System

Abstract

An object of the system according to the embodiment is to effectively perform training for customer service and improve the quality of the hospitality industry.SOLUTION: A system according to an embodiment includes a simulator, a trainer, and an evaluator. The simulation unit simulates the personality and emotion of the customer. The training unit performs training based on the scenario corresponding to the customer simulated by the simulation unit. The evaluation unit evaluates a result of the training performed by the training unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques do not adequately train staff in customer service, leaving room for improvement in quality.

[0005] The system according to the embodiment aims to effectively provide training in customer service and improve the quality of customer service. [Means for solving the problem]

[0006] The system according to the embodiment includes a simulation unit, a training unit, and an evaluation unit. The simulation unit simulates the personality and emotions of customers. The training unit conducts training based on the customer interaction scenarios simulated by the simulation unit. The evaluation unit evaluates the results of the training conducted by the training unit. [Effects of the Invention]

[0007] The system according to the embodiment can effectively provide training in customer service and improve the quality of customer service. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example 1) A customer service training system according to an embodiment of the present invention simulates customer personalities and emotions to provide training and evaluation. This system uses a generative AI to recreate various customer personalities, recreating a variety of situations, including customers unsure about a contract, customers anxious about a product, and customers angry about dissatisfaction. For example, in a customer service training system, the generative AI simulates customer personalities and emotions to generate realistic customer service scenarios. Then, training for new employees and quality improvement is conducted based on the customer service scenarios recreated by the generative AI. For example, for a customer anxious about a product, the generative AI recreates that anxiety, allowing employees to learn appropriate explanations and ways to respond. For a customer angry about a dissatisfaction, the generative AI recreates the cause of that anger, allowing employees to learn calm and appropriate ways to respond. This allows the customer service training system to effectively train new employees and improve quality for those involved in customer service, thereby improving their on-site skills. This allows the customer service training system to effectively train new employees and improve quality for those involved in customer service, thereby improving their on-site skills. For example, for customers who are unsure about a contract, the AI ​​can learn how to provide appropriate explanations and persuade them through scenarios recreated by the AI. For customers who are unsure about a product, the AI ​​can learn how to provide appropriate explanations and reassure them through scenarios recreated by the AI. Furthermore, for customers who are angry because they are not satisfied, the AI ​​can learn how to respond calmly and appropriately through scenarios recreated by the AI.

[0029] A customer service training system according to an embodiment includes a simulation unit, a training unit, and an evaluation unit. The simulation unit simulates a customer's personality and emotions. The simulation unit simulates the customer's personality and emotions using, for example, a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and can realistically reproduce a customer's personality traits and emotions. For example, the generation AI simulates a customer's behavior patterns and reactions based on the customer's personality traits. The generation AI can also simulate a customer's emotions and reproduce changes in the customer's emotions in real time. The training unit conducts training based on customer service scenarios simulated by the simulation unit. The training unit conducts training for people involved in the customer service industry based on, for example, customer service scenarios simulated using the generation AI. For example, the training unit can learn appropriate response methods based on the customer service scenarios simulated by the generation AI. The training unit can also conduct training to improve on-site response capabilities based on the scenarios simulated by the generation AI. The evaluation unit evaluates the results of the training conducted by the training unit. For example, the evaluation unit evaluates the results of the training using, for example, the generation AI. The generation AI can evaluate the effectiveness of the training based on the training results and provide feedback. For example, the evaluation unit analyzes the training results and evaluates the effectiveness of the training by the generation AI. The evaluation unit can also point out areas for improvement in the training based on the training results by the generation AI. As a result, the customer service training system according to the embodiment effectively trains new employees involved in the customer service industry and provides training to improve quality, thereby improving response capabilities in actual work settings.

[0030] The simulation unit can simulate the customer's personality and emotions using a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and can realistically reproduce the customer's personality traits and emotions. For example, the generation AI can simulate the customer's behavioral patterns and reactions based on the customer's personality traits. The generation AI can also simulate the customer's emotions and reproduce changes in the customer's emotions in real time. This allows the use of the generation AI to simulate the customer's personality and emotions with high accuracy. For example, the generation AI can simulate the customer's behavioral patterns and reactions based on the customer's personality traits. The generation AI can also simulate the customer's emotions and reproduce changes in the customer's emotions in real time.

[0031] The simulation unit can use generation AI to simulate the reasons for a customer's hesitation to enter into a contract. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and can realistically reproduce the reasons for a customer's hesitation to enter into a contract. For example, the generation AI can identify the reasons for a customer's hesitation and simulate the customer's behavioral patterns and reactions based on those reasons. The generation AI can also simulate the reasons for a customer's hesitation and reproduce the reasons for the customer's hesitation in real time. This allows the system to learn appropriate ways to respond by simulating the reasons for a customer's hesitation to enter into a contract. For example, the generation AI can identify the reasons for a customer's hesitation and simulate the customer's behavioral patterns and reactions based on those reasons. The generation AI can also simulate the reasons for a customer's hesitation and reproduce the reasons for the customer's hesitation in real time.

[0032] The simulation unit can use a generation AI to simulate the anxiety of customers who are unsure about a product. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and can realistically reproduce the anxiety of customers who are unsure about a product. For example, the generation AI can identify the cause of a customer's anxiety and simulate the customer's behavioral patterns and reactions based on that cause. The generation AI can also simulate customer anxiety and reproduce the cause of the customer's anxiety in real time. This makes it possible to learn appropriate explanations and ways of responding by simulating the anxiety of customers who are unsure about a product. For example, the generation AI can identify the cause of a customer's anxiety and simulate the customer's behavioral patterns and reactions based on that cause. The generation AI can also simulate customer anxiety and reproduce the cause of the customer's anxiety in real time.

[0033] The simulation unit can use the generation AI to simulate the causes of a customer's anger when they are not satisfied with something. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and can realistically reproduce the causes of a customer's anger when they are not satisfied with something. For example, the generation AI can identify the causes of a customer's anger and simulate the customer's behavioral patterns and reactions based on those causes. The generation AI can also simulate the causes of a customer's anger and reproduce the causes of the customer's anger in real time. This allows the system to learn how to respond calmly and appropriately by simulating the causes of a customer's anger when they are not satisfied with something. For example, the generation AI can identify the causes of a customer's anger and simulate the customer's behavioral patterns and reactions based on those causes. The generation AI can also simulate the causes of a customer's anger and reproduce the causes of the customer's anger in real time.

[0034] The training department can perform training based on customer interaction scenarios simulated by the generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and can perform training based on simulated customer interaction scenarios. For example, the generation AI can learn appropriate response methods based on customer interaction scenarios. The generation AI can also perform training to improve response capabilities in actual on-site situations based on simulated scenarios. In this way, by using the generation AI, training based on simulated customer interaction scenarios can be effectively performed. For example, the generation AI can learn appropriate response methods based on customer interaction scenarios. The generation AI can also perform training to improve response capabilities in actual on-site situations based on simulated scenarios.

[0035] The evaluation unit can evaluate the training results using the generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and can evaluate the training results. The generation AI can evaluate the effectiveness of the training based on the training results and provide feedback. For example, the generation AI analyzes the training results and evaluates the effectiveness of the training. The generation AI can also point out areas for improvement in the training based on the training results. In this way, the use of the generation AI can accurately evaluate the training results. For example, the generation AI analyzes the training results and evaluates the effectiveness of the training. The generation AI can also point out areas for improvement in the training based on the training results.

[0036] The simulation unit can analyze a customer's past behavioral history and generate an optimal simulation scenario. The simulation unit can, for example, use a generation AI to analyze a customer's past behavioral history and generate an optimal simulation scenario. For example, the generation AI can analyze a customer's past purchase history and generate a scenario based on similar situations. The generation AI can also analyze a customer's past complaint history and generate a response scenario for a similar problem. Furthermore, the generation AI can analyze a customer's past feedback and generate a scenario tailored to the customer's preferences. In this way, by analyzing a customer's past behavioral history, more appropriate simulation scenarios can be generated. For example, the generation AI can analyze a customer's past purchase history and generate a scenario based on similar situations. The generation AI can also analyze a customer's past complaint history and generate a response scenario for a similar problem. Furthermore, the generation AI can analyze a customer's past feedback and generate a scenario tailored to the customer's preferences.

[0037] The simulation unit can take into account the customer's cultural background and language when simulating the customer's personality and emotions. The simulation unit can take into account the customer's cultural background and language, for example, when using the generation AI to simulate the customer's personality and emotions. For example, the generation AI can take into account the customer's cultural background and generate a response scenario appropriate for the culture. The generation AI can also take into account the customer's language and generate a response scenario appropriate for the language. Furthermore, the generation AI can combine the customer's cultural background and language to generate an optimal response scenario. In this way, by taking the customer's cultural background and language into consideration, a more appropriate response scenario can be generated. For example, the generation AI can take into account the customer's cultural background and generate a response scenario appropriate for the culture. The generation AI can also take into account the customer's language and generate a response scenario appropriate for the language. Furthermore, the generation AI can combine the customer's cultural background and language to generate an optimal response scenario.

[0038] The simulation unit can generate region-specific customer interaction scenarios by taking into account the geographical location information of the customer. The simulation unit can generate region-specific customer interaction scenarios by taking into account the geographical location information of the customer using, for example, a generation AI. For example, the generation AI can generate scenarios based on region-specific cultures and customs by taking into account the geographical location information of the customer. The generation AI can also generate scenarios based on region-specific languages ​​or dialects by taking into account the geographical location information of the customer. Furthermore, the generation AI can generate scenarios based on region-specific problems and challenges by taking into account the geographical location information of the customer. In this way, region-specific customer interaction scenarios can be generated by taking into account the geographical location information of the customer. For example, the generation AI can generate scenarios based on region-specific cultures and customs by taking into account the geographical location information of the customer. The generation AI can also generate scenarios based on region-specific languages ​​or dialects by taking into account the geographical location information of the customer. Furthermore, the generation AI can generate scenarios based on region-specific problems and challenges by taking into account the geographical location information of the customer.

[0039] The simulation unit can analyze the customer's social media activity and generate a related simulation scenario. The simulation unit can, for example, use a generation AI to analyze the customer's social media activity and generate a related simulation scenario. For example, the generation AI can analyze the customer's social media activity and generate a scenario based on the customer's interests and concerns. The generation AI can also analyze the customer's social media activity and generate a scenario based on the customer's past posts. Furthermore, the generation AI can analyze the customer's social media activity and generate a scenario based on the activities of the customer's friends and followers. This makes it possible to generate more appropriate simulation scenarios by analyzing the customer's social media activity. For example, the generation AI can analyze the customer's social media activity and generate a scenario based on the customer's interests and concerns. The generation AI can also analyze the customer's social media activity and generate a scenario based on the customer's past posts. Furthermore, the generation AI can analyze the customer's social media activity and generate a scenario based on the activities of the customer's friends and followers.

[0040] The simulation unit can customize the simulation scenario by reflecting the customer's past feedback. The simulation unit can customize the simulation scenario by using, for example, a generation AI to reflect the customer's past feedback. For example, the generation AI can analyze the customer's past feedback and generate a scenario that matches the customer's preferences. The generation AI can also analyze the customer's past feedback and generate a scenario to resolve the customer's dissatisfaction. Furthermore, the generation AI can analyze the customer's past feedback and generate a scenario to meet the customer's expectations. In this way, by reflecting the customer's past feedback, a more appropriate simulation scenario can be generated. For example, the generation AI can analyze the customer's past feedback and generate a scenario that matches the customer's preferences. The generation AI can also analyze the customer's past feedback and generate a scenario to resolve the customer's dissatisfaction. Furthermore, the generation AI can analyze the customer's past feedback and generate a scenario to meet the customer's expectations.

[0041] The training unit can apply different training algorithms during training depending on the customer's personality and emotions. The training unit can apply different training algorithms during training using, for example, a generation AI depending on the customer's personality and emotions. For example, the generation AI can analyze the customer's personality and apply a gentle training algorithm to introverted customers. The generation AI can also analyze the customer's personality and apply an aggressive training algorithm to extroverted customers. Furthermore, the generation AI can analyze the customer's emotions and dynamically adjust the training algorithm according to changes in emotions. This enables more effective training by applying training algorithms according to the customer's personality and emotions. For example, the generation AI can analyze the customer's personality and apply a gentle training algorithm to introverted customers. The generation AI can also analyze the customer's personality and apply an aggressive training algorithm to extroverted customers. Furthermore, the generation AI can analyze the customer's emotions and dynamically adjust the training algorithm according to changes in emotions.

[0042] The training unit can improve the accuracy of training by referring to past training results during training. The training unit can improve the accuracy of training by referring to past training results during training, for example, using a generation AI. For example, the generation AI can analyze past training results and provide feedback to improve the accuracy of training. The generation AI can also analyze past training results and optimize the training content. Furthermore, the generation AI can analyze past training results and adjust the algorithm to maximize the effectiveness of training. In this way, the accuracy of training is improved by referring to past training results. For example, the generation AI can analyze past training results and provide feedback to improve the accuracy of training. The generation AI can also analyze past training results and optimize the training content. Furthermore, the generation AI can analyze past training results and adjust the algorithm to maximize the effectiveness of training.

[0043] The training department can determine the priority of training based on the timing of customer submission during training. The training department can determine the priority of training based on the timing of customer submission during training, for example, using generation AI. For example, the generation AI can analyze the timing of customer submission and prioritize training that was submitted early. The generation AI can also analyze the timing of customer submission and prioritize training that is delayed. Furthermore, the generation AI can analyze the timing of customer submission and prioritize training that is close to the deadline. In this way, efficient training can be achieved by prioritizing training based on the timing of customer submission. For example, the generation AI can analyze the timing of customer submission and prioritize training that was submitted early. The generation AI can also analyze the timing of customer submission and prioritize training that is delayed. Furthermore, the generation AI can analyze the timing of customer submission and prioritize training that is close to the deadline.

[0044] The training department can adjust the order of training based on the relevance of the customer during training. The training department can adjust the order of training based on the relevance of the customer during training, for example, using a generation AI. For example, the generation AI analyzes the relevance of the customer and prioritizes highly relevant training. The generation AI can also analyze the relevance of the customer and postpone less relevant training. Furthermore, the generation AI can analyze the relevance of the customer and optimize the order of training based on relevance. As a result, adjusting the order of training based on the relevance of the customer enables efficient training. For example, the generation AI analyzes the relevance of the customer and prioritizes highly relevant training. The generation AI can also analyze the relevance of the customer and postpone less relevant training. Furthermore, the generation AI can analyze the relevance of the customer and optimize the order of training based on relevance.

[0045] The training department can adjust the use of technical terms during training according to the customer's level of expertise. For example, the training department can use a generation AI to adjust the use of technical terms during training according to the customer's level of expertise. For example, the generation AI can analyze the customer's level of expertise and avoid technical terms in training for beginners. The generation AI can also analyze the customer's level of expertise and actively use technical terms in training for advanced users. The generation AI can also analyze the customer's level of expertise and use technical terms moderately in training for intermediate users. This allows for more effective training by adjusting the use of technical terms during training according to the customer's level of expertise. For example, the generation AI can analyze the customer's level of expertise and avoid technical terms in training for beginners. The generation AI can also analyze the customer's level of expertise and actively use technical terms in training for advanced users. The generation AI can also analyze the customer's level of expertise and use technical terms moderately in training for intermediate users.

[0046] The evaluation unit can analyze the training results in detail during evaluation to improve the accuracy of the evaluation. The evaluation unit can analyze the training results in detail during evaluation, for example, using a generation AI to improve the accuracy of the evaluation. For example, the generation AI can analyze the training results in detail and provide feedback to improve the accuracy of the evaluation. The generation AI can also analyze the training results in detail and optimize the evaluation criteria. Furthermore, the generation AI can analyze the training results in detail and adjust the algorithm to maximize the effectiveness of the evaluation. In this way, the accuracy of the evaluation is improved by analyzing the training results in detail. For example, the generation AI can analyze the training results in detail and provide feedback to improve the accuracy of the evaluation. The generation AI can also analyze the training results in detail and optimize the evaluation criteria. Furthermore, the generation AI can analyze the training results in detail and adjust the algorithm to maximize the effectiveness of the evaluation.

[0047] The evaluation unit can record the training process during evaluation so that it can be re-evaluated later. The evaluation unit can, for example, use the generation AI to record the training process during evaluation so that it can be re-evaluated later. For example, the generation AI can record the training process so that it can be re-evaluated later. The generation AI can also record the training process and provide data for improving the accuracy of the evaluation. Furthermore, the generation AI can record the training process and adjust the algorithm for maximizing the effectiveness of the evaluation. In this way, recording the training process makes it possible to re-evaluate later. For example, the generation AI can record the training process so that it can be re-evaluated later. Furthermore, the generation AI can record the training process and provide data for improving the accuracy of the evaluation. Furthermore, the generation AI can record the training process and adjust the algorithm for maximizing the effectiveness of the evaluation.

[0048] The evaluation unit can set evaluation criteria by taking into account the geographical location information of the customer during evaluation. The evaluation unit can set evaluation criteria by taking into account the geographical location information of the customer, for example, using the generation AI during evaluation. For example, the generation AI can take into account the geographical location information of the customer and set evaluation criteria based on the culture and customs specific to the region. The generation AI can also take into account the geographical location information of the customer and set evaluation criteria based on the language or dialect specific to the region. Furthermore, the generation AI can take into account the geographical location information of the customer and set evaluation criteria based on the problems and challenges specific to the region. In this way, region-specific evaluation criteria can be set by taking into account the geographical location information of the customer. For example, the generation AI can take into account the geographical location information of the customer and set evaluation criteria based on the culture and customs specific to the region. The generation AI can also take into account the geographical location information of the customer and set evaluation criteria based on the language or dialect specific to the region. Furthermore, the generation AI can take into account the geographical location information of the customer and set evaluation criteria based on the problems and challenges specific to the region.

[0049] The evaluation unit can analyze the customer's social media activity and set relevant evaluation criteria during evaluation. The evaluation unit can, for example, use the generation AI to analyze the customer's social media activity and set relevant evaluation criteria during evaluation. For example, the generation AI can analyze the customer's social media activity and set evaluation criteria based on the customer's interests and concerns. The generation AI can also analyze the customer's social media activity and set evaluation criteria based on the customer's past posts. Furthermore, the generation AI can analyze the customer's social media activity and set evaluation criteria based on the activities of the customer's friends and followers. In this way, by analyzing the customer's social media activity, more appropriate evaluation criteria can be set. For example, the generation AI can analyze the customer's social media activity and set evaluation criteria based on the customer's interests and concerns. The generation AI can also analyze the customer's social media activity and set evaluation criteria based on the customer's past posts. Furthermore, the generation AI can analyze the customer's social media activity and set evaluation criteria based on the customer's friends and followers.

[0050] The evaluation unit can customize the evaluation criteria by reflecting the customer's past feedback when making an evaluation. The evaluation unit can customize the evaluation criteria by reflecting the customer's past feedback when making an evaluation, for example, using the generation AI. For example, the generation AI can analyze the customer's past feedback and set evaluation criteria that match the customer's preferences. The generation AI can also analyze the customer's past feedback and set evaluation criteria to resolve the customer's dissatisfaction points. The generation AI can also analyze the customer's past feedback and set evaluation criteria to meet the customer's expectations. In this way, by reflecting the customer's past feedback, more appropriate evaluation criteria can be set. For example, the generation AI can analyze the customer's past feedback and set evaluation criteria that match the customer's preferences. The generation AI can also analyze the customer's past feedback and set evaluation criteria to resolve the customer's dissatisfaction points. The generation AI can also analyze the customer's past feedback and set evaluation criteria to meet the customer's expectations.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The customer-facing training system can further include a "feedback section." The feedback section provides individual feedback based on the results of the training. For example, the feedback section may specifically point out mistakes made during training and areas for improvement, and provide advice for the next training session. The feedback section can also monitor the progress of training in real time and adjust the training content as necessary. Furthermore, the feedback section can evaluate the effectiveness of the training and propose a plan for long-term skill improvement. This maximizes the effectiveness of training and enables flexible responses to individual training needs.

[0053] The customer service training system can further include a "data collection unit." The data collection unit collects and analyzes audio and video data during training. For example, the data collection unit converts the content of conversations during training into text and analyzes it using natural language processing technology. The data collection unit can also analyze facial expressions and gestures during training to point out areas for improvement in non-verbal communication. Furthermore, the data collection unit can measure stress levels and concentration levels during training to evaluate the effectiveness of the training. This improves the quality of training and enables more effective acquisition of customer service skills.

[0054] The customer service training system can further include a "scenario generation unit." The scenario generation unit automatically generates optimal training scenarios according to the purpose and target of the training. For example, the scenario generation unit can generate a wide range of training scenarios, from basic scenarios for new employees to advanced scenarios for advanced employees. The scenario generation unit can also generate scenarios specialized for specific industries or tasks to provide practical training. Furthermore, the scenario generation unit can dynamically adjust the scenarios based on the progress of the training and feedback. This maximizes the effectiveness of the training and enables flexible responses to individual training needs.

[0055] The customer service training system can further include a "performance evaluation unit." The performance evaluation unit evaluates performance during training in real time and provides feedback. For example, the performance evaluation unit analyzes the content of conversations and behavior during training and evaluates appropriate response methods. The performance evaluation unit can also specifically point out mistakes and areas for improvement during training and provide advice for the next training session. Furthermore, the performance evaluation unit can monitor the progress of training and adjust the training content as necessary. This maximizes the effectiveness of training and enables flexible responses to individual training needs.

[0056] The customer-facing training system can further include a "learning history management unit." The learning history management unit records the learning history of training participants and provides individual learning plans. For example, the learning history management unit records past training content and evaluation results and reflects them in the next training. The learning history management unit can also provide individual learning plans based on the training progress. Furthermore, the learning history management unit can evaluate the effectiveness of training and propose plans for long-term skill improvement. This maximizes the effectiveness of training and enables flexible responses to individual training needs.

[0057] The customer service training system can also be equipped with a "virtual reality section." The virtual reality section uses VR technology to provide a more realistic training environment. For example, the virtual reality section can recreate an actual store or office environment, allowing training participants to simulate actual on-site responses. The virtual reality section can also generate various scenarios in real time to maximize the effectiveness of training. Furthermore, the virtual reality section can evaluate performance during training in real time and provide feedback. This improves the quality of training and enables participants to acquire more effective customer service skills.

[0058] The customer-facing training system can further include a "personalized training department." The personalized training department customizes the training content according to the individual needs and goals of the training participants. For example, the personalized training department provides an optimal training plan based on the participant's past training history and evaluation results. The personalized training department can also adjust the training content according to the participant's skill level and learning style. Furthermore, the personalized training department can dynamically adjust the training plan according to the training progress. This maximizes the effectiveness of the training and enables flexible response to individual training needs.

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

[0060] Step 1: The simulation unit simulates the customer's personality and emotions. For example, a generation AI is used to simulate the customer's personality and emotions. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and can realistically reproduce the customer's personality traits and emotions. The generation AI can simulate the customer's behavioral patterns and reactions based on the customer's personality traits, and can also reproduce changes in the customer's emotions in real time. Step 2: The training department conducts training based on the customer interaction scenarios simulated by the simulation department. For example, training is provided to people involved in customer service based on customer interaction scenarios simulated using the generation AI. Based on the customer interaction scenarios simulated by the generation AI, appropriate response methods can be learned and training can be provided to improve response capabilities in actual workplaces. Step 3: The evaluation unit evaluates the results of the training conducted by the training unit. For example, the evaluation unit uses a generation AI to evaluate the training results. The generation AI can evaluate the effectiveness of the training based on the training results and provide feedback. The generation AI can also analyze the training results, evaluate the effectiveness of the training, and point out areas for improvement.

[0061] (Example 2) A customer service training system according to an embodiment of the present invention simulates customer personalities and emotions to provide training and evaluation. This system uses a generative AI to recreate various customer personalities, recreating a variety of situations, including customers unsure about a contract, customers anxious about a product, and customers angry about dissatisfaction. For example, in a customer service training system, the generative AI simulates customer personalities and emotions to generate realistic customer service scenarios. Then, training for new employees and quality improvement is conducted based on the customer service scenarios recreated by the generative AI. For example, for a customer anxious about a product, the generative AI recreates that anxiety, allowing employees to learn appropriate explanations and ways to respond. For a customer angry about a dissatisfaction, the generative AI recreates the cause of that anger, allowing employees to learn calm and appropriate ways to respond. This allows the customer service training system to effectively train new employees and improve quality for those involved in customer service, thereby improving their on-site skills. This allows the customer service training system to effectively train new employees and improve quality for those involved in customer service, thereby improving their on-site skills. For example, for customers who are unsure about a contract, the AI ​​can learn how to provide appropriate explanations and persuade them through scenarios recreated by the AI. For customers who are unsure about a product, the AI ​​can learn how to provide appropriate explanations and reassure them through scenarios recreated by the AI. Furthermore, for customers who are angry because they are not satisfied, the AI ​​can learn how to respond calmly and appropriately through scenarios recreated by the AI.

[0062] A customer service training system according to an embodiment includes a simulation unit, a training unit, and an evaluation unit. The simulation unit simulates a customer's personality and emotions. The simulation unit simulates the customer's personality and emotions using, for example, a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and can realistically reproduce a customer's personality traits and emotions. For example, the generation AI simulates a customer's behavior patterns and reactions based on the customer's personality traits. The generation AI can also simulate a customer's emotions and reproduce changes in the customer's emotions in real time. The training unit conducts training based on customer service scenarios simulated by the simulation unit. The training unit conducts training for people involved in the customer service industry based on, for example, customer service scenarios simulated using the generation AI. For example, the training unit can learn appropriate response methods based on the customer service scenarios simulated by the generation AI. The training unit can also conduct training to improve on-site response capabilities based on the scenarios simulated by the generation AI. The evaluation unit evaluates the results of the training conducted by the training unit. For example, the evaluation unit evaluates the results of the training using, for example, the generation AI. The generation AI can evaluate the effectiveness of the training based on the training results and provide feedback. For example, the evaluation unit analyzes the training results and evaluates the effectiveness of the training by the generation AI. The evaluation unit can also point out areas for improvement in the training based on the training results by the generation AI. As a result, the customer service training system according to the embodiment effectively trains new employees involved in the customer service industry and provides training to improve quality, thereby improving response capabilities in actual work settings.

[0063] The simulation unit can simulate the customer's personality and emotions using a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and can realistically reproduce the customer's personality traits and emotions. For example, the generation AI can simulate the customer's behavioral patterns and reactions based on the customer's personality traits. The generation AI can also simulate the customer's emotions and reproduce changes in the customer's emotions in real time. This allows the use of the generation AI to simulate the customer's personality and emotions with high accuracy. For example, the generation AI can simulate the customer's behavioral patterns and reactions based on the customer's personality traits. The generation AI can also simulate the customer's emotions and reproduce changes in the customer's emotions in real time.

[0064] The simulation unit can use generation AI to simulate the reasons for a customer's hesitation to enter into a contract. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and can realistically reproduce the reasons for a customer's hesitation to enter into a contract. For example, the generation AI can identify the reasons for a customer's hesitation and simulate the customer's behavioral patterns and reactions based on those reasons. The generation AI can also simulate the reasons for a customer's hesitation and reproduce the reasons for the customer's hesitation in real time. This allows the system to learn appropriate ways to respond by simulating the reasons for a customer's hesitation to enter into a contract. For example, the generation AI can identify the reasons for a customer's hesitation and simulate the customer's behavioral patterns and reactions based on those reasons. The generation AI can also simulate the reasons for a customer's hesitation and reproduce the reasons for the customer's hesitation in real time.

[0065] The simulation unit can use a generation AI to simulate the anxiety of customers who are unsure about a product. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and can realistically reproduce the anxiety of customers who are unsure about a product. For example, the generation AI can identify the cause of a customer's anxiety and simulate the customer's behavioral patterns and reactions based on that cause. The generation AI can also simulate customer anxiety and reproduce the cause of the customer's anxiety in real time. This makes it possible to learn appropriate explanations and ways of responding by simulating the anxiety of customers who are unsure about a product. For example, the generation AI can identify the cause of a customer's anxiety and simulate the customer's behavioral patterns and reactions based on that cause. The generation AI can also simulate customer anxiety and reproduce the cause of the customer's anxiety in real time.

[0066] The simulation unit can use the generation AI to simulate the causes of a customer's anger when they are not satisfied with something. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and can realistically reproduce the causes of a customer's anger when they are not satisfied with something. For example, the generation AI can identify the causes of a customer's anger and simulate the customer's behavioral patterns and reactions based on those causes. The generation AI can also simulate the causes of a customer's anger and reproduce the causes of the customer's anger in real time. This allows the system to learn how to respond calmly and appropriately by simulating the causes of a customer's anger when they are not satisfied with something. For example, the generation AI can identify the causes of a customer's anger and simulate the customer's behavioral patterns and reactions based on those causes. The generation AI can also simulate the causes of a customer's anger and reproduce the causes of the customer's anger in real time.

[0067] The training department can perform training based on customer interaction scenarios simulated by the generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and can perform training based on simulated customer interaction scenarios. For example, the generation AI can learn appropriate response methods based on customer interaction scenarios. The generation AI can also perform training to improve response capabilities in actual on-site situations based on simulated scenarios. In this way, by using the generation AI, training based on simulated customer interaction scenarios can be effectively performed. For example, the generation AI can learn appropriate response methods based on customer interaction scenarios. The generation AI can also perform training to improve response capabilities in actual on-site situations based on simulated scenarios.

[0068] The evaluation unit can evaluate the training results using the generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and can evaluate the training results. The generation AI can evaluate the effectiveness of the training based on the training results and provide feedback. For example, the generation AI analyzes the training results and evaluates the effectiveness of the training. The generation AI can also point out areas for improvement in the training based on the training results. In this way, the use of the generation AI can accurately evaluate the training results. For example, the generation AI analyzes the training results and evaluates the effectiveness of the training. The generation AI can also point out areas for improvement in the training based on the training results.

[0069] The simulation unit can estimate the customer's emotions and adjust the simulation scenario based on the estimated customer's emotions. The simulation unit can, for example, estimate the customer's emotions using a generation AI and adjust the simulation scenario based on the estimated customer's emotions. For example, if the generation AI estimates the customer's emotions and the customer is feeling anxious, it can generate a scenario to alleviate the anxiety. Also, if the generation AI estimates the customer's emotions and the customer is feeling angry, it can generate a scenario to calm the anger. Furthermore, if the generation AI estimates the customer's emotions and the customer is hesitating, it can generate a scenario to resolve the hesitating. This allows for more realistic training by adjusting the simulation scenario based on the customer's emotions. For example, if the generation AI estimates the customer's emotions and the customer is feeling anxious, it can generate a scenario to alleviate the anxiety. Also, if the generation AI estimates the customer's emotions and the customer is feeling angry, it can generate a scenario to calm the anger. Furthermore, if the generation AI estimates the customer's emotions and the customer is hesitating, it can generate a scenario to resolve the hesitating.

[0070] The simulation unit can analyze a customer's past behavioral history and generate an optimal simulation scenario. The simulation unit can, for example, use a generation AI to analyze a customer's past behavioral history and generate an optimal simulation scenario. For example, the generation AI can analyze a customer's past purchase history and generate a scenario based on similar situations. The generation AI can also analyze a customer's past complaint history and generate a response scenario for a similar problem. Furthermore, the generation AI can analyze a customer's past feedback and generate a scenario tailored to the customer's preferences. In this way, by analyzing a customer's past behavioral history, more appropriate simulation scenarios can be generated. For example, the generation AI can analyze a customer's past purchase history and generate a scenario based on similar situations. The generation AI can also analyze a customer's past complaint history and generate a response scenario for a similar problem. Furthermore, the generation AI can analyze a customer's past feedback and generate a scenario tailored to the customer's preferences.

[0071] The simulation unit can take into account the customer's cultural background and language when simulating the customer's personality and emotions. The simulation unit can take into account the customer's cultural background and language, for example, when using the generation AI to simulate the customer's personality and emotions. For example, the generation AI can take into account the customer's cultural background and generate a response scenario appropriate for the culture. The generation AI can also take into account the customer's language and generate a response scenario appropriate for the language. Furthermore, the generation AI can combine the customer's cultural background and language to generate an optimal response scenario. In this way, by taking the customer's cultural background and language into consideration, a more appropriate response scenario can be generated. For example, the generation AI can take into account the customer's cultural background and generate a response scenario appropriate for the culture. The generation AI can also take into account the customer's language and generate a response scenario appropriate for the language. Furthermore, the generation AI can combine the customer's cultural background and language to generate an optimal response scenario.

[0072] The simulation unit can simulate changes in customer emotions in real time and dynamically change the response method. The simulation unit can, for example, use a generation AI to simulate changes in customer emotions in real time and dynamically change the response method. For example, the generation AI can detect changes in customer emotions in real time and dynamically adjust the scenario. The generation AI can also change the response method in real time in response to changes in customer emotions. Furthermore, the generation AI can predict changes in customer emotions and prepare response methods in advance. This enables more appropriate responses by dynamically changing the response method in response to changes in customer emotions. For example, the generation AI can detect changes in customer emotions in real time and dynamically adjust the scenario. The generation AI can also change the response method in real time in response to changes in customer emotions. Furthermore, the generation AI can predict changes in customer emotions and prepare response methods in advance.

[0073] The simulation unit can estimate the customer's emotions and adjust the difficulty of the simulation based on the estimated customer's emotions. The simulation unit can, for example, estimate the customer's emotions using a generation AI and adjust the difficulty of the simulation based on the estimated customer's emotions. For example, if the generation AI estimates the customer's emotions and the customer is relaxed, it can generate a low-difficulty scenario. Also, if the generation AI estimates the customer's emotions and the customer is nervous, it can generate a high-difficulty scenario. Furthermore, if the generation AI estimates the customer's emotions and the customer is excited, it can generate a medium-difficulty scenario. This adjusts the difficulty of the simulation based on the customer's emotions, improving the effectiveness of training. For example, if the generation AI estimates the customer's emotions and the customer is relaxed, it can generate a low-difficulty scenario. Also, if the generation AI estimates the customer's emotions and the customer is nervous, it can generate a high-difficulty scenario. Furthermore, if the generation AI estimates the customer's emotions and the customer is excited, it can generate a medium-difficulty scenario.

[0074] The simulation unit can generate region-specific customer interaction scenarios by taking into account the geographical location information of the customer. The simulation unit can generate region-specific customer interaction scenarios by taking into account the geographical location information of the customer using, for example, a generation AI. For example, the generation AI can generate scenarios based on region-specific cultures and customs by taking into account the geographical location information of the customer. The generation AI can also generate scenarios based on region-specific languages ​​or dialects by taking into account the geographical location information of the customer. Furthermore, the generation AI can generate scenarios based on region-specific problems and challenges by taking into account the geographical location information of the customer. In this way, region-specific customer interaction scenarios can be generated by taking into account the geographical location information of the customer. For example, the generation AI can generate scenarios based on region-specific cultures and customs by taking into account the geographical location information of the customer. The generation AI can also generate scenarios based on region-specific languages ​​or dialects by taking into account the geographical location information of the customer. Furthermore, the generation AI can generate scenarios based on region-specific problems and challenges by taking into account the geographical location information of the customer.

[0075] The simulation unit can analyze the customer's social media activity and generate a related simulation scenario. The simulation unit can, for example, use a generation AI to analyze the customer's social media activity and generate a related simulation scenario. For example, the generation AI can analyze the customer's social media activity and generate a scenario based on the customer's interests and concerns. The generation AI can also analyze the customer's social media activity and generate a scenario based on the customer's past posts. Furthermore, the generation AI can analyze the customer's social media activity and generate a scenario based on the activities of the customer's friends and followers. This makes it possible to generate more appropriate simulation scenarios by analyzing the customer's social media activity. For example, the generation AI can analyze the customer's social media activity and generate a scenario based on the customer's interests and concerns. The generation AI can also analyze the customer's social media activity and generate a scenario based on the customer's past posts. Furthermore, the generation AI can analyze the customer's social media activity and generate a scenario based on the activities of the customer's friends and followers.

[0076] The simulation unit can customize the simulation scenario by reflecting the customer's past feedback. The simulation unit can customize the simulation scenario by using, for example, a generation AI to reflect the customer's past feedback. For example, the generation AI can analyze the customer's past feedback and generate a scenario that matches the customer's preferences. The generation AI can also analyze the customer's past feedback and generate a scenario to resolve the customer's dissatisfaction. Furthermore, the generation AI can analyze the customer's past feedback and generate a scenario to meet the customer's expectations. In this way, by reflecting the customer's past feedback, a more appropriate simulation scenario can be generated. For example, the generation AI can analyze the customer's past feedback and generate a scenario that matches the customer's preferences. The generation AI can also analyze the customer's past feedback and generate a scenario to resolve the customer's dissatisfaction. Furthermore, the generation AI can analyze the customer's past feedback and generate a scenario to meet the customer's expectations.

[0077] The training unit can estimate the customer's emotions and adjust the training content based on the estimated customer's emotions. The training unit can, for example, estimate the customer's emotions using a generation AI and adjust the training content based on the estimated customer's emotions. For example, if the generation AI estimates the customer's emotions and the customer is feeling anxious, it can provide training content to alleviate the anxiety. Also, if the generation AI estimates the customer's emotions and the customer is feeling angry, it can provide training content to calm the anger. Furthermore, if the generation AI estimates the customer's emotions and the customer is indecisive, it can provide training content to resolve the hesitation. In this way, adjusting the training content based on the customer's emotions enables more effective training. For example, if the generation AI estimates the customer's emotions and the customer is feeling anxious, it can provide training content to alleviate the anxiety. Also, if the generation AI estimates the customer's emotions and the customer is feeling anger, it can provide training content to calm the anger. Furthermore, if the generation AI estimates the customer's emotions and the customer is indecisive, it can provide training content to resolve the hesitation.

[0078] The training unit can apply different training algorithms during training depending on the customer's personality and emotions. The training unit can apply different training algorithms during training using, for example, a generation AI depending on the customer's personality and emotions. For example, the generation AI can analyze the customer's personality and apply a gentle training algorithm to introverted customers. The generation AI can also analyze the customer's personality and apply an aggressive training algorithm to extroverted customers. Furthermore, the generation AI can analyze the customer's emotions and dynamically adjust the training algorithm according to changes in emotions. This enables more effective training by applying training algorithms according to the customer's personality and emotions. For example, the generation AI can analyze the customer's personality and apply a gentle training algorithm to introverted customers. The generation AI can also analyze the customer's personality and apply an aggressive training algorithm to extroverted customers. Furthermore, the generation AI can analyze the customer's emotions and dynamically adjust the training algorithm according to changes in emotions.

[0079] The training unit can improve the accuracy of training by referring to past training results during training. The training unit can improve the accuracy of training by referring to past training results during training, for example, using a generation AI. For example, the generation AI can analyze past training results and provide feedback to improve the accuracy of training. The generation AI can also analyze past training results and optimize the training content. Furthermore, the generation AI can analyze past training results and adjust the algorithm to maximize the effectiveness of training. In this way, the accuracy of training is improved by referring to past training results. For example, the generation AI can analyze past training results and provide feedback to improve the accuracy of training. The generation AI can also analyze past training results and optimize the training content. Furthermore, the generation AI can analyze past training results and adjust the algorithm to maximize the effectiveness of training.

[0080] The training unit can dynamically change the training content in response to changes in the customer's emotions during training. The training unit can dynamically change the training content in response to changes in the customer's emotions during training, for example, using a generation AI. For example, the generation AI can detect changes in the customer's emotions in real time and dynamically adjust the training content. The generation AI can also adjust the speed at which the training progresses in response to changes in the customer's emotions. Furthermore, the generation AI can predict changes in the customer's emotions and prepare the training content in advance. This enables more effective training by dynamically changing the training content in response to changes in the customer's emotions. For example, the generation AI can detect changes in the customer's emotions in real time and dynamically adjust the training content. The generation AI can also adjust the speed at which the training progresses in response to changes in the customer's emotions. Furthermore, the generation AI can predict changes in the customer's emotions and prepare the training content in advance.

[0081] The training unit can estimate the customer's emotions and adjust the length of the training based on the estimated customer's emotions. The training unit can, for example, estimate the customer's emotions using a generation AI and adjust the length of the training based on the estimated customer's emotions. For example, if the generation AI estimates the customer's emotions and the customer is relaxed, it can provide a longer training session. Also, if the generation AI estimates the customer's emotions and the customer is nervous, it can provide a shorter training session. Furthermore, if the generation AI estimates the customer's emotions and the customer is excited, it can provide a training session of an appropriate length. This enables more effective training by adjusting the length of the training based on the customer's emotions. For example, if the generation AI estimates the customer's emotions and the customer is relaxed, it can provide a longer training session. Also, if the generation AI estimates the customer's emotions and the customer is nervous, it can provide a shorter training session. Furthermore, if the generation AI estimates the customer's emotions and the customer is excited, it can provide a training session of an appropriate length.

[0082] The training department can determine the priority of training based on the timing of customer submission during training. The training department can determine the priority of training based on the timing of customer submission during training, for example, using generation AI. For example, the generation AI can analyze the timing of customer submission and prioritize training that was submitted early. The generation AI can also analyze the timing of customer submission and prioritize training that is delayed. Furthermore, the generation AI can analyze the timing of customer submission and prioritize training that is close to the deadline. In this way, efficient training can be achieved by prioritizing training based on the timing of customer submission. For example, the generation AI can analyze the timing of customer submission and prioritize training that was submitted early. The generation AI can also analyze the timing of customer submission and prioritize training that is delayed. Furthermore, the generation AI can analyze the timing of customer submission and prioritize training that is close to the deadline.

[0083] The training department can adjust the order of training based on the relevance of the customer during training. The training department can adjust the order of training based on the relevance of the customer during training, for example, using a generation AI. For example, the generation AI analyzes the relevance of the customer and prioritizes highly relevant training. The generation AI can also analyze the relevance of the customer and postpone less relevant training. Furthermore, the generation AI can analyze the relevance of the customer and optimize the order of training based on relevance. As a result, adjusting the order of training based on the relevance of the customer enables efficient training. For example, the generation AI analyzes the relevance of the customer and prioritizes highly relevant training. The generation AI can also analyze the relevance of the customer and postpone less relevant training. Furthermore, the generation AI can analyze the relevance of the customer and optimize the order of training based on relevance.

[0084] The training department can adjust the use of technical terms during training according to the customer's level of expertise. For example, the training department can use a generation AI to adjust the use of technical terms during training according to the customer's level of expertise. For example, the generation AI can analyze the customer's level of expertise and avoid technical terms in training for beginners. The generation AI can also analyze the customer's level of expertise and actively use technical terms in training for advanced users. The generation AI can also analyze the customer's level of expertise and use technical terms moderately in training for intermediate users. This allows for more effective training by adjusting the use of technical terms during training according to the customer's level of expertise. For example, the generation AI can analyze the customer's level of expertise and avoid technical terms in training for beginners. The generation AI can also analyze the customer's level of expertise and actively use technical terms in training for advanced users. The generation AI can also analyze the customer's level of expertise and use technical terms moderately in training for intermediate users.

[0085] The evaluation unit can estimate the customer's emotions and adjust the evaluation criteria based on the estimated customer's emotions. The evaluation unit can, for example, estimate the customer's emotions using a generation AI and adjust the evaluation criteria based on the estimated customer's emotions. For example, if the generation AI estimates the customer's emotions and the customer is feeling anxious, it can set evaluation criteria to alleviate the anxiety. Also, if the generation AI estimates the customer's emotions and the customer is feeling angry, it can set evaluation criteria to calm the anger. Furthermore, if the generation AI estimates the customer's emotions and the customer is unsure, it can set evaluation criteria to resolve the unsure. This allows for more appropriate evaluation by adjusting the evaluation criteria based on the customer's emotions. For example, if the generation AI estimates the customer's emotions and the customer is feeling anxious, it can set evaluation criteria to alleviate the anxiety. Also, if the generation AI estimates the customer's emotions and the customer is feeling angry, it can set evaluation criteria to calm the anger. Furthermore, if the generation AI estimates the customer's emotions and the customer is unsure, it can set evaluation criteria to resolve the unsure.

[0086] The evaluation unit can analyze the training results in detail during evaluation to improve the accuracy of the evaluation. The evaluation unit can analyze the training results in detail during evaluation, for example, using a generation AI to improve the accuracy of the evaluation. For example, the generation AI can analyze the training results in detail and provide feedback to improve the accuracy of the evaluation. The generation AI can also analyze the training results in detail and optimize the evaluation criteria. Furthermore, the generation AI can analyze the training results in detail and adjust the algorithm to maximize the effectiveness of the evaluation. In this way, the accuracy of the evaluation is improved by analyzing the training results in detail. For example, the generation AI can analyze the training results in detail and provide feedback to improve the accuracy of the evaluation. The generation AI can also analyze the training results in detail and optimize the evaluation criteria. Furthermore, the generation AI can analyze the training results in detail and adjust the algorithm to maximize the effectiveness of the evaluation.

[0087] The evaluation unit can record the training process during evaluation so that it can be re-evaluated later. The evaluation unit can, for example, use the generation AI to record the training process during evaluation so that it can be re-evaluated later. For example, the generation AI can record the training process so that it can be re-evaluated later. The generation AI can also record the training process and provide data for improving the accuracy of the evaluation. Furthermore, the generation AI can record the training process and adjust the algorithm for maximizing the effectiveness of the evaluation. In this way, recording the training process makes it possible to re-evaluate later. For example, the generation AI can record the training process so that it can be re-evaluated later. Furthermore, the generation AI can record the training process and provide data for improving the accuracy of the evaluation. Furthermore, the generation AI can record the training process and adjust the algorithm for maximizing the effectiveness of the evaluation.

[0088] The evaluation unit can dynamically change the evaluation criteria during evaluation, taking into account changes in customer emotions. The evaluation unit can dynamically change the evaluation criteria during evaluation, taking into account changes in customer emotions, for example, using a generation AI. For example, the generation AI can detect changes in customer emotions in real time and dynamically adjust the evaluation criteria. The generation AI can also adjust the speed at which the evaluation progresses in accordance with changes in customer emotions. Furthermore, the generation AI can predict changes in customer emotions and prepare evaluation criteria in advance. This enables more appropriate evaluation by dynamically changing the evaluation criteria in accordance with changes in customer emotions. For example, the generation AI can detect changes in customer emotions in real time and dynamically adjust the evaluation criteria. The generation AI can also adjust the speed at which the evaluation progresses in accordance with changes in customer emotions. Furthermore, the generation AI can predict changes in customer emotions and prepare evaluation criteria in advance.

[0089] The evaluation unit can estimate the customer's emotions and adjust the display method of the evaluation based on the estimated customer's emotions. The evaluation unit can, for example, estimate the customer's emotions using a generation AI and adjust the display method of the evaluation based on the estimated customer's emotions. For example, if the generation AI estimates the customer's emotions and the customer is relaxed, a detailed evaluation result can be displayed. Also, if the generation AI estimates the customer's emotions and the customer is nervous, a concise evaluation result can be displayed. Furthermore, if the generation AI estimates the customer's emotions and the customer is excited, a visually stimulating evaluation result can be displayed. This allows for more appropriate evaluations by adjusting the display method of the evaluation based on the customer's emotions. For example, if the generation AI estimates the customer's emotions and the customer is relaxed, a detailed evaluation result can be displayed. Also, if the generation AI estimates the customer's emotions and the customer is nervous, a concise evaluation result can be displayed. Furthermore, if the generation AI estimates the customer's emotions and the customer is excited, a visually stimulating evaluation result can be displayed.

[0090] The evaluation unit can set evaluation criteria by taking into account the geographical location information of the customer during evaluation. The evaluation unit can set evaluation criteria by taking into account the geographical location information of the customer, for example, using the generation AI during evaluation. For example, the generation AI can take into account the geographical location information of the customer and set evaluation criteria based on the culture and customs specific to the region. The generation AI can also take into account the geographical location information of the customer and set evaluation criteria based on the language or dialect specific to the region. Furthermore, the generation AI can take into account the geographical location information of the customer and set evaluation criteria based on the problems and challenges specific to the region. In this way, region-specific evaluation criteria can be set by taking into account the geographical location information of the customer. For example, the generation AI can take into account the geographical location information of the customer and set evaluation criteria based on the culture and customs specific to the region. The generation AI can also take into account the geographical location information of the customer and set evaluation criteria based on the language or dialect specific to the region. Furthermore, the generation AI can take into account the geographical location information of the customer and set evaluation criteria based on the problems and challenges specific to the region.

[0091] The evaluation unit can analyze the customer's social media activity and set relevant evaluation criteria during evaluation. The evaluation unit can, for example, use the generation AI to analyze the customer's social media activity and set relevant evaluation criteria during evaluation. For example, the generation AI can analyze the customer's social media activity and set evaluation criteria based on the customer's interests and concerns. The generation AI can also analyze the customer's social media activity and set evaluation criteria based on the customer's past posts. Furthermore, the generation AI can analyze the customer's social media activity and set evaluation criteria based on the activities of the customer's friends and followers. In this way, by analyzing the customer's social media activity, more appropriate evaluation criteria can be set. For example, the generation AI can analyze the customer's social media activity and set evaluation criteria based on the customer's interests and concerns. The generation AI can also analyze the customer's social media activity and set evaluation criteria based on the customer's past posts. Furthermore, the generation AI can analyze the customer's social media activity and set evaluation criteria based on the customer's friends and followers.

[0092] The evaluation unit can customize the evaluation criteria by reflecting the customer's past feedback when making an evaluation. The evaluation unit can customize the evaluation criteria by reflecting the customer's past feedback when making an evaluation, for example, using the generation AI. For example, the generation AI can analyze the customer's past feedback and set evaluation criteria that match the customer's preferences. The generation AI can also analyze the customer's past feedback and set evaluation criteria to resolve the customer's dissatisfaction points. The generation AI can also analyze the customer's past feedback and set evaluation criteria to meet the customer's expectations. In this way, by reflecting the customer's past feedback, more appropriate evaluation criteria can be set. For example, the generation AI can analyze the customer's past feedback and set evaluation criteria that match the customer's preferences. The generation AI can also analyze the customer's past feedback and set evaluation criteria to resolve the customer's dissatisfaction points. The generation AI can also analyze the customer's past feedback and set evaluation criteria to meet the customer's expectations. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned simulating unit, training unit, and evaluating unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the simulating unit is realized by the processor 46 of the smart device 14 and the specific processing unit 290 of the data processing device 12, and simulates customer personalities and emotions using generative AI. The training unit is realized, for example, by the control unit 46A of the smart device 14 and the specific processing unit 290 of the data processing device 12, and performs training based on simulated customer interaction scenarios. The evaluating unit is realized, for example, by the control unit 46A of the smart device 14 and the specific processing unit 290 of the data processing device 12, and evaluates the results of the training and provides feedback. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned simulating unit, training unit, and evaluating unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the simulating unit is realized by the processor 46 of the smart glasses 214 and the specific processing unit 290 of the data processing device 12, and simulates customer personalities and emotions using generative AI. The training unit is realized, for example, by the control unit 46A of the smart glasses 214 and the specific processing unit 290 of the data processing device 12, and performs training based on simulated customer interaction scenarios. The evaluating unit is realized, for example, by the control unit 46A of the smart glasses 214 and the specific processing unit 290 of the data processing device 12, and evaluates the results of the training and provides feedback. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned simulating unit, training unit, and evaluating unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the simulating unit is realized by the processor 46 of the headset type terminal 314 and the specific processing unit 290 of the data processing device 12, and simulates the personality and emotions of customers using generative AI. The training unit is realized, for example, by the control unit 46A of the headset type terminal 314 and the specific processing unit 290 of the data processing device 12, and performs training based on simulated customer interaction scenarios. The evaluating unit is realized, for example, by the control unit 46A of the headset type terminal 314 and the specific processing unit 290 of the data processing device 12, and evaluates the results of the training and provides feedback. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned simulating unit, training unit, and evaluating unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the simulating unit is realized by the processor 46 of the robot 414 and the specific processing unit 290 of the data processing device 12, and simulates the personality and emotions of customers using generative AI. The training unit is realized, for example, by the control unit 46A of the robot 414 and the specific processing unit 290 of the data processing device 12, and performs training based on simulated customer interaction scenarios. The evaluating unit is realized, for example, by the control unit 46A of the robot 414 and the specific processing unit 290 of the data processing device 12, and evaluates the results of the training and provides feedback.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] The customer-facing training system can further include a "feedback section." The feedback section provides individual feedback based on the results of the training. For example, the feedback section may specifically point out mistakes made during training and areas for improvement, and provide advice for the next training session. The feedback section can also monitor the progress of training in real time and adjust the training content as necessary. Furthermore, the feedback section can evaluate the effectiveness of the training and propose a plan for long-term skill improvement. This maximizes the effectiveness of training and enables flexible responses to individual training needs.

[0095] The customer service training system can further include a "data collection unit." The data collection unit collects and analyzes audio and video data during training. For example, the data collection unit converts the content of conversations during training into text and analyzes it using natural language processing technology. The data collection unit can also analyze facial expressions and gestures during training to point out areas for improvement in non-verbal communication. Furthermore, the data collection unit can measure stress levels and concentration levels during training to evaluate the effectiveness of the training. This improves the quality of training and enables more effective acquisition of customer service skills.

[0096] The customer service training system can further include a "scenario generation unit." The scenario generation unit automatically generates optimal training scenarios according to the purpose and target of the training. For example, the scenario generation unit can generate a wide range of training scenarios, from basic scenarios for new employees to advanced scenarios for advanced employees. The scenario generation unit can also generate scenarios specialized for specific industries or tasks to provide practical training. Furthermore, the scenario generation unit can dynamically adjust the scenarios based on the progress of the training and feedback. This maximizes the effectiveness of the training and enables flexible responses to individual training needs.

[0097] The customer service training system can further include an "emotion analysis unit." The emotion analysis unit analyzes audio and video data during training and estimates the emotions of the training participants in real time. For example, the emotion analysis unit analyzes the tone of voice, speaking speed, and changes in facial expressions to estimate the participants' stress levels and concentration levels. The emotion analysis unit can also monitor changes in emotions during training and provide feedback at appropriate times. Furthermore, the emotion analysis unit can evaluate the effectiveness of the training and adjust the training content based on changes in emotions. This improves the quality of training and enables participants to acquire more effective customer service skills.

[0098] The customer service training system can further include a "performance evaluation unit." The performance evaluation unit evaluates performance during training in real time and provides feedback. For example, the performance evaluation unit analyzes the content of conversations and behavior during training and evaluates appropriate response methods. The performance evaluation unit can also specifically point out mistakes and areas for improvement during training and provide advice for the next training session. Furthermore, the performance evaluation unit can monitor the progress of training and adjust the training content as necessary. This maximizes the effectiveness of training and enables flexible responses to individual training needs.

[0099] The customer service training system can further include a "stress management unit." The stress management unit monitors stress levels during training in real time and provides appropriate countermeasures. For example, the stress management unit analyzes audio and video data during training to estimate stress levels. The stress management unit can also provide advice on relaxation methods and stress reduction when stress levels are high. Furthermore, the stress management unit can provide training content to adjust stress levels according to the progress of the training. This improves the quality of training and enables more effective acquisition of customer service skills.

[0100] The customer-facing training system can further include a "learning history management unit." The learning history management unit records the learning history of training participants and provides individual learning plans. For example, the learning history management unit records past training content and evaluation results and reflects them in the next training. The learning history management unit can also provide individual learning plans based on the training progress. Furthermore, the learning history management unit can evaluate the effectiveness of training and propose plans for long-term skill improvement. This maximizes the effectiveness of training and enables flexible responses to individual training needs.

[0101] The customer service training system can also be equipped with a "virtual reality section." The virtual reality section uses VR technology to provide a more realistic training environment. For example, the virtual reality section can recreate an actual store or office environment, allowing training participants to simulate actual on-site responses. The virtual reality section can also generate various scenarios in real time to maximize the effectiveness of training. Furthermore, the virtual reality section can evaluate performance during training in real time and provide feedback. This improves the quality of training and enables participants to acquire more effective customer service skills.

[0102] The customer service training system can further include an "emotion feedback unit." The emotion feedback unit monitors changes in emotions during training in real time and provides appropriate feedback. For example, the emotion feedback unit analyzes audio and video data during training to estimate changes in emotions. The emotion feedback unit can also adjust the training content according to changes in emotions. Furthermore, the emotion feedback unit can evaluate the effectiveness of the training and provide feedback based on changes in emotions. This improves the quality of training and enables more effective acquisition of customer service skills.

[0103] The customer-facing training system can further include a "personalized training department." The personalized training department customizes the training content according to the individual needs and goals of the training participants. For example, the personalized training department provides an optimal training plan based on the participant's past training history and evaluation results. The personalized training department can also adjust the training content according to the participant's skill level and learning style. Furthermore, the personalized training department can dynamically adjust the training plan according to the training progress. This maximizes the effectiveness of the training and enables flexible response to individual training needs.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The simulation unit simulates the customer's personality and emotions. For example, a generation AI is used to simulate the customer's personality and emotions. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and can realistically reproduce the customer's personality traits and emotions. The generation AI can simulate the customer's behavioral patterns and reactions based on the customer's personality traits, and can also reproduce changes in the customer's emotions in real time. Step 2: The training department conducts training based on the customer interaction scenarios simulated by the simulation department. For example, training is provided to people involved in customer service based on customer interaction scenarios simulated using the generation AI. Based on the customer interaction scenarios simulated by the generation AI, appropriate response methods can be learned and training can be provided to improve response capabilities in actual workplaces. Step 3: The evaluation unit evaluates the results of the training conducted by the training unit. For example, the evaluation unit uses a generation AI to evaluate the training results. The generation AI can evaluate the effectiveness of the training based on the training results and provide feedback. The generation AI can also analyze the training results, evaluate the effectiveness of the training, and point out areas for improvement.

[0106] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0107] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0108] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0109] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

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

[0112] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0113] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0114] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0115] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0116] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0117] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0118] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0119] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0120] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0121] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0124] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 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.

[0144] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0150] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0151] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0152] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0153] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0154] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0155] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0156] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0157] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0160] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0161] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0162] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0163] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0164] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0165] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0166] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0167] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0168] 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.

[0169] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0170] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0171] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0172] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0173] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0174] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0175] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0176] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0177] [Explanation of symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a simulation unit for simulating the personality and emotions of a customer; a training unit that performs training based on the customer interaction scenarios simulated by the simulation unit; an evaluation unit that evaluates the results of the training performed by the training unit; A system characterized by:

2. The simulating unit Generative AI simulates customer personalities and emotions 2. The system of claim 1.

3. The simulating unit Using generative AI to simulate the reasons why customers are unsure about whether to sign a contract 2. The system of claim 1.

4. The simulating unit Generative AI simulates the concerns of customers who are unsure about a product 2. The system of claim 1.

5. The simulating unit Generative AI simulates the causes of customer anger when something doesn't make sense to them 2. The system of claim 1.

6. The training section Training based on simulated customer interaction scenarios using generative AI 2. The system of claim 1.

7. The evaluation unit Evaluating training results with generative AI 2. The system of claim 1.

8. The simulating unit Estimate customer sentiment and adjust simulation scenarios based on estimated customer sentiment 2. The system of claim 1.

Images