system

Abstract

The system according to this embodiment aims to efficiently improve customer service skills by utilizing AI. [Solution] The system according to the embodiment comprises a collection unit, a learning unit, a role-playing unit, and a feedback unit. The collection unit collects customer service data. The learning unit allows the AI ​​to learn based on the data collected by the collection unit. The role-playing unit performs role-playing using the AI ​​professional crew learned by the learning unit. The feedback unit provides feedback on the evaluation results of the role-playing performed by the role-playing unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the improvement of customer service skills for new employees and new products has not been efficiently carried out, and there is room for improvement.

[0005] The system according to the embodiment aims to efficiently improve customer service skills by utilizing AI.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, a learning unit, a role-playing unit, and a feedback unit. The data collection unit collects customer service data. The learning unit allows the AI ​​to learn based on the data collected by the data collection unit. The role-playing unit performs role-playing using the AI ​​professional crew that has been trained by the learning unit. The feedback unit provides feedback on the evaluation results of the role-playing performed by the role-playing unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently improve customer service skills by utilizing AI. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example of form 1) The training system according to an embodiment of the present invention is a system that uses AI to create role-playing partners and conduct training in order to address the lack of skills among new employees and the lack of customer service skills when new products are introduced. This training system collects customer service data from highly productive and highly skilled crew members and uses it to train the AI. Shop crew members perform role-playing using the trained AI professional crew, and the AI ​​evaluates their smiles, tone of voice, smoothness of responses, clarity of explanations, and persuasive talk with customers. The evaluation results are provided as feedback and scored. This allows new crew members to objectively understand their own skills and clearly identify areas for improvement. For example, the training system collects customer service data from highly productive and highly skilled crew members. The collected data is converted into a format that is easy for the AI ​​to analyze. Next, the training system uses the AI ​​to learn based on the collected data. The AI ​​learns using algorithms such as neural networks and support vector machines. The trained AI professional crew is used as a role-playing partner. For example, when shop crew members perform role-playing, the training system has the AI ​​professional crew respond in real time and evaluate their customer service skills. The evaluation criteria include factors such as smiles, tone of voice, smoothness of responses, clarity of explanations, and persuasive sales techniques. The evaluation results are provided as feedback and scored. For example, the training system visually displays the evaluation results as graphs and charts, allowing users to understand them intuitively. The training system can also suggest specific areas for improvement based on the evaluation results. This allows new crew members to objectively understand their own skills and clearly identify areas for improvement. Furthermore, the training system has a function to anonymize personal information during data collection, enhancing privacy protection. For example, the training system anonymizes personal information using technologies such as data masking and pseudo-anonymization. As a result, the training system is expected to effectively address the lack of customer service skills among new crew members and new products, and improve the overall quality of customer service in the shop.This allows the training system to effectively address the lack of customer service skills among new crew members and those handling new products, thereby improving the overall quality of customer service in the shop.

[0029] The training system according to the embodiment comprises a collection unit, a learning unit, a role-playing unit, and a feedback unit. The collection unit collects customer service data. Customer service data includes, but is not limited to, audio data, video data, and text data. The collection unit collects, for example, customer service data from highly productive or highly skilled crew members. The collected data is converted into a format that is easy for the AI ​​to analyze. The learning unit allows the AI ​​to learn based on the data collected by the collection unit. Learning is performed using, for example, algorithms such as neural networks and support vector machines, but is not limited to, such examples. For example, the learning unit allows the AI ​​to learn using methods such as supervised learning, unsupervised learning, and reinforcement learning. The role-playing unit performs role-playing using the AI ​​professional crew trained by the learning unit. The role-playing is performed based on, for example, the content of the simulation and the tools used, but is not limited to, such examples. For example, the role-playing unit allows the AI ​​professional crew to respond in real time and evaluate customer service skills. The feedback unit provides feedback on the evaluation results of the role-playing performed by the role-playing unit. Feedback is provided based on, but is not limited to, evaluation items, evaluation criteria, and feedback format. For example, the feedback department may evaluate smiles, tone of voice, smoothness of responses, clarity of explanations, and persuasive sales talk. This allows the training system according to the embodiment to consistently handle everything from collecting customer service data to learning, role-playing, and feedback. This effectively addresses the lack of customer service skills among new crew members and new products, and improves the overall customer service quality of the shop.

[0030] The training system includes an evaluation criteria setting unit that sets evaluation criteria. The evaluation criteria include, but are not limited to, evaluation items, evaluation scales, and methods for setting criteria. For example, the evaluation criteria setting unit sets evaluation criteria for things like smiles, tone of voice, smoothness of responses, clarity of explanations, and persuasive sales talk. This improves the accuracy and consistency of feedback by setting evaluation criteria. Some or all of the above processing in the evaluation criteria setting unit may be performed using, for example, AI, or not using AI. For example, the evaluation criteria setting unit can set evaluation criteria using an AI model that sets optimal evaluation criteria based on past evaluation data.

[0031] The training system includes a visual feedback unit that provides feedback visually. The visual feedback unit provides feedback visually. Methods of providing feedback visually include, but are not limited to, graphs, charts, and dashboards. For example, the visual feedback unit visually displays evaluation results as graphs or charts so that the user can understand them intuitively. This makes it easier for the user to intuitively understand the feedback through visual feedback. Some or all of the above processing in the visual feedback unit may be performed using, for example, AI, or not using AI. For example, the visual feedback unit can provide feedback visually using an AI model that provides optimal visual feedback based on the evaluation results.

[0032] The training system includes an anonymization unit that anonymizes personal information during data collection. The anonymization unit anonymizes personal information during data collection. Methods of anonymization include, but are not limited to, data masking, pseudo-anonymization, and complete anonymization. For example, the anonymization unit anonymizes personal information using data masking. The anonymization unit can also anonymize personal information using pseudo-anonymization. Furthermore, the anonymization unit can anonymize personal information using complete anonymization. This enhances privacy protection through the anonymization of personal information. Some or all of the above processing in the anonymization unit may be performed using, for example, AI, or not using AI. For example, the anonymization unit can anonymize personal information using an AI model that performs data masking or pseudo-anonymization.

[0033] The data collection unit can collect customer service data from highly productive or highly skilled crew members. For example, the data collection unit collects customer service data from highly productive or highly skilled crew members. This data may include, but is not limited to, audio data, video data, and text data. For example, the data collection unit collects customer service data from highly productive crew members. This data may include metrics such as sales, service time, and customer satisfaction. For example, the data collection unit collects customer service data from highly skilled crew members. This data may include metrics such as customer service skills, communication skills, and problem-solving abilities. This allows for more effective learning by collecting customer service data from highly productive or highly skilled crew members. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can collect customer service data using an AI model that collects customer service data from highly productive or highly skilled crew members.

[0034] The learning unit allows the AI ​​to learn based on the collected data. The learning unit allows the AI ​​to learn based on the data collected by the collection unit. Learning is performed using algorithms such as neural networks and support vector machines, but is not limited to these examples. For example, the learning unit allows the AI ​​to learn using methods such as supervised learning, unsupervised learning, and reinforcement learning. As a result, the accuracy of the AI ​​professional crew improves as the AI ​​learns based on the collected data. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit allows the AI ​​to learn using an AI model that learns based on collected data.

[0035] The role-playing unit can perform role-playing using a trained AI professional crew. The role-playing unit performs role-playing using an AI professional crew trained by the learning unit. The role-playing is based on, for example, the content of the simulation and the tools used, but is not limited to such examples. For example, the role-playing unit has the AI ​​professional crew respond in real time and evaluate customer service skills. This makes it possible to perform more realistic role-playing by using a trained AI professional crew. Some or all of the above processing in the role-playing unit may be performed using, for example, AI, or not using AI. For example, the role-playing unit can perform role-playing using an AI model that performs role-playing using a trained AI professional crew.

[0036] The feedback department can evaluate smiles, tone of voice, smoothness of responses, clarity of explanations, and customer-engaging conversation. The feedback department provides feedback on the evaluation results of role-playing conducted by the role-playing department. Feedback is based on, but is not limited to, evaluation items, evaluation criteria, and feedback format. For example, the feedback department evaluates smiles, tone of voice, smoothness of responses, clarity of explanations, and customer-engaging conversation. This promotes the improvement of crew skills by providing feedback based on detailed evaluation items. Some or all of the above processing in the feedback department may be performed using, for example, AI, or not using AI. For example, the feedback department can provide feedback using an AI model that evaluates smiles, tone of voice, smoothness of responses, clarity of explanations, and customer-engaging conversation.

[0037] The data collection unit can analyze the past customer service history of high-productivity crew members and select the optimal data collection method. Past customer service history includes, but is not limited to, customer service records, customer feedback, and sales data. For example, the data collection unit can analyze the customer service history of high-productivity crew members and prioritize the collection of data from peak hours. The data collection unit can also analyze the customer service history of high-productivity crew members and focus on collecting customer service data for specific customer segments. Furthermore, the data collection unit can analyze the customer service history of high-productivity crew members and prioritize the collection of customer service data for specific products. This allows for the selection of the optimal data collection method by analyzing past customer service history. Some or all of the above processes in the data collection unit may be performed using, for example, AI, or not. For example, the data collection unit can select a data collection method using an AI model that analyzes the past customer service history of high-productivity crew members and selects the optimal data collection method.

[0038] The data collection unit can filter customer service data based on the crew's current work status and areas of interest. Work status includes, but is not limited to, work progress, type of work, and workload. For example, the data collection unit prioritizes collecting customer service data related to the work the crew is currently working on. The data collection unit can also filter and collect relevant customer service data based on the crew's areas of interest. Furthermore, the data collection unit can collect customer service data during times when the crew's workload is low. This allows for the collection of more relevant data by filtering the data based on the crew's work status and areas of interest. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not. For example, the data collection unit can filter customer service data using an AI model that filters based on the crew's current work status and areas of interest.

[0039] The data collection unit can prioritize the collection of highly relevant data by considering the crew's geographical location information when collecting customer service data. Geographic location information includes, but is not limited to, GPS data, location services, and map data. For example, if a crew member is providing customer service in a specific area, the data collection unit will prioritize the collection of customer service data relevant to that area. Furthermore, if a crew member is on the move, the data collection unit can prioritize the collection of customer service data relevant to their current location. Additionally, if a crew member is providing customer service at a specific store, the data collection unit can prioritize the collection of customer service data relevant to that store. This allows for the collection of more relevant data by considering the crew member's geographical location information. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not. For example, the data collection unit can collect data using an AI model that prioritizes the collection of highly relevant data by considering the crew member's geographical location information.

[0040] The data collection unit can analyze the social media activities of crew members and collect relevant data when collecting customer service data. Social media activities include, but are not limited to, posts, follower counts, and engagement rates. For example, the data collection unit can analyze the social media activities of crew members and collect customer service data related to specific trends. The data collection unit can also analyze the social media activities of crew members and collect customer service data related to specific customer segments. Furthermore, the data collection unit can analyze the social media activities of crew members and collect customer service data related to specific products. This allows for the collection of more relevant data by analyzing the social media activities of crew members. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not. For example, the data collection unit can collect data using an AI model that analyzes the social media activities of crew members and collects relevant data.

[0041] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. Past learning data includes, but is not limited to, learning records, learning results, and learning feedback. For example, the learning unit can refer to past learning data to set optimal learning parameters. The learning unit can also refer to past learning data to adjust the hyperparameters of the learning algorithm. Furthermore, the learning unit can refer to past learning data to optimize the structure of the learning algorithm. This makes it possible to optimize the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using, for example, AI, or not. For example, the learning unit can optimize the learning algorithm using an AI model that optimizes the learning algorithm by referring to past learning data.

[0042] The learning unit can apply different learning algorithms during training depending on the category of customer service data. The customer service data categories include, but are not limited to, product categories, customer segments, and customer service situations. For example, the learning unit can apply a natural language processing algorithm if the customer service data relates to customer interaction. It can also apply an image recognition algorithm if the customer service data relates to product descriptions. Furthermore, it can apply a recommendation system algorithm if the customer service data relates to sales promotion. This improves the accuracy of training by applying different learning algorithms depending on the category of customer service data. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can perform training using an AI model that applies different learning algorithms depending on the category of customer service data.

[0043] The learning unit can weight the training data based on the submission timing of customer service data during training. The training unit weights the training data based on the submission timing of customer service data during training. Submission timing includes, but is not limited to, temporal importance, data freshness, and past trends. For example, the training unit can train by giving high weight to recently submitted customer service data. The training unit can also train by giving low weight to previously submitted customer service data. Furthermore, the training unit can train by giving medium weight to customer service data submitted during a specific period. This improves the accuracy of training by weighting based on the submission timing of customer service data. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the training unit can weight the training data using an AI model that weights based on the submission timing of customer service data.

[0044] The learning unit can improve the accuracy of its learning by referring to relevant literature on customer service data during the learning process. Relevant literature includes, but is not limited to, academic papers, industry reports, and books. For example, the learning unit can learn by referring to academic papers related to customer service data. It can also learn by referring to industry reports related to customer service data. Furthermore, it can learn by referring to books related to customer service data. This improves the accuracy of learning by referring to relevant literature. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can improve the accuracy of its learning by using an AI model that learns by referring to relevant literature on customer service data.

[0045] The role-playing unit can select the optimal scenario during role-playing by referring to the crew's past customer service history. Past customer service history includes, but is not limited to, customer service records, customer feedback, and sales data. For example, the role-playing unit can refer to the crew's past customer service history and provide similar scenarios. It can also refer to the crew's past customer service history and provide different scenarios. Furthermore, the role-playing unit can refer to the crew's past customer service history and provide scenarios corresponding to specific customer segments. This allows for the selection of the optimal scenario by referring to past customer service history. Some or all of the above processing in the role-playing unit may be performed using, for example, AI, or not. For example, the role-playing unit can select a scenario using an AI model that selects the optimal scenario by referring to the crew's past customer service history.

[0046] The role-playing unit can customize scenarios during role-playing based on the crew's current work situation. Work situation includes, but is not limited to, the progress of tasks, the type of task, and the workload. For example, the role-playing unit can provide scenarios related to the tasks the crew is currently working on. The role-playing unit can also provide complex scenarios during periods when the crew's workload is low. Furthermore, the role-playing unit can provide simple scenarios during periods when the crew's workload is high. This allows for more realistic role-playing by customizing scenarios based on the crew's work situation. Some or all of the above processing in the role-playing unit may be performed using, for example, AI, or not. For example, the role-playing unit can customize scenarios using an AI model that customizes scenarios based on the crew's current work situation.

[0047] The role-playing unit can select the optimal scenario during role-playing by considering the crew's geographical location information. Geographic location information includes, but is not limited to, GPS data, location services, and map data. For example, if the role-playing unit is providing customer service in a specific area, it can provide a scenario relevant to that area. It can also provide a scenario relevant to the crew's current location if they are on the move. Furthermore, if the role-playing unit is providing customer service in a specific store, it can provide a scenario relevant to that store. This allows for the provision of more relevant scenarios by considering the crew's geographical location information. Some or all of the above processing in the role-playing unit may be performed using, for example, AI, or not. For example, the role-playing unit can select a scenario using an AI model that selects the optimal scenario considering the crew's geographical location information.

[0048] The role-playing unit can analyze the crew's social media activity during role-playing and propose scenarios. Social media activity includes, but is not limited to, posts, follower count, and engagement rate. For example, the role-playing unit can analyze the crew's social media activity and provide scenarios related to specific trends. It can also analyze the crew's social media activity and provide scenarios related to specific customer segments. Furthermore, it can analyze the crew's social media activity and provide scenarios related to specific products. This allows for the provision of more relevant scenarios by analyzing the crew's social media activity. Some or all of the above processing in the role-playing unit may be performed using, for example, AI, or not. For example, the role-playing unit can propose scenarios using an AI model that analyzes the crew's social media activity and proposes scenarios.

[0049] The feedback unit can adjust the level of detail of the feedback based on the importance of the customer service when providing feedback. The level of detail of the feedback includes, but is not limited to, the depth, scope, and specificity of the feedback. For example, the feedback unit provides detailed feedback for important customer service. The feedback unit can also provide concise feedback for general customer service. Furthermore, the feedback unit can provide individualized feedback for customer service. By adjusting the level of detail of the feedback based on the importance of the customer service, more appropriate feedback can be provided. Some or all of the above processing in the feedback unit may be performed using, for example, AI, or not using AI. For example, the feedback unit can adjust the level of detail of the feedback using an AI model that adjusts the level of detail of the feedback based on the importance of the customer service.

[0050] The feedback unit can apply different feedback algorithms depending on the customer service category when providing feedback. These feedback algorithms include, but are not limited to, rule-based algorithms and machine learning algorithms. For example, the feedback unit can apply a natural language processing algorithm to customer service related to customer interaction. It can also apply an image recognition algorithm to product description services. Furthermore, it can apply a recommendation system algorithm to sales promotion services. This improves the accuracy of feedback by applying different feedback algorithms depending on the customer service category. Some or all of the processing described above in the feedback unit may be performed using, for example, AI, or not. For example, the feedback unit can provide feedback using an AI model that applies different feedback algorithms depending on the customer service category.

[0051] The feedback unit can prioritize feedback based on the timing of customer service submissions. The methods for determining priority include, but are not limited to, evaluating importance, urgency, and resource allocation. For example, the feedback unit may prioritize feedback for recent customer service submissions. It may also postpone feedback for past customer service submissions. Furthermore, the feedback unit may assign a medium priority to customer service submissions made within a specific period. This allows for more timely feedback delivery by prioritizing feedback based on the timing of customer service submissions. Some or all of the above processes in the feedback unit may be performed using, for example, AI, or not. For example, the feedback unit may use an AI model that prioritizes feedback based on the timing of customer service submissions to determine feedback priorities.

[0052] The feedback unit can adjust the order of feedback based on the relevance of the customer service when providing feedback. The order of feedback may include, but is not limited to, the importance, relevance, and urgency of the feedback. For example, the feedback unit may provide feedback first for important customer service. It may also provide feedback later for general customer service. Furthermore, the feedback unit may provide individual feedback for customer service to a specific customer. This allows for prioritizing the delivery of more important feedback by adjusting the order of feedback based on the relevance of the customer service. Some or all of the above processing in the feedback unit may be performed using, for example, AI, or not using AI. For example, the feedback unit may adjust the order of feedback using an AI model that adjusts the order of feedback based on the relevance of the customer service.

[0053] The evaluation criteria setting unit can select the optimal criteria by referring to past evaluation data when setting evaluation criteria. Past evaluation data includes, but is not limited to, evaluation records, evaluation results, and evaluation feedback. For example, the evaluation criteria setting unit can set the optimal evaluation criteria by referring to past evaluation data. The evaluation criteria setting unit can also adjust the hyperparameters of the evaluation criteria by referring to past evaluation data. Furthermore, the evaluation criteria setting unit can optimize the structure of the evaluation criteria by referring to past evaluation data. This allows for the setting of optimal evaluation criteria by referring to past evaluation data. Some or all of the above-described processes in the evaluation criteria setting unit may be performed using, for example, AI, or without AI. For example, the evaluation criteria setting unit can set evaluation criteria using an AI model that selects the optimal criteria by referring to past evaluation data.

[0054] The evaluation criteria setting unit can select the optimal criteria when setting evaluation criteria, taking into account the crew's geographical location information. The evaluation criteria setting unit selects the optimal criteria when setting evaluation criteria, taking into account the crew's geographical location information. Geographical location information includes, but is not limited to, GPS data, location information services, and map data. For example, if a crew member is providing customer service in a specific area, the evaluation criteria setting unit can set evaluation criteria related to that area. The evaluation criteria setting unit can also set evaluation criteria related to the crew member's current location if the crew member is on the move. Furthermore, if a crew member is providing customer service at a specific store, the evaluation criteria setting unit can also set evaluation criteria related to that store. This allows for the setting of more relevant evaluation criteria by taking into account the crew member's geographical location information. Some or all of the above processing in the evaluation criteria setting unit may be performed using, for example, AI, or not using AI. For example, the evaluation criteria setting unit can set evaluation criteria using an AI model that selects the optimal criteria considering the crew member's geographical location information.

[0055] The visual feedback unit can select the optimal display method by referring to the crew's past feedback history when displaying visual feedback. The visual feedback unit selects the optimal display method by referring to the crew's past feedback history when displaying visual feedback. Past feedback history includes, but is not limited to, feedback records, feedback results, and feedback content. For example, the visual feedback unit can refer to the crew's past feedback history and provide a similar display method. The visual feedback unit can also refer to the crew's past feedback history and provide a different display method. Furthermore, the visual feedback unit can refer to the crew's past feedback history and provide a display method that corresponds to a specific customer segment. This allows the optimal display method to be selected by referring to past feedback history. Some or all of the above processing in the visual feedback unit may be performed using, for example, AI, or not using AI. For example, the visual feedback unit can select a display method using an AI model that selects the optimal display method by referring to the crew's past feedback history.

[0056] The visual feedback unit can select the optimal display method when displaying visual feedback, taking into account the crew's device information. The visual feedback unit selects the optimal display method when displaying visual feedback, taking into account the crew's device information. Device information includes, but is not limited to, the type of device, device performance, and device settings. For example, if the crew is using a smartphone, the visual feedback unit provides a display method adapted to the screen size. Furthermore, if the crew is using a tablet, the visual feedback unit can provide a display method optimized for a larger screen. In addition, if the crew is using a smartwatch, the visual feedback unit can provide a concise and highly visible display method. Thus, by considering the crew's device information, the optimal display method can be provided. Some or all of the above processing in the visual feedback unit may be performed using, for example, AI, or not. For example, the visual feedback unit can select a display method using an AI model that selects the optimal display method considering the crew's device information.

[0057] The anonymization unit can select the optimal anonymization method by referring to past anonymization data during the anonymization process. Past anonymization data includes, but is not limited to, records of anonymization, results of anonymization, and methods of anonymization. For example, the anonymization unit can select the optimal anonymization method by referring to past anonymization data. The anonymization unit can also adjust the hyperparameters of the anonymization algorithm by referring to past anonymization data. Furthermore, the anonymization unit can optimize the structure of the anonymization algorithm by referring to past anonymization data. This allows the anonymization unit to select the optimal anonymization method by referring to past anonymization data. Some or all of the above-described processes in the anonymization unit may be performed using, for example, AI, or not. For example, the anonymization unit can select an anonymization method using an AI model that selects the optimal anonymization method by referring to past anonymization data.

[0058] The anonymization unit can select the optimal anonymization method when anonymizing, taking into account the crew's geographical location information. The anonymization unit selects the optimal anonymization method when anonymizing, taking into account the crew's geographical location information. Geographical location information includes, but is not limited to, GPS data, location information services, and map data. For example, if the crew is providing customer service in a specific area, the anonymization unit applies an anonymization method related to that area. The anonymization unit can also apply an anonymization method related to the current location if the crew is on the move. Furthermore, if the crew is providing customer service at a specific store, the anonymization unit can apply an anonymization method related to that store. In this way, the anonymization unit can provide the optimal anonymization method by taking into account the crew's geographical location information. Some or all of the above processing in the anonymization unit may be performed using, for example, AI, or not using AI. For example, the anonymization unit can select an anonymization method using an AI model that selects the optimal anonymization method considering the crew's geographical location information.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] The training system can also include a plan suggestion unit that analyzes the user's past training data and proposes an optimal training plan. For example, it can identify the user's weaknesses based on past training data and propose a training plan to overcome those weaknesses. It can also propose a training plan to strengthen the user's strengths based on past training data. Furthermore, it can propose a training plan tailored to the user's progress based on past training data. This allows for the provision of more effective training plans by utilizing past training data.

[0061] The training system can also include a location-based customization unit that customizes the training content by taking into account the user's geographical location. For example, if the user is providing customer service in a specific area, the system can provide training content relevant to that area. Furthermore, if the user is on the move, the system can provide training content relevant to their current location. Additionally, if the user is providing customer service at a specific store, the system can provide training content relevant to that store. This allows for the provision of more relevant training content by considering the user's geographical location.

[0062] The training system can also include a social media customization section that analyzes users' social media activity and customizes the training content. For example, it can analyze users' social media activity and provide training content related to specific trends. It can also analyze users' social media activity and provide training content related to specific customer segments. Furthermore, it can analyze users' social media activity and provide training content related to specific products. This allows for the analysis of users' social media activity and the provision of more relevant training content.

[0063] The training system can also include a device customization section that customizes the training interface considering the user's device information. For example, if the user is using a smartphone, it can provide an interface that matches the screen size. If the user is using a tablet, it can provide an interface optimized for a larger screen. Furthermore, if the user is using a smartwatch, it can provide a concise and highly visible interface. This allows for the provision of the optimal interface considering the user's device information.

[0064] The training system can also include a feedback analysis unit that analyzes the user's past feedback data and customizes the content of the feedback. For example, it can identify the user's weaknesses based on past feedback data and provide feedback to overcome those weaknesses. It can also provide feedback to strengthen the user's strengths based on past feedback data. Furthermore, it can provide feedback tailored to the user's progress based on past feedback data. This allows for the provision of more effective feedback by utilizing past feedback data.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The data collection unit collects customer service data. This data includes audio, video, and text data. The data collection unit collects customer service data from highly productive and skilled crew members, and the collected data is converted into a format that is easy for AI to analyze. Step 2: The learning unit uses the data collected by the collection unit to train the AI. Learning is performed using algorithms such as neural networks and support vector machines, employing methods such as supervised learning, unsupervised learning, and reinforcement learning. Step 3: The role-playing team conducts role-playing using the AI ​​professional crew trained by the learning team. The role-playing is conducted based on the simulation content and the tools used, with the AI ​​professional crew responding in real time and evaluating customer service skills. Step 4: The Feedback Department provides feedback on the evaluation results of the role-playing conducted by the Role-Playing Department. The feedback is based on evaluation items, evaluation criteria, and feedback format, and evaluates aspects such as smiles, tone of voice, smoothness of responses, clarity of explanations, and persuasive sales talk.

[0067] (Example of form 2) The training system according to an embodiment of the present invention is a system that uses AI to create role-playing partners and conduct training in order to address the lack of skills among new employees and the lack of customer service skills when new products are introduced. This training system collects customer service data from highly productive and highly skilled crew members and uses it to train the AI. Shop crew members perform role-playing using the trained AI professional crew, and the AI ​​evaluates their smiles, tone of voice, smoothness of responses, clarity of explanations, and persuasive talk with customers. The evaluation results are provided as feedback and scored. This allows new crew members to objectively understand their own skills and clearly identify areas for improvement. For example, the training system collects customer service data from highly productive and highly skilled crew members. The collected data is converted into a format that is easy for the AI ​​to analyze. Next, the training system uses the AI ​​to learn based on the collected data. The AI ​​learns using algorithms such as neural networks and support vector machines. The trained AI professional crew is used as a role-playing partner. For example, when shop crew members perform role-playing, the training system has the AI ​​professional crew respond in real time and evaluate their customer service skills. The evaluation criteria include factors such as smiles, tone of voice, smoothness of responses, clarity of explanations, and persuasive sales techniques. The evaluation results are provided as feedback and scored. For example, the training system visually displays the evaluation results as graphs and charts, allowing users to understand them intuitively. The training system can also suggest specific areas for improvement based on the evaluation results. This allows new crew members to objectively understand their own skills and clearly identify areas for improvement. Furthermore, the training system has a function to anonymize personal information during data collection, enhancing privacy protection. For example, the training system anonymizes personal information using technologies such as data masking and pseudo-anonymization. As a result, the training system is expected to effectively address the lack of customer service skills among new crew members and new products, and improve the overall quality of customer service in the shop.This allows the training system to effectively address the lack of customer service skills among new crew members and those handling new products, thereby improving the overall quality of customer service in the shop.

[0068] The training system according to the embodiment comprises a collection unit, a learning unit, a role-playing unit, and a feedback unit. The collection unit collects customer service data. Customer service data includes, but is not limited to, audio data, video data, and text data. The collection unit collects, for example, customer service data from highly productive or highly skilled crew members. The collected data is converted into a format that is easy for the AI ​​to analyze. The learning unit allows the AI ​​to learn based on the data collected by the collection unit. Learning is performed using, for example, algorithms such as neural networks and support vector machines, but is not limited to, such examples. For example, the learning unit allows the AI ​​to learn using methods such as supervised learning, unsupervised learning, and reinforcement learning. The role-playing unit performs role-playing using the AI ​​professional crew trained by the learning unit. The role-playing is performed based on, for example, the content of the simulation and the tools used, but is not limited to, such examples. For example, the role-playing unit allows the AI ​​professional crew to respond in real time and evaluate customer service skills. The feedback unit provides feedback on the evaluation results of the role-playing performed by the role-playing unit. Feedback is provided based on, but is not limited to, evaluation items, evaluation criteria, and feedback format. For example, the feedback department may evaluate smiles, tone of voice, smoothness of responses, clarity of explanations, and persuasive sales talk. This allows the training system according to the embodiment to consistently handle everything from collecting customer service data to learning, role-playing, and feedback. This effectively addresses the lack of customer service skills among new crew members and new products, and improves the overall customer service quality of the shop.

[0069] The training system includes an evaluation criteria setting unit that sets evaluation criteria. The evaluation criteria include, but are not limited to, evaluation items, evaluation scales, and methods for setting criteria. For example, the evaluation criteria setting unit sets evaluation criteria for things like smiles, tone of voice, smoothness of responses, clarity of explanations, and persuasive sales talk. This improves the accuracy and consistency of feedback by setting evaluation criteria. Some or all of the above processing in the evaluation criteria setting unit may be performed using, for example, AI, or not using AI. For example, the evaluation criteria setting unit can set evaluation criteria using an AI model that sets optimal evaluation criteria based on past evaluation data.

[0070] The training system includes a visual feedback unit that provides feedback visually. The visual feedback unit provides feedback visually. Methods of providing feedback visually include, but are not limited to, graphs, charts, and dashboards. For example, the visual feedback unit visually displays evaluation results as graphs or charts so that the user can understand them intuitively. This makes it easier for the user to intuitively understand the feedback through visual feedback. Some or all of the above processing in the visual feedback unit may be performed using, for example, AI, or not using AI. For example, the visual feedback unit can provide feedback visually using an AI model that provides optimal visual feedback based on the evaluation results.

[0071] The training system includes an anonymization unit that anonymizes personal information during data collection. The anonymization unit anonymizes personal information during data collection. Methods of anonymization include, but are not limited to, data masking, pseudo-anonymization, and complete anonymization. For example, the anonymization unit anonymizes personal information using data masking. The anonymization unit can also anonymize personal information using pseudo-anonymization. Furthermore, the anonymization unit can anonymize personal information using complete anonymization. This enhances privacy protection through the anonymization of personal information. Some or all of the above processing in the anonymization unit may be performed using, for example, AI, or not using AI. For example, the anonymization unit can anonymize personal information using an AI model that performs data masking or pseudo-anonymization.

[0072] The data collection unit can collect customer service data from highly productive or highly skilled crew members. For example, the data collection unit collects customer service data from highly productive or highly skilled crew members. This data may include, but is not limited to, audio data, video data, and text data. For example, the data collection unit collects customer service data from highly productive crew members. This data may include metrics such as sales, service time, and customer satisfaction. For example, the data collection unit collects customer service data from highly skilled crew members. This data may include metrics such as customer service skills, communication skills, and problem-solving abilities. This allows for more effective learning by collecting customer service data from highly productive or highly skilled crew members. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can collect customer service data using an AI model that collects customer service data from highly productive or highly skilled crew members.

[0073] The learning unit allows the AI ​​to learn based on the collected data. The learning unit allows the AI ​​to learn based on the data collected by the collection unit. Learning is performed using algorithms such as neural networks and support vector machines, but is not limited to these examples. For example, the learning unit allows the AI ​​to learn using methods such as supervised learning, unsupervised learning, and reinforcement learning. As a result, the accuracy of the AI ​​professional crew improves as the AI ​​learns based on the collected data. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit allows the AI ​​to learn using an AI model that learns based on collected data.

[0074] The role-playing unit can perform role-playing using a trained AI professional crew. The role-playing unit performs role-playing using an AI professional crew trained by the learning unit. The role-playing is based on, for example, the content of the simulation and the tools used, but is not limited to such examples. For example, the role-playing unit has the AI ​​professional crew respond in real time and evaluate customer service skills. This makes it possible to perform more realistic role-playing by using a trained AI professional crew. Some or all of the above processing in the role-playing unit may be performed using, for example, AI, or not using AI. For example, the role-playing unit can perform role-playing using an AI model that performs role-playing using a trained AI professional crew.

[0075] The feedback department can evaluate smiles, tone of voice, smoothness of responses, clarity of explanations, and customer-engaging conversation. The feedback department provides feedback on the evaluation results of role-playing conducted by the role-playing department. Feedback is based on, but is not limited to, evaluation items, evaluation criteria, and feedback format. For example, the feedback department evaluates smiles, tone of voice, smoothness of responses, clarity of explanations, and customer-engaging conversation. This promotes the improvement of crew skills by providing feedback based on detailed evaluation items. Some or all of the above processing in the feedback department may be performed using, for example, AI, or not using AI. For example, the feedback department can provide feedback using an AI model that evaluates smiles, tone of voice, smoothness of responses, clarity of explanations, and customer-engaging conversation.

[0076] The data collection unit can estimate the user's emotions and adjust the timing of customer service data collection based on the estimated emotions. Methods for estimating user emotions include, but are not limited to, facial expression recognition, speech analysis, and text analysis. For example, the data collection unit can estimate user emotions using facial expression recognition technology. It can also estimate user emotions using speech analysis technology. Furthermore, it can estimate user emotions using text analysis technology. Methods for adjusting collection timing include, but are not limited to, real-time analysis and pre-configured rules. For example, if the user is relaxed, the data collection unit can collect customer service data during normal business hours. If the user is stressed, the data collection unit can also collect customer service data after work or during breaks. Furthermore, if the user is focused, the data collection unit can collect customer service data immediately after a specific work task is completed. This allows for more appropriate data collection by adjusting the collection timing according to the user's emotions. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can adjust the timing of customer service data collection using an AI model that estimates the user's emotions and adjusts the collection timing based on the estimated user emotions.

[0077] The data collection unit can analyze the past customer service history of high-productivity crew members and select the optimal data collection method. Past customer service history includes, but is not limited to, customer service records, customer feedback, and sales data. For example, the data collection unit can analyze the customer service history of high-productivity crew members and prioritize the collection of data from peak hours. The data collection unit can also analyze the customer service history of high-productivity crew members and focus on collecting customer service data for specific customer segments. Furthermore, the data collection unit can analyze the customer service history of high-productivity crew members and prioritize the collection of customer service data for specific products. This allows for the selection of the optimal data collection method by analyzing past customer service history. Some or all of the above processes in the data collection unit may be performed using, for example, AI, or not. For example, the data collection unit can select a data collection method using an AI model that analyzes the past customer service history of high-productivity crew members and selects the optimal data collection method.

[0078] The data collection unit can filter customer service data based on the crew's current work status and areas of interest. Work status includes, but is not limited to, work progress, type of work, and workload. For example, the data collection unit prioritizes collecting customer service data related to the work the crew is currently working on. The data collection unit can also filter and collect relevant customer service data based on the crew's areas of interest. Furthermore, the data collection unit can collect customer service data during times when the crew's workload is low. This allows for the collection of more relevant data by filtering the data based on the crew's work status and areas of interest. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not. For example, the data collection unit can filter customer service data using an AI model that filters based on the crew's current work status and areas of interest.

[0079] The data collection unit can estimate the user's emotions and determine the priority of customer service data to collect based on the estimated emotions. Methods for estimating user emotions include, but are not limited to, facial recognition, speech analysis, and text analysis. For example, the data collection unit can estimate user emotions using facial recognition technology. It can also estimate user emotions using speech analysis technology. Furthermore, it can also estimate user emotions using text analysis technology. Methods for determining priorities include, but are not limited to, importance assessment, urgency assessment, and resource allocation. For example, if the user is relaxed, the data collection unit prioritizes collecting normal customer service data. If the user is stressed, the data collection unit may prioritize collecting customer service data related to specific problem-solving. Furthermore, if the user is focused, the data collection unit may prioritize collecting detailed customer service data. This allows for the priority collection of more important data by prioritizing data based on user emotions. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can determine the priority of data using an AI model that estimates the user's emotions and determines the priority of customer service data to be collected based on the estimated user emotions.

[0080] The data collection unit can prioritize the collection of highly relevant data by considering the crew's geographical location information when collecting customer service data. Geographic location information includes, but is not limited to, GPS data, location services, and map data. For example, if a crew member is providing customer service in a specific area, the data collection unit will prioritize the collection of customer service data relevant to that area. Furthermore, if a crew member is on the move, the data collection unit can prioritize the collection of customer service data relevant to their current location. Additionally, if a crew member is providing customer service at a specific store, the data collection unit can prioritize the collection of customer service data relevant to that store. This allows for the collection of more relevant data by considering the crew member's geographical location information. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not. For example, the data collection unit can collect data using an AI model that prioritizes the collection of highly relevant data by considering the crew member's geographical location information.

[0081] The data collection unit can analyze the social media activities of crew members and collect relevant data when collecting customer service data. Social media activities include, but are not limited to, posts, follower counts, and engagement rates. For example, the data collection unit can analyze the social media activities of crew members and collect customer service data related to specific trends. The data collection unit can also analyze the social media activities of crew members and collect customer service data related to specific customer segments. Furthermore, the data collection unit can analyze the social media activities of crew members and collect customer service data related to specific products. This allows for the collection of more relevant data by analyzing the social media activities of crew members. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not. For example, the data collection unit can collect data using an AI model that analyzes the social media activities of crew members and collects relevant data.

[0082] The learning unit can estimate the user's emotions and select training data based on those estimated emotions. Methods for estimating user emotions include, but are not limited to, facial expression recognition, speech analysis, and text analysis. For example, the learning unit can estimate user emotions using facial expression recognition technology. It can also estimate user emotions using speech analysis technology. Furthermore, it can estimate user emotions using text analysis technology. Criteria for selecting training data include, but are not limited to, data quality, data diversity, and data relevance. For example, if the user is relaxed, the learning unit can select normal customer service data as training data. If the user is stressed, the learning unit can also select customer service data related to specific problem-solving. Furthermore, if the user is focused, the learning unit can also select detailed customer service data as training data. This allows for more effective learning by selecting training data based on user emotions. Some or all of the above-described processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can select training data using an AI model that estimates the user's emotions and selects training data based on the estimated user emotions.

[0083] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. Past learning data includes, but is not limited to, learning records, learning results, and learning feedback. For example, the learning unit can refer to past learning data to set optimal learning parameters. The learning unit can also refer to past learning data to adjust the hyperparameters of the learning algorithm. Furthermore, the learning unit can refer to past learning data to optimize the structure of the learning algorithm. This makes it possible to optimize the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using, for example, AI, or not. For example, the learning unit can optimize the learning algorithm using an AI model that optimizes the learning algorithm by referring to past learning data.

[0084] The learning unit can apply different learning algorithms during training depending on the category of customer service data. The customer service data categories include, but are not limited to, product categories, customer segments, and customer service situations. For example, the learning unit can apply a natural language processing algorithm if the customer service data relates to customer interaction. It can also apply an image recognition algorithm if the customer service data relates to product descriptions. Furthermore, it can apply a recommendation system algorithm if the customer service data relates to sales promotion. This improves the accuracy of training by applying different learning algorithms depending on the category of customer service data. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can perform training using an AI model that applies different learning algorithms depending on the category of customer service data.

[0085] The learning unit can estimate the user's emotions and adjust the learning frequency based on those emotions. Methods for estimating user emotions include, but are not limited to, facial recognition, speech analysis, and text analysis. For example, the learning unit can estimate user emotions using facial recognition technology. It can also estimate user emotions using speech analysis technology. Furthermore, it can estimate user emotions using text analysis technology. Methods for adjusting the learning frequency include, but are not limited to, the learning schedule, data update frequency, and resource allocation. For example, the learning unit will learn at a normal learning frequency when the user is relaxed. It can also lower the learning frequency when the user is stressed. Furthermore, it can increase the learning frequency when the user is focused. This allows for more effective learning by adjusting the learning frequency based on user emotions. Some or all of the processing described above in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can adjust the frequency of learning using an AI model that estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions.

[0086] The learning unit can weight the training data based on the submission timing of customer service data during training. The training unit weights the training data based on the submission timing of customer service data during training. Submission timing includes, but is not limited to, temporal importance, data freshness, and past trends. For example, the training unit can train by giving high weight to recently submitted customer service data. The training unit can also train by giving low weight to previously submitted customer service data. Furthermore, the training unit can train by giving medium weight to customer service data submitted during a specific period. This improves the accuracy of training by weighting based on the submission timing of customer service data. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the training unit can weight the training data using an AI model that weights based on the submission timing of customer service data.

[0087] The learning unit can improve the accuracy of its learning by referring to relevant literature on customer service data during the learning process. Relevant literature includes, but is not limited to, academic papers, industry reports, and books. For example, the learning unit can learn by referring to academic papers related to customer service data. It can also learn by referring to industry reports related to customer service data. Furthermore, it can learn by referring to books related to customer service data. This improves the accuracy of learning by referring to relevant literature. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can improve the accuracy of its learning by using an AI model that learns by referring to relevant literature on customer service data.

[0088] The role-playing unit can estimate the user's emotions and adjust the role-playing scenario based on those emotions. Methods for estimating user emotions include, but are not limited to, facial recognition, speech analysis, and text analysis. For example, the role-playing unit can estimate user emotions using facial recognition technology. It can also estimate user emotions using speech analysis technology. Furthermore, it can estimate user emotions using text analysis technology. Methods for adjusting the scenario include, but are not limited to, scenario content, scenario difficulty, and scenario application conditions. For example, if the user is relaxed, the role-playing unit can provide a normal scenario. If the user is stressed, it can provide a simpler scenario. Furthermore, if the user is focused, it can provide a more complex scenario. This allows for more effective role-playing by adjusting the scenario based on user emotions. Some or all of the above-described processes in the role-playing section may be performed using AI, for example, or without AI. For example, the role-playing section can adjust the role-playing scenario using an AI model that estimates the user's emotions and adjusts the scenario based on the estimated user emotions.

[0089] The role-playing unit can select the optimal scenario during role-playing by referring to the crew's past customer service history. Past customer service history includes, but is not limited to, customer service records, customer feedback, and sales data. For example, the role-playing unit can refer to the crew's past customer service history and provide similar scenarios. It can also refer to the crew's past customer service history and provide different scenarios. Furthermore, the role-playing unit can refer to the crew's past customer service history and provide scenarios corresponding to specific customer segments. This allows for the selection of the optimal scenario by referring to past customer service history. Some or all of the above processing in the role-playing unit may be performed using, for example, AI, or not. For example, the role-playing unit can select a scenario using an AI model that selects the optimal scenario by referring to the crew's past customer service history.

[0090] The role-playing unit can customize scenarios during role-playing based on the crew's current work situation. Work situation includes, but is not limited to, the progress of tasks, the type of task, and the workload. For example, the role-playing unit can provide scenarios related to the tasks the crew is currently working on. The role-playing unit can also provide complex scenarios during periods when the crew's workload is low. Furthermore, the role-playing unit can provide simple scenarios during periods when the crew's workload is high. This allows for more realistic role-playing by customizing scenarios based on the crew's work situation. Some or all of the above processing in the role-playing unit may be performed using, for example, AI, or not. For example, the role-playing unit can customize scenarios using an AI model that customizes scenarios based on the crew's current work situation.

[0091] The role-playing unit can estimate the user's emotions and determine the priority of role-playing based on those estimated emotions. Methods for estimating user emotions include, but are not limited to, facial recognition, speech analysis, and text analysis. For example, the role-playing unit can estimate user emotions using facial recognition technology. It can also estimate user emotions using speech analysis technology. Furthermore, it can estimate user emotions using text analysis technology. Methods for determining priorities include, but are not limited to, importance assessment, urgency assessment, and resource allocation. For example, if the user is relaxed, the role-playing unit will prioritize normal role-playing. It can also prioritize simpler role-playing if the user is stressed. Furthermore, it can prioritize more complex role-playing if the user is focused. This allows for more effective training by prioritizing role-playing based on user emotions. Some or all of the above-described processes in the role-playing unit may be performed using AI, for example, or without AI. For example, the role-playing unit can determine the priority of role-playing using an AI model that estimates the user's emotions and determines the priority of role-playing based on the estimated user emotions.

[0092] The role-playing unit can select the optimal scenario during role-playing by considering the crew's geographical location information. Geographic location information includes, but is not limited to, GPS data, location services, and map data. For example, if the role-playing unit is providing customer service in a specific area, it can provide a scenario relevant to that area. It can also provide a scenario relevant to the crew's current location if they are on the move. Furthermore, if the role-playing unit is providing customer service in a specific store, it can provide a scenario relevant to that store. This allows for the provision of more relevant scenarios by considering the crew's geographical location information. Some or all of the above processing in the role-playing unit may be performed using, for example, AI, or not. For example, the role-playing unit can select a scenario using an AI model that selects the optimal scenario considering the crew's geographical location information.

[0093] The role-playing unit can analyze the crew's social media activity during role-playing and propose scenarios. Social media activity includes, but is not limited to, posts, follower count, and engagement rate. For example, the role-playing unit can analyze the crew's social media activity and provide scenarios related to specific trends. It can also analyze the crew's social media activity and provide scenarios related to specific customer segments. Furthermore, it can analyze the crew's social media activity and provide scenarios related to specific products. This allows for the provision of more relevant scenarios by analyzing the crew's social media activity. Some or all of the above processing in the role-playing unit may be performed using, for example, AI, or not. For example, the role-playing unit can propose scenarios using an AI model that analyzes the crew's social media activity and proposes scenarios.

[0094] The feedback unit can estimate the user's emotions and adjust the way it presents the feedback based on those emotions. Methods for estimating user emotions include, but are not limited to, facial recognition, speech analysis, and text analysis. For example, the feedback unit can use facial recognition technology to estimate the user's emotions. It can also use speech analysis technology to estimate the user's emotions. Furthermore, it can use text analysis technology to estimate the user's emotions. Methods for presenting feedback include, but are not limited to, the format, tone, and content of the feedback. For example, if the user is relaxed, the feedback unit can provide detailed feedback. If the user is stressed, it can provide concise feedback. Furthermore, if the user is focused, it can provide feedback that includes specific areas for improvement. This allows for more effective feedback by adjusting the presentation of feedback based on the user's emotions. Some or all of the processing described above in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can adjust the way feedback is expressed using an AI model that estimates the user's emotions and adjusts the way feedback is expressed based on the estimated user emotions.

[0095] The feedback unit can adjust the level of detail of the feedback based on the importance of the customer service when providing feedback. The level of detail of the feedback includes, but is not limited to, the depth, scope, and specificity of the feedback. For example, the feedback unit provides detailed feedback for important customer service. The feedback unit can also provide concise feedback for general customer service. Furthermore, the feedback unit can provide individualized feedback for customer service. By adjusting the level of detail of the feedback based on the importance of the customer service, more appropriate feedback can be provided. Some or all of the above processing in the feedback unit may be performed using, for example, AI, or not using AI. For example, the feedback unit can adjust the level of detail of the feedback using an AI model that adjusts the level of detail of the feedback based on the importance of the customer service.

[0096] The feedback unit can apply different feedback algorithms depending on the customer service category when providing feedback. These feedback algorithms include, but are not limited to, rule-based algorithms and machine learning algorithms. For example, the feedback unit can apply a natural language processing algorithm to customer service related to customer interaction. It can also apply an image recognition algorithm to product description services. Furthermore, it can apply a recommendation system algorithm to sales promotion services. This improves the accuracy of feedback by applying different feedback algorithms depending on the customer service category. Some or all of the processing described above in the feedback unit may be performed using, for example, AI, or not. For example, the feedback unit can provide feedback using an AI model that applies different feedback algorithms depending on the customer service category.

[0097] The feedback unit can estimate the user's emotions and adjust the length of the feedback based on the estimated emotions. Methods for estimating user emotions include, but are not limited to, facial recognition, speech analysis, and text analysis. For example, the feedback unit can estimate user emotions using facial recognition technology. The feedback unit can also estimate user emotions using speech analysis technology. Furthermore, the feedback unit can also estimate user emotions using text analysis technology. The length of the feedback includes, but is not limited to, the duration of the feedback, the number of characters in the feedback, and the level of detail in the feedback. For example, the feedback unit can provide detailed feedback when the user is relaxed. The feedback unit can also provide concise feedback when the user is stressed. Furthermore, the feedback unit can provide feedback that includes specific areas for improvement when the user is focused. This allows for more effective feedback by adjusting the length of the feedback based on the user's emotions. Some or all of the above processing in the feedback unit may be performed using, for example, AI, or not using AI. For example, the feedback unit can adjust the length of the feedback using an AI model that estimates the user's emotions and adjusts the length of the feedback based on the estimated user emotions.

[0098] The feedback unit can prioritize feedback based on the timing of customer service submissions. The methods for determining priority include, but are not limited to, evaluating importance, urgency, and resource allocation. For example, the feedback unit may prioritize feedback for recent customer service submissions. It may also postpone feedback for past customer service submissions. Furthermore, the feedback unit may assign a medium priority to customer service submissions made within a specific period. This allows for more timely feedback delivery by prioritizing feedback based on the timing of customer service submissions. Some or all of the above processes in the feedback unit may be performed using, for example, AI, or not. For example, the feedback unit may use an AI model that prioritizes feedback based on the timing of customer service submissions to determine feedback priorities.

[0099] The feedback unit can adjust the order of feedback based on the relevance of the customer service when providing feedback. The order of feedback may include, but is not limited to, the importance, relevance, and urgency of the feedback. For example, the feedback unit may provide feedback first for important customer service. It may also provide feedback later for general customer service. Furthermore, the feedback unit may provide individual feedback for customer service to a specific customer. This allows for prioritizing the delivery of more important feedback by adjusting the order of feedback based on the relevance of the customer service. Some or all of the above processing in the feedback unit may be performed using, for example, AI, or not using AI. For example, the feedback unit may adjust the order of feedback using an AI model that adjusts the order of feedback based on the relevance of the customer service.

[0100] The evaluation criteria setting unit can estimate the user's emotions and adjust the evaluation criteria based on the estimated emotions. Methods for estimating user emotions include, but are not limited to, facial expression recognition, speech analysis, and text analysis. For example, the evaluation criteria setting unit can estimate user emotions using facial expression recognition technology. It can also estimate user emotions using speech analysis technology. Furthermore, it can estimate user emotions using text analysis technology. Setting evaluation criteria includes, but are not limited to, evaluation items, evaluation scales, and methods for setting criteria. For example, the evaluation criteria setting unit sets normal evaluation criteria when the user is relaxed. It can also set simple evaluation criteria when the user is stressed. Furthermore, it can set detailed evaluation criteria when the user is focused. This allows for the setting of more appropriate evaluation criteria by adjusting the evaluation criteria based on user emotions. Some or all of the above-described processes in the evaluation criteria setting unit may be performed using AI, for example, or without AI. For example, the evaluation criteria setting unit can adjust the evaluation criteria using an AI model that estimates the user's emotions and adjusts the evaluation criteria based on the estimated user emotions.

[0101] The evaluation criteria setting unit can select the optimal criteria by referring to past evaluation data when setting evaluation criteria. Past evaluation data includes, but is not limited to, evaluation records, evaluation results, and evaluation feedback. For example, the evaluation criteria setting unit can set the optimal evaluation criteria by referring to past evaluation data. The evaluation criteria setting unit can also adjust the hyperparameters of the evaluation criteria by referring to past evaluation data. Furthermore, the evaluation criteria setting unit can optimize the structure of the evaluation criteria by referring to past evaluation data. This allows for the setting of optimal evaluation criteria by referring to past evaluation data. Some or all of the above-described processes in the evaluation criteria setting unit may be performed using, for example, AI, or without AI. For example, the evaluation criteria setting unit can set evaluation criteria using an AI model that selects the optimal criteria by referring to past evaluation data.

[0102] The evaluation criteria setting unit can estimate the user's emotions and determine the priority of evaluation criteria based on the estimated user emotions. Methods for estimating user emotions include, but are not limited to, facial expression recognition, speech analysis, and text analysis. For example, the evaluation criteria setting unit can estimate user emotions using facial expression recognition technology. It can also estimate user emotions using speech analysis technology. Furthermore, it can also estimate user emotions using text analysis technology. Methods for determining priority include, but are not limited to, evaluation of importance, evaluation of urgency, and resource allocation. For example, if the user is relaxed, the evaluation criteria setting unit prioritizes normal evaluation criteria. It can also prioritize simple evaluation criteria if the user is stressed. Furthermore, it can prioritize detailed evaluation criteria if the user is focused. This allows for more appropriate evaluation by determining the priority of evaluation criteria based on user emotions. Some or all of the above-described processes in the evaluation criteria setting unit may be performed using AI, for example, or without AI. For example, the evaluation criteria setting unit can determine the priority of evaluation criteria using an AI model that estimates the user's emotions and determines the priority of evaluation criteria based on the estimated user emotions.

[0103] The evaluation criteria setting unit can select the optimal criteria when setting evaluation criteria, taking into account the crew's geographical location information. The evaluation criteria setting unit selects the optimal criteria when setting evaluation criteria, taking into account the crew's geographical location information. Geographical location information includes, but is not limited to, GPS data, location information services, and map data. For example, if a crew member is providing customer service in a specific area, the evaluation criteria setting unit can set evaluation criteria related to that area. The evaluation criteria setting unit can also set evaluation criteria related to the crew member's current location if the crew member is on the move. Furthermore, if a crew member is providing customer service at a specific store, the evaluation criteria setting unit can also set evaluation criteria related to that store. This allows for the setting of more relevant evaluation criteria by taking into account the crew member's geographical location information. Some or all of the above processing in the evaluation criteria setting unit may be performed using, for example, AI, or not using AI. For example, the evaluation criteria setting unit can set evaluation criteria using an AI model that selects the optimal criteria considering the crew member's geographical location information.

[0104] The visual feedback unit can estimate the user's emotions and adjust the display method of the visual feedback based on the estimated emotions. Methods for estimating user emotions include, but are not limited to, facial expression recognition, speech analysis, and text analysis. For example, the visual feedback unit can estimate the user's emotions using facial expression recognition technology. It can also estimate user emotions using speech analysis technology. Furthermore, it can estimate user emotions using text analysis technology. Methods for displaying visual feedback include, but are not limited to, display format, display timing, and display content. For example, the visual feedback unit can provide detailed visual feedback when the user is relaxed. It can also provide concise visual feedback when the user is stressed. Furthermore, it can provide visual feedback including specific areas for improvement when the user is focused. This allows for more effective feedback by adjusting the display method of visual feedback based on the user's emotions. Some or all of the processing described above in the visual feedback unit may be performed using AI, for example, or without AI. For example, the visual feedback unit can adjust the display method of the visual feedback using an AI model that estimates the user's emotions and adjusts the display method of the visual feedback based on the estimated user emotions.

[0105] The visual feedback unit can select the optimal display method by referring to the crew's past feedback history when displaying visual feedback. The visual feedback unit selects the optimal display method by referring to the crew's past feedback history when displaying visual feedback. Past feedback history includes, but is not limited to, feedback records, feedback results, and feedback content. For example, the visual feedback unit can refer to the crew's past feedback history and provide a similar display method. The visual feedback unit can also refer to the crew's past feedback history and provide a different display method. Furthermore, the visual feedback unit can refer to the crew's past feedback history and provide a display method that corresponds to a specific customer segment. This allows the optimal display method to be selected by referring to past feedback history. Some or all of the above processing in the visual feedback unit may be performed using, for example, AI, or not using AI. For example, the visual feedback unit can select a display method using an AI model that selects the optimal display method by referring to the crew's past feedback history.

[0106] The visual feedback unit can estimate the user's emotions and adjust the visual feedback operation procedure based on the estimated user emotions. Methods for estimating user emotions include, but are not limited to, facial expression recognition, speech analysis, and text analysis. For example, the visual feedback unit can estimate user emotions using facial expression recognition technology. It can also estimate user emotions using speech analysis technology. Furthermore, it can also estimate user emotions using text analysis technology. Methods for adjusting the operation procedure include, but are not limited to, the flow of operations, difficulty of operations, and timing of operations. For example, if the user is relaxed, the visual feedback unit can provide detailed operation instructions. If the user is stressed, it can also provide concise operation instructions. Furthermore, if the user is focused, it can provide operation instructions that include specific areas for improvement. This allows for more effective feedback by adjusting the operation procedure based on the user's emotions. Some or all of the processing described above in the visual feedback unit may be performed using AI, for example, or without AI. For example, the visual feedback unit can adjust the operation procedure using an AI model that estimates the user's emotions and adjusts the operation procedure based on the estimated user emotions.

[0107] The visual feedback unit can select the optimal display method when displaying visual feedback, taking into account the crew's device information. The visual feedback unit selects the optimal display method when displaying visual feedback, taking into account the crew's device information. Device information includes, but is not limited to, the type of device, device performance, and device settings. For example, if the crew is using a smartphone, the visual feedback unit provides a display method adapted to the screen size. Furthermore, if the crew is using a tablet, the visual feedback unit can provide a display method optimized for a larger screen. In addition, if the crew is using a smartwatch, the visual feedback unit can provide a concise and highly visible display method. Thus, by considering the crew's device information, the optimal display method can be provided. Some or all of the above processing in the visual feedback unit may be performed using, for example, AI, or not. For example, the visual feedback unit can select a display method using an AI model that selects the optimal display method considering the crew's device information.

[0108] The anonymization unit can estimate the user's emotions and adjust the anonymization method based on the estimated emotions. Methods for estimating user emotions include, but are not limited to, facial expression recognition, speech analysis, and text analysis. For example, the anonymization unit can estimate user emotions using facial expression recognition technology. The anonymization unit can also estimate user emotions using speech analysis technology. Furthermore, the anonymization unit can also estimate user emotions using text analysis technology. Methods for anonymization include, but are not limited to, data masking, pseudo-anonymization, and complete anonymization. For example, the anonymization unit applies a standard anonymization method when the user is relaxed. It can also apply a simple anonymization method when the user is stressed. Furthermore, it can apply a detailed anonymization method when the user is focused. This allows for more appropriate anonymization by adjusting the anonymization method based on user emotions. Some or all of the above-described processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can adjust the anonymization method using an AI model that estimates the user's emotions and adjusts the anonymization method based on the estimated user emotions.

[0109] The anonymization unit can select the optimal anonymization method by referring to past anonymization data during the anonymization process. Past anonymization data includes, but is not limited to, records of anonymization, results of anonymization, and methods of anonymization. For example, the anonymization unit can select the optimal anonymization method by referring to past anonymization data. The anonymization unit can also adjust the hyperparameters of the anonymization algorithm by referring to past anonymization data. Furthermore, the anonymization unit can optimize the structure of the anonymization algorithm by referring to past anonymization data. This allows the anonymization unit to select the optimal anonymization method by referring to past anonymization data. Some or all of the above-described processes in the anonymization unit may be performed using, for example, AI, or not. For example, the anonymization unit can select an anonymization method using an AI model that selects the optimal anonymization method by referring to past anonymization data.

[0110] The anonymization unit can estimate the user's emotions and determine the priority of anonymization based on the estimated emotions. Methods for estimating user emotions include, but are not limited to, facial recognition, speech analysis, and text analysis. For example, the anonymization unit can estimate user emotions using facial recognition technology. It can also estimate user emotions using speech analysis technology. Furthermore, it can also estimate user emotions using text analysis technology. Methods for determining priority include, but are not limited to, evaluation of importance, evaluation of urgency, and resource allocation. For example, the anonymization unit prioritizes normal anonymization when the user is relaxed. It can also prioritize simple anonymization when the user is stressed. Furthermore, it can prioritize detailed anonymization when the user is focused. This allows for more appropriate anonymization by determining the priority of anonymization based on user emotions. Some or all of the above-described processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can determine the anonymization priority using an AI model that estimates the user's emotions and determines the anonymization priority based on the estimated user emotions.

[0111] The anonymization unit can select the optimal anonymization method when anonymizing, taking into account the crew's geographical location information. The anonymization unit selects the optimal anonymization method when anonymizing, taking into account the crew's geographical location information. Geographical location information includes, but is not limited to, GPS data, location information services, and map data. For example, if the crew is providing customer service in a specific area, the anonymization unit applies an anonymization method related to that area. The anonymization unit can also apply an anonymization method related to the current location if the crew is on the move. Furthermore, if the crew is providing customer service at a specific store, the anonymization unit can apply an anonymization method related to that store. In this way, the anonymization unit can provide the optimal anonymization method by taking into account the crew's geographical location information. Some or all of the above processing in the anonymization unit may be performed using, for example, AI, or not using AI. For example, the anonymization unit can select an anonymization method using an AI model that selects the optimal anonymization method considering the crew's geographical location information. === Hard Collateral 1-1 === Each of the multiple elements described above, including the data collection unit, learning unit, role-playing unit, feedback unit, evaluation criteria setting unit, visual feedback unit, and anonymization unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data collection unit collects customer service data using the camera 42 and microphone 38B of the smart device 14 and transmits it to the data processing unit 12 via the control unit 46A. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, and the AI ​​learns based on the collected data. The role-playing unit is implemented by the control unit 46A of the smart device 14, and the AI ​​professional crew responds in real time. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides feedback on the evaluation results. The evaluation criteria setting unit is implemented by the specific processing unit 290 of the data processing unit 12 and sets evaluation criteria. The visual feedback unit is implemented by the control unit 46A of the smart device 14 and provides the evaluation results visually. The anonymization unit is implemented by the specific processing unit 290 of the data processing unit 12 and anonymizes personal information. === Hard Collateral 1-2 === Each of the multiple elements described above, including the data collection unit, learning unit, role-playing unit, feedback unit, evaluation criteria setting unit, visual feedback unit, and anonymization unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit collects customer service data using the camera 42 and microphone 238 of the smart glasses 214 and transmits it to the data processing unit 12 via the control unit 46A. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, and the AI ​​learns based on the collected data. The role-playing unit is implemented by the control unit 46A of the smart glasses 214, and the AI ​​professional crew responds in real time. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides feedback on the evaluation results. The evaluation criteria setting unit is implemented by the specific processing unit 290 of the data processing unit 12 and sets evaluation criteria. The visual feedback unit is implemented by the control unit 46A of the smart glasses 214 and provides the evaluation results visually. The anonymization unit is implemented by the specific processing unit 290 of the data processing device 12, and anonymizes personal information. === Hard Collateral 1-3 === Each of the multiple elements described above, including the data collection unit, learning unit, role-playing unit, feedback unit, evaluation criteria setting unit, visual feedback unit, and anonymization unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data collection unit collects customer service data using the camera 42 and microphone 238 of the headset terminal 314 and transmits it to the data processing unit 12 via the control unit 46A. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, and the AI ​​learns based on the collected data. The role-playing unit is implemented by the control unit 46A of the headset terminal 314, and the AI ​​professional crew responds in real time. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides feedback on the evaluation results. The evaluation criteria setting unit is implemented by the specific processing unit 290 of the data processing unit 12 and sets evaluation criteria. The visual feedback unit is implemented by the control unit 46A of the headset terminal 314 and provides the evaluation results visually. The anonymization unit is implemented by the specific processing unit 290 of the data processing device 12, and anonymizes personal information. === Hard Collateral 1-4 === Each of the multiple elements described above, including the data collection unit, learning unit, role-playing unit, feedback unit, evaluation criteria setting unit, visual feedback unit, and anonymization unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the data collection unit collects customer service data using the camera 42 and microphone 238 of the robot 414 and transmits it to the data processing unit 12 via the control unit 46A. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, and the AI ​​learns based on the collected data. The role-playing unit is implemented by the control unit 46A of the robot 414, and the AI ​​professional crew responds in real time. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides feedback on the evaluation results. The evaluation criteria setting unit is implemented by the specific processing unit 290 of the data processing unit 12 and sets evaluation criteria. The visual feedback unit is implemented by the control unit 46A of the robot 414 and provides evaluation results visually. The anonymization unit is implemented by the specific processing unit 290 of the data processing unit 12 and anonymizes personal information.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] The training system can also include a difficulty adjustment unit that estimates the user's emotions and adjusts the training difficulty based on those emotions. For example, if the user is relaxed, it can provide training at a normal difficulty level. If the user is stressed, it can provide easier training. Furthermore, if the user is focused, it can provide more difficult training. By adjusting the training difficulty according to the user's emotions, more effective training becomes possible.

[0114] The training system can also include a feedback customization unit that estimates the user's emotions and customizes the training feedback based on those emotions. For example, if the user is relaxed, it can provide detailed feedback. If the user is stressed, it can provide concise feedback. Furthermore, if the user is focused, it can provide feedback that includes specific areas for improvement. By customizing feedback based on the user's emotions, more effective feedback becomes possible.

[0115] The training system can also include a scheduling unit that estimates the user's emotions and adjusts the training schedule based on those emotions. For example, if the user is relaxed, the training will proceed according to the normal schedule. If the user is stressed, the training frequency can be reduced. Furthermore, if the user is focused, the training frequency can be increased. By adjusting the training schedule based on the user's emotions, more effective training becomes possible.

[0116] The training system can also include a content customization unit that estimates the user's emotions and customizes the training content based on those emotions. For example, if the user is relaxed, it can provide standard training content. If the user is stressed, it can provide training content designed to promote relaxation. Furthermore, if the user is focused, it can provide more advanced training content. By customizing the training content based on the user's emotions, more effective training becomes possible.

[0117] The training system may also include an interface adjustment unit that estimates the user's emotions and adjusts the training interface based on those emotions. For example, if the user is relaxed, a normal interface may be provided. If the user is stressed, a simpler interface may be provided. Furthermore, if the user is focused, an interface containing detailed information may be provided. This allows for more effective training by adjusting the interface based on the user's emotions.

[0118] The training system can also include a plan suggestion unit that analyzes the user's past training data and proposes an optimal training plan. For example, it can identify the user's weaknesses based on past training data and propose a training plan to overcome those weaknesses. It can also propose a training plan to strengthen the user's strengths based on past training data. Furthermore, it can propose a training plan tailored to the user's progress based on past training data. This allows for the provision of more effective training plans by utilizing past training data.

[0119] The training system can also include a location-based customization unit that customizes the training content by taking into account the user's geographical location. For example, if the user is providing customer service in a specific area, the system can provide training content relevant to that area. Furthermore, if the user is on the move, the system can provide training content relevant to their current location. Additionally, if the user is providing customer service at a specific store, the system can provide training content relevant to that store. This allows for the provision of more relevant training content by considering the user's geographical location.

[0120] The training system can also include a social media customization section that analyzes users' social media activity and customizes the training content. For example, it can analyze users' social media activity and provide training content related to specific trends. It can also analyze users' social media activity and provide training content related to specific customer segments. Furthermore, it can analyze users' social media activity and provide training content related to specific products. This allows for the analysis of users' social media activity and the provision of more relevant training content.

[0121] The training system can also include a device customization section that customizes the training interface considering the user's device information. For example, if the user is using a smartphone, it can provide an interface that matches the screen size. If the user is using a tablet, it can provide an interface optimized for a larger screen. Furthermore, if the user is using a smartwatch, it can provide a concise and highly visible interface. This allows for the provision of the optimal interface considering the user's device information.

[0122] The training system can also include a feedback analysis unit that analyzes the user's past feedback data and customizes the content of the feedback. For example, it can identify the user's weaknesses based on past feedback data and provide feedback to overcome those weaknesses. It can also provide feedback to strengthen the user's strengths based on past feedback data. Furthermore, it can provide feedback tailored to the user's progress based on past feedback data. This allows for the provision of more effective feedback by utilizing past feedback data.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The data collection unit collects customer service data. This data includes audio, video, and text data. The data collection unit collects customer service data from highly productive and skilled crew members, and the collected data is converted into a format that is easy for AI to analyze. Step 2: The learning unit uses the data collected by the collection unit to train the AI. Learning is performed using algorithms such as neural networks and support vector machines, employing methods such as supervised learning, unsupervised learning, and reinforcement learning. Step 3: The role-playing team conducts role-playing using the AI ​​professional crew trained by the learning team. The role-playing is conducted based on the simulation content and the tools used, with the AI ​​professional crew responding in real time and evaluating customer service skills. Step 4: The Feedback Department provides feedback on the evaluation results of the role-playing conducted by the Role-Playing Department. The feedback is based on evaluation items, evaluation criteria, and feedback format, and evaluates aspects such as smiles, tone of voice, smoothness of responses, clarity of explanations, and persuasive sales talk.

[0125] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0126] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (for example, still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or Naive Bayes, and can perform a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0127] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0128] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0143] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0148] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0152] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0153] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0154] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0155] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0156] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0157] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0159] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0160] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] As shown in Figure 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.

[0163] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0164] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0165] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0167] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0168] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0169] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0170] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0171] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0172] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0173] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0174] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0175] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0176] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0177] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0178] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0179] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0180] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0181] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0182] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0183] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0184] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0185] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0186] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0187] 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.

[0188] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0189] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0190] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0191] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0192] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0193] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0194] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0195] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0196] [Explanation of Symbols]

[0197] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The data collection department collects customer service data, A learning unit in which the AI ​​learns based on the data collected by the aforementioned collection unit, A role-playing unit that performs role-playing using the AI ​​professional crew trained by the aforementioned learning unit, The system includes a feedback unit that provides feedback on the evaluation results of the role-playing performed by the role-playing unit. A system characterized by the following features.

2. It includes an evaluation criteria setting unit for setting evaluation criteria. The system according to feature 1.

3. It features a visual feedback unit that provides feedback visually. The system according to feature 1.

4. It is equipped with an anonymization unit that anonymizes personal information during data collection. The system according to feature 1.

5. The aforementioned collection unit is Collect customer service data from highly productive or highly skilled crew members. The system according to feature 1.

6. The aforementioned learning unit, The AI ​​learns based on the collected data. The system according to feature 1.

7. The aforementioned role-playing section is Role-playing will be conducted using the trained AI professional crew. The system according to feature 1.

8. The aforementioned feedback unit is We evaluate smiles, tone of voice, smoothness of responses, clarity of explanations, and persuasive sales pitches. The system according to claim 3.

9. The aforementioned collection unit is We estimate the user's emotions and adjust the timing of customer service data collection based on the estimated user emotions. The system according to feature 1.

Images