system

Abstract

The system according to this embodiment aims to improve the quality of customer service training by performing customer simulations using VR. [Solution] The system according to the embodiment comprises a reception unit, a generation unit, a response generation unit, an experience unit, and a judgment unit. The reception unit sets a customer persona. The generation unit generates a customer avatar based on the persona set by the reception unit. The response generation unit generates customer responses generated by the generation unit. The experience unit provides a customer service experience based on the responses generated by the response generation unit. The judgment unit evaluates the customer service experience performed by the experience unit and provides feedback.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, simulations for improving the quality of customer service training have not been sufficiently carried out, and there is room for improvement.

[0005] The system according to the embodiment aims to perform customer simulation using VR and improve the quality of customer service training.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a generation unit, a response generation unit, an experience unit, and a judgment unit. The reception unit sets a customer persona. The generation unit generates a customer avatar based on the persona set by the reception unit. The response generation unit generates customer responses generated by the generation unit. The experience unit provides a customer service experience based on the responses generated by the response generation unit. The judgment unit evaluates the customer service experience provided by the experience unit and provides feedback. [Effects of the Invention]

[0007] The system according to this embodiment can perform customer simulations using VR and improve the quality of customer service training. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The customer service training system according to an embodiment of the present invention is a system that allows for customer simulation in VR using a customer service training agent. This customer service training system uses a generating AI to generate customer avatars and responses, and by pre-setting customer personas, it can reproduce various situations and provide customer service experiences. After the experience, users can receive evaluations and feedback from the AI ​​to improve their customer service level. Furthermore, by using a VR customer simulator, employee training can be conducted anytime, anywhere, enabling the provision of high-quality service. As online sales increase, the VR customer service market is also expanding. This customer service training system is an entry point to VR customer service, and in the future, the goal is to create an era where AI avatars provide automated customer service in the XR domain. For example, a user can activate the customer service training agent and set a customer persona. For example, a complaint handling situation can be set. Next, the generating AI generates a customer avatar and customer responses based on the set persona. This allows the user to have a realistic customer service experience. After the experience, the AI ​​evaluates the user's customer service and provides feedback. For example, it evaluates the speed of response, language use, attitude, etc., and points out areas for improvement. This allows users to improve their customer service skills. Furthermore, by using a VR customer simulator, employee training can be conducted anytime, anywhere, without requiring physical space. This solves problems such as inconsistent training quality across branches and the difficulty of conducting customer service training in multiple scenarios. As online sales increase, the VR customer service market is expected to expand. In the future, the goal is to reach an era where AI avatars provide automated customer service in the XR domain. This will enable the customer service training system to conduct efficient training and improve customer service skills.

[0029] The customer service training system according to this embodiment comprises a reception unit, a generation unit, a response generation unit, an experience unit, and a judgment unit. The reception unit sets up a customer persona. The customer persona includes, but is not limited to, attribute information such as age, gender, occupation, and hobbies. For example, the reception unit sets up a customer persona based on information entered by the user. The reception unit can also analyze past customer service data and propose the optimal persona setting. The generation unit uses a generation AI to generate a customer avatar based on the persona set up by the reception unit. The generation AI is, for example, a text generation AI (e.g., LLM) or an image generation AI, and realistically generates the customer's appearance, clothing, facial expressions, etc. The generation unit adjusts the details of the avatar based on, for example, the customer's attribute information. The generation unit can also apply different generation algorithms depending on the customer category. The response generation unit uses a generation AI to generate the customer's response generated by the generation unit. The response generation unit generates the response considering, for example, the customer's wording, tone, and the appropriateness of the content. The response generation unit adjusts the level of detail in the response based on, for example, the importance of the customer. The response generation unit can also apply different response algorithms depending on the customer category. The experience unit provides a customer service experience based on the responses generated by the response generation unit. The experience unit sets up scenarios and interaction formats to provide a realistic customer service experience. The experience unit estimates the user's emotions and adjusts the customer service experience based on the estimated emotions. The experience unit can also select the optimal experience method by referring to the user's past customer service history. The judgment unit evaluates the customer service experience performed by the experience unit and provides feedback. The judgment unit evaluates, for example, the speed of the response, language, and attitude, and points out areas for improvement. The judgment unit estimates the user's emotions and adjusts the judgment method based on the estimated emotions. The judgment unit can also select the optimal judgment method by referring to the user's past customer service evaluations. As a result, the customer service training system according to this embodiment can perform a series of customer service training sessions, from setting customer personas to generating avatars, generating responses, providing customer service experiences, judgments, and feedback.

[0030] The reception department sets up customer personas. Customer personas include, but are not limited to, attribute information such as age, gender, occupation, and hobbies. For example, the reception department sets up customer personas based on information entered by the user. Specifically, when a user logs into the system, a screen is displayed where they can enter basic customer information. Here, the user can enter detailed information such as the customer's age, gender, occupation, hobbies, past purchase history, and preferences. This allows the reception department to set up detailed customer personas based on the information entered by the user. The reception department can also analyze past customer service data and suggest the optimal persona settings. For example, it can extract and analyze from the database how customers with similar attributes received and how they reacted in the past. This allows the reception department to suggest the optimal persona settings based on the information entered by the user. Furthermore, the reception department can automate customer persona setting using AI. For example, the AI ​​can analyze the information entered by the user and automatically set up the optimal persona. This reduces the burden on the user and allows the reception department to set up customer personas efficiently.

[0031] The generation unit uses a generation AI to create customer avatars based on personas set by the reception unit. The generation AI, such as text generation AI (e.g., LLM) or image generation AI, realistically generates the customer's appearance, clothing, and facial expressions. Specifically, the generation AI receives customer attribute information set by the reception unit as input and generates the avatar's appearance based on that information. For example, it adjusts facial features according to age and gender, and selects clothing and accessories according to occupation and hobbies. The generation AI can also realistically reproduce the customer's facial expressions and posture. This allows the generation unit to create realistic avatars based on the customer's persona. Furthermore, the generation unit can apply different generation algorithms depending on the customer category. For example, it can generate avatars with formal clothing and calm expressions for business professionals, and avatars with casual clothing and cheerful expressions for young customers. This allows the generation unit to generate the optimal avatar according to the customer's attributes. The generation unit can also allow the user to review the generated avatar and make corrections as needed. For example, a user can provide feedback on the appearance and clothing of their avatar, and the avatar can be regenerated based on that feedback. This allows the generation unit to create a customer avatar that meets the user's requests.

[0032] The response generation unit uses generation AI to generate customer responses generated by the main generation unit. The response generation unit considers factors such as the customer's language, tone, and the appropriateness of the content when generating responses. Specifically, it sets appropriate language and tone based on customer persona information and predicts what questions or requests the customer will make. For example, it uses polite and formal language for business professionals and casual and friendly language for younger customers. The response generation unit also adjusts the level of detail in the response based on the customer's importance. For example, it generates more detailed and polite responses for VIP customers and concise and efficient responses for general customers. Furthermore, the response generation unit can apply different response algorithms depending on the customer's category. For example, it generates responses with specialized knowledge for customers asking technical questions and clear and concise responses for customers asking general questions. This allows the response generation unit to generate optimal responses tailored to the customer's attributes and situation. The response generation unit can also allow the user to review the generated responses and make corrections as needed. For example, the user can provide feedback on the content and tone of the response, and the response can be regenerated based on that feedback. This allows the response generation unit to generate customer responses that meet the user's needs.

[0033] The Experience Unit conducts the customer service experience based on the responses generated by the Response Generation Unit. For example, the Experience Unit sets the format of scenarios and interactions in order to provide a realistic customer service experience. Specifically, the Experience Unit sets up scenarios in which the user interacts with a customer and conducts interactions based on those scenarios. For example, it sets up scenarios for various situations, such as a scenario in which a customer visits a store or an online inquiry scenario. The Experience Unit also estimates the user's emotions and adjusts the method of the customer service experience based on the estimated emotions of the user. For example, if the user is nervous, it conducts interactions to help them relax, and if the user is excited, it conducts interactions to help them respond calmly. Furthermore, the Experience Unit can also select the optimal experience method by referring to the user's past customer service history. For example, it extracts and analyzes from a database what kind of responses were taken and what results were obtained in similar scenarios in the past. This allows the Experience Unit to select the optimal experience method based on the user's past customer service history. In addition, the Experience Unit can collect user feedback and continuously improve the accuracy and effectiveness of the customer service experience. For example, the scenarios and interactions are reviewed and improved based on feedback provided by users after their experience. This allows the experience department to provide users with a realistic and effective customer service experience.

[0034] The evaluation unit assesses the customer service experience conducted by the experience unit and provides feedback. For example, the evaluation unit evaluates aspects such as response speed, language use, and attitude, and points out areas for improvement. Specifically, the evaluation unit evaluates each step of the customer service experience in detail and determines whether the user's response was appropriate. For example, it evaluates the speed of response to customer questions, the politeness of language use, and the friendliness of attitude. The evaluation unit also estimates the user's emotions and adjusts its evaluation method based on the estimated emotions. For example, if the user is nervous, it provides advice to help them relax; if the user is excited, it provides advice to help them respond calmly. Furthermore, the evaluation unit can select the optimal evaluation method by referring to the user's past customer service evaluations. For example, it extracts and analyzes from a database what evaluations were given in similar scenarios in the past and what areas for improvement were pointed out. This allows the evaluation unit to select the optimal evaluation method based on the user's past customer service evaluations. The evaluation unit also provides specific feedback to the user to support the improvement of their customer service skills. For example, it provides specific methods for improving response speed and specific advice for using polite language. This allows the judgment unit to improve the user's customer service skills and provide a better customer service experience.

[0035] The reception department can set up scenarios for handling complaints. For example, the reception department can set up the content and circumstances of the complaint, as well as the method of handling it. For example, the reception department can set up a complaint about a product defect as a scenario for handling complaints. The reception department can also set up a complaint about a delay in service. The reception department can also set up a complaint about the staff's conduct. This makes it possible to conduct customer service training that is tailored to specific situations by setting up scenarios for handling complaints. Some or all of the above processing in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input a scenario for handling complaints into a generating AI and have the generating AI execute the setup of the scenario for handling complaints.

[0036] The generation unit can generate customer avatars using a generation AI. For example, the generation unit realistically generates the customer's appearance, clothing, and facial expressions using the generation AI. The generation unit adjusts the avatar details based on the customer's attribute information. The generation unit can also apply different generation algorithms depending on the customer's category. For example, if the customer is young, the generation unit can generate an avatar in casual clothing. If the customer is a business person, the generation unit can also generate an avatar in formal clothing. If the customer is elderly, the generation unit can also generate an avatar with a calm demeanor. In this way, by using a generation AI, customer avatars can be realistically generated. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input customer attribute information into the generation AI and have the generation AI perform avatar generation.

[0037] The response generation unit can generate customer responses using a generation AI. For example, the response generation unit uses the generation AI to generate responses while considering the customer's wording, tone, and the appropriateness of the content. The response generation unit can adjust the level of detail in the response based on the customer's importance, for example. The response generation unit can also apply different response algorithms depending on the customer's category. For example, if the customer is making a complaint, the response generation unit can apply an algorithm that generates a calm and polite response. If the customer is a new customer, the response generation unit can also apply an algorithm that generates a friendly response. If the customer is a repeat customer, the response generation unit can also apply an algorithm that generates a trustworthy response. In this way, by using a generation AI, customer responses can be generated realistically. Some or all of the above processing in the response generation unit may be performed using AI, for example, or without AI. For example, the response generation unit can input the customer's wording, tone, and the appropriateness of the content into the generation AI and have the generation AI perform the response generation.

[0038] The experience department can provide a realistic customer service experience. For example, the experience department sets the format of scenarios and interactions. For example, the experience department estimates the user's emotions and adjusts the customer service experience based on the estimated emotions. The experience department can also select the optimal experience method by referring to the user's past customer service history. For example, the experience department proposes the optimal experience method based on customer service situations the user has experienced in the past. The experience department can also select an experience method that corresponds to frequently occurring situations from the user's past customer service history. Furthermore, the experience department can analyze the user's past customer service history and provide an experience method that focuses on areas that need improvement. This makes it possible to provide training that closely resembles actual customer service by providing a realistic customer service experience. Some or all of the above processes in the experience department may be performed using AI, for example, or not using AI. For example, the experience department can input user emotion data into a generating AI and have the generating AI adjust the customer service experience method.

[0039] The evaluation unit can assess the speed of the response, language use, attitude, etc., and point out areas for improvement. For example, the evaluation unit can assess the speed of the response. For example, the evaluation unit makes an evaluation based on response time, processing time, etc. The evaluation unit can also assess language use. For example, the evaluation unit makes an evaluation based on the use of polite language and appropriate expressions. The evaluation unit can also assess attitude. For example, the evaluation unit makes an evaluation based on facial expressions, posture, tone of voice, etc. In this way, by evaluating the speed of the response, language use, attitude, etc., and pointing out areas for improvement, customer service skills can be improved. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit can input data such as the speed of the response, language use, and attitude into a generating AI, and have the generating AI perform the evaluation and point out areas for improvement.

[0040] The Experience Department does not require physical space and can conduct employee training anytime, anywhere. For example, the Experience Department can use a VR customer simulator to conduct customer service training without requiring physical space. For example, users can receive customer service training in any location, such as their home or office. The Experience Department can also provide customer service training that covers multiple situations. For example, the Experience Department can provide customer service training that covers various situations, such as handling complaints and new customer interactions. This increases the flexibility of training because it does not require physical space and can be conducted anytime, anywhere. Some or all of the above processes in the Experience Department may be performed using AI, for example, or not using AI. For example, the Experience Department can input the settings for the VR customer simulator into a generating AI and have the generating AI execute the provision of training.

[0041] The reception desk can analyze past customer service data and propose the optimal persona settings. For example, the reception desk can automatically propose the optimal persona settings based on data of customers the user has previously interacted with. The reception desk can also recommend personas suitable for specific situations based on past customer service data. Furthermore, the reception desk can analyze the user's past customer service history and propose persona settings that correspond to frequently occurring situations. In this way, the optimal persona settings can be proposed by analyzing past customer service data. Some or all of the above processes in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input past customer service data into a generating AI and have the generating AI execute the persona setting proposal.

[0042] The reception desk can customize persona settings according to the user's industry and business type. For example, if the user is in the retail industry, the reception desk can provide a persona setting option specialized for customer service. If the user is in the food and beverage industry, the reception desk can also suggest a persona setting suitable for handling complaints and managing reservations. If the user is in the service industry, the reception desk can also provide a persona setting focused on improving customer satisfaction. This allows for more appropriate persona settings by customizing them according to the user's industry and business type. Some or all of the above processes in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input data on the user's industry and business type into a generating AI and have the generating AI perform the persona setting customization.

[0043] The reception desk can prioritize setting highly relevant personas by considering the user's geographical location when creating personas. For example, if the user is in a specific region, the reception desk can prioritize setting personas based on the customer characteristics of that region. The reception desk can also prioritize setting traveler personas if the user is traveling. Furthermore, if the user is in a specific city, the reception desk can prioritize setting personas based on the culture and customs of that city. This allows for the prioritization of highly relevant personas by considering the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the user's geographical location information into a generating AI and have the generating AI create the personas.

[0044] The reception desk can analyze a user's social media activity and set relevant personas when creating personas. For example, the reception desk can analyze the content of a user's social media posts and set personas based on their interests. The reception desk can also set relevant personas by referring to the activities of the user's followers and friends. Furthermore, the reception desk can analyze the frequency and patterns of the user's social media activity and set the optimal persona. In this way, relevant personas can be set by analyzing the user's social media activity. Some or all of the above processes in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's social media data into a generating AI and have the generating AI perform the persona creation.

[0045] The generation unit can adjust the level of detail of the avatar based on the customer's attribute information when generating the avatar. For example, if the customer is young, the generation unit can generate an avatar in casual clothing. If the customer is a business person, the generation unit can also generate an avatar in formal clothing. If the customer is elderly, the generation unit can also generate an avatar with a calm demeanor. By adjusting the level of detail of the avatar based on the customer's attribute information, a more appropriate avatar can be generated. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the customer's attribute information into a generation AI and have the generation AI perform the adjustment of the level of detail of the avatar.

[0046] The generation unit can apply different generation algorithms depending on the customer's category when generating avatars. For example, if the customer is handling a complaint, the generation unit can apply an algorithm to generate a calm and polite avatar. If the customer is a new customer, the generation unit can also apply an algorithm to generate a friendly avatar. Furthermore, if the customer is a repeat customer, the generation unit can apply an algorithm to generate a trustworthy avatar. By applying different generation algorithms depending on the customer's category, a more appropriate avatar can be generated. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input customer category information into a generation AI and have the generation AI execute the application of the generation algorithm.

[0047] The generation unit can determine the priority of avatars based on the customer's submission timing when generating avatars. For example, if the customer is in a hurry, the generation unit will generate an avatar quickly. If the customer has ample time, the generation unit can also generate a more detailed avatar. Furthermore, if the customer submits within a specific time frame, the generation unit can generate an avatar suitable for that time frame. This allows for the generation of more appropriate avatars by determining the priority of avatars based on the customer's submission timing. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or not. For example, the generation unit can input customer submission timing data into a generation AI and have the generation AI determine the priority of avatars.

[0048] The generation unit can adjust the order of avatars based on customer relevance during avatar generation. For example, if a customer is an important customer, the generation unit will prioritize generating avatars for them. The generation unit can also quickly generate avatars if the customer is a new customer. Furthermore, if the customer is a repeat customer, the generation unit can generate trustworthy avatars. This allows for the generation of more appropriate avatars by adjusting the order of avatars based on customer relevance. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input customer relevance data into a generation AI and have the generation AI perform the adjustment of the avatar order.

[0049] The response generation unit can adjust the level of detail in the response based on the customer's importance when generating a response. For example, if the customer is an important customer, the response generation unit will generate a detailed response. The response generation unit can also generate a concise response if the customer is a new customer. Furthermore, the response generation unit can generate a trustworthy response if the customer is a repeat customer. In this way, by adjusting the level of detail in the response based on the customer's importance, a more appropriate response can be generated. Some or all of the above processing in the response generation unit may be performed using AI, for example, or without AI. For example, the response generation unit can input customer importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the response.

[0050] The response generation unit can apply different response algorithms depending on the customer's category when generating a response. For example, if the customer is making a complaint, the response generation unit can apply an algorithm that generates a calm and polite response. It can also apply an algorithm that generates a friendly response if the customer is a new customer. Furthermore, it can apply an algorithm that generates a trustworthy response if the customer is a repeat customer. By applying different response algorithms depending on the customer's category, a more appropriate response can be generated. Some or all of the above processing in the response generation unit may be performed using AI, for example, or without AI. For example, the response generation unit can input customer category information into a generation AI and have the generation AI execute the application of the response algorithm.

[0051] The response generation unit can determine the priority of responses based on the customer's submission timing when generating responses. For example, if the customer is in a hurry, the response generation unit will generate a response quickly. The response generation unit can also generate a detailed response if the customer has ample time. Furthermore, if the customer submits within a specific time frame, the response generation unit can generate a response appropriate for that time frame. This allows for the generation of more appropriate responses by determining the priority of responses based on the customer's submission timing. Some or all of the above processing in the response generation unit may be performed using AI, for example, or without AI. For example, the response generation unit can input customer submission timing data into a generation AI and have the generation AI determine the priority of responses.

[0052] The response generation unit can adjust the order of responses based on customer relevance during response generation. For example, the response generation unit prioritizes generating responses for important customers. It can also quickly generate responses for new customers. Furthermore, it can generate trustworthy responses for repeat customers. By adjusting the order of responses based on customer relevance, more appropriate responses can be generated. Some or all of the above processing in the response generation unit may be performed using AI, for example, or without AI. For example, the response generation unit can input customer relevance data into a generation AI and have the generation AI perform the adjustment of the response order.

[0053] The experience department can select the optimal experience method by referring to the user's past customer service history during a customer service experience. For example, the experience department can propose the optimal experience method based on customer service situations the user has experienced in the past. The experience department can also select an experience method that corresponds to frequently occurring situations from the user's past customer service history. Furthermore, the experience department can analyze the user's past customer service history and provide an experience method that focuses on areas that need improvement. In this way, the optimal experience method can be selected by referring to the user's past customer service history. Some or all of the above processing in the experience department may be performed using AI, for example, or not using AI. For example, the experience department can input data of the user's past customer service history into a generating AI and have the generating AI perform the selection of an experience method.

[0054] The experience department can customize the customer service experience based on the user's current work situation. For example, if the user is busy, the experience department can provide a short and effective customer service experience. If the user has time, the experience department can also provide a customer service experience that includes detailed scenarios. Furthermore, depending on the user's work content, the experience department can provide a customer service experience that strengthens specific skills. In this way, a more appropriate customer service experience can be provided by customizing the experience based on the user's current work situation. Some or all of the above processing in the experience department may be performed using AI, for example, or not using AI. For example, the experience department can input data on the user's current work situation into a generating AI and have the generating AI perform the customization of the experience.

[0055] The Experience Department can select the optimal experience method during a customer service experience, taking into account the user's geographical location. For example, if the user is in a specific region, the Experience Department can provide a customer service experience based on the customer characteristics of that region. Furthermore, if the user is traveling, the Experience Department can provide a customer service experience tailored to travelers. Also, if the user is in a specific city, the Experience Department can provide a customer service experience based on the culture and customs of that city. This allows for the selection of the optimal experience method by considering the user's geographical location. Some or all of the above processing in the Experience Department may be performed using AI, for example, or without AI. For example, the Experience Department can input the user's geographical location information into a generating AI and have the generating AI select the experience method.

[0056] The Experience Department can analyze a user's social media activity during a customer service experience and propose ways to enhance that experience. For example, the Experience Department can analyze a user's social media posts and provide a customer service experience based on their interests. It can also refer to the activities of the user's followers and friends to provide relevant customer service experiences. Furthermore, the Experience Department can analyze the frequency and patterns of a user's social media activity to provide the optimal customer service experience. In this way, by analyzing a user's social media activity, the optimal customer service experience can be provided. Some or all of the above processing in the Experience Department may be performed using AI, for example, or without AI. For example, the Experience Department can input the user's social media data into a generating AI and have the generating AI propose ways to enhance the experience.

[0057] The judgment unit can select the optimal judgment method by referring to the user's past customer service evaluations during the judgment process. For example, the judgment unit can propose the optimal judgment method based on evaluations the user has received in the past. The judgment unit can also select a judgment method that focuses on frequently pointed-out points from the user's past customer service evaluations. Furthermore, the judgment unit can analyze the user's past customer service evaluations and provide a judgment method that focuses on areas that need improvement. In this way, the optimal judgment method can be selected by referring to the user's past customer service evaluations. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input data on the user's past customer service evaluations into a generating AI and have the generating AI perform the selection of a judgment method.

[0058] The judgment unit can customize the judgment method based on the user's current work situation at the time of judgment. For example, if the user is busy, the judgment unit can provide an effective judgment in a short time. Also, if the user has time, the judgment unit can provide detailed feedback. Furthermore, depending on the user's work content, the judgment unit can provide judgment methods to strengthen specific skills. This allows for more appropriate feedback to be provided by customizing the judgment method based on the user's current work situation. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input data on the user's current work situation into a generating AI and have the generating AI perform the customization of the judgment method.

[0059] The determination unit can select the optimal determination method by considering the user's geographical location information during the determination process. For example, if the user is in a specific region, the determination unit can provide a determination method based on the customer characteristics of that region. Furthermore, if the user is traveling, the determination unit can provide a determination method tailored for travelers. Also, if the user is in a specific city, the determination unit can provide a determination method based on the culture and customs of that city. This allows the determination unit to select the optimal determination method by considering the user's geographical location information. Some or all of the above-described processes in the determination unit may be performed using AI, for example, or without AI. For example, the determination unit can input the user's geographical location information into a generating AI and have the generating AI select the determination method.

[0060] The determination unit can analyze the user's social media activity and propose a determination method during the determination process. For example, the determination unit can analyze the user's social media posts and provide a determination method based on their interests. The determination unit can also refer to the activities of the user's followers and friends and provide relevant determination methods. Furthermore, the determination unit can analyze the frequency and patterns of the user's social media activity and provide the optimal determination method. In this way, the optimal determination method can be provided by analyzing the user's social media activity. Some or all of the above processing in the determination unit may be performed using AI, for example, or without AI. For example, the determination unit can input the user's social media data into a generating AI and have the generating AI execute the proposal of a determination method.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] The customer service training system can analyze a user's past customer service history and propose the most suitable training scenario. For example, if a user has struggled with handling complaints in the past, the system will provide a scenario specifically focused on complaint handling. Similarly, if a user excels at handling new customers, the system can provide a scenario to further improve that skill. Furthermore, it can extract frequently occurring situations from the user's past customer service history and provide corresponding training scenarios. This allows for the provision of an optimal training experience based on the user's past experience. The system inputs the user's past customer service history data into a generating AI, which then generates training scenario suggestions.

[0063] The customer service training system can customize training content based on the user's geographical location. For example, if the user is in a specific region, it can provide scenarios based on the customer characteristics of that region. It can also provide traveler-oriented scenarios if the user is traveling. Furthermore, if the user is in a specific city, it can provide scenarios based on the city's culture and customs. This allows for the provision of an optimal training experience that takes the user's geographical location into account. The system inputs the user's geographical location information into a generating AI, which then performs the customization of the training content.

[0064] The customer service training system can analyze users' social media activity and provide relevant training scenarios. For example, it can analyze users' social media posts and provide scenarios based on their interests. It can also provide relevant scenarios by referring to the activities of users' followers and friends. Furthermore, it can analyze the frequency and patterns of users' social media activity and provide the optimal scenario. This allows for the provision of an optimal training experience that takes into account users' social media activity. The system can input users' social media data into a generating AI and have the AI ​​generate training scenario suggestions.

[0065] The customer service training system can customize training content based on the user's current work situation. For example, if the user is busy, it can provide a short and effective training scenario. If the user has more time, it can also provide a training scenario that includes detailed situations. Furthermore, it can provide training scenarios to strengthen specific skills depending on the user's job responsibilities. This allows for the provision of an optimal training experience based on the user's current work situation. The system inputs data on the user's current work situation into a generating AI, which then performs the customization of the training content.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The reception department sets up customer personas. Customer personas include attribute information such as age, gender, occupation, and hobbies. The reception department sets up customer personas based on the information entered by the user. They can also analyze past customer service data and suggest the most suitable persona settings. Step 2: The generation unit uses a generation AI to generate customer avatars based on the personas set by the reception unit. The generation AI includes text generation AI and image generation AI, and realistically generates the customer's appearance, clothing, facial expressions, etc. The generation unit can also adjust the avatar details based on the customer's attribute information and apply different generation algorithms depending on the customer's category. Step 3: The response generation unit uses a generation AI to generate customer responses generated by the generation unit. The response generation unit generates responses considering the customer's wording, tone, and appropriateness of content, and adjusts the level of detail of the response based on the importance of the customer. It can also apply different response algorithms depending on the customer category. Step 4: The experience unit conducts the customer service experience based on the responses generated by the response generation unit. The experience unit sets the scenario and interaction format, estimates the user's emotions, and adjusts the method of the customer service experience to provide a realistic customer service experience. It can also select the optimal experience method by referring to the user's past customer service history. Step 5: The evaluation unit evaluates the customer service experience conducted by the experience unit and provides feedback. The evaluation unit assesses the speed of the response, language use, attitude, etc., and points out areas for improvement. It estimates the user's emotions and adjusts the evaluation method based on the estimated user emotions. It can also select the optimal evaluation method by referring to the user's past customer service evaluations.

[0068] (Example of form 2) The customer service training system according to an embodiment of the present invention is a system that allows for customer simulation in VR using a customer service training agent. This customer service training system uses a generating AI to generate customer avatars and responses, and by pre-setting customer personas, it can reproduce various situations and provide customer service experiences. After the experience, users can receive evaluations and feedback from the AI ​​to improve their customer service level. Furthermore, by using a VR customer simulator, employee training can be conducted anytime, anywhere, enabling the provision of high-quality service. As online sales increase, the VR customer service market is also expanding. This customer service training system is an entry point to VR customer service, and in the future, the goal is to create an era where AI avatars provide automated customer service in the XR domain. For example, a user can activate the customer service training agent and set a customer persona. For example, a complaint handling situation can be set. Next, the generating AI generates a customer avatar and customer responses based on the set persona. This allows the user to have a realistic customer service experience. After the experience, the AI ​​evaluates the user's customer service and provides feedback. For example, it evaluates the speed of response, language use, attitude, etc., and points out areas for improvement. This allows users to improve their customer service skills. Furthermore, by using a VR customer simulator, employee training can be conducted anytime, anywhere, without requiring physical space. This solves problems such as inconsistent training quality across branches and the difficulty of conducting customer service training in multiple scenarios. As online sales increase, the VR customer service market is expected to expand. In the future, the goal is to reach an era where AI avatars provide automated customer service in the XR domain. This will enable the customer service training system to conduct efficient training and improve customer service skills.

[0069] The customer service training system according to this embodiment comprises a reception unit, a generation unit, a response generation unit, an experience unit, and a judgment unit. The reception unit sets up a customer persona. The customer persona includes, but is not limited to, attribute information such as age, gender, occupation, and hobbies. For example, the reception unit sets up a customer persona based on information entered by the user. The reception unit can also analyze past customer service data and propose the optimal persona setting. The generation unit uses a generation AI to generate a customer avatar based on the persona set up by the reception unit. The generation AI is, for example, a text generation AI (e.g., LLM) or an image generation AI, and realistically generates the customer's appearance, clothing, facial expressions, etc. The generation unit adjusts the details of the avatar based on, for example, the customer's attribute information. The generation unit can also apply different generation algorithms depending on the customer category. The response generation unit uses a generation AI to generate the customer's response generated by the generation unit. The response generation unit generates the response considering, for example, the customer's wording, tone, and the appropriateness of the content. The response generation unit adjusts the level of detail in the response based on, for example, the importance of the customer. The response generation unit can also apply different response algorithms depending on the customer category. The experience unit provides a customer service experience based on the responses generated by the response generation unit. The experience unit sets up scenarios and interaction formats to provide a realistic customer service experience. The experience unit estimates the user's emotions and adjusts the customer service experience based on the estimated emotions. The experience unit can also select the optimal experience method by referring to the user's past customer service history. The judgment unit evaluates the customer service experience performed by the experience unit and provides feedback. The judgment unit evaluates, for example, the speed of the response, language, and attitude, and points out areas for improvement. The judgment unit estimates the user's emotions and adjusts the judgment method based on the estimated emotions. The judgment unit can also select the optimal judgment method by referring to the user's past customer service evaluations. As a result, the customer service training system according to this embodiment can perform a series of customer service training sessions, from setting customer personas to generating avatars, generating responses, providing customer service experiences, judgments, and feedback.

[0070] The reception department sets up customer personas. Customer personas include, but are not limited to, attribute information such as age, gender, occupation, and hobbies. For example, the reception department sets up customer personas based on information entered by the user. Specifically, when a user logs into the system, a screen is displayed where they can enter basic customer information. Here, the user can enter detailed information such as the customer's age, gender, occupation, hobbies, past purchase history, and preferences. This allows the reception department to set up detailed customer personas based on the information entered by the user. The reception department can also analyze past customer service data and suggest the optimal persona settings. For example, it can extract and analyze from the database how customers with similar attributes received and how they reacted in the past. This allows the reception department to suggest the optimal persona settings based on the information entered by the user. Furthermore, the reception department can automate customer persona setting using AI. For example, the AI ​​can analyze the information entered by the user and automatically set up the optimal persona. This reduces the burden on the user and allows the reception department to set up customer personas efficiently.

[0071] The generation unit uses a generation AI to create customer avatars based on personas set by the reception unit. The generation AI, such as text generation AI (e.g., LLM) or image generation AI, realistically generates the customer's appearance, clothing, and facial expressions. Specifically, the generation AI receives customer attribute information set by the reception unit as input and generates the avatar's appearance based on that information. For example, it adjusts facial features according to age and gender, and selects clothing and accessories according to occupation and hobbies. The generation AI can also realistically reproduce the customer's facial expressions and posture. This allows the generation unit to create realistic avatars based on the customer's persona. Furthermore, the generation unit can apply different generation algorithms depending on the customer category. For example, it can generate avatars with formal clothing and calm expressions for business professionals, and avatars with casual clothing and cheerful expressions for young customers. This allows the generation unit to generate the optimal avatar according to the customer's attributes. The generation unit can also allow the user to review the generated avatar and make corrections as needed. For example, a user can provide feedback on the appearance and clothing of their avatar, and the avatar can be regenerated based on that feedback. This allows the generation unit to create a customer avatar that meets the user's requests.

[0072] The response generation unit uses generation AI to generate customer responses generated by the main generation unit. The response generation unit considers factors such as the customer's language, tone, and the appropriateness of the content when generating responses. Specifically, it sets appropriate language and tone based on customer persona information and predicts what questions or requests the customer will make. For example, it uses polite and formal language for business professionals and casual and friendly language for younger customers. The response generation unit also adjusts the level of detail in the response based on the customer's importance. For example, it generates more detailed and polite responses for VIP customers and concise and efficient responses for general customers. Furthermore, the response generation unit can apply different response algorithms depending on the customer's category. For example, it generates responses with specialized knowledge for customers asking technical questions and clear and concise responses for customers asking general questions. This allows the response generation unit to generate optimal responses tailored to the customer's attributes and situation. The response generation unit can also allow the user to review the generated responses and make corrections as needed. For example, the user can provide feedback on the content and tone of the response, and the response can be regenerated based on that feedback. This allows the response generation unit to generate customer responses that meet the user's needs.

[0073] The Experience Unit conducts the customer service experience based on the responses generated by the Response Generation Unit. For example, the Experience Unit sets the format of scenarios and interactions in order to provide a realistic customer service experience. Specifically, the Experience Unit sets up scenarios in which the user interacts with a customer and conducts interactions based on those scenarios. For example, it sets up scenarios for various situations, such as a scenario in which a customer visits a store or an online inquiry scenario. The Experience Unit also estimates the user's emotions and adjusts the method of the customer service experience based on the estimated emotions of the user. For example, if the user is nervous, it conducts interactions to help them relax, and if the user is excited, it conducts interactions to help them respond calmly. Furthermore, the Experience Unit can also select the optimal experience method by referring to the user's past customer service history. For example, it extracts and analyzes from a database what kind of responses were taken and what results were obtained in similar scenarios in the past. This allows the Experience Unit to select the optimal experience method based on the user's past customer service history. In addition, the Experience Unit can collect user feedback and continuously improve the accuracy and effectiveness of the customer service experience. For example, the scenarios and interactions are reviewed and improved based on feedback provided by users after their experience. This allows the experience department to provide users with a realistic and effective customer service experience.

[0074] The evaluation unit assesses the customer service experience conducted by the experience unit and provides feedback. For example, the evaluation unit evaluates aspects such as response speed, language use, and attitude, and points out areas for improvement. Specifically, the evaluation unit evaluates each step of the customer service experience in detail and determines whether the user's response was appropriate. For example, it evaluates the speed of response to customer questions, the politeness of language use, and the friendliness of attitude. The evaluation unit also estimates the user's emotions and adjusts its evaluation method based on the estimated emotions. For example, if the user is nervous, it provides advice to help them relax; if the user is excited, it provides advice to help them respond calmly. Furthermore, the evaluation unit can select the optimal evaluation method by referring to the user's past customer service evaluations. For example, it extracts and analyzes from a database what evaluations were given in similar scenarios in the past and what areas for improvement were pointed out. This allows the evaluation unit to select the optimal evaluation method based on the user's past customer service evaluations. The evaluation unit also provides specific feedback to the user to support the improvement of their customer service skills. For example, it provides specific methods for improving response speed and specific advice for using polite language. This allows the judgment unit to improve the user's customer service skills and provide a better customer service experience.

[0075] The reception department can set up scenarios for handling complaints. For example, the reception department can set up the content and circumstances of the complaint, as well as the method of handling it. For example, the reception department can set up a complaint about a product defect as a scenario for handling complaints. The reception department can also set up a complaint about a delay in service. The reception department can also set up a complaint about the staff's conduct. This makes it possible to conduct customer service training that is tailored to specific situations by setting up scenarios for handling complaints. Some or all of the above processing in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input a scenario for handling complaints into a generating AI and have the generating AI execute the setup of the scenario for handling complaints.

[0076] The generation unit can generate customer avatars using a generation AI. For example, the generation unit realistically generates the customer's appearance, clothing, and facial expressions using the generation AI. The generation unit adjusts the avatar details based on the customer's attribute information. The generation unit can also apply different generation algorithms depending on the customer's category. For example, if the customer is young, the generation unit can generate an avatar in casual clothing. If the customer is a business person, the generation unit can also generate an avatar in formal clothing. If the customer is elderly, the generation unit can also generate an avatar with a calm demeanor. In this way, by using a generation AI, customer avatars can be realistically generated. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input customer attribute information into the generation AI and have the generation AI perform avatar generation.

[0077] The response generation unit can generate customer responses using a generation AI. For example, the response generation unit uses the generation AI to generate responses while considering the customer's wording, tone, and the appropriateness of the content. The response generation unit can adjust the level of detail in the response based on the customer's importance, for example. The response generation unit can also apply different response algorithms depending on the customer's category. For example, if the customer is making a complaint, the response generation unit can apply an algorithm that generates a calm and polite response. If the customer is a new customer, the response generation unit can also apply an algorithm that generates a friendly response. If the customer is a repeat customer, the response generation unit can also apply an algorithm that generates a trustworthy response. In this way, by using a generation AI, customer responses can be generated realistically. Some or all of the above processing in the response generation unit may be performed using AI, for example, or without AI. For example, the response generation unit can input the customer's wording, tone, and the appropriateness of the content into the generation AI and have the generation AI perform the response generation.

[0078] The experience department can provide a realistic customer service experience. For example, the experience department sets the format of scenarios and interactions. For example, the experience department estimates the user's emotions and adjusts the customer service experience based on the estimated emotions. The experience department can also select the optimal experience method by referring to the user's past customer service history. For example, the experience department proposes the optimal experience method based on customer service situations the user has experienced in the past. The experience department can also select an experience method that corresponds to frequently occurring situations from the user's past customer service history. Furthermore, the experience department can analyze the user's past customer service history and provide an experience method that focuses on areas that need improvement. This makes it possible to provide training that closely resembles actual customer service by providing a realistic customer service experience. Some or all of the above processes in the experience department may be performed using AI, for example, or not using AI. For example, the experience department can input user emotion data into a generating AI and have the generating AI adjust the customer service experience method.

[0079] The evaluation unit can assess the speed of the response, language use, attitude, etc., and point out areas for improvement. For example, the evaluation unit can assess the speed of the response. For example, the evaluation unit makes an evaluation based on response time, processing time, etc. The evaluation unit can also assess language use. For example, the evaluation unit makes an evaluation based on the use of polite language and appropriate expressions. The evaluation unit can also assess attitude. For example, the evaluation unit makes an evaluation based on facial expressions, posture, tone of voice, etc. In this way, by evaluating the speed of the response, language use, attitude, etc., and pointing out areas for improvement, customer service skills can be improved. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit can input data such as the speed of the response, language use, and attitude into a generating AI, and have the generating AI perform the evaluation and point out areas for improvement.

[0080] The Experience Department does not require physical space and can conduct employee training anytime, anywhere. For example, the Experience Department can use a VR customer simulator to conduct customer service training without requiring physical space. For example, users can receive customer service training in any location, such as their home or office. The Experience Department can also provide customer service training that covers multiple situations. For example, the Experience Department can provide customer service training that covers various situations, such as handling complaints and new customer interactions. This increases the flexibility of training because it does not require physical space and can be conducted anytime, anywhere. Some or all of the above processes in the Experience Department may be performed using AI, for example, or not using AI. For example, the Experience Department can input the settings for the VR customer simulator into a generating AI and have the generating AI execute the provision of training.

[0081] The reception desk can estimate the user's emotions and adjust the persona settings based on those emotions. For example, if the user is nervous, the reception desk can provide a simple and intuitive interface and simplify the persona setting process. If the user is relaxed, the reception desk can also provide detailed persona setting options and suggest customizable settings. If the user is in a hurry, the reception desk can prioritize voice input to allow for quick persona setting. This allows for more appropriate persona setting by adjusting the persona settings according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the user's emotion data into a generative AI and have the generative AI perform the adjustment of the persona settings.

[0082] The reception desk can analyze past customer service data and propose the optimal persona settings. For example, the reception desk can automatically propose the optimal persona settings based on data of customers the user has previously interacted with. The reception desk can also recommend personas suitable for specific situations based on past customer service data. Furthermore, the reception desk can analyze the user's past customer service history and propose persona settings that correspond to frequently occurring situations. In this way, the optimal persona settings can be proposed by analyzing past customer service data. Some or all of the above processes in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input past customer service data into a generating AI and have the generating AI execute the persona setting proposal.

[0083] The reception desk can customize persona settings according to the user's industry and business type. For example, if the user is in the retail industry, the reception desk can provide a persona setting option specialized for customer service. If the user is in the food and beverage industry, the reception desk can also suggest a persona setting suitable for handling complaints and managing reservations. If the user is in the service industry, the reception desk can also provide a persona setting focused on improving customer satisfaction. This allows for more appropriate persona settings by customizing them according to the user's industry and business type. Some or all of the above processes in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input data on the user's industry and business type into a generating AI and have the generating AI perform the persona setting customization.

[0084] The reception desk can estimate the user's emotions and determine the priority of personas based on the estimated emotions. For example, if the user is stressed, the reception desk will prioritize high-importance personas. If the user is relaxed, the reception desk can also perform detailed persona settings and adjust the priorities. If the user is in a hurry, the reception desk can also prioritize personas that can be set up quickly. This allows for more appropriate persona settings by determining the priority of personas according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not using AI. For example, the reception desk can input user emotion data into a generative AI and have the generative AI determine the priority of personas.

[0085] The reception desk can prioritize setting highly relevant personas by considering the user's geographical location when creating personas. For example, if the user is in a specific region, the reception desk can prioritize setting personas based on the customer characteristics of that region. The reception desk can also prioritize setting traveler personas if the user is traveling. Furthermore, if the user is in a specific city, the reception desk can prioritize setting personas based on the culture and customs of that city. This allows for the prioritization of highly relevant personas by considering the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the user's geographical location information into a generating AI and have the generating AI create the personas.

[0086] The reception desk can analyze a user's social media activity and set relevant personas when creating personas. For example, the reception desk can analyze the content of a user's social media posts and set personas based on their interests. The reception desk can also set relevant personas by referring to the activities of the user's followers and friends. Furthermore, the reception desk can analyze the frequency and patterns of the user's social media activity and set the optimal persona. In this way, relevant personas can be set by analyzing the user's social media activity. Some or all of the above processes in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's social media data into a generating AI and have the generating AI perform the persona creation.

[0087] The generation unit can estimate the user's emotions and adjust the avatar's expression based on the estimated emotions. For example, if the user is relaxed, the generation unit can generate an avatar with a calm expression. If the user is tense, the generation unit can also generate an avatar with a friendly expression. If the user is excited, the generation unit can also generate an avatar with a lively expression. By adjusting the avatar's expression according to the user's emotions, a more appropriate avatar can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the avatar's expression.

[0088] The generation unit can adjust the level of detail of the avatar based on the customer's attribute information when generating the avatar. For example, if the customer is young, the generation unit can generate an avatar in casual clothing. If the customer is a business person, the generation unit can also generate an avatar in formal clothing. If the customer is elderly, the generation unit can also generate an avatar with a calm demeanor. By adjusting the level of detail of the avatar based on the customer's attribute information, a more appropriate avatar can be generated. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the customer's attribute information into a generation AI and have the generation AI perform the adjustment of the level of detail of the avatar.

[0089] The generation unit can apply different generation algorithms depending on the customer's category when generating avatars. For example, if the customer is handling a complaint, the generation unit can apply an algorithm to generate a calm and polite avatar. If the customer is a new customer, the generation unit can also apply an algorithm to generate a friendly avatar. Furthermore, if the customer is a repeat customer, the generation unit can apply an algorithm to generate a trustworthy avatar. By applying different generation algorithms depending on the customer's category, a more appropriate avatar can be generated. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input customer category information into a generation AI and have the generation AI execute the application of the generation algorithm.

[0090] The generation unit can estimate the user's emotions and adjust the avatar's appearance based on the estimated emotions. For example, if the user is relaxed, the generation unit can generate an avatar with a calm expression. If the user is tense, the generation unit can also generate an avatar with a friendly expression. If the user is excited, the generation unit can also generate an avatar with a lively expression. By adjusting the avatar's appearance according to the user's emotions, a more appropriate avatar can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the avatar's appearance.

[0091] The generation unit can determine the priority of avatars based on the customer's submission timing when generating avatars. For example, if the customer is in a hurry, the generation unit will generate an avatar quickly. If the customer has ample time, the generation unit can also generate a more detailed avatar. Furthermore, if the customer submits within a specific time frame, the generation unit can generate an avatar suitable for that time frame. This allows for the generation of more appropriate avatars by determining the priority of avatars based on the customer's submission timing. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or not. For example, the generation unit can input customer submission timing data into a generation AI and have the generation AI determine the priority of avatars.

[0092] The generation unit can adjust the order of avatars based on customer relevance during avatar generation. For example, if a customer is an important customer, the generation unit will prioritize generating avatars for them. The generation unit can also quickly generate avatars if the customer is a new customer. Furthermore, if the customer is a repeat customer, the generation unit can generate trustworthy avatars. This allows for the generation of more appropriate avatars by adjusting the order of avatars based on customer relevance. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input customer relevance data into a generation AI and have the generation AI perform the adjustment of the avatar order.

[0093] The response generation unit can estimate the user's emotions and adjust the way the response is expressed based on the estimated emotions. For example, if the user is relaxed, the response generation unit will generate a response in a calm tone. If the user is tense, the response generation unit can also generate a response in a friendly tone. If the user is excited, the response generation unit can also generate a response in a lively tone. In this way, by adjusting the way the response is expressed according to the user's emotions, a more appropriate response can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the response generation unit may be performed using AI, for example, or without AI. For example, the response generation unit can input user emotion data into the generative AI and have the generative AI adjust the way the response is expressed.

[0094] The response generation unit can adjust the level of detail in the response based on the customer's importance when generating a response. For example, if the customer is an important customer, the response generation unit will generate a detailed response. The response generation unit can also generate a concise response if the customer is a new customer. Furthermore, the response generation unit can generate a trustworthy response if the customer is a repeat customer. In this way, by adjusting the level of detail in the response based on the customer's importance, a more appropriate response can be generated. Some or all of the above processing in the response generation unit may be performed using AI, for example, or without AI. For example, the response generation unit can input customer importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the response.

[0095] The response generation unit can apply different response algorithms depending on the customer's category when generating a response. For example, if the customer is making a complaint, the response generation unit can apply an algorithm that generates a calm and polite response. It can also apply an algorithm that generates a friendly response if the customer is a new customer. Furthermore, it can apply an algorithm that generates a trustworthy response if the customer is a repeat customer. By applying different response algorithms depending on the customer's category, a more appropriate response can be generated. Some or all of the above processing in the response generation unit may be performed using AI, for example, or without AI. For example, the response generation unit can input customer category information into a generation AI and have the generation AI execute the application of the response algorithm.

[0096] The response generation unit can estimate the user's emotions and adjust the length of the response based on the estimated emotions. For example, if the user is relaxed, the response generation unit can generate a detailed response. If the user is tense, the response generation unit can also generate a concise response. If the user is excited, the response generation unit can also generate a lively response. By adjusting the length of the response according to the user's emotions, a more appropriate response can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response generation unit may be performed using AI, for example, or without AI. For example, the response generation unit can input user emotion data into the generative AI and have the generative AI adjust the length of the response.

[0097] The response generation unit can determine the priority of responses based on the customer's submission timing when generating responses. For example, if the customer is in a hurry, the response generation unit will generate a response quickly. The response generation unit can also generate a detailed response if the customer has ample time. Furthermore, if the customer submits within a specific time frame, the response generation unit can generate a response appropriate for that time frame. This allows for the generation of more appropriate responses by determining the priority of responses based on the customer's submission timing. Some or all of the above processing in the response generation unit may be performed using AI, for example, or without AI. For example, the response generation unit can input customer submission timing data into a generation AI and have the generation AI determine the priority of responses.

[0098] The response generation unit can adjust the order of responses based on customer relevance during response generation. For example, the response generation unit prioritizes generating responses for important customers. It can also quickly generate responses for new customers. Furthermore, it can generate trustworthy responses for repeat customers. By adjusting the order of responses based on customer relevance, more appropriate responses can be generated. Some or all of the above processing in the response generation unit may be performed using AI, for example, or without AI. For example, the response generation unit can input customer relevance data into a generation AI and have the generation AI perform the adjustment of the response order.

[0099] The experience unit can estimate the user's emotions and adjust the customer service experience based on those emotions. For example, if the user is relaxed, the experience unit can provide a calm customer service experience. If the user is tense, the experience unit can provide a friendly customer service experience. If the user is excited, the experience unit can provide a lively customer service experience. By adjusting the customer service experience according to the user's emotions, a more appropriate customer service experience can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the experience unit may be performed using AI, for example, or not using AI. For example, the experience unit can input user emotion data into a generative AI and have the generative AI adjust the customer service experience.

[0100] The experience department can select the optimal experience method by referring to the user's past customer service history during a customer service experience. For example, the experience department can propose the optimal experience method based on customer service situations the user has experienced in the past. The experience department can also select an experience method that corresponds to frequently occurring situations from the user's past customer service history. Furthermore, the experience department can analyze the user's past customer service history and provide an experience method that focuses on areas that need improvement. In this way, the optimal experience method can be selected by referring to the user's past customer service history. Some or all of the above processing in the experience department may be performed using AI, for example, or not using AI. For example, the experience department can input data of the user's past customer service history into a generating AI and have the generating AI perform the selection of an experience method.

[0101] The experience department can customize the customer service experience based on the user's current work situation. For example, if the user is busy, the experience department can provide a short and effective customer service experience. If the user has time, the experience department can also provide a customer service experience that includes detailed scenarios. Furthermore, depending on the user's work content, the experience department can provide a customer service experience that strengthens specific skills. In this way, a more appropriate customer service experience can be provided by customizing the experience based on the user's current work situation. Some or all of the above processing in the experience department may be performed using AI, for example, or not using AI. For example, the experience department can input data on the user's current work situation into a generating AI and have the generating AI perform the customization of the experience.

[0102] The experience unit can estimate the user's emotions and prioritize customer service experiences based on those emotions. For example, if the user is stressed, the experience unit will prioritize providing high-priority customer service experiences. If the user is relaxed, the experience unit can also provide more detailed customer service experiences and adjust priorities accordingly. Furthermore, if the user is in a hurry, the experience unit can prioritize providing customer service experiences that can be completed quickly. This allows for the provision of more appropriate customer service experiences by prioritizing them according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the experience unit may be performed using AI, or not. For example, the experience unit can input user emotion data into a generative AI and have the generative AI determine the priority of customer service experiences.

[0103] The Experience Department can select the optimal experience method during a customer service experience, taking into account the user's geographical location. For example, if the user is in a specific region, the Experience Department can provide a customer service experience based on the customer characteristics of that region. Furthermore, if the user is traveling, the Experience Department can provide a customer service experience tailored to travelers. Also, if the user is in a specific city, the Experience Department can provide a customer service experience based on the culture and customs of that city. This allows for the selection of the optimal experience method by considering the user's geographical location. Some or all of the above processing in the Experience Department may be performed using AI, for example, or without AI. For example, the Experience Department can input the user's geographical location information into a generating AI and have the generating AI select the experience method.

[0104] The Experience Department can analyze a user's social media activity during a customer service experience and propose ways to enhance that experience. For example, the Experience Department can analyze a user's social media posts and provide a customer service experience based on their interests. It can also refer to the activities of the user's followers and friends to provide relevant customer service experiences. Furthermore, the Experience Department can analyze the frequency and patterns of a user's social media activity to provide the optimal customer service experience. In this way, by analyzing a user's social media activity, the optimal customer service experience can be provided. Some or all of the above processing in the Experience Department may be performed using AI, for example, or without AI. For example, the Experience Department can input the user's social media data into a generating AI and have the generating AI propose ways to enhance the experience.

[0105] The judgment unit can estimate the user's emotions and adjust its judgment method based on the estimated emotions. For example, if the user is relaxed, the judgment unit can provide feedback in a calm tone. If the user is tense, the judgment unit can provide feedback in a friendly tone. If the user is excited, the judgment unit can provide feedback in an energetic tone. By adjusting the judgment method according to the user's emotions, more appropriate feedback can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input user emotion data into the generative AI and have the generative AI adjust the judgment method.

[0106] The judgment unit can select the optimal judgment method by referring to the user's past customer service evaluations during the judgment process. For example, the judgment unit can propose the optimal judgment method based on evaluations the user has received in the past. The judgment unit can also select a judgment method that focuses on frequently pointed-out points from the user's past customer service evaluations. Furthermore, the judgment unit can analyze the user's past customer service evaluations and provide a judgment method that focuses on areas that need improvement. In this way, the optimal judgment method can be selected by referring to the user's past customer service evaluations. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input data on the user's past customer service evaluations into a generating AI and have the generating AI perform the selection of a judgment method.

[0107] The judgment unit can customize the judgment method based on the user's current work situation at the time of judgment. For example, if the user is busy, the judgment unit can provide an effective judgment in a short time. Also, if the user has time, the judgment unit can provide detailed feedback. Furthermore, depending on the user's work content, the judgment unit can provide judgment methods to strengthen specific skills. This allows for more appropriate feedback to be provided by customizing the judgment method based on the user's current work situation. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input data on the user's current work situation into a generating AI and have the generating AI perform the customization of the judgment method.

[0108] The judgment unit can estimate the user's emotions and determine the priority of judgments based on the estimated emotions. For example, if the user is feeling stressed, the judgment unit will prioritize providing high-importance judgments. If the user is relaxed, the judgment unit can also provide detailed judgments and adjust the priorities. If the user is in a hurry, the judgment unit can also prioritize providing judgments that can be completed quickly. This allows for more appropriate feedback by determining the priority of judgments according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the judgment unit may be performed using AI or not using AI. For example, the judgment unit can input user emotion data into a generative AI and have the generative AI determine the priority of judgments.

[0109] The determination unit can select the optimal determination method by considering the user's geographical location information during the determination process. For example, if the user is in a specific region, the determination unit can provide a determination method based on the customer characteristics of that region. Furthermore, if the user is traveling, the determination unit can provide a determination method tailored for travelers. Also, if the user is in a specific city, the determination unit can provide a determination method based on the culture and customs of that city. This allows the determination unit to select the optimal determination method by considering the user's geographical location information. Some or all of the above-described processes in the determination unit may be performed using AI, for example, or without AI. For example, the determination unit can input the user's geographical location information into a generating AI and have the generating AI select the determination method.

[0110] The determination unit can analyze the user's social media activity and propose a determination method during the determination process. For example, the determination unit can analyze the user's social media posts and provide a determination method based on their interests. The determination unit can also refer to the activities of the user's followers and friends and provide relevant determination methods. Furthermore, the determination unit can analyze the frequency and patterns of the user's social media activity and provide the optimal determination method. In this way, the optimal determination method can be provided by analyzing the user's social media activity. Some or all of the above processing in the determination unit may be performed using AI, for example, or without AI. For example, the determination unit can input the user's social media data into a generating AI and have the generating AI execute the proposal of a determination method.

[0111] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0112] The customer service training system can estimate the user's emotions and customize the training content based on those emotions. For example, if the user is stressed, the system can provide a relaxing scenario; if the user is relaxed, it can provide a more challenging scenario. If the user is excited, the system can provide a scenario that utilizes that energy. This allows for the provision of an optimal training experience tailored to the user's emotions. Emotion estimation is achieved using, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The system can input user emotion data into the generative AI and have the generative AI customize the training content.

[0113] The customer service training system can analyze a user's past customer service history and propose the most suitable training scenario. For example, if a user has struggled with handling complaints in the past, the system will provide a scenario specifically focused on complaint handling. Similarly, if a user excels at handling new customers, the system can provide a scenario to further improve that skill. Furthermore, it can extract frequently occurring situations from the user's past customer service history and provide corresponding training scenarios. This allows for the provision of an optimal training experience based on the user's past experience. The system inputs the user's past customer service history data into a generating AI, which then generates training scenario suggestions.

[0114] The customer service training system can customize training content based on the user's geographical location. For example, if the user is in a specific region, it can provide scenarios based on the customer characteristics of that region. It can also provide traveler-oriented scenarios if the user is traveling. Furthermore, if the user is in a specific city, it can provide scenarios based on the city's culture and customs. This allows for the provision of an optimal training experience that takes the user's geographical location into account. The system inputs the user's geographical location information into a generating AI, which then performs the customization of the training content.

[0115] The customer service training system can analyze users' social media activity and provide relevant training scenarios. For example, it can analyze users' social media posts and provide scenarios based on their interests. It can also provide relevant scenarios by referring to the activities of users' followers and friends. Furthermore, it can analyze the frequency and patterns of users' social media activity and provide the optimal scenario. This allows for the provision of an optimal training experience that takes into account users' social media activity. The system can input users' social media data into a generating AI and have the AI ​​generate training scenario suggestions.

[0116] The customer service training system can estimate the user's emotions and adjust the feedback method based on the estimated emotions. For example, if the user is relaxed, feedback can be provided in a calm tone. If the user is tense, feedback can be provided in a friendly tone. Furthermore, if the user is excited, feedback can be provided in an energetic tone. This allows for the provision of optimal feedback tailored to the user's emotions. Emotion estimation is achieved using, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The system can input user emotion data into the generative AI and have the generative AI adjust the feedback method.

[0117] The customer service training system can customize training content based on the user's current work situation. For example, if the user is busy, it can provide a short and effective training scenario. If the user has more time, it can also provide a training scenario that includes detailed situations. Furthermore, it can provide training scenarios to strengthen specific skills depending on the user's job responsibilities. This allows for the provision of an optimal training experience based on the user's current work situation. The system inputs data on the user's current work situation into a generating AI, which then performs the customization of the training content.

[0118] The customer service training system can estimate the user's emotions and prioritize training based on those emotions. For example, if the user is stressed, it can prioritize providing high-priority training scenarios. If the user is relaxed, it can provide more detailed training scenarios and adjust priorities accordingly. Furthermore, if the user is in a hurry, it can prioritize providing training scenarios that can be completed quickly. This allows for the provision of an optimal training experience tailored to the user's emotions. Emotion estimation is achieved using, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The system can input user emotion data into the generative AI and have the generative AI determine the training priorities.

[0119] The customer service training system can estimate the user's emotions and adjust the avatar's expression based on the estimated emotions. For example, if the user is relaxed, it can generate an avatar with a calm expression. If the user is tense, it can generate an avatar with a friendly expression. Furthermore, if the user is excited, it can generate an avatar with a lively expression. This allows for the generation of the optimal avatar according to the user's emotions. Emotion estimation is achieved using, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The system can input the user's emotion data into the generative AI and have the generative AI adjust the avatar's expression.

[0120] The customer service training system can estimate the user's emotions and adjust the way it expresses its responses based on those emotions. For example, if the user is relaxed, it can generate a response in a calm tone. If the user is nervous, it can generate a response in a friendly tone. Furthermore, if the user is excited, it can generate a response in an energetic tone. This allows the system to generate the optimal response according to the user's emotions. Emotion estimation is achieved using, for example, an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The system can input user emotion data into the generative AI and have the generative AI adjust the way it expresses its responses.

[0121] The customer service training system can estimate the user's emotions and prioritize judgments based on those emotions. For example, if the user is stressed, it can prioritize high-priority judgments. If the user is relaxed, it can provide more detailed judgments and adjust priorities accordingly. Furthermore, if the user is in a hurry, it can prioritize judgments that can be completed quickly. This allows for the provision of optimal feedback tailored to the user's emotions. Emotion estimation is achieved using, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The system can input user emotion data into the generative AI and have the generative AI determine the priority of judgments.

[0122] The following briefly describes the processing flow for example form 2.

[0123] Step 1: The reception department sets up customer personas. Customer personas include attribute information such as age, gender, occupation, and hobbies. The reception department sets up customer personas based on the information entered by the user. They can also analyze past customer service data and suggest the most suitable persona settings. Step 2: The generation unit uses a generation AI to generate customer avatars based on the personas set by the reception unit. The generation AI includes text generation AI and image generation AI, and realistically generates the customer's appearance, clothing, facial expressions, etc. The generation unit can also adjust the avatar details based on the customer's attribute information and apply different generation algorithms depending on the customer's category. Step 3: The response generation unit uses a generation AI to generate customer responses generated by the generation unit. The response generation unit generates responses considering the customer's wording, tone, and appropriateness of content, and adjusts the level of detail of the response based on the importance of the customer. It can also apply different response algorithms depending on the customer category. Step 4: The experience unit conducts the customer service experience based on the responses generated by the response generation unit. The experience unit sets the scenario and interaction format, estimates the user's emotions, and adjusts the method of the customer service experience to provide a realistic customer service experience. It can also select the optimal experience method by referring to the user's past customer service history. Step 5: The evaluation unit evaluates the customer service experience conducted by the experience unit and provides feedback. The evaluation unit assesses the speed of the response, language use, attitude, etc., and points out areas for improvement. It estimates the user's emotions and adjusts the evaluation method based on the estimated user emotions. It can also select the optimal evaluation method by referring to the user's past customer service evaluations.

[0124] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0125] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0126] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0127] Each of the multiple elements described above, including the reception unit, generation unit, response generation unit, experience unit, and judgment unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and sets up a customer persona based on information entered by the user. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a customer avatar using a generation AI. The response generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a customer response using a generation AI. The experience unit is implemented by the control unit 46A of the smart device 14 and provides a realistic customer service experience. The judgment unit is implemented by the specific processing unit 290 of the data processing unit 12 and judges the customer service experience and provides feedback. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0128] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0129] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0130] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0131] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0132] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0134] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0135] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0136] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0137] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0138] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0139] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0140] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0141] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0142] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0143] Each of the multiple elements described above, including the reception unit, generation unit, response generation unit, experience unit, and judgment unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and sets up a customer persona based on information entered by the user. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a customer avatar using a generation AI. The response generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a customer response using a generation AI. The experience unit is implemented by the control unit 46A of the smart glasses 214 and provides a realistic customer service experience. The judgment unit is implemented by the specific processing unit 290 of the data processing unit 12 and judges the customer service experience and provides feedback. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0144] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0145] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0146] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0147] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0148] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0150] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0151] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0152] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0153] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0154] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0155] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0156] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0157] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0158] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0159] Each of the multiple elements described above, including the reception unit, generation unit, response generation unit, experience unit, and judgment unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and sets up a customer persona based on information entered by the user. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a customer avatar using a generation AI. The response generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a customer response using a generation AI. The experience unit is implemented by the control unit 46A of the headset terminal 314 and provides a realistic customer service experience. The judgment unit is implemented by the specific processing unit 290 of the data processing unit 12 and judges the customer service experience and provides feedback. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0160] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0161] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0162] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0163] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0164] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0165] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0166] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0167] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0168] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0169] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0170] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0171] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0172] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0173] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0174] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0175] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0176] Each of the multiple elements described above, including the reception unit, generation unit, response generation unit, experience unit, and judgment unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and sets up a customer persona based on information entered by the user. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates a customer avatar using a generation AI. The response generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates a customer response using a generation AI. The experience unit is implemented by, for example, the control unit 46A of the robot 414 and provides a realistic customer service experience. The judgment unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and judges the customer service experience and provides feedback. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0177] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0178] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0179] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0180] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0181] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0182] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0183] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0184] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0185] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0186] 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.

[0187] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0188] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0189] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0190] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0191] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0192] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0193] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0194] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0195] (Note 1) The reception department sets up customer personas, A generation unit that generates customer avatars based on personas set by the reception unit, A response generation unit that generates customer responses generated by the generation unit, An experience unit that provides a customer service experience based on the response generated by the response generation unit, The system includes a determination unit that evaluates the customer service experience performed by the aforementioned experience unit and provides feedback. A system characterized by the following features. (Note 2) The aforementioned reception unit is Set up a scenario for handling customer complaints. The system described in Appendix 1, characterized by the features described herein. (Note 3) The generating unit is Generating customer avatars using AI. The system described in Appendix 1, characterized by the features described herein. (Note 4) The response generation unit, Generating customer responses using AI. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned experience section is, Providing a realistic customer service experience The system described in Appendix 1, characterized by the features described herein. (Note 6) The determination unit, We evaluate the speed of response, language use, and attitude, and point out areas for improvement. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned experience section is, Employee training can be conducted anytime, anywhere, without requiring any physical space. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is We estimate the user's emotions and adjust the persona settings based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is We analyze past customer service data and propose the optimal persona setting. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When setting up personas, customize them according to the user's industry and business type. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is We estimate the user's emotions and prioritize personas based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When creating personas, prioritize setting highly relevant personas by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is When creating personas, analyze the user's social media activity and create relevant personas. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is It estimates the user's emotions and adjusts the avatar's representation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is When generating an avatar, the level of detail of the avatar is adjusted based on the customer's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is When generating avatars, different generation algorithms are applied depending on the customer's category. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is It estimates the user's emotions and adjusts the avatar's appearance based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is When generating avatars, the priority of avatars is determined based on the customer's submission date. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is When generating avatars, the order of avatars is adjusted based on customer relevance. The system described in Appendix 1, characterized by the features described herein. (Note 20) The response generation unit, It estimates the user's emotions and adjusts the way responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The response generation unit, When generating a response, adjust the level of detail in the response based on the customer's importance. The system described in Appendix 1, characterized by the features described herein. (Note 22) The response generation unit, When generating a response, different response algorithms are applied depending on the customer's category. The system described in Appendix 1, characterized by the features described herein. (Note 23) The response generation unit, It estimates the user's emotions and adjusts the length of the response based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The response generation unit, When generating a response, we prioritize responses based on when the customer submitted them. The system described in Appendix 1, characterized by the features described herein. (Note 25) The response generation unit, When generating responses, the order of responses is adjusted based on customer relevance. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned experience section is, It estimates the user's emotions and adjusts the customer service experience based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned experience section is, During the customer service experience, the system selects the optimal experience method by referring to the user's past customer service history. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned experience section is, During the customer service experience, customize the experience based on the user's current work situation. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned experience section is, It estimates the user's emotions and determines the priority of the customer service experience based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned experience section is, During the customer service experience, the system selects the optimal experience method by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned experience section is, During customer service interactions, we analyze users' social media activity and suggest ways to enhance the experience. The system described in Appendix 1, characterized by the features described herein. (Note 32) The determination unit, The system estimates the user's emotions and adjusts the decision-making method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The determination unit, During the evaluation process, the system selects the optimal evaluation method by referring to the user's past customer service evaluations. The system described in Appendix 1, characterized by the features described herein. (Note 34) The determination unit, During the decision-making process, the decision-making method is customized based on the user's current work situation. The system described in Appendix 1, characterized by the features described herein. (Note 35) The determination unit, The system estimates the user's emotions and determines the priority of decisions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The determination unit, During the determination process, the optimal determination method is selected by considering the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 37) The determination unit, When making a determination, we analyze the user's social media activity and propose a method for making that determination. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0196] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The reception department sets up customer personas, A generation unit that generates customer avatars based on personas set by the reception unit, A response generation unit that generates customer responses generated by the generation unit, An experience unit that provides a customer service experience based on the response generated by the response generation unit, The system includes a determination unit that evaluates the customer service experience performed by the aforementioned experience unit and provides feedback. A system characterized by the following features.

2. The aforementioned reception unit is Set up a scenario for handling customer complaints. The system according to feature 1.

3. The generating unit is Generating customer avatars using AI. The system according to feature 1.

4. The response generation unit, Generating customer responses using AI. The system according to feature 1.

5. The aforementioned experience section is, Providing a realistic customer service experience The system according to feature 1.

6. The determination unit, We evaluate the speed of response, language use, and attitude, and point out areas for improvement. The system according to feature 1.

7. The aforementioned experience section is, Employee training can be conducted anytime, anywhere, without requiring any physical space. The system according to feature 1.

8. The aforementioned reception unit is We estimate the user's emotions and adjust the persona settings based on those estimated emotions. The system according to feature 1.

Images