew members may chat or video call with other crew members in real time during training. The social interaction section may also provide a platform for crew members to share their training progress and results and provide feedback to each other. Furthermore, the social interaction section may provide scenarios and missions for crew members to train together as a team. This may deepen bonds among crew members and improve teamwork.

[0075] The training system can also use the emotion estimation function to adjust the difficulty of the training based on the crew's emotional state. For example, if the crew is feeling stressed, the difficulty of the training can be lowered to make it more relaxing. Alternatively, if the crew is feeling confident, the difficulty can be increased to make it more challenging. Furthermore, the emotion estimation function can also be used to provide feedback according to the crew's emotional state. For example, if the crew is feeling anxious, an encouraging message can be displayed. This enables flexible training according to the crew's emotional state, resulting in effective skill improvement.

[0076] The training system can further include a voice recognition unit. The voice recognition unit analyzes the crew's speech in real time and provides appropriate feedback. For example, when the crew performs role-playing of customer service, the voice recognition unit analyzes the speech and points out appropriate wording and expressions. The voice recognition unit can also analyze the crew's speaking speed and tone of voice and provide feedback on areas for improvement. Furthermore, the voice recognition unit can convert the crew's speech into text so that it can be reviewed later. This makes it possible to provide specific feedback to improve the crew's communication skills.

[0077] The training system can also use the emotion estimation function to adjust the training pace based on the crew's emotional state. For example, if the crew is nervous, the training pace can be slowed down to allow them to relax. Alternatively, if the crew is concentrating, the pace can be increased to allow for more efficient training. Furthermore, the emotion estimation function can also be used to suggest break times based on the crew's emotional state. For example, if the crew is tired, the system can suggest that they take a break at an appropriate time. This enables flexible training based on the crew's emotional state, resulting in effective skill improvement.

[0078] The training system can further include an automatic translation unit. The automatic translation unit supports training of crew members to deal with customers who speak different languages. For example, when a crew member practices customer service in a foreign language, the automatic translation unit provides real-time translations and teaches appropriate expressions. The automatic translation unit can also provide translated scenarios when the crew member performs training scenarios in different languages. Furthermore, the automatic translation unit can provide feedback on areas for improvement in pronunciation and grammar when the crew member is training in a foreign language. This makes it possible to provide specific training to improve the crew member's multilingual skills.

[0079] The training system can also use the emotion estimation function to personalize the training content based on the crew's emotional state. For example, if the crew is tired, it can provide them with relaxing training content. On the other hand, if the crew is feeling motivated, it can provide them with challenging training content. Furthermore, the emotion estimation function can also be used to provide feedback according to the crew's emotional state. For example, if the crew is feeling anxious, it can display an encouraging message. This enables flexible training according to the crew's emotional state, resulting in effective skill improvement.

[0080] The training system can further include a data visualization section. The data visualization section visually displays the crew's training data, allowing them to understand their progress and areas for improvement at a glance. For example, training results can be displayed in graphs and charts, allowing crew members to check their own growth. The data visualization section can also visually show the crew's skill improvement trends and clarify which areas are being strengthened. Furthermore, the data visualization section can provide a function that allows crew members to compare their training progress with other crew members. This allows crew members to visually understand their training results and increase their motivation.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The role-playing implementation unit uses the generation AI to act as the partner in a customer service role-play conducted by the shop staff. For example, the generation AI provides various scenarios for the customer role, and the shop staff acts as the customer based on those scenarios. The generation AI uses text generation AI such as GPT-3 or BERT to generate responses for the customer role. Step 2: The training customization department conducts training based on scenarios provided by the role-playing implementation department. For example, the generation AI customizes the training content according to the skill level of the shop crew and the training objectives. For beginners, the AI ​​provides practice in basic customer service skills, while for advanced staff, it provides practice in advanced complaint handling and closing techniques. Step 3: The feedback provision unit analyzes the results of the training conducted by the training customization unit and provides feedback. For example, the generation AI analyzes the audio and text data during training, evaluates the flow of customer service, the use of language, and the appropriateness of responding to customer requests, and points out areas for improvement. Step 4: The recording and analysis unit records and analyzes the feedback provided by the feedback providing unit. For example, the generation AI can save a record of the training conducted by the shop crew and analyze it later. Step 5: The schedule management unit manages the training schedule based on the data obtained by the record analysis unit. For example, the generative AI can suggest optimal training times based on the shop crew schedule, supporting efficient schedule management.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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).

[0092] 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.

[0093] 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.

[0094] 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.

[0095] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0096] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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).

[0107] 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.

[0108] 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.

[0109] 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.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0111] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0127] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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."

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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, in order to avoid confusion and to 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.

[0149] 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]

[0150] 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-playing implementation department using generative AI, a training customization unit that performs training based on a scenario provided by the role-playing implementation unit; a feedback providing unit that analyzes the results of the training performed by the training customization unit and provides feedback; a recording and analyzing unit that records and analyzes the feedback provided by the feedback providing unit; a schedule management unit that manages a training schedule based on the data obtained by the record analysis unit. A system characterized by:

2. The role-playing implementation unit: Change customer sentiment or attitude in real time 2. The system of claim 1.

3. The training customization unit: Analyzing past training data of shop crew members to identify individual weaknesses and provide focused training 2. The system of claim 1.

4. The feedback providing unit: Analyzes audio data and provides specific suggestions for improving pronunciation or intonation 2. The system of claim 1.

5. The record analysis unit The audio and text data from the training will be saved for a long period of time, and the skill improvement will be analyzed over time.

2. The system of claim 1.

6. The schedule management unit To propose optimal training times based on the shop crew's schedules and support efficient schedule management 2. The system of claim 1.

7. The training customization unit: To understand the emotional state of shop crews and propose training content to reduce stress 2. The system of claim 1.

8. The schedule management unit Consider the emotional state of the shop crew and propose the schedule to reduce stress.

2. The system of claim 1.

Images